First developed 30 years ago,the Compendium of Physical Activities(Compendium)was created to provide a standardized way of measuring and classifying specific physical activities(PAs),allowing researchers and health pr...First developed 30 years ago,the Compendium of Physical Activities(Compendium)was created to provide a standardized way of measuring and classifying specific physical activities(PAs),allowing researchers and health professionals to assess the energy expenditure and health benefits associated with different PA.1Since its inception,the Compendium has been widely utilized and recognized as a fundamental PA and health resource.展开更多
A machine learning(ML)-based random forest(RF)classification model algorithm was employed to investigate the main factors affecting the formation of the core-shell structure of BaTiO_(3)-based ceramics and their inter...A machine learning(ML)-based random forest(RF)classification model algorithm was employed to investigate the main factors affecting the formation of the core-shell structure of BaTiO_(3)-based ceramics and their interpretability was analyzed by using Shapley additive explanations(SHAP).An F1-score changed from 0.8795 to 0.9310,accuracy from 0.8450 to 0.9070,precision from 0.8714 to 0.9000,recall from 0.8929 to 0.9643,and ROC/AUC value of 0.97±0.03 was achieved by the RF classification with the optimal set of features containing only 5 features,demonstrating the high accuracy of our model and its high robustness.During the interpretability analysis of the model,it was found that the electronegativity,melting point,and sintering temperature of the dopant contribute highly to the formation of the core-shell structure,and based on these characteristics,specific ranges were delineated and twelve elements were finally obtained that met all the requirements,namely Si,Sc,Mn,Fe,Co,Ni,Pd,Er,Tm,Lu,Pa,and Cm.In the process of exploring the structure of the core-shell,the doping elements can be effectively localized to be selected by choosing the range of features.展开更多
Manual investigation of chest radiography(CXR)images by physicians is crucial for effective decision-making in COVID-19 diagnosis.However,the high demand during the pandemic necessitates auxiliary help through image a...Manual investigation of chest radiography(CXR)images by physicians is crucial for effective decision-making in COVID-19 diagnosis.However,the high demand during the pandemic necessitates auxiliary help through image analysis and machine learning techniques.This study presents a multi-threshold-based segmentation technique to probe high pixel intensity regions in CXR images of various pathologies,including normal cases.Texture information is extracted using gray co-occurrence matrix(GLCM)-based features,while vessel-like features are obtained using Frangi,Sato,and Meijering filters.Machine learning models employing Decision Tree(DT)and RandomForest(RF)approaches are designed to categorize CXR images into common lung infections,lung opacity(LO),COVID-19,and viral pneumonia(VP).The results demonstrate that the fusion of texture and vesselbased features provides an effective ML model for aiding diagnosis.The ML model validation using performance measures,including an accuracy of approximately 91.8%with an RF-based classifier,supports the usefulness of the feature set and classifier model in categorizing the four different pathologies.Furthermore,the study investigates the importance of the devised features in identifying the underlying pathology and incorporates histogrambased analysis.This analysis reveals varying natural pixel distributions in CXR images belonging to the normal,COVID-19,LO,and VP groups,motivating the incorporation of additional features such as mean,standard deviation,skewness,and percentile based on the filtered images.Notably,the study achieves a considerable improvement in categorizing COVID-19 from LO,with a true positive rate of 97%,further substantiating the effectiveness of the methodology implemented.展开更多
The Internet of Things(IoT)is a growing technology that allows the sharing of data with other devices across wireless networks.Specifically,IoT systems are vulnerable to cyberattacks due to its opennes The proposed wo...The Internet of Things(IoT)is a growing technology that allows the sharing of data with other devices across wireless networks.Specifically,IoT systems are vulnerable to cyberattacks due to its opennes The proposed work intends to implement a new security framework for detecting the most specific and harmful intrusions in IoT networks.In this framework,a Covariance Linear Learning Embedding Selection(CL2ES)methodology is used at first to extract the features highly associated with the IoT intrusions.Then,the Kernel Distributed Bayes Classifier(KDBC)is created to forecast attacks based on the probability distribution value precisely.In addition,a unique Mongolian Gazellas Optimization(MGO)algorithm is used to optimize the weight value for the learning of the classifier.The effectiveness of the proposed CL2ES-KDBC framework has been assessed using several IoT cyber-attack datasets,The obtained results are then compared with current classification methods regarding accuracy(97%),precision(96.5%),and other factors.Computational analysis of the CL2ES-KDBC system on IoT intrusion datasets is performed,which provides valuable insight into its performance,efficiency,and suitability for securing IoT networks.展开更多
The study aims to recognize how efficiently Educational DataMining(EDM)integrates into Artificial Intelligence(AI)to develop skills for predicting students’performance.The study used a survey questionnaire and collec...The study aims to recognize how efficiently Educational DataMining(EDM)integrates into Artificial Intelligence(AI)to develop skills for predicting students’performance.The study used a survey questionnaire and collected data from 300 undergraduate students of Al Neelain University.The first step’s initial population placements were created using Particle Swarm Optimization(PSO).Then,using adaptive feature space search,Educational Grey Wolf Optimization(EGWO)was employed to choose the optimal attribute combination.The second stage uses the SVMclassifier to forecast classification accuracy.Different classifiers were utilized to evaluate the performance of students.According to the results,it was revealed that AI could forecast the final grades of students with an accuracy rate of 97%on the test dataset.Furthermore,the present study showed that successful students could be selected by the Decision Tree model with an efficiency rate of 87.50%and could be categorized as having equal information ratio gain after the semester.While the random forest provided an accuracy of 28%.These findings indicate the higher accuracy rate in the results when these models were implemented on the data set which provides significantly accurate results as compared to a linear regression model with accuracy(12%).The study concluded that the methodology used in this study can prove to be helpful for students and teachers in upgrading academic performance,reducing chances of failure,and taking appropriate steps at the right time to raise the standards of education.The study also motivates academics to assess and discover EDM at several other universities.展开更多
Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation...Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation metric for image classifier models and apply it to the CT image classification of lung cancer. A convolutional neural network is employed as the deep neural network (DNN) image classifier, with the residual network (ResNet) 50 chosen as the DNN archi-tecture. The image data used comprise a lung CT image set. Two classification models are built from datasets with varying amounts of data, and lung cancer is categorized into four classes using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic neighbor embedding to visually explain the data distribution after classification. Experimental results demonstrate that cross en-tropy is a highly useful metric for evaluating the reliability of image classifier models. It is noted that for a more comprehensive evaluation of model perfor-mance, combining with other evaluation metrics is considered essential. .展开更多
Probability theory and mathematical statistics are fundamental courses for various majors in science and engineering.In response to the current teaching situation,we should integrate theory with practice,implement tea...Probability theory and mathematical statistics are fundamental courses for various majors in science and engineering.In response to the current teaching situation,we should integrate theory with practice,implement teaching reform,and carry out teaching innovation.The article carries out blended teaching with deep integration of online and offline modes and within and outside of class,constructing innovative measures of“four integrations and four reshaping.”The article conducts diversified evaluations to stimulate learning motivation and help achieve talent cultivation goals.Through the close integration of probability theory and mathematical statistics course teaching with professional education and practical application,the“three-in-one”teaching goal of value shaping,ability cultivation,and knowledge exploration is achieved.The fundamental task of“cultivating morality and talents”is implemented.展开更多
Day by day,biometric-based systems play a vital role in our daily lives.This paper proposed an intelligent assistant intended to identify emotions via voice message.A biometric system has been developed to detect huma...Day by day,biometric-based systems play a vital role in our daily lives.This paper proposed an intelligent assistant intended to identify emotions via voice message.A biometric system has been developed to detect human emotions based on voice recognition and control a few electronic peripherals for alert actions.This proposed smart assistant aims to provide a support to the people through buzzer and light emitting diodes(LED)alert signals and it also keep track of the places like households,hospitals and remote areas,etc.The proposed approach is able to detect seven emotions:worry,surprise,neutral,sadness,happiness,hate and love.The key elements for the implementation of speech emotion recognition are voice processing,and once the emotion is recognized,the machine interface automatically detects the actions by buzzer and LED.The proposed system is trained and tested on various benchmark datasets,i.e.,Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS)database,Acoustic-Phonetic Continuous Speech Corpus(TIMIT)database,Emotional Speech database(Emo-DB)database and evaluated based on various parameters,i.e.,accuracy,error rate,and time.While comparing with existing technologies,the proposed algorithm gave a better error rate and less time.Error rate and time is decreased by 19.79%,5.13 s.for the RAVDEES dataset,15.77%,0.01 s for the Emo-DB dataset and 14.88%,3.62 for the TIMIT database.The proposed model shows better accuracy of 81.02%for the RAVDEES dataset,84.23%for the TIMIT dataset and 85.12%for the Emo-DB dataset compared to Gaussian Mixture Modeling(GMM)and Support Vector Machine(SVM)Model.展开更多
For a long time,legal entities have developed and used crime prediction methodologies.The techniques are frequently updated based on crime evaluations and responses from scientific communities.There is a need to devel...For a long time,legal entities have developed and used crime prediction methodologies.The techniques are frequently updated based on crime evaluations and responses from scientific communities.There is a need to develop type-based crime prediction methodologies that can be used to address issues at the subgroup level.Child maltreatment is not adequately addressed because children are voiceless.As a result,the possibility of developing a model for predicting child abuse was investigated in this study.Various exploratory analysis methods were used to examine the city of Chicago’s child abuse events.The data set was balanced using the Borderline-SMOTE technique,and then a stacking classifier was employed to ensemble multiple algorithms to predict various types of child abuse.The proposed approach successfully predicted crime types with 93%of accuracy,precision,recall,and F1-Score.The AUC value of the same was 0.989.However,when compared to the Extra Trees model(17.55),which is the second best,the proposed model’s execution time was significantly longer(476.63).We discovered that Machine Learning methods effectively evaluate the demographic and spatial-temporal characteristics of the crimes and predict the occurrences of various subtypes of child abuse.The results indicated that the proposed Borderline-SMOTE enabled Stacking Classifier model(BS-SC Model)would be effective in the real-time child abuse prediction and prevention process.展开更多
Multiple classifier system exhibits strong classification capacity compared with single classifiers,but they require significant computational resources.Selective ensemble system aims to attain equivalent or better cl...Multiple classifier system exhibits strong classification capacity compared with single classifiers,but they require significant computational resources.Selective ensemble system aims to attain equivalent or better classification accuracy with fewer classifiers.However,current methods fail to identify precise solutions for constructing an ensemble classifier.In this study,we propose an ensemble classifier design technique based on the perturbation binary salp swarm algorithm(ECDPB).Considering that extreme learning machines(ELMs)have rapid learning rates and good generalization ability,they can serve as the basic classifier for creating multiple candidates while using fewer computational resources.Meanwhile,we introduce a combined diversity measure by taking the complementarity and accuracy of ELMs into account;it is used to identify the ELMs that have good diversity and low error.In addition,we propose an ECDPB with powerful optimizing ability;it is employed to find the optimal subset of ELMs.The selected ELMs can then be used to forman ensemble classifier.Experiments on 10 benchmark datasets have been conducted,and the results demonstrate that the proposed ECDPB delivers superior classification capacity when compared with alternative methods.展开更多
Voice classification is important in creating more intelligent systems that help with student exams,identifying criminals,and security systems.The main aim of the research is to develop a system able to predicate and ...Voice classification is important in creating more intelligent systems that help with student exams,identifying criminals,and security systems.The main aim of the research is to develop a system able to predicate and classify gender,age,and accent.So,a newsystem calledClassifyingVoice Gender,Age,and Accent(CVGAA)is proposed.Backpropagation and bagging algorithms are designed to improve voice recognition systems that incorporate sensory voice features such as rhythm-based features used to train the device to distinguish between the two gender categories.It has high precision compared to other algorithms used in this problem,as the adaptive backpropagation algorithm had an accuracy of 98%and the Bagging algorithm had an accuracy of 98.10%in the gender identification data.Bagging has the best accuracy among all algorithms,with 55.39%accuracy in the voice common dataset and age classification and accent accuracy in a speech accent of 78.94%.展开更多
Mobile Ad Hoc Networks(MANET)is the framework for social networking with a realistic framework.In theMANETenvironment,based on the query,information is transmitted between the sender and receiver.In the MANET network,...Mobile Ad Hoc Networks(MANET)is the framework for social networking with a realistic framework.In theMANETenvironment,based on the query,information is transmitted between the sender and receiver.In the MANET network,the nodes within the communication range are involved in data transmission.Even the nodes that lie outside of the communication range are involved in the transmission of relay messages.However,due to the openness and frequent mobility of nodes,they are subjected to the vast range of security threats inMANET.Hence,it is necessary to develop an appropriate security mechanism for the dataMANET environment for data transmission.This paper proposed a security framework for the MANET network signature escrow scheme.The proposed framework uses the centralised Software Defined Network(SDN)with an ECC cryptographic technique.The developed security framework is stated as Escrow Elliptical Curve Cryptography SDN(EsECC_SDN)for attack detection and classification.The developed EsECC-SDN was adopted in two stages for attack classification and detection:(1)to perform secure data transmission between nodes SDN performs encryption and decryption of the data;and(2)to detect and classifies the attack in theMANET hyper alert based HiddenMarkovModel Transductive Deep Learning.Furthermore,the EsECC_SDN is involved in the assignment of labels in the transmitted data in the database(DB).The escrow handles these processes,and attacks are evaluated using the hyper alert.The labels are assigned based on the k-medoids attack clustering through label assignment through a transductive deep learning model.The proposed model uses the CICIDS dataset for attack detection and classification.The developed framework EsECC_SDN’s performance is compared to that of other classifiers such as AdaBoost,Regression,and Decision Tree.The performance of the proposed EsECC_SDN exhibits∼3%improved performance compared with conventional techniques.展开更多
Biometric recognition refers to the identification of individuals through their unique behavioral features(e.g.,fingerprint,face,and iris).We need distinguishing characteristics to identify people,such as fingerprints...Biometric recognition refers to the identification of individuals through their unique behavioral features(e.g.,fingerprint,face,and iris).We need distinguishing characteristics to identify people,such as fingerprints,which are world-renowned as the most reliablemethod to identify people.The recognition of fingerprints has become a standard procedure in forensics,and different techniques are available for this purpose.Most current techniques lack interest in image enhancement and rely on high-dimensional features to generate classification models.Therefore,we proposed an effective fingerprint classification method for classifying the fingerprint image as authentic or altered since criminals and hackers routinely change their fingerprints to generate fake ones.In order to improve fingerprint classification accuracy,our proposed method used the most effective texture features and classifiers.Discriminant Analysis(DCA)and Gaussian Discriminant Analysis(GDA)are employed as classifiers,along with Histogram of Oriented Gradient(HOG)and Segmentation-based Feature Texture Analysis(SFTA)feature vectors as inputs.The performance of the classifiers is determined by assessing a range of feature sets,and the most accurate results are obtained.The proposed method is tested using a Sokoto Coventry Fingerprint Dataset(SOCOFing).The SOCOFing project includes 6,000 fingerprint images collected from 600 African people whose fingerprints were taken ten times.Three distinct degrees of obliteration,central rotation,and z-cut have been performed to obtain synthetically altered replicas of the genuine fingerprints.The proposal achieved massive success with a classification accuracy reaching 99%.The experimental results indicate that the proposed method for fingerprint classification is feasible and effective.The experiments also showed that the proposed SFTA-based GDA method outperformed state-of-art approaches in feature dimension and classification accuracy.展开更多
The use of freely-available multi-source imagery for mapping vegetation in montane terrain is important for many developing countries that do not have the funding for high-resolution data capture.Radar images are also...The use of freely-available multi-source imagery for mapping vegetation in montane terrain is important for many developing countries that do not have the funding for high-resolution data capture.Radar images are also now freely available and include Sentinel-1 in dual polarisation,and PALSAR-2.These images can penetrate cloud cover and provide the advantage of acquiring data in a cloudy tropical region.This research evaluated whether the addition of radar with optical and topographic data improves classification accuracy in a montane region in Sri Lanka.Six classification experiments were designed based on different combinations of image data to test whether radar data improved land cover classification accuracy compared with optical data alone.Random forest classifier in the Google Earth Engine has been utilised to classify the tropical montane vegetation.The results indicate that radar or optical data alone cannot obtain satisfactory results.However,when combining radar with optical data the overall accuracy increased by approximately 5%,and by an additional 2%when topography data were added.The highest accuracy(92%)was achieved with multiple imagery,and adding the vegetation indices improved the model slightly by 0.3%.In addition,feature importance analysis showed that radar data makes a significant contribution to the classification.These positive outcomes demonstrate that freely-accessible multi-source remotely-sensed data have impressive capability for vegetation mapping,and support the monitoring and managing of forest ecological resources in tropical montane regions.展开更多
Epilepsy is a common neurological disorder that occurs at all ages.Epilepsy not only brings physical pain to patients,but also brings a huge burden to the lives of patients and their families.At present,epilepsy detec...Epilepsy is a common neurological disorder that occurs at all ages.Epilepsy not only brings physical pain to patients,but also brings a huge burden to the lives of patients and their families.At present,epilepsy detection is still achieved through the observation of electroencephalography(EEG)by medical staff.However,this process takes a long time and consumes energy,which will create a huge workload to medical staff.Therefore,it is particularly important to realize the automatic detection of epilepsy.This paper introduces,in detail,the overall framework of EEG-based automatic epilepsy identification and the typical methods involved in each step.Aiming at the core modules,that is,signal acquisition analog front end(AFE),feature extraction and classifier selection,method summary and theoretical explanation are carried out.Finally,the future research directions in the field of automatic detection of epilepsy are prospected.展开更多
A single-qubit quantum classifier(SQC)based on a gradient-free optimization(GFO)algorithm,named the GFO-based SQC,is proposed to overcome the effects of barren plateaus caused by quantum devices.Here,a rotation gate R...A single-qubit quantum classifier(SQC)based on a gradient-free optimization(GFO)algorithm,named the GFO-based SQC,is proposed to overcome the effects of barren plateaus caused by quantum devices.Here,a rotation gate R_(X)(φ)is applied on the single-qubit binary quantum classifier,and the training data and parameters are loaded intoφin the form of vector multiplication.The cost function is decreased by finding the value of each parameter that yields the minimum expectation value of measuring the quantum circuit.The algorithm is performed iteratively for all parameters one by one until the cost function satisfies the stop condition.The proposed GFO-based SQC is demonstrated for classification tasks in Iris and MNIST datasets and compared with the Adam-based SQC and the quantum support vector machine(QSVM).Furthermore,the performance of the GFO-based SQC is discussed when the rotation gate in the quantum device is under different types of noise.The simulation results show that the GFO-based SQC can reach a high accuracy in reduced time.Additionally,the proposed GFO algorithm can quickly complete the training process of the SQC.Importantly,the GFO-based SQC has a good performance in noisy environments.展开更多
A main task in condensed-matter physics is to recognize,classify,and characterize phases of matter and the corresponding phase transitions,for which machine learning provides a new class of research tools due to the r...A main task in condensed-matter physics is to recognize,classify,and characterize phases of matter and the corresponding phase transitions,for which machine learning provides a new class of research tools due to the remarkable development in computing power and algorithms.Despite much exploration in this new field,usually different methods and techniques are needed for different scenarios.Here,we present SimCLP:a simple framework for contrastive learning phases of matter,which is inspired by the recent development in contrastive learning of visual representations.We demonstrate the success of this framework on several representative systems,including non-interacting and quantum many-body,conventional and topological.SimCLP is flexible and free of usual burdens such as manual feature engineering and prior knowledge.The only prerequisite is to prepare enough state configurations.Furthermore,it can generate representation vectors and labels and hence help tackle other problems.SimCLP therefore paves an alternative way to the development of a generic tool for identifying unexplored phase transitions.展开更多
Subclassification of tumors based on molecular features may facilitate therapeutic choice and increase the response rate of cancer patients.However,the highly complex cell origin involved in osteosarcoma(OS)limits the...Subclassification of tumors based on molecular features may facilitate therapeutic choice and increase the response rate of cancer patients.However,the highly complex cell origin involved in osteosarcoma(OS)limits the utility of traditional bulk RNA sequencing for OS subclassification.Single-cell RNA sequencing(sc RNA-seq)holds great promise for identifying cell heterogeneity.However,this technique has rarely been used in the study of tumor subclassification.By analyzing sc RNA-seq data for six conventional OS and nine cancellous bone(CB)samples,we identified 29 clusters in OS and CB samples and discovered three differentiation trajectories from the cancer stem cell(CSC)-like subset,which allowed us to classify OS samples into three groups.The classification model was further examined using the TARGET dataset.Each subgroup of OS had different prognoses and possible drug sensitivities,and OS cells in the three differentiation branches showed distinct interactions with other clusters in the OS microenvironment.In addition,we verified the classification model through IHC staining in 138 OS samples,revealing a worse prognosis for Group B patients.Furthermore,we describe the novel transcriptional program of CSCs and highlight the activation of EZH2 in CSCs of OS.These findings provide a novel subclassification method based on sc RNA-seq and shed new light on the molecular features of CSCs in OS and may serve as valuable references for precision treatment for and therapeutic development in OS.展开更多
One of the most common types of threats to the digital world is malicious software.It is of great importance to detect and prevent existing and new malware before it damages information assets.Machine learning approac...One of the most common types of threats to the digital world is malicious software.It is of great importance to detect and prevent existing and new malware before it damages information assets.Machine learning approaches are used effectively for this purpose.In this study,we present a model in which supervised and unsupervised learning algorithms are used together.Clustering is used to enhance the prediction performance of the supervised classifiers.The aim of the proposed model is to make predictions in the shortest possible time with high accuracy and f1 score.In the first stage of the model,the data are clustered with the k-means algorithm.In the second stage,the prediction is made with the combination of the classifier with the best prediction performance for the related cluster.While choosing the best classifiers for the given clusters,triple combinations of ten machine learning algorithms(kernel support vector machine,k-nearest neighbor,naive Bayes,decision tree,random forest,extra gradient boosting,categorical boosting,adaptive boosting,extra trees,and gradient boosting)are used.The selected triple classifier combination is positioned in two stages.The prediction time of the model is improved by positioning the classifier with the slowest prediction time in the second stage.The selected triple classifier combination is positioned in two tiers.The prediction time of the model is improved by positioning the classifier with the highest prediction time in the second tier.It is seen that clustering before classification improves prediction performance,which is presented using Blue Hexagon Open Dataset for Malware Analysis(BODMAS),Elastic Malware Benchmark for Empowering Researchers(EMBER)2018 and Kaggle malware detection datasets.The model has 99.74%accuracy and 99.77%f1 score for the BODMAS dataset,99.04%accuracy and 98.63%f1 score for the Kaggle malware detection dataset,and 96.77%accuracy and 96.77%f1 score for the EMBER 2018 dataset.In addition,the tiered positioning of classifiers shortened the average prediction time by 76.13%for the BODMAS dataset and 95.95%for the EMBER 2018 dataset.The proposed method’s prediction performance is better than the rest of the studies in the literature in which BODMAS and EMBER 2018 datasets are used.展开更多
In defense-in-depth,humans have always been the weakest link in cybersecurity.However,unlike common threats,social engineering poses vulnerabilities not directly quantifiable in penetration testing.Most skilled social...In defense-in-depth,humans have always been the weakest link in cybersecurity.However,unlike common threats,social engineering poses vulnerabilities not directly quantifiable in penetration testing.Most skilled social engineers trick users into giving up information voluntarily through attacks like phishing and adware.Social Engineering(SE)in social media is structurally similar to regular posts but contains malicious intrinsic meaning within the sentence semantic.In this paper,a novel SE model is trained using a Recurrent Neural Network Long Short Term Memory(RNN-LSTM)to identify well-disguised SE threats in social media posts.We use a custom dataset crawled from hundreds of corporate and personal Facebook posts.First,the social engineering attack detection pipeline(SEAD)is designed to filter out social posts with malicious intents using domain heuristics.Next,each social media post is tokenized into sentences and then analyzed with a sentiment analyzer before being labelled as an anomaly or normal training data.Then,we train an RNN-LSTM model to detect five types of social engineering attacks that potentially contain signs of information gathering.The experimental result showed that the Social Engineering Attack(SEA)model achieves 0.84 in classification precision and 0.81 in recall compared to the ground truth labeled by network experts.The experimental results showed that the semantics and linguistics similarities are an effective indicator for early detection of SEA.展开更多
文摘First developed 30 years ago,the Compendium of Physical Activities(Compendium)was created to provide a standardized way of measuring and classifying specific physical activities(PAs),allowing researchers and health professionals to assess the energy expenditure and health benefits associated with different PA.1Since its inception,the Compendium has been widely utilized and recognized as a fundamental PA and health resource.
基金Funded by the National Key Research and Development Program of China(No.2023YFB3812200)。
文摘A machine learning(ML)-based random forest(RF)classification model algorithm was employed to investigate the main factors affecting the formation of the core-shell structure of BaTiO_(3)-based ceramics and their interpretability was analyzed by using Shapley additive explanations(SHAP).An F1-score changed from 0.8795 to 0.9310,accuracy from 0.8450 to 0.9070,precision from 0.8714 to 0.9000,recall from 0.8929 to 0.9643,and ROC/AUC value of 0.97±0.03 was achieved by the RF classification with the optimal set of features containing only 5 features,demonstrating the high accuracy of our model and its high robustness.During the interpretability analysis of the model,it was found that the electronegativity,melting point,and sintering temperature of the dopant contribute highly to the formation of the core-shell structure,and based on these characteristics,specific ranges were delineated and twelve elements were finally obtained that met all the requirements,namely Si,Sc,Mn,Fe,Co,Ni,Pd,Er,Tm,Lu,Pa,and Cm.In the process of exploring the structure of the core-shell,the doping elements can be effectively localized to be selected by choosing the range of features.
文摘Manual investigation of chest radiography(CXR)images by physicians is crucial for effective decision-making in COVID-19 diagnosis.However,the high demand during the pandemic necessitates auxiliary help through image analysis and machine learning techniques.This study presents a multi-threshold-based segmentation technique to probe high pixel intensity regions in CXR images of various pathologies,including normal cases.Texture information is extracted using gray co-occurrence matrix(GLCM)-based features,while vessel-like features are obtained using Frangi,Sato,and Meijering filters.Machine learning models employing Decision Tree(DT)and RandomForest(RF)approaches are designed to categorize CXR images into common lung infections,lung opacity(LO),COVID-19,and viral pneumonia(VP).The results demonstrate that the fusion of texture and vesselbased features provides an effective ML model for aiding diagnosis.The ML model validation using performance measures,including an accuracy of approximately 91.8%with an RF-based classifier,supports the usefulness of the feature set and classifier model in categorizing the four different pathologies.Furthermore,the study investigates the importance of the devised features in identifying the underlying pathology and incorporates histogrambased analysis.This analysis reveals varying natural pixel distributions in CXR images belonging to the normal,COVID-19,LO,and VP groups,motivating the incorporation of additional features such as mean,standard deviation,skewness,and percentile based on the filtered images.Notably,the study achieves a considerable improvement in categorizing COVID-19 from LO,with a true positive rate of 97%,further substantiating the effectiveness of the methodology implemented.
文摘The Internet of Things(IoT)is a growing technology that allows the sharing of data with other devices across wireless networks.Specifically,IoT systems are vulnerable to cyberattacks due to its opennes The proposed work intends to implement a new security framework for detecting the most specific and harmful intrusions in IoT networks.In this framework,a Covariance Linear Learning Embedding Selection(CL2ES)methodology is used at first to extract the features highly associated with the IoT intrusions.Then,the Kernel Distributed Bayes Classifier(KDBC)is created to forecast attacks based on the probability distribution value precisely.In addition,a unique Mongolian Gazellas Optimization(MGO)algorithm is used to optimize the weight value for the learning of the classifier.The effectiveness of the proposed CL2ES-KDBC framework has been assessed using several IoT cyber-attack datasets,The obtained results are then compared with current classification methods regarding accuracy(97%),precision(96.5%),and other factors.Computational analysis of the CL2ES-KDBC system on IoT intrusion datasets is performed,which provides valuable insight into its performance,efficiency,and suitability for securing IoT networks.
基金supported via funding from Prince Sattam bin Abdulaziz University Project Number(PSAU/2024/R/1445).
文摘The study aims to recognize how efficiently Educational DataMining(EDM)integrates into Artificial Intelligence(AI)to develop skills for predicting students’performance.The study used a survey questionnaire and collected data from 300 undergraduate students of Al Neelain University.The first step’s initial population placements were created using Particle Swarm Optimization(PSO).Then,using adaptive feature space search,Educational Grey Wolf Optimization(EGWO)was employed to choose the optimal attribute combination.The second stage uses the SVMclassifier to forecast classification accuracy.Different classifiers were utilized to evaluate the performance of students.According to the results,it was revealed that AI could forecast the final grades of students with an accuracy rate of 97%on the test dataset.Furthermore,the present study showed that successful students could be selected by the Decision Tree model with an efficiency rate of 87.50%and could be categorized as having equal information ratio gain after the semester.While the random forest provided an accuracy of 28%.These findings indicate the higher accuracy rate in the results when these models were implemented on the data set which provides significantly accurate results as compared to a linear regression model with accuracy(12%).The study concluded that the methodology used in this study can prove to be helpful for students and teachers in upgrading academic performance,reducing chances of failure,and taking appropriate steps at the right time to raise the standards of education.The study also motivates academics to assess and discover EDM at several other universities.
文摘Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation metric for image classifier models and apply it to the CT image classification of lung cancer. A convolutional neural network is employed as the deep neural network (DNN) image classifier, with the residual network (ResNet) 50 chosen as the DNN archi-tecture. The image data used comprise a lung CT image set. Two classification models are built from datasets with varying amounts of data, and lung cancer is categorized into four classes using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic neighbor embedding to visually explain the data distribution after classification. Experimental results demonstrate that cross en-tropy is a highly useful metric for evaluating the reliability of image classifier models. It is noted that for a more comprehensive evaluation of model perfor-mance, combining with other evaluation metrics is considered essential. .
文摘Probability theory and mathematical statistics are fundamental courses for various majors in science and engineering.In response to the current teaching situation,we should integrate theory with practice,implement teaching reform,and carry out teaching innovation.The article carries out blended teaching with deep integration of online and offline modes and within and outside of class,constructing innovative measures of“four integrations and four reshaping.”The article conducts diversified evaluations to stimulate learning motivation and help achieve talent cultivation goals.Through the close integration of probability theory and mathematical statistics course teaching with professional education and practical application,the“three-in-one”teaching goal of value shaping,ability cultivation,and knowledge exploration is achieved.The fundamental task of“cultivating morality and talents”is implemented.
基金Deanship of Scientific Research at Majmaah University for supporting this work under Project No.R-2022-166.
文摘Day by day,biometric-based systems play a vital role in our daily lives.This paper proposed an intelligent assistant intended to identify emotions via voice message.A biometric system has been developed to detect human emotions based on voice recognition and control a few electronic peripherals for alert actions.This proposed smart assistant aims to provide a support to the people through buzzer and light emitting diodes(LED)alert signals and it also keep track of the places like households,hospitals and remote areas,etc.The proposed approach is able to detect seven emotions:worry,surprise,neutral,sadness,happiness,hate and love.The key elements for the implementation of speech emotion recognition are voice processing,and once the emotion is recognized,the machine interface automatically detects the actions by buzzer and LED.The proposed system is trained and tested on various benchmark datasets,i.e.,Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS)database,Acoustic-Phonetic Continuous Speech Corpus(TIMIT)database,Emotional Speech database(Emo-DB)database and evaluated based on various parameters,i.e.,accuracy,error rate,and time.While comparing with existing technologies,the proposed algorithm gave a better error rate and less time.Error rate and time is decreased by 19.79%,5.13 s.for the RAVDEES dataset,15.77%,0.01 s for the Emo-DB dataset and 14.88%,3.62 for the TIMIT database.The proposed model shows better accuracy of 81.02%for the RAVDEES dataset,84.23%for the TIMIT dataset and 85.12%for the Emo-DB dataset compared to Gaussian Mixture Modeling(GMM)and Support Vector Machine(SVM)Model.
文摘For a long time,legal entities have developed and used crime prediction methodologies.The techniques are frequently updated based on crime evaluations and responses from scientific communities.There is a need to develop type-based crime prediction methodologies that can be used to address issues at the subgroup level.Child maltreatment is not adequately addressed because children are voiceless.As a result,the possibility of developing a model for predicting child abuse was investigated in this study.Various exploratory analysis methods were used to examine the city of Chicago’s child abuse events.The data set was balanced using the Borderline-SMOTE technique,and then a stacking classifier was employed to ensemble multiple algorithms to predict various types of child abuse.The proposed approach successfully predicted crime types with 93%of accuracy,precision,recall,and F1-Score.The AUC value of the same was 0.989.However,when compared to the Extra Trees model(17.55),which is the second best,the proposed model’s execution time was significantly longer(476.63).We discovered that Machine Learning methods effectively evaluate the demographic and spatial-temporal characteristics of the crimes and predict the occurrences of various subtypes of child abuse.The results indicated that the proposed Borderline-SMOTE enabled Stacking Classifier model(BS-SC Model)would be effective in the real-time child abuse prediction and prevention process.
基金supported in part by the Anhui Provincial Natural Science Founda-tion[1908085QG298,1908085MG232]the National Nature Science Foundation of China[91546108,61806068]+5 种基金the National Social Science Foundation of China[21BTJ002]the Anhui Provincial Science:and Technology Major Projects Grant[201903a05020020]the Fundamental Research Funds for the Central Universities[Z2019HGTA0053,JZ2019HG BZ0128]the Humanities and Social Science Fund of Ministry of Education of China[20YJA790021]the Major Project of Philosophy and Social Science Planning of Zhejiang Province[22YJRC07ZD]the Open Research Fund Program of Key Laboratory of Process Optimization and Intelligent Decision-Making(Hefei University of Technology),Ministry of Education.
文摘Multiple classifier system exhibits strong classification capacity compared with single classifiers,but they require significant computational resources.Selective ensemble system aims to attain equivalent or better classification accuracy with fewer classifiers.However,current methods fail to identify precise solutions for constructing an ensemble classifier.In this study,we propose an ensemble classifier design technique based on the perturbation binary salp swarm algorithm(ECDPB).Considering that extreme learning machines(ELMs)have rapid learning rates and good generalization ability,they can serve as the basic classifier for creating multiple candidates while using fewer computational resources.Meanwhile,we introduce a combined diversity measure by taking the complementarity and accuracy of ELMs into account;it is used to identify the ELMs that have good diversity and low error.In addition,we propose an ECDPB with powerful optimizing ability;it is employed to find the optimal subset of ELMs.The selected ELMs can then be used to forman ensemble classifier.Experiments on 10 benchmark datasets have been conducted,and the results demonstrate that the proposed ECDPB delivers superior classification capacity when compared with alternative methods.
文摘Voice classification is important in creating more intelligent systems that help with student exams,identifying criminals,and security systems.The main aim of the research is to develop a system able to predicate and classify gender,age,and accent.So,a newsystem calledClassifyingVoice Gender,Age,and Accent(CVGAA)is proposed.Backpropagation and bagging algorithms are designed to improve voice recognition systems that incorporate sensory voice features such as rhythm-based features used to train the device to distinguish between the two gender categories.It has high precision compared to other algorithms used in this problem,as the adaptive backpropagation algorithm had an accuracy of 98%and the Bagging algorithm had an accuracy of 98.10%in the gender identification data.Bagging has the best accuracy among all algorithms,with 55.39%accuracy in the voice common dataset and age classification and accent accuracy in a speech accent of 78.94%.
基金Deanship of Scientific Research at Umm Al-Qura University,Grant Code,funds this research:22UQU4281768DSR05.
文摘Mobile Ad Hoc Networks(MANET)is the framework for social networking with a realistic framework.In theMANETenvironment,based on the query,information is transmitted between the sender and receiver.In the MANET network,the nodes within the communication range are involved in data transmission.Even the nodes that lie outside of the communication range are involved in the transmission of relay messages.However,due to the openness and frequent mobility of nodes,they are subjected to the vast range of security threats inMANET.Hence,it is necessary to develop an appropriate security mechanism for the dataMANET environment for data transmission.This paper proposed a security framework for the MANET network signature escrow scheme.The proposed framework uses the centralised Software Defined Network(SDN)with an ECC cryptographic technique.The developed security framework is stated as Escrow Elliptical Curve Cryptography SDN(EsECC_SDN)for attack detection and classification.The developed EsECC-SDN was adopted in two stages for attack classification and detection:(1)to perform secure data transmission between nodes SDN performs encryption and decryption of the data;and(2)to detect and classifies the attack in theMANET hyper alert based HiddenMarkovModel Transductive Deep Learning.Furthermore,the EsECC_SDN is involved in the assignment of labels in the transmitted data in the database(DB).The escrow handles these processes,and attacks are evaluated using the hyper alert.The labels are assigned based on the k-medoids attack clustering through label assignment through a transductive deep learning model.The proposed model uses the CICIDS dataset for attack detection and classification.The developed framework EsECC_SDN’s performance is compared to that of other classifiers such as AdaBoost,Regression,and Decision Tree.The performance of the proposed EsECC_SDN exhibits∼3%improved performance compared with conventional techniques.
文摘Biometric recognition refers to the identification of individuals through their unique behavioral features(e.g.,fingerprint,face,and iris).We need distinguishing characteristics to identify people,such as fingerprints,which are world-renowned as the most reliablemethod to identify people.The recognition of fingerprints has become a standard procedure in forensics,and different techniques are available for this purpose.Most current techniques lack interest in image enhancement and rely on high-dimensional features to generate classification models.Therefore,we proposed an effective fingerprint classification method for classifying the fingerprint image as authentic or altered since criminals and hackers routinely change their fingerprints to generate fake ones.In order to improve fingerprint classification accuracy,our proposed method used the most effective texture features and classifiers.Discriminant Analysis(DCA)and Gaussian Discriminant Analysis(GDA)are employed as classifiers,along with Histogram of Oriented Gradient(HOG)and Segmentation-based Feature Texture Analysis(SFTA)feature vectors as inputs.The performance of the classifiers is determined by assessing a range of feature sets,and the most accurate results are obtained.The proposed method is tested using a Sokoto Coventry Fingerprint Dataset(SOCOFing).The SOCOFing project includes 6,000 fingerprint images collected from 600 African people whose fingerprints were taken ten times.Three distinct degrees of obliteration,central rotation,and z-cut have been performed to obtain synthetically altered replicas of the genuine fingerprints.The proposal achieved massive success with a classification accuracy reaching 99%.The experimental results indicate that the proposed method for fingerprint classification is feasible and effective.The experiments also showed that the proposed SFTA-based GDA method outperformed state-of-art approaches in feature dimension and classification accuracy.
文摘The use of freely-available multi-source imagery for mapping vegetation in montane terrain is important for many developing countries that do not have the funding for high-resolution data capture.Radar images are also now freely available and include Sentinel-1 in dual polarisation,and PALSAR-2.These images can penetrate cloud cover and provide the advantage of acquiring data in a cloudy tropical region.This research evaluated whether the addition of radar with optical and topographic data improves classification accuracy in a montane region in Sri Lanka.Six classification experiments were designed based on different combinations of image data to test whether radar data improved land cover classification accuracy compared with optical data alone.Random forest classifier in the Google Earth Engine has been utilised to classify the tropical montane vegetation.The results indicate that radar or optical data alone cannot obtain satisfactory results.However,when combining radar with optical data the overall accuracy increased by approximately 5%,and by an additional 2%when topography data were added.The highest accuracy(92%)was achieved with multiple imagery,and adding the vegetation indices improved the model slightly by 0.3%.In addition,feature importance analysis showed that radar data makes a significant contribution to the classification.These positive outcomes demonstrate that freely-accessible multi-source remotely-sensed data have impressive capability for vegetation mapping,and support the monitoring and managing of forest ecological resources in tropical montane regions.
基金supported by the Strategic Priority Research Program of Chinese Academy of Sciences,Grant No.XDA0330000 and Grant No.XDB44000000。
文摘Epilepsy is a common neurological disorder that occurs at all ages.Epilepsy not only brings physical pain to patients,but also brings a huge burden to the lives of patients and their families.At present,epilepsy detection is still achieved through the observation of electroencephalography(EEG)by medical staff.However,this process takes a long time and consumes energy,which will create a huge workload to medical staff.Therefore,it is particularly important to realize the automatic detection of epilepsy.This paper introduces,in detail,the overall framework of EEG-based automatic epilepsy identification and the typical methods involved in each step.Aiming at the core modules,that is,signal acquisition analog front end(AFE),feature extraction and classifier selection,method summary and theoretical explanation are carried out.Finally,the future research directions in the field of automatic detection of epilepsy are prospected.
基金Project supported by the National Natural Science Foundation of China(Grant No.62375140)Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX190900)。
文摘A single-qubit quantum classifier(SQC)based on a gradient-free optimization(GFO)algorithm,named the GFO-based SQC,is proposed to overcome the effects of barren plateaus caused by quantum devices.Here,a rotation gate R_(X)(φ)is applied on the single-qubit binary quantum classifier,and the training data and parameters are loaded intoφin the form of vector multiplication.The cost function is decreased by finding the value of each parameter that yields the minimum expectation value of measuring the quantum circuit.The algorithm is performed iteratively for all parameters one by one until the cost function satisfies the stop condition.The proposed GFO-based SQC is demonstrated for classification tasks in Iris and MNIST datasets and compared with the Adam-based SQC and the quantum support vector machine(QSVM).Furthermore,the performance of the GFO-based SQC is discussed when the rotation gate in the quantum device is under different types of noise.The simulation results show that the GFO-based SQC can reach a high accuracy in reduced time.Additionally,the proposed GFO algorithm can quickly complete the training process of the SQC.Importantly,the GFO-based SQC has a good performance in noisy environments.
基金supported by the National Natural Science Foundation of China(Grant Nos.11874421 and 11934020)。
文摘A main task in condensed-matter physics is to recognize,classify,and characterize phases of matter and the corresponding phase transitions,for which machine learning provides a new class of research tools due to the remarkable development in computing power and algorithms.Despite much exploration in this new field,usually different methods and techniques are needed for different scenarios.Here,we present SimCLP:a simple framework for contrastive learning phases of matter,which is inspired by the recent development in contrastive learning of visual representations.We demonstrate the success of this framework on several representative systems,including non-interacting and quantum many-body,conventional and topological.SimCLP is flexible and free of usual burdens such as manual feature engineering and prior knowledge.The only prerequisite is to prepare enough state configurations.Furthermore,it can generate representation vectors and labels and hence help tackle other problems.SimCLP therefore paves an alternative way to the development of a generic tool for identifying unexplored phase transitions.
基金National Natural Science Foundation of China(Nos.31970663 and 82173028 to J.X.,No.81874180 to T.W.,No.81201556 to W.Z.,No.82072971 to H.W.and No.81972505 to Z.W.)。
文摘Subclassification of tumors based on molecular features may facilitate therapeutic choice and increase the response rate of cancer patients.However,the highly complex cell origin involved in osteosarcoma(OS)limits the utility of traditional bulk RNA sequencing for OS subclassification.Single-cell RNA sequencing(sc RNA-seq)holds great promise for identifying cell heterogeneity.However,this technique has rarely been used in the study of tumor subclassification.By analyzing sc RNA-seq data for six conventional OS and nine cancellous bone(CB)samples,we identified 29 clusters in OS and CB samples and discovered three differentiation trajectories from the cancer stem cell(CSC)-like subset,which allowed us to classify OS samples into three groups.The classification model was further examined using the TARGET dataset.Each subgroup of OS had different prognoses and possible drug sensitivities,and OS cells in the three differentiation branches showed distinct interactions with other clusters in the OS microenvironment.In addition,we verified the classification model through IHC staining in 138 OS samples,revealing a worse prognosis for Group B patients.Furthermore,we describe the novel transcriptional program of CSCs and highlight the activation of EZH2 in CSCs of OS.These findings provide a novel subclassification method based on sc RNA-seq and shed new light on the molecular features of CSCs in OS and may serve as valuable references for precision treatment for and therapeutic development in OS.
文摘One of the most common types of threats to the digital world is malicious software.It is of great importance to detect and prevent existing and new malware before it damages information assets.Machine learning approaches are used effectively for this purpose.In this study,we present a model in which supervised and unsupervised learning algorithms are used together.Clustering is used to enhance the prediction performance of the supervised classifiers.The aim of the proposed model is to make predictions in the shortest possible time with high accuracy and f1 score.In the first stage of the model,the data are clustered with the k-means algorithm.In the second stage,the prediction is made with the combination of the classifier with the best prediction performance for the related cluster.While choosing the best classifiers for the given clusters,triple combinations of ten machine learning algorithms(kernel support vector machine,k-nearest neighbor,naive Bayes,decision tree,random forest,extra gradient boosting,categorical boosting,adaptive boosting,extra trees,and gradient boosting)are used.The selected triple classifier combination is positioned in two stages.The prediction time of the model is improved by positioning the classifier with the slowest prediction time in the second stage.The selected triple classifier combination is positioned in two tiers.The prediction time of the model is improved by positioning the classifier with the highest prediction time in the second tier.It is seen that clustering before classification improves prediction performance,which is presented using Blue Hexagon Open Dataset for Malware Analysis(BODMAS),Elastic Malware Benchmark for Empowering Researchers(EMBER)2018 and Kaggle malware detection datasets.The model has 99.74%accuracy and 99.77%f1 score for the BODMAS dataset,99.04%accuracy and 98.63%f1 score for the Kaggle malware detection dataset,and 96.77%accuracy and 96.77%f1 score for the EMBER 2018 dataset.In addition,the tiered positioning of classifiers shortened the average prediction time by 76.13%for the BODMAS dataset and 95.95%for the EMBER 2018 dataset.The proposed method’s prediction performance is better than the rest of the studies in the literature in which BODMAS and EMBER 2018 datasets are used.
基金The authors acknowledge the funding support ofFRGS/1/2021/ICT07/UTAR/02/3 and IPSR/RMC/UTARRF/2020-C2/G01 for this study.
文摘In defense-in-depth,humans have always been the weakest link in cybersecurity.However,unlike common threats,social engineering poses vulnerabilities not directly quantifiable in penetration testing.Most skilled social engineers trick users into giving up information voluntarily through attacks like phishing and adware.Social Engineering(SE)in social media is structurally similar to regular posts but contains malicious intrinsic meaning within the sentence semantic.In this paper,a novel SE model is trained using a Recurrent Neural Network Long Short Term Memory(RNN-LSTM)to identify well-disguised SE threats in social media posts.We use a custom dataset crawled from hundreds of corporate and personal Facebook posts.First,the social engineering attack detection pipeline(SEAD)is designed to filter out social posts with malicious intents using domain heuristics.Next,each social media post is tokenized into sentences and then analyzed with a sentiment analyzer before being labelled as an anomaly or normal training data.Then,we train an RNN-LSTM model to detect five types of social engineering attacks that potentially contain signs of information gathering.The experimental result showed that the Social Engineering Attack(SEA)model achieves 0.84 in classification precision and 0.81 in recall compared to the ground truth labeled by network experts.The experimental results showed that the semantics and linguistics similarities are an effective indicator for early detection of SEA.