While progress has been made in information source localization,it has overlooked the prevalent friend and adversarial relationships in social networks.This paper addresses this gap by focusing on source localization ...While progress has been made in information source localization,it has overlooked the prevalent friend and adversarial relationships in social networks.This paper addresses this gap by focusing on source localization in signed network models.Leveraging the topological characteristics of signed networks and transforming the propagation probability into effective distance,we propose an optimization method for observer selection.Additionally,by using the reverse propagation algorithm we present a method for information source localization in signed networks.Extensive experimental results demonstrate that a higher proportion of positive edges within signed networks contributes to more favorable source localization,and the higher the ratio of propagation rates between positive and negative edges,the more accurate the source localization becomes.Interestingly,this aligns with our observation that,in reality,the number of friends tends to be greater than the number of adversaries,and the likelihood of information propagation among friends is often higher than among adversaries.In addition,the source located at the periphery of the network is not easy to identify.Furthermore,our proposed observer selection method based on effective distance achieves higher operational efficiency and exhibits higher accuracy in information source localization,compared with three strategies for observer selection based on the classical full-order neighbor coverage.展开更多
Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automa...Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automatically recognizing and interpreting sign language gestures,has gained significant attention in recent years due to its potential to bridge the communication gap between the hearing impaired and the hearing world.The emergence and continuous development of deep learning techniques have provided inspiration and momentum for advancing SLR.This paper presents a comprehensive and up-to-date analysis of the advancements,challenges,and opportunities in deep learning-based sign language recognition,focusing on the past five years of research.We explore various aspects of SLR,including sign data acquisition technologies,sign language datasets,evaluation methods,and different types of neural networks.Convolutional Neural Networks(CNN)and Recurrent Neural Networks(RNN)have shown promising results in fingerspelling and isolated sign recognition.However,the continuous nature of sign language poses challenges,leading to the exploration of advanced neural network models such as the Transformer model for continuous sign language recognition(CSLR).Despite significant advancements,several challenges remain in the field of SLR.These challenges include expanding sign language datasets,achieving user independence in recognition systems,exploring different input modalities,effectively fusing features,modeling co-articulation,and improving semantic and syntactic understanding.Additionally,developing lightweight network architectures for mobile applications is crucial for practical implementation.By addressing these challenges,we can further advance the field of deep learning for sign language recognition and improve communication for the hearing-impaired community.展开更多
We theoretically study nonlinear thermoelectric transport through a topological superconductor nanowire hosting Majorana bound states(MBSs) at its two ends, a system named as Majorana nanowire(MNW). We consider that t...We theoretically study nonlinear thermoelectric transport through a topological superconductor nanowire hosting Majorana bound states(MBSs) at its two ends, a system named as Majorana nanowire(MNW). We consider that the MNW is coupled to the left and right normal metallic leads subjected to either bias voltage or temperature gradient. We focus our attention on the sign change of nonlinear Seebeck and Peltier coefficients induced by mechanisms related to the MBSs, by which the possible existence of MBSs might be proved. Our results show that for a fixed temperature difference between the two leads, the sign of the nonlinear Seebeck coefficient(thermopower) can be reversed by changing the overlap amplitude between the MBSs or the system equilibrium temperature, which are similar to the cases in linear response regime. By optimizing the MBS–MBS interaction amplitude and system equilibrium temperature, we find that the temperature difference may also induce sign change of the nonlinear thermopower. For zero temperature difference and finite bias voltage, both the sign and magnitude of nonlinear Peltier coefficient can be adjusted by changing the bias voltage or overlap amplitude between the MBSs. In the presence of both bias voltage and temperature difference, we show that the electrical current at zero Fermi level and the states induced by overlap between the MBSs keep unchanged, regardless of the amplitude of temperature difference. We also find that the direction of the heat current driven by bias voltage may be changed by weak temperature difference.展开更多
Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seaml...Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free HCI.HGRoc technology is pivotal in healthcare and communication for the deaf community.Despite significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature extraction.Therefore,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and scalability.Additionally,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer interaction.The proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,respectively.These results demonstrate the effectiveness of CNN as a promising HGRoc approach.The findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.展开更多
Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japane...Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.展开更多
Deaf people or people facing hearing issues can communicate using sign language(SL),a visual language.Many works based on rich source language have been proposed;however,the work using poor resource language is still ...Deaf people or people facing hearing issues can communicate using sign language(SL),a visual language.Many works based on rich source language have been proposed;however,the work using poor resource language is still lacking.Unlike other SLs,the visuals of the Urdu Language are different.This study presents a novel approach to translating Urdu sign language(UrSL)using the UrSL-CNN model,a convolutional neural network(CNN)architecture specifically designed for this purpose.Unlike existingworks that primarily focus on languageswith rich resources,this study addresses the challenge of translating a sign language with limited resources.We conducted experiments using two datasets containing 1500 and 78,000 images,employing a methodology comprising four modules:data collection,pre-processing,categorization,and prediction.To enhance prediction accuracy,each sign image was transformed into a greyscale image and underwent noise filtering.Comparative analysis with machine learning baseline methods(support vectormachine,GaussianNaive Bayes,randomforest,and k-nearest neighbors’algorithm)on the UrSL alphabets dataset demonstrated the superiority of UrSL-CNN,achieving an accuracy of 0.95.Additionally,our model exhibited superior performance in Precision,Recall,and F1-score evaluations.This work not only contributes to advancing sign language translation but also holds promise for improving communication accessibility for individuals with hearing impairments.展开更多
Research on Chinese Sign Language(CSL)provides convenience and support for individuals with hearing impairments to communicate and integrate into society.This article reviews the relevant literature on Chinese Sign La...Research on Chinese Sign Language(CSL)provides convenience and support for individuals with hearing impairments to communicate and integrate into society.This article reviews the relevant literature on Chinese Sign Language Recognition(CSLR)in the past 20 years.Hidden Markov Models(HMM),Support Vector Machines(SVM),and Dynamic Time Warping(DTW)were found to be the most commonly employed technologies among traditional identificationmethods.Benefiting from the rapid development of computer vision and artificial intelligence technology,Convolutional Neural Networks(CNN),3D-CNN,YOLO,Capsule Network(CapsNet)and various deep neural networks have sprung up.Deep Neural Networks(DNNs)and their derived models are integral tomodern artificial intelligence recognitionmethods.In addition,technologies thatwerewidely used in the early days have also been integrated and applied to specific hybrid models and customized identification methods.Sign language data collection includes acquiring data from data gloves,data sensors(such as Kinect,LeapMotion,etc.),and high-definition photography.Meanwhile,facial expression recognition,complex background processing,and 3D sign language recognition have also attracted research interests among scholars.Due to the uniqueness and complexity of Chinese sign language,accuracy,robustness,real-time performance,and user independence are significant challenges for future sign language recognition research.Additionally,suitable datasets and evaluation criteria are also worth pursuing.展开更多
This paper investigates the tracking control problem for unmanned underwater vehicles(UUVs)systems with sensor faults,input saturation,and external disturbance caused by waves and ocean currents.An active sensor fault...This paper investigates the tracking control problem for unmanned underwater vehicles(UUVs)systems with sensor faults,input saturation,and external disturbance caused by waves and ocean currents.An active sensor fault-tolerant control scheme is proposed.First,the developed method only requires the inertia matrix of the UUV,without other dynamic information,and can handle both additive and multiplicative sensor faults.Subsequently,an adaptive fault-tolerant controller is designed to achieve asymptotic tracking control of the UUV by employing robust integral of the sign of error feedback method.It is shown that the effect of sensor faults is online estimated and compensated by an adaptive estimator.With the proposed controller,the tracking error and estimation error can asymptotically converge to zero.Finally,simulation results are performed to demonstrate the effectiveness of the proposed method.展开更多
BACKGROUND Appendiceal intussusception is a pathological condition in which the appendix is inverted into the cecum,which may cause symptoms that resemble those of other gastrointestinal disorders and may induce intes...BACKGROUND Appendiceal intussusception is a pathological condition in which the appendix is inverted into the cecum,which may cause symptoms that resemble those of other gastrointestinal disorders and may induce intestinal obstruction.The rarity of this case presentation is the co-occurrence of appendiceal intussusception and cecal adenocarcinoma,a combination that to our knowledge has not previously been reported in the medical literature.This case provides new insights into the complexities of diagnosing and managing overlapping pathologies.CASE SUMMARY A 25-year-old woman presented with persistent periumbilical pain and bloody stools.An initial biopsy showed cecal cancer;however,subsequent colonoscopy and computed tomography findings raised the suspicion of appendiceal intussus-ception,which was later confirmed postoperatively.This unique case was charac-terized by a combination of intussusception and adenocarcinoma of the cecum.The intervention included a laparoscopic right hemicolectomy,which led to the histopathological diagnosis of mucinous adenocarcinoma with appendiceal intussusception.The patient recovered well postoperatively and was advised to initiate adjuvant chemotherapy.This case highlights not only the importance of considering appendiceal intussusception in the differential diagnosis,but also the possibility of appendicitis and the atypical presentation of neoplastic lesions.CONCLUSIONS Physicians should consider the possibility of appendiceal intussusception in cases of atypical appendicitis,particularly when associated with neoplastic presentation.展开更多
BACKGROUND Sleep deprivation is a prevalent issue that impacts cognitive function.Although numerous neuroimaging studies have explored the neural correlates of sleep loss,inconsistencies persist in the reported result...BACKGROUND Sleep deprivation is a prevalent issue that impacts cognitive function.Although numerous neuroimaging studies have explored the neural correlates of sleep loss,inconsistencies persist in the reported results,necessitating an investigation into the consistent brain functional changes resulting from sleep loss.AIM To establish the consistency of brain functional alterations associated with sleep deprivation through systematic searches of neuroimaging databases.Two metaanalytic methods,signed differential mapping(SDM)and activation likelihood estimation(ALE),were employed to analyze functional magnetic resonance imaging(fMRI)data.METHODS A systematic search performed according to PRISMA guidelines was conducted across multiple databases through July 29,2023.Studies that met specific inclusion criteria,focused on healthy subjects with acute sleep deprivation and reported whole-brain functional data in English were considered.A total of 21 studies were selected for SDM and ALE meta-analyses.RESULTS Twenty-one studies,including 23 experiments and 498 subjects,were included.Compared to pre-sleep deprivation,post-sleep deprivation brain function was associated with increased gray matter in the right corpus callosum and decreased activity in the left medial frontal gyrus and left inferior parietal lobule.SDM revealed increased brain functional activity in the left striatum and right central posterior gyrus and decreased activity in the right cerebellar gyrus,left middle frontal gyrus,corpus callosum,and right cuneus.CONCLUSION This meta-analysis consistently identified brain regions affected by sleep deprivation,notably the left medial frontal gyrus and corpus callosum,shedding light on the neuropathology of sleep deprivation and offering insights into its neurological impact.展开更多
Objective:This study aimed to determine the effectiveness of aromatherapy with lavender essential oil compared to progressive muscle relaxation(PMR)on anxiety and vital signs of patients under spinal anesthesia.Materi...Objective:This study aimed to determine the effectiveness of aromatherapy with lavender essential oil compared to progressive muscle relaxation(PMR)on anxiety and vital signs of patients under spinal anesthesia.Materials and Methods:This clinical trial was conducted on 120 spinal anesthesia candidates who were randomly assigned into three groups of 40 including control,PMR(Jacobsen group),and aromatherapy.The state-trait anxiety inventory was completed on surgery day and 15 min after the end of the intervention by the samples of all three groups,and at the same time as completing the questionnaire,vital signs were also measured and recorded.Results:The mean score of anxiety after intervention was lower than that before the intervention in the aromatherapy group(P<0.001).The mean score of anxiety in the aromatherapy group was significantly lower than that in the Jacobsen group(P<0.001).Moreover,data analysis showed a significant decrease in the mean arterial blood pressure scores of the PMR(P=008)and aromatherapy(P<0.001)groups and a statistically significant increase in the mean heart rate scores in the control group(P=0.002).Conclusion:The use of aromatherapy with lavender is more effective than PMR therapy in reducing the anxiety level of patients undergoing spinal anesthesia.Due to the high level of anxiety and its serious effects on the patient’s hemodynamics,aromatherapy with lavender can be used as an easy and cheap method to reduce anxiety in operation rooms.展开更多
Background: Tuberculosis (TB) is one of the major killer diseases among infectious diseases. The success of TB control depends on the capability of the health care system to detect and accurately manage TB cases. Tube...Background: Tuberculosis (TB) is one of the major killer diseases among infectious diseases. The success of TB control depends on the capability of the health care system to detect and accurately manage TB cases. Tuberculosis in children remained a low public health priority with limited epidemiologic studies. Struggles for TB control in children need to be enhanced as children are providing the reservoir for future cases to develop. Objectives: The study evaluated diagnostic and treatment practices related to childhood pulmonary tuberculosis in Gilgit Baltistan (GB), Pakistan. Methods: A descriptive, cross-sectional study based on retrospective record review of childhood Pulmonary Tuberculosis patients registered in the year 2020 with self-administered questionnaire. Results: Data of 557 childhood cases were collected. Most childhood cases were in age group 1 - 4 years (54%) with male predominance. More than 90% were diagnosed and treated at public sector facilities. 99% of the cases were clinically diagnosed with passive case finding. Cough was considered as a symptom of childhood Tuberculosis (TB) by 94% of physicians. Other important features included failure to thrive (13%), contact with a family history of TB (15%), Malnutrition(24%) and respiratory signs (21%). 99% physicians advised chest X-ray, Complete blood count (CBC) (95%) and Erythrocytes sedimentation rate (ESR) (72%) for diagnosis and fewer physicians (2%) used sputum smear microscopy and induced sputum (0.1%). Combining data on dosage, frequency and duration for drugs, 99% of the cases were found receiving correct regimen. The treatment outcomes of the cases were cured 4 (0.8%), treatment completed 551 (99.3%) and died 2 (0.4%) with no lost to follow up. Conclusions: The study highlights inappropriate diagnostic and treatment practices for managing childhood pulmonary TB among physicians in public and private sectors of Gilgit Baltistan. Most of the cases are managed by general practitioners with no post graduate qualification in medicine or pediatrics. The deviations from the guidelines for TB control cannot be negated in the region.展开更多
The observation study was conducted in Battambang City,Battambang province,by interviewing the 88 dog owners,who came to the animal pharmacy stores and clinics by using convenience sampling method of nonrandomized sam...The observation study was conducted in Battambang City,Battambang province,by interviewing the 88 dog owners,who came to the animal pharmacy stores and clinics by using convenience sampling method of nonrandomized sampling.Though the results of the interviews,showed that the dog owners were selected in different range of age and gender,however,most of them were in middle age from 21-40 years old,with medium and rich living wellbeing.The confinement in premise/house was primarily applied by dog owners.The number of bitches per household was from 1 to 3 batches,and there was no association with the wellbeing of the owners,and the age was from 2 to 4 years old,but some bitches had older age.Most of the bitches were dewormed in last 3 months and 6 months,however,there were some bitches last more than 6 months after deworming.The bitch vaccination was applied by owner around for 60.00%.There were two popular types of vaccination,Rabies and DHLPP(Distemper,Hepatitis,Leptospirosis,Parvovirus,and Parainfluenza).For dog population management,about 94.29%of the owners apply nonsurgical method with applying medicine.The reasons for using nonsurgical method were not only the cheapest price and easy way,but also there was no information on the consequence of using medication for birth control.The medication was highly used before heat.But,almost half of them got health problem in less than 3 months after administration,also some got long-term effect.Among clinical signs observed,the enlargement of belly was the most evidence,since 54.76%of affected bitches had shown it,then followed by discharge blood from vulvar,clear discharge and thick white pus from vulvar,accounting for 38.10%,35.71%and 26.71%,respectively.展开更多
Introduction: The management of fractures of the tibia shaft is an important aspect of orthopaedic care, and the selection of the surgical method for fixation can substantially impact patient outcomes. The current rev...Introduction: The management of fractures of the tibia shaft is an important aspect of orthopaedic care, and the selection of the surgical method for fixation can substantially impact patient outcomes. The current review aims to compare the outcomes of adult tibia fractures treated with solid nails to those treated with hollow nails. Methods: A search on Scopus, PubMed, and Cochrane Library, using three keywords (Outcome, Tibia shaft fractures, Nail) was conducted in April 2023. Results were compiled and two independent reviewers screened and selected eligible articles After removing duplicates, titles and abstracts were read to exclude ineligible studies. Full-text articles of the remaining papers were read to select eligible studies which were further critically appraised to ascertain their methodological quality. The data extracted from the selected papers were synthesized using a combination of pooling of results, tests of statistical difference (t-test and chi-square) and narrative synthesis methods. Results: A total of 2295 articles were obtained from the databases and citation searching. A total of 9 papers were identified as eligible and included in the review. Findings revealed that there is no statistical difference in the outcomes of tibia fractures treated with either solid or hollow nail groups such as duration of surgery (p = 0.541), rate of delayed and non-union (p = 0.342), and rate of surgical site infections (p = 0.395). Conclusion: Intramedullary nailing of tibia shaft fractures with either solid or hollow nails have similar functional outcomes.展开更多
Traffic intersections are incredibly dangerous for drivers and pedestrians. Statistics from both Canada and the U.S. show a high number of fatalities and serious injuries related to crashes at intersections. In Canada...Traffic intersections are incredibly dangerous for drivers and pedestrians. Statistics from both Canada and the U.S. show a high number of fatalities and serious injuries related to crashes at intersections. In Canada, during 2019, the National Collision Database shows that 28% of traffic fatalities and 42% of serious injuries occurred at intersections. Likewise, the U.S. National Highway Traffic Administration (NHTSA) found that about 40% of the estimated 5,811,000 accidents in the U.S. during the year studied were intersection-related crashes. In fact, a major survey by the car insurance industry found that nearly 85% of drivers could not identify the correct action to take when approaching a yellow traffic light at an intersection. One major reason for these accidents is the “yellow light dilemma,” the ambiguous situation where a driver should stop or proceed forward when unexpectedly faced with a yellow light. This situation is even further exacerbated by the tendency of aggressive drivers to inappropriately speed up on the yellow just to get through the traffic light. A survey of Canadian drivers conducted by the Traffic Injury Research Foundation found that 9% of drivers admitted to speeding up to get through a traffic light. Another reason for these accidents is the increased danger of making a left-hand turn on yellow. According to the National Highway Traffic Safety Association (NHTSA), left turns occur in approximately 22.2% of collisions—as opposed to just 1.2% for right turns. Moreover, a study by CNN found left turns are three times as likely to kill pedestrians than right turns. The reason left turns are so much more likely to cause an accident is because they take a driver against traffic and in the path of oncoming cars. Additionally, most of these left turns occur at the driver’s discretion—as opposed to the distressingly brief left-hand arrow at busy intersections. Drive Safe Now proposes a workable solution for reducing the number of accidents occurring during a yellow light at intersections. We believe this fairly simple solution will save lives, prevent injuries, reduce damage to public and private property, and decrease insurance costs.展开更多
We report on the verification of a multi-party contract signing protocol described by Baum-Waidner and Waidner (BW). Based on Paulson's inductive approach, we give the protocol model that includes infinitely many s...We report on the verification of a multi-party contract signing protocol described by Baum-Waidner and Waidner (BW). Based on Paulson's inductive approach, we give the protocol model that includes infinitely many signatories and contract texts signing simuhaneously. We consider composite attacks of the dishonest signatory and the external intruder, formalize cryptographic primitives and protocol arithmetic including attack model, show formal description of key distribution, and prove signature key secrecy theorems and fairness property theorems of the BW protocol using the interactive theorem prover Isabelle/HOL.展开更多
Continuous sign language recognition(CSLR)is challenging due to the complexity of video background,hand gesture variability,and temporal modeling difficulties.This work proposes a CSLR method based on a spatialtempora...Continuous sign language recognition(CSLR)is challenging due to the complexity of video background,hand gesture variability,and temporal modeling difficulties.This work proposes a CSLR method based on a spatialtemporal graph attention network to focus on essential features of video series.The method considers local details of sign language movements by taking the information on joints and bones as inputs and constructing a spatialtemporal graph to reflect inter-frame relevance and physical connections between nodes.The graph-based multihead attention mechanism is utilized with adjacent matrix calculation for better local-feature exploration,and short-term motion correlation modeling is completed via a temporal convolutional network.We adopted BLSTM to learn the long-termdependence and connectionist temporal classification to align the word-level sequences.The proposed method achieves competitive results regarding word error rates(1.59%)on the Chinese Sign Language dataset and the mean Jaccard Index(65.78%)on the ChaLearn LAP Continuous Gesture Dataset.展开更多
The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine ...The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine Learning(ML)have been used in road infrastructure and construction,particularly with the Internet of Things(IoT)devices.Object detection in Computer Vision also plays a key role in improving road infrastructure and addressing trafficrelated problems.This study aims to use You Only Look Once version 7(YOLOv7),Convolutional Block Attention Module(CBAM),the most optimized object-detection algorithm,to detect and identify traffic signs,and analyze effective combinations of adaptive optimizers like Adaptive Moment estimation(Adam),Root Mean Squared Propagation(RMSprop)and Stochastic Gradient Descent(SGD)with the YOLOv7.Using a portion of German traffic signs for training,the study investigates the feasibility of adopting smaller datasets while maintaining high accuracy.The model proposed in this study not only improves traffic safety by detecting traffic signs but also has the potential to contribute to the rapid development of autonomous vehicle systems.The study results showed an impressive accuracy of 99.7%when using a batch size of 8 and the Adam optimizer.This high level of accuracy demonstrates the effectiveness of the proposed model for the image classification task of traffic sign recognition.展开更多
This paper is concerned with bipartite consensus tracking for multi-agent systems with unknown disturbances.A barrier function-based adaptive sliding-mode control(SMC)approach is proposed such that the bipartite stead...This paper is concerned with bipartite consensus tracking for multi-agent systems with unknown disturbances.A barrier function-based adaptive sliding-mode control(SMC)approach is proposed such that the bipartite steady-state error is converged to a predefined region of zero in finite time.Specifically,based on an error auxiliary taking neighboring antagonistic interactions into account,an SMC law is designed with an adaptive gain.The gain can switch to a positive semi-definite barrier function to ensure that the error auxiliary is constrained to a predefined neighborhood of zero,which in turn guarantees practical bipartite consensus tracking.A distinguished feature of the proposed controller is its independence on the bound of disturbances,while the input chattering phenomenon is alleviated.Finally,a numerical example is provided to verify the effectiveness of the proposed controller.展开更多
Communication between people with disabilities and people who do not understand sign language is a growing social need and can be a tedious task.One of the main functions of sign language is to communicate with each o...Communication between people with disabilities and people who do not understand sign language is a growing social need and can be a tedious task.One of the main functions of sign language is to communicate with each other through hand gestures.Recognition of hand gestures has become an important challenge for the recognition of sign language.There are many existing models that can produce a good accuracy,but if the model test with rotated or translated images,they may face some difficulties to make good performance accuracy.To resolve these challenges of hand gesture recognition,we proposed a Rotation,Translation and Scale-invariant sign word recognition system using a convolu-tional neural network(CNN).We have followed three steps in our work:rotated,translated and scaled(RTS)version dataset generation,gesture segmentation,and sign word classification.Firstly,we have enlarged a benchmark dataset of 20 sign words by making different amounts of Rotation,Translation and Scale of the ori-ginal images to create the RTS version dataset.Then we have applied the gesture segmentation technique.The segmentation consists of three levels,i)Otsu Thresholding with YCbCr,ii)Morphological analysis:dilation through opening morphology and iii)Watershed algorithm.Finally,our designed CNN model has been trained to classify the hand gesture as well as the sign word.Our model has been evaluated using the twenty sign word dataset,five sign word dataset and the RTS version of these datasets.We achieved 99.30%accuracy from the twenty sign word dataset evaluation,99.10%accuracy from the RTS version of the twenty sign word evolution,100%accuracy from thefive sign word dataset evaluation,and 98.00%accuracy from the RTS versionfive sign word dataset evolution.Furthermore,the influence of our model exists in competitive results with state-of-the-art methods in sign word recognition.展开更多
基金Project supported by the National Natural Science Foundation of China(Grant Nos.62103375 and 62006106)the Zhejiang Provincial Philosophy and Social Science Planning Project(Grant No.22NDJC009Z)+1 种基金the Education Ministry Humanities and Social Science Foundation of China(Grant Nos.19YJCZH056 and 21YJC630120)the Natural Science Foundation of Zhejiang Province of China(Grant Nos.LY23F030003 and LQ21F020005).
文摘While progress has been made in information source localization,it has overlooked the prevalent friend and adversarial relationships in social networks.This paper addresses this gap by focusing on source localization in signed network models.Leveraging the topological characteristics of signed networks and transforming the propagation probability into effective distance,we propose an optimization method for observer selection.Additionally,by using the reverse propagation algorithm we present a method for information source localization in signed networks.Extensive experimental results demonstrate that a higher proportion of positive edges within signed networks contributes to more favorable source localization,and the higher the ratio of propagation rates between positive and negative edges,the more accurate the source localization becomes.Interestingly,this aligns with our observation that,in reality,the number of friends tends to be greater than the number of adversaries,and the likelihood of information propagation among friends is often higher than among adversaries.In addition,the source located at the periphery of the network is not easy to identify.Furthermore,our proposed observer selection method based on effective distance achieves higher operational efficiency and exhibits higher accuracy in information source localization,compared with three strategies for observer selection based on the classical full-order neighbor coverage.
基金supported from the National Philosophy and Social Sciences Foundation(Grant No.20BTQ065).
文摘Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automatically recognizing and interpreting sign language gestures,has gained significant attention in recent years due to its potential to bridge the communication gap between the hearing impaired and the hearing world.The emergence and continuous development of deep learning techniques have provided inspiration and momentum for advancing SLR.This paper presents a comprehensive and up-to-date analysis of the advancements,challenges,and opportunities in deep learning-based sign language recognition,focusing on the past five years of research.We explore various aspects of SLR,including sign data acquisition technologies,sign language datasets,evaluation methods,and different types of neural networks.Convolutional Neural Networks(CNN)and Recurrent Neural Networks(RNN)have shown promising results in fingerspelling and isolated sign recognition.However,the continuous nature of sign language poses challenges,leading to the exploration of advanced neural network models such as the Transformer model for continuous sign language recognition(CSLR).Despite significant advancements,several challenges remain in the field of SLR.These challenges include expanding sign language datasets,achieving user independence in recognition systems,exploring different input modalities,effectively fusing features,modeling co-articulation,and improving semantic and syntactic understanding.Additionally,developing lightweight network architectures for mobile applications is crucial for practical implementation.By addressing these challenges,we can further advance the field of deep learning for sign language recognition and improve communication for the hearing-impaired community.
基金Project supported by the National Natural Science Foundation of China(Grant No.12264037)the Innovation Team of Colleges and Universities in Guangdong Province(Grant No.2021KCXTD040)+2 种基金Guangdong Province Education Department(Grant No.2023KTSCX174)the Key Laboratory of Guangdong Higher Education Institutes(Grant No.2023KSYS011)Science and Technology Bureau of Zhongshan(Grant No.2023B2035)。
文摘We theoretically study nonlinear thermoelectric transport through a topological superconductor nanowire hosting Majorana bound states(MBSs) at its two ends, a system named as Majorana nanowire(MNW). We consider that the MNW is coupled to the left and right normal metallic leads subjected to either bias voltage or temperature gradient. We focus our attention on the sign change of nonlinear Seebeck and Peltier coefficients induced by mechanisms related to the MBSs, by which the possible existence of MBSs might be proved. Our results show that for a fixed temperature difference between the two leads, the sign of the nonlinear Seebeck coefficient(thermopower) can be reversed by changing the overlap amplitude between the MBSs or the system equilibrium temperature, which are similar to the cases in linear response regime. By optimizing the MBS–MBS interaction amplitude and system equilibrium temperature, we find that the temperature difference may also induce sign change of the nonlinear thermopower. For zero temperature difference and finite bias voltage, both the sign and magnitude of nonlinear Peltier coefficient can be adjusted by changing the bias voltage or overlap amplitude between the MBSs. In the presence of both bias voltage and temperature difference, we show that the electrical current at zero Fermi level and the states induced by overlap between the MBSs keep unchanged, regardless of the amplitude of temperature difference. We also find that the direction of the heat current driven by bias voltage may be changed by weak temperature difference.
基金funded by Researchers Supporting Project Number(RSPD2024 R947),King Saud University,Riyadh,Saudi Arabia.
文摘Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free HCI.HGRoc technology is pivotal in healthcare and communication for the deaf community.Despite significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature extraction.Therefore,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and scalability.Additionally,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer interaction.The proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,respectively.These results demonstrate the effectiveness of CNN as a promising HGRoc approach.The findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.
基金supported by the Competitive Research Fund of the University of Aizu,Japan.
文摘Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.
文摘Deaf people or people facing hearing issues can communicate using sign language(SL),a visual language.Many works based on rich source language have been proposed;however,the work using poor resource language is still lacking.Unlike other SLs,the visuals of the Urdu Language are different.This study presents a novel approach to translating Urdu sign language(UrSL)using the UrSL-CNN model,a convolutional neural network(CNN)architecture specifically designed for this purpose.Unlike existingworks that primarily focus on languageswith rich resources,this study addresses the challenge of translating a sign language with limited resources.We conducted experiments using two datasets containing 1500 and 78,000 images,employing a methodology comprising four modules:data collection,pre-processing,categorization,and prediction.To enhance prediction accuracy,each sign image was transformed into a greyscale image and underwent noise filtering.Comparative analysis with machine learning baseline methods(support vectormachine,GaussianNaive Bayes,randomforest,and k-nearest neighbors’algorithm)on the UrSL alphabets dataset demonstrated the superiority of UrSL-CNN,achieving an accuracy of 0.95.Additionally,our model exhibited superior performance in Precision,Recall,and F1-score evaluations.This work not only contributes to advancing sign language translation but also holds promise for improving communication accessibility for individuals with hearing impairments.
基金supported by National Social Science Foundation Annual Project“Research on Evaluation and Improvement Paths of Integrated Development of Disabled Persons”(Grant No.20BRK029)the National Language Commission’s“14th Five-Year Plan”Scientific Research Plan 2023 Project“Domain Digital Language Service Resource Construction and Key Technology Research”(YB145-72)the National Philosophy and Social Sciences Foundation(Grant No.20BTQ065).
文摘Research on Chinese Sign Language(CSL)provides convenience and support for individuals with hearing impairments to communicate and integrate into society.This article reviews the relevant literature on Chinese Sign Language Recognition(CSLR)in the past 20 years.Hidden Markov Models(HMM),Support Vector Machines(SVM),and Dynamic Time Warping(DTW)were found to be the most commonly employed technologies among traditional identificationmethods.Benefiting from the rapid development of computer vision and artificial intelligence technology,Convolutional Neural Networks(CNN),3D-CNN,YOLO,Capsule Network(CapsNet)and various deep neural networks have sprung up.Deep Neural Networks(DNNs)and their derived models are integral tomodern artificial intelligence recognitionmethods.In addition,technologies thatwerewidely used in the early days have also been integrated and applied to specific hybrid models and customized identification methods.Sign language data collection includes acquiring data from data gloves,data sensors(such as Kinect,LeapMotion,etc.),and high-definition photography.Meanwhile,facial expression recognition,complex background processing,and 3D sign language recognition have also attracted research interests among scholars.Due to the uniqueness and complexity of Chinese sign language,accuracy,robustness,real-time performance,and user independence are significant challenges for future sign language recognition research.Additionally,suitable datasets and evaluation criteria are also worth pursuing.
基金the National Natural Science Foundation of China(62303012,62236002,61911004,62303008)。
文摘This paper investigates the tracking control problem for unmanned underwater vehicles(UUVs)systems with sensor faults,input saturation,and external disturbance caused by waves and ocean currents.An active sensor fault-tolerant control scheme is proposed.First,the developed method only requires the inertia matrix of the UUV,without other dynamic information,and can handle both additive and multiplicative sensor faults.Subsequently,an adaptive fault-tolerant controller is designed to achieve asymptotic tracking control of the UUV by employing robust integral of the sign of error feedback method.It is shown that the effect of sensor faults is online estimated and compensated by an adaptive estimator.With the proposed controller,the tracking error and estimation error can asymptotically converge to zero.Finally,simulation results are performed to demonstrate the effectiveness of the proposed method.
基金the National Natural Science Foundation of China,No.82060440.
文摘BACKGROUND Appendiceal intussusception is a pathological condition in which the appendix is inverted into the cecum,which may cause symptoms that resemble those of other gastrointestinal disorders and may induce intestinal obstruction.The rarity of this case presentation is the co-occurrence of appendiceal intussusception and cecal adenocarcinoma,a combination that to our knowledge has not previously been reported in the medical literature.This case provides new insights into the complexities of diagnosing and managing overlapping pathologies.CASE SUMMARY A 25-year-old woman presented with persistent periumbilical pain and bloody stools.An initial biopsy showed cecal cancer;however,subsequent colonoscopy and computed tomography findings raised the suspicion of appendiceal intussus-ception,which was later confirmed postoperatively.This unique case was charac-terized by a combination of intussusception and adenocarcinoma of the cecum.The intervention included a laparoscopic right hemicolectomy,which led to the histopathological diagnosis of mucinous adenocarcinoma with appendiceal intussusception.The patient recovered well postoperatively and was advised to initiate adjuvant chemotherapy.This case highlights not only the importance of considering appendiceal intussusception in the differential diagnosis,but also the possibility of appendicitis and the atypical presentation of neoplastic lesions.CONCLUSIONS Physicians should consider the possibility of appendiceal intussusception in cases of atypical appendicitis,particularly when associated with neoplastic presentation.
文摘BACKGROUND Sleep deprivation is a prevalent issue that impacts cognitive function.Although numerous neuroimaging studies have explored the neural correlates of sleep loss,inconsistencies persist in the reported results,necessitating an investigation into the consistent brain functional changes resulting from sleep loss.AIM To establish the consistency of brain functional alterations associated with sleep deprivation through systematic searches of neuroimaging databases.Two metaanalytic methods,signed differential mapping(SDM)and activation likelihood estimation(ALE),were employed to analyze functional magnetic resonance imaging(fMRI)data.METHODS A systematic search performed according to PRISMA guidelines was conducted across multiple databases through July 29,2023.Studies that met specific inclusion criteria,focused on healthy subjects with acute sleep deprivation and reported whole-brain functional data in English were considered.A total of 21 studies were selected for SDM and ALE meta-analyses.RESULTS Twenty-one studies,including 23 experiments and 498 subjects,were included.Compared to pre-sleep deprivation,post-sleep deprivation brain function was associated with increased gray matter in the right corpus callosum and decreased activity in the left medial frontal gyrus and left inferior parietal lobule.SDM revealed increased brain functional activity in the left striatum and right central posterior gyrus and decreased activity in the right cerebellar gyrus,left middle frontal gyrus,corpus callosum,and right cuneus.CONCLUSION This meta-analysis consistently identified brain regions affected by sleep deprivation,notably the left medial frontal gyrus and corpus callosum,shedding light on the neuropathology of sleep deprivation and offering insights into its neurological impact.
基金financially supported by Arak University of Medical Sciences.
文摘Objective:This study aimed to determine the effectiveness of aromatherapy with lavender essential oil compared to progressive muscle relaxation(PMR)on anxiety and vital signs of patients under spinal anesthesia.Materials and Methods:This clinical trial was conducted on 120 spinal anesthesia candidates who were randomly assigned into three groups of 40 including control,PMR(Jacobsen group),and aromatherapy.The state-trait anxiety inventory was completed on surgery day and 15 min after the end of the intervention by the samples of all three groups,and at the same time as completing the questionnaire,vital signs were also measured and recorded.Results:The mean score of anxiety after intervention was lower than that before the intervention in the aromatherapy group(P<0.001).The mean score of anxiety in the aromatherapy group was significantly lower than that in the Jacobsen group(P<0.001).Moreover,data analysis showed a significant decrease in the mean arterial blood pressure scores of the PMR(P=008)and aromatherapy(P<0.001)groups and a statistically significant increase in the mean heart rate scores in the control group(P=0.002).Conclusion:The use of aromatherapy with lavender is more effective than PMR therapy in reducing the anxiety level of patients undergoing spinal anesthesia.Due to the high level of anxiety and its serious effects on the patient’s hemodynamics,aromatherapy with lavender can be used as an easy and cheap method to reduce anxiety in operation rooms.
文摘Background: Tuberculosis (TB) is one of the major killer diseases among infectious diseases. The success of TB control depends on the capability of the health care system to detect and accurately manage TB cases. Tuberculosis in children remained a low public health priority with limited epidemiologic studies. Struggles for TB control in children need to be enhanced as children are providing the reservoir for future cases to develop. Objectives: The study evaluated diagnostic and treatment practices related to childhood pulmonary tuberculosis in Gilgit Baltistan (GB), Pakistan. Methods: A descriptive, cross-sectional study based on retrospective record review of childhood Pulmonary Tuberculosis patients registered in the year 2020 with self-administered questionnaire. Results: Data of 557 childhood cases were collected. Most childhood cases were in age group 1 - 4 years (54%) with male predominance. More than 90% were diagnosed and treated at public sector facilities. 99% of the cases were clinically diagnosed with passive case finding. Cough was considered as a symptom of childhood Tuberculosis (TB) by 94% of physicians. Other important features included failure to thrive (13%), contact with a family history of TB (15%), Malnutrition(24%) and respiratory signs (21%). 99% physicians advised chest X-ray, Complete blood count (CBC) (95%) and Erythrocytes sedimentation rate (ESR) (72%) for diagnosis and fewer physicians (2%) used sputum smear microscopy and induced sputum (0.1%). Combining data on dosage, frequency and duration for drugs, 99% of the cases were found receiving correct regimen. The treatment outcomes of the cases were cured 4 (0.8%), treatment completed 551 (99.3%) and died 2 (0.4%) with no lost to follow up. Conclusions: The study highlights inappropriate diagnostic and treatment practices for managing childhood pulmonary TB among physicians in public and private sectors of Gilgit Baltistan. Most of the cases are managed by general practitioners with no post graduate qualification in medicine or pediatrics. The deviations from the guidelines for TB control cannot be negated in the region.
文摘The observation study was conducted in Battambang City,Battambang province,by interviewing the 88 dog owners,who came to the animal pharmacy stores and clinics by using convenience sampling method of nonrandomized sampling.Though the results of the interviews,showed that the dog owners were selected in different range of age and gender,however,most of them were in middle age from 21-40 years old,with medium and rich living wellbeing.The confinement in premise/house was primarily applied by dog owners.The number of bitches per household was from 1 to 3 batches,and there was no association with the wellbeing of the owners,and the age was from 2 to 4 years old,but some bitches had older age.Most of the bitches were dewormed in last 3 months and 6 months,however,there were some bitches last more than 6 months after deworming.The bitch vaccination was applied by owner around for 60.00%.There were two popular types of vaccination,Rabies and DHLPP(Distemper,Hepatitis,Leptospirosis,Parvovirus,and Parainfluenza).For dog population management,about 94.29%of the owners apply nonsurgical method with applying medicine.The reasons for using nonsurgical method were not only the cheapest price and easy way,but also there was no information on the consequence of using medication for birth control.The medication was highly used before heat.But,almost half of them got health problem in less than 3 months after administration,also some got long-term effect.Among clinical signs observed,the enlargement of belly was the most evidence,since 54.76%of affected bitches had shown it,then followed by discharge blood from vulvar,clear discharge and thick white pus from vulvar,accounting for 38.10%,35.71%and 26.71%,respectively.
文摘Introduction: The management of fractures of the tibia shaft is an important aspect of orthopaedic care, and the selection of the surgical method for fixation can substantially impact patient outcomes. The current review aims to compare the outcomes of adult tibia fractures treated with solid nails to those treated with hollow nails. Methods: A search on Scopus, PubMed, and Cochrane Library, using three keywords (Outcome, Tibia shaft fractures, Nail) was conducted in April 2023. Results were compiled and two independent reviewers screened and selected eligible articles After removing duplicates, titles and abstracts were read to exclude ineligible studies. Full-text articles of the remaining papers were read to select eligible studies which were further critically appraised to ascertain their methodological quality. The data extracted from the selected papers were synthesized using a combination of pooling of results, tests of statistical difference (t-test and chi-square) and narrative synthesis methods. Results: A total of 2295 articles were obtained from the databases and citation searching. A total of 9 papers were identified as eligible and included in the review. Findings revealed that there is no statistical difference in the outcomes of tibia fractures treated with either solid or hollow nail groups such as duration of surgery (p = 0.541), rate of delayed and non-union (p = 0.342), and rate of surgical site infections (p = 0.395). Conclusion: Intramedullary nailing of tibia shaft fractures with either solid or hollow nails have similar functional outcomes.
文摘Traffic intersections are incredibly dangerous for drivers and pedestrians. Statistics from both Canada and the U.S. show a high number of fatalities and serious injuries related to crashes at intersections. In Canada, during 2019, the National Collision Database shows that 28% of traffic fatalities and 42% of serious injuries occurred at intersections. Likewise, the U.S. National Highway Traffic Administration (NHTSA) found that about 40% of the estimated 5,811,000 accidents in the U.S. during the year studied were intersection-related crashes. In fact, a major survey by the car insurance industry found that nearly 85% of drivers could not identify the correct action to take when approaching a yellow traffic light at an intersection. One major reason for these accidents is the “yellow light dilemma,” the ambiguous situation where a driver should stop or proceed forward when unexpectedly faced with a yellow light. This situation is even further exacerbated by the tendency of aggressive drivers to inappropriately speed up on the yellow just to get through the traffic light. A survey of Canadian drivers conducted by the Traffic Injury Research Foundation found that 9% of drivers admitted to speeding up to get through a traffic light. Another reason for these accidents is the increased danger of making a left-hand turn on yellow. According to the National Highway Traffic Safety Association (NHTSA), left turns occur in approximately 22.2% of collisions—as opposed to just 1.2% for right turns. Moreover, a study by CNN found left turns are three times as likely to kill pedestrians than right turns. The reason left turns are so much more likely to cause an accident is because they take a driver against traffic and in the path of oncoming cars. Additionally, most of these left turns occur at the driver’s discretion—as opposed to the distressingly brief left-hand arrow at busy intersections. Drive Safe Now proposes a workable solution for reducing the number of accidents occurring during a yellow light at intersections. We believe this fairly simple solution will save lives, prevent injuries, reduce damage to public and private property, and decrease insurance costs.
基金Supported by the National Natural Science Foun-dation of China (60373068)
文摘We report on the verification of a multi-party contract signing protocol described by Baum-Waidner and Waidner (BW). Based on Paulson's inductive approach, we give the protocol model that includes infinitely many signatories and contract texts signing simuhaneously. We consider composite attacks of the dishonest signatory and the external intruder, formalize cryptographic primitives and protocol arithmetic including attack model, show formal description of key distribution, and prove signature key secrecy theorems and fairness property theorems of the BW protocol using the interactive theorem prover Isabelle/HOL.
基金supported by the Key Research&Development Plan Project of Shandong Province,China(No.2017GGX10127).
文摘Continuous sign language recognition(CSLR)is challenging due to the complexity of video background,hand gesture variability,and temporal modeling difficulties.This work proposes a CSLR method based on a spatialtemporal graph attention network to focus on essential features of video series.The method considers local details of sign language movements by taking the information on joints and bones as inputs and constructing a spatialtemporal graph to reflect inter-frame relevance and physical connections between nodes.The graph-based multihead attention mechanism is utilized with adjacent matrix calculation for better local-feature exploration,and short-term motion correlation modeling is completed via a temporal convolutional network.We adopted BLSTM to learn the long-termdependence and connectionist temporal classification to align the word-level sequences.The proposed method achieves competitive results regarding word error rates(1.59%)on the Chinese Sign Language dataset and the mean Jaccard Index(65.78%)on the ChaLearn LAP Continuous Gesture Dataset.
文摘The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine Learning(ML)have been used in road infrastructure and construction,particularly with the Internet of Things(IoT)devices.Object detection in Computer Vision also plays a key role in improving road infrastructure and addressing trafficrelated problems.This study aims to use You Only Look Once version 7(YOLOv7),Convolutional Block Attention Module(CBAM),the most optimized object-detection algorithm,to detect and identify traffic signs,and analyze effective combinations of adaptive optimizers like Adaptive Moment estimation(Adam),Root Mean Squared Propagation(RMSprop)and Stochastic Gradient Descent(SGD)with the YOLOv7.Using a portion of German traffic signs for training,the study investigates the feasibility of adopting smaller datasets while maintaining high accuracy.The model proposed in this study not only improves traffic safety by detecting traffic signs but also has the potential to contribute to the rapid development of autonomous vehicle systems.The study results showed an impressive accuracy of 99.7%when using a batch size of 8 and the Adam optimizer.This high level of accuracy demonstrates the effectiveness of the proposed model for the image classification task of traffic sign recognition.
文摘This paper is concerned with bipartite consensus tracking for multi-agent systems with unknown disturbances.A barrier function-based adaptive sliding-mode control(SMC)approach is proposed such that the bipartite steady-state error is converged to a predefined region of zero in finite time.Specifically,based on an error auxiliary taking neighboring antagonistic interactions into account,an SMC law is designed with an adaptive gain.The gain can switch to a positive semi-definite barrier function to ensure that the error auxiliary is constrained to a predefined neighborhood of zero,which in turn guarantees practical bipartite consensus tracking.A distinguished feature of the proposed controller is its independence on the bound of disturbances,while the input chattering phenomenon is alleviated.Finally,a numerical example is provided to verify the effectiveness of the proposed controller.
基金This work was supported by the Competitive Research Fund of The University of Aizu,Japan.
文摘Communication between people with disabilities and people who do not understand sign language is a growing social need and can be a tedious task.One of the main functions of sign language is to communicate with each other through hand gestures.Recognition of hand gestures has become an important challenge for the recognition of sign language.There are many existing models that can produce a good accuracy,but if the model test with rotated or translated images,they may face some difficulties to make good performance accuracy.To resolve these challenges of hand gesture recognition,we proposed a Rotation,Translation and Scale-invariant sign word recognition system using a convolu-tional neural network(CNN).We have followed three steps in our work:rotated,translated and scaled(RTS)version dataset generation,gesture segmentation,and sign word classification.Firstly,we have enlarged a benchmark dataset of 20 sign words by making different amounts of Rotation,Translation and Scale of the ori-ginal images to create the RTS version dataset.Then we have applied the gesture segmentation technique.The segmentation consists of three levels,i)Otsu Thresholding with YCbCr,ii)Morphological analysis:dilation through opening morphology and iii)Watershed algorithm.Finally,our designed CNN model has been trained to classify the hand gesture as well as the sign word.Our model has been evaluated using the twenty sign word dataset,five sign word dataset and the RTS version of these datasets.We achieved 99.30%accuracy from the twenty sign word dataset evaluation,99.10%accuracy from the RTS version of the twenty sign word evolution,100%accuracy from thefive sign word dataset evaluation,and 98.00%accuracy from the RTS versionfive sign word dataset evolution.Furthermore,the influence of our model exists in competitive results with state-of-the-art methods in sign word recognition.