Improved YOLOv8n Model for Detecting Helmets and License Plates on Electric Bicycles

Wearing helmetswhile riding electric bicycles can significantly reduce head injuries resulting fromtraffic accidents.To effectively monitor compliance,the utilization of target detection algorithms through traffic cameras plays a vital role in identifying helmet usage by electric bicycle riders and recognizing license plates on electric bicycles.However,manual enforcement by traffic police is time-consuming and labor-intensive.Traditional methods face challenges in accurately identifying small targets such as helmets and license plates using deep learning techniques.This paper proposes an enhanced model for detecting helmets and license plates on electric bicycles,addressing these challenges.The proposedmodel improves uponYOLOv8n by deepening the network structure,incorporating weighted connections,and introducing lightweight convolutional modules.These modifications aim to enhance the precision of small target recognition while reducing the model’s parameters,making it suitable for deployment on low-performance devices in real traffic scenarios.Experimental results demonstrate that the model achieves an mAP@0.5 of 91.8%,showing an 11.5%improvement over the baselinemodel,with a 16.2%reduction in parameters.Additionally,themodel achieves a frames per second(FPS)rate of 58,meeting the accuracy and speed requirements for detection in actual traffic scenarios.

Securing Cloud-Encrypted Data:Detecting Ransomware-as-a-Service(RaaS)Attacks through Deep Learning Ensemble

Data security assurance is crucial due to the increasing prevalence of cloud computing and its widespread use across different industries,especially in light of the growing number of cybersecurity threats.A major and everpresent threat is Ransomware-as-a-Service(RaaS)assaults,which enable even individuals with minimal technical knowledge to conduct ransomware operations.This study provides a new approach for RaaS attack detection which uses an ensemble of deep learning models.For this purpose,the network intrusion detection dataset“UNSWNB15”from the Intelligent Security Group of the University of New South Wales,Australia is analyzed.In the initial phase,the rectified linear unit-,scaled exponential linear unit-,and exponential linear unit-based three separate Multi-Layer Perceptron(MLP)models are developed.Later,using the combined predictive power of these three MLPs,the RansoDetect Fusion ensemble model is introduced in the suggested methodology.The proposed ensemble technique outperforms previous studieswith impressive performance metrics results,including 98.79%accuracy and recall,98.85%precision,and 98.80%F1-score.The empirical results of this study validate the ensemble model’s ability to improve cybersecurity defenses by showing that it outperforms individual MLPmodels.In expanding the field of cybersecurity strategy,this research highlights the significance of combined deep learning models in strengthening intrusion detection systems against sophisticated cyber threats.

Detecting XSS with Random Forest and Multi-Channel Feature Extraction

In the era of the Internet,widely used web applications have become the target of hacker attacks because they contain a large amount of personal information.Among these vulnerabilities,stealing private data through crosssite scripting(XSS)attacks is one of the most commonly used attacks by hackers.Currently,deep learning-based XSS attack detection methods have good application prospects;however,they suffer from problems such as being prone to overfitting,a high false alarm rate,and low accuracy.To address these issues,we propose a multi-stage feature extraction and fusion model for XSS detection based on Random Forest feature enhancement.The model utilizes RandomForests to capture the intrinsic structure and patterns of the data by extracting leaf node indices as features,which are subsequentlymergedwith the original data features to forma feature setwith richer information content.Further feature extraction is conducted through three parallel channels.Channel I utilizes parallel onedimensional convolutional layers(1Dconvolutional layers)with different convolutional kernel sizes to extract local features at different scales and performmulti-scale feature fusion;Channel II employsmaximum one-dimensional pooling layers(max 1D pooling layers)of various sizes to extract key features from the data;and Channel III extracts global information bi-directionally using a Bi-Directional Long-Short TermMemory Network(Bi-LSTM)and incorporates a multi-head attention mechanism to enhance global features.Finally,effective classification and prediction of XSS are performed by fusing the features of the three channels.To test the effectiveness of the model,we conduct experiments on six datasets.We achieve an accuracy of 100%on the UNSW-NB15 dataset and 99.99%on the CICIDS2017 dataset,which is higher than that of the existing models.

Method for Detecting Industrial Defects in Intelligent Manufacturing Using Deep Learning

With the advent of Industry 4.0,marked by a surge in intelligent manufacturing,advanced sensors embedded in smart factories now enable extensive data collection on equipment operation.The analysis of such data is pivotal for ensuring production safety,a critical factor in monitoring the health status of manufacturing apparatus.Conventional defect detection techniques,typically limited to specific scenarios,often require manual feature extraction,leading to inefficiencies and limited versatility in the overall process.Our research presents an intelligent defect detection methodology that leverages deep learning techniques to automate feature extraction and defect localization processes.Our proposed approach encompasses a suite of components:the high-level feature learning block(HLFLB),the multi-scale feature learning block(MSFLB),and a dynamic adaptive fusion block(DAFB),working in tandem to extract meticulously and synergistically aggregate defect-related characteristics across various scales and hierarchical levels.We have conducted validation of the proposed method using datasets derived from gearbox and bearing assessments.The empirical outcomes underscore the superior defect detection capability of our approach.It demonstrates consistently high performance across diverse datasets and possesses the accuracy required to categorize defects,taking into account their specific locations and the extent of damage,proving the method’s effectiveness and reliability in identifying defects in industrial components.

A Model for Detecting Fake News by Integrating Domain-Specific Emotional and Semantic Features

With the rapid spread of Internet information and the spread of fake news,the detection of fake news becomes more and more important.Traditional detection methods often rely on a single emotional or semantic feature to identify fake news,but these methods have limitations when dealing with news in specific domains.In order to solve the problem of weak feature correlation between data from different domains,a model for detecting fake news by integrating domain-specific emotional and semantic features is proposed.This method makes full use of the attention mechanism,grasps the correlation between different features,and effectively improves the effect of feature fusion.The algorithm first extracts the semantic features of news text through the Bi-LSTM(Bidirectional Long Short-Term Memory)layer to capture the contextual relevance of news text.Senta-BiLSTM is then used to extract emotional features and predict the probability of positive and negative emotions in the text.It then uses domain features as an enhancement feature and attention mechanism to fully capture more fine-grained emotional features associated with that domain.Finally,the fusion features are taken as the input of the fake news detection classifier,combined with the multi-task representation of information,and the MLP and Softmax functions are used for classification.The experimental results show that on the Chinese dataset Weibo21,the F1 value of this model is 0.958,4.9% higher than that of the sub-optimal model;on the English dataset FakeNewsNet,the F1 value of the detection result of this model is 0.845,1.8% higher than that of the sub-optimal model,which is advanced and feasible.

A Method for Detecting and Recognizing Yi Character Based on Deep Learning

Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.

Detecting Malicious Uniform Resource Locators Using an Applied Intelligence Framework

The potential of text analytics is revealed by Machine Learning(ML)and Natural Language Processing(NLP)techniques.In this paper,we propose an NLP framework that is applied to multiple datasets to detect malicious Uniform Resource Locators(URLs).Three categories of features,both ML and Deep Learning(DL)algorithms and a ranking schema are included in the proposed framework.We apply frequency and prediction-based embeddings,such as hash vectorizer,Term Frequency-Inverse Dense Frequency(TF-IDF)and predictors,word to vector-word2vec(continuous bag of words,skip-gram)from Google,to extract features from text.Further,we apply more state-of-the-art methods to create vectorized features,such as GloVe.Additionally,feature engineering that is specific to URL structure is deployed to detect scams and other threats.For framework assessment,four ranking indicators are weighted:computational time and performance as accuracy,F1 score and type error II.For the computational time,we propose a new metric-Feature Building Time(FBT)as the cutting-edge feature builders(like doc2vec or GloVe)require more time.By applying the proposed assessment step,the skip-gram algorithm of word2vec surpasses other feature builders in performance.Additionally,eXtreme Gradient Boost(XGB)outperforms other classifiers.With this setup,we attain an accuracy of 99.5%and an F1 score of 0.99.

Standard-definition White-light,High-definition White-light versus Narrow-band Imaging Endoscopy for Detecting Colorectal Adenomas:A Multicenter Randomized Controlled Trial

Objective This study aimed to compare the performance of standard-definition white-light endoscopy(SD-WL),high-definition white-light endoscopy(HD-WL),and high-definition narrow-band imaging(HD-NBI)in detecting colorectal lesions in the Chinese population.Methods This was a multicenter,single-blind,randomized,controlled trial with a non-inferiority design.Patients undergoing endoscopy for physical examination,screening,and surveillance were enrolled from July 2017 to December 2020.The primary outcome measure was the adenoma detection rate(ADR),defined as the proportion of patients with at least one adenoma detected.The associated factors for detecting adenomas were assessed using univariate and multivariate logistic regression.Results Out of 653 eligible patients enrolled,data from 596 patients were analyzed.The ADRs were 34.5%in the SD-WL group,33.5%in the HD-WL group,and 37.5%in the HD-NBI group(P=0.72).The advanced neoplasm detection rates(ANDRs)in the three arms were 17.1%,15.5%,and 10.4%(P=0.17).No significant differences were found between the SD group and HD group regarding ADR or ANDR(ADR:34.5%vs.35.6%,P=0.79;ANDR:17.1%vs.13.0%,P=0.16,respectively).Similar results were observed between the HD-WL group and HD-NBI group(ADR:33.5%vs.37.7%,P=0.45;ANDR:15.5%vs.10.4%,P=0.18,respectively).In the univariate and multivariate logistic regression analyses,neither HD-WL nor HD-NBI led to a significant difference in overall adenoma detection compared to SD-WL(HD-WL:OR 0.91,P=0.69;HD-NBI:OR 1.15,P=0.80).Conclusion HD-NBI and HD-WL are comparable to SD-WL for overall adenoma detection among Chinese outpatients.It can be concluded that HD-NBI or HD-WL is not superior to SD-WL,but more effective instruction may be needed to guide the selection of different endoscopic methods in the future.Our study’s conclusions may aid in the efficient allocation and utilization of limited colonoscopy resources,especially advanced imaging technologies.

A proposal for detecting weak electromagnetic waves around 2.6μm wavelength with Sr optical clock

Infrared signal detection is widely used in many fields.Due to the detection principle,however,the accuracy and range of detection are limited.Thanks to the ultra stability of the^(87)Sr optical lattice clock,external infrared electromagnetic wave disturbances can be responded to.Utilizing the ac Stark shift of the clock transition,we propose a new method to detect infrared signals.According to our calculations,the theoretical detection accuracy in the vicinity of its resonance band of 2.6μm can reach the order of 10-14W,while the minimum detectable signal of common detectors is on the order of 10^(-10)W.

Improved Mechanism for Detecting Examinations Impersonations in Public Higher Learning Institutions: Case of the Mwalimu Nyerere Memorial Academy (MNMA)

Currently, most public higher learning institutions in Tanzania rely on traditional in-class examinations, requiring students to register and present identification documents for examinations eligibility verification. This system, however, is prone to impersonations due to security vulnerabilities in current students’ verification system. These vulnerabilities include weak authentication, lack of encryption, and inadequate anti-counterfeiting measures. Additionally, advanced printing technologies and online marketplaces which claim to produce convincing fake identification documents make it easy to create convincing fake identity documents. The Improved Mechanism for Detecting Impersonations (IMDIs) system detects impersonations in in-class exams by integrating QR codes and dynamic question generation based on student profiles. It consists of a mobile verification app, built with Flutter and communicating via RESTful APIs, and a web system, developed with Laravel using HTML, CSS, and JavaScript. The two components communicate through APIs, with MySQL managing the database. The mobile app and web server interact to ensure efficient verification and security during examinations. The implemented IMDIs system was validated by a mobile application which is integrated with a QR codes scanner for capturing codes embedded in student Identity Cards and linking them to a dynamic question generation model. The QG model uses natural language processing (NLP) algorithm and Question Generation (QG) techniques to create dynamic profile questions. Results show that the IMDIs system could generate four challenging profile-based questions within two seconds, allowing the verification of 200 students in 33 minutes by one operator. The IMDIs system also tracks exam-eligible students, aiding in exam attendance and integrates with a Short Message Service (SMS) to report impersonation incidents to a dedicated security officer in real-time. The IMDIs system was tested and found to be 98% secure, 100% convenient, with a 0% false rejection rate and a 2% false acceptance rate, demonstrating its security, reliability, and high performance.

Optimization of Chromatographic Conditions for Detecting Ellagic Acid in Pomegranate Peels Using HPLC Method

[Objective] This study aimed to optimize the chromatographic conditions for detecting ellagic acid in pomegranate peels using HPLC method. [Method] By using 0.2 mg/ml ellagic acid standard solution, on the basis of single-factor experiment and orthogonal experiment, chromatographic conditions （mobile phase ratio, flow rate, col- umn temperature） for detecting ellagic acid using HPLC were optimized. Based on the optimal chromatographic conditions, the ellagic acid content in experimental pomegranate peels was determined. [Resull] The optimal chromatographic conditions for detecting ellagic acid in pomegranate peels using HPLC method are： 1.2% phos- phoric acid：acetonitrile=85：15, column temperature of 35 ℃, and flow rate of 1.0 ml/min. The linear regression equation of ellagic acid is： y=2.9e＋0.6x＋4.4e＋5 （FF=9 999）. Ac- cording to the standard addition recovery test, the average recovery rate of ellagic acid is 98.20%, and RSD is 0.60%. Under above optimized chromatographic condi- tions, ellagic acid can be well separated from other interfering components in pomegranate peels, with shorter peak time and ideal effect, which is convenient for the detection in production practices. [Conclusion] This study laid the foundation for detecting ellagic acid in pomegranate peels using HPLC method.

Development of TaqMan-based Real-time PCR Assay for Detecting Transmissible Gastroenteritis Virus and Its Application in Vaccine Evaluation

[Objective] This study aimed to establish a TaqMan-based real-time PCR assay for detecting transmissible gastroenteritis virus （TGEV）. [Method] Primers and a probe were designed according to the conserved sequence of N gene in TGEV genome. After gradient dilution, the recombinant plasmid harboring the N gene was used as a standard for real-time PCR assay to establish the standard curve. [Re- sult] The results showed that the established real-time PCR assay exhibited a good linear relationship within the range of 102-10^10 copies/ul; the correlation coefficient was above 0.99 and the amplification efficiency ranged from 90% to 110%. The de- tection limit of real-time PCR assay for TGEV was 10 copies/μl, suggesting a high sensitivity; there was no cross reaction with other porcine viruses, indicating a good specificity; coefficients of variation within and among batches were lower than 3%, suggesting a good repeatability. The established real-time PCR method could be ap- plied in quantitative analysis and evaluation of the immune efficacy of TGEV vac- cines and detection of TGEV in clinical samples. [Conclusion] The TaqMan-based real-time PCR assay established in this study is highly sensitive and specific, which can provide technical means for the epidemiological survey of TGEV, development of TGEV vaccines and investigation of the pathogenesis of TGE.

Establishment of a Multiplex PCR System for Detecting Transgenic Ingredients from Citrus

[Objective] This study aimed to establish a multiplex PCR system for de- tecting transgenic ingredients from Citrus. [Method] Based on the pBI121 plasmid sequences published in GenBank and actin gene sequence of Citrus, the primers specific to CaMV35S promoter, NOS promoter, NOS terminator and actin gene were designed, to establish a multiple PCR system which could detect four types of sequences. In addition, orthogonal tests were performed to determine the optimal concentrations of all the components in PCR reaction system, as well as the optimal PCR cycle parameters. [Result] The optimal PCR reaction system should contain 2.5μl of 10xPCR buffer, 2.0μl of MgCI2 （25 mmol/L）, 2.0 μl of dNTP mixture （2.5 mmol/L of each dNTP）, 1.0 μl of actin gene primers （10μmol/L）, 1.0μl of 35S promoter primers （10 μmol/L）, 1.5 μl of NOS promoter primers （10 μmol/L） and 0.5 μl of NOS terminator primers （10μmol/L）, 0.1 μg of template DNA, 1.25 U of Taq DNA polymerase; ddH20 was added to the total reaction system of 25μl. The PCR reaction program consisted of pre-denaturing at 94℃ for 5 min; 31 cycles of denaturing at 94℃ for 30 s, annealing at 64.1℃ for 45 s and extension at 72℃ for 50 s; final extension at 72℃ for 10 min. The reaction system optimized with the orthogonal tests could detect as less as 0.1% transgenic component in the tested samples. [Conclusion] The MPCR detection system established in this study can meet the requirements in theory for detecting the genetically modified ingredients in Citrus or the deep-processed products.

DC LOOP-CURRENT DETECTING AND RESTRAINING METHODS FOR PARALLEL INVERTER SYSTEM

DC component is contained in inverter output voltage due to many reasons such as the zero-point deviation of operational amplifiers and the differences between power switching transistors′ characteristics. For the parallel inverter system without output isolation transformers, the difference of DC components of the output voltage can cause large DC loop-current among modular inverters. Aiming at this problem, this paper studies several DC loop-current detecting and restraining methods. By digital adjustment with high precision on the DC components of reference sine wave, the DC components of inverter′s output voltage can be adjusted to restrain DC loop-current. Experimental results prove that the DC loop-current detecting and restraining methods have a good performance.

A Temperature-Autocompensated Detecting Circuit for the Capacitance Fuze

In view of drastic possible changes in fuze environment tempera- ture,a kind of temperature autocompensated detecting circuit for the capaci- tance fuze is proposed.It provides a steady detected output when the envi- ronment temperature varies from-50℃ to 65℃ and keeps a stable detecting sensitivity.Based on an analysis of the circuit,influence of the major param- eters of the oscillating circuit on the amplitude are explored.A few impor- tant controllable parameters affecting the circuit feature are found out.A parameter-control method is given in order to improve the circuit perfor- mance.

Comparison between Two Methods for Detecting Gene Flow and Analysis on the Influencing Factors

[Objective] The aim was to test the consistency between two commonly used methods PCR detection and protein detection for detecting gene flow,and investigate the factors influencing the consistency.[Method] 1 769 samples of three varieties under three treatments（wind,bee and control）were detected with both methods.[Result] There was phenomenon in field that Bt gene was transferred into F1 generations but couldn＇t express,that meant,the result of PCR detection was not consistent with that of protein detection.By comparing environmental factors,it was proved that wind and bee treatments didn＇t significantly affect the expression of gene flow.However,the Bt gene expression rate in bee treatment was higher than that in wind treatment.[Conclusion] The paper will provide reference for accurate detection of gene flow.

Detecting abnormalities for empty nest elder in smart monitoring system

In order to implement the real-time detection of abnormality of elder and devices in an empty nest home,multi-modal joint sensors are used to collect discrete action sequences of behavior,and the improved hierarchical hidden Markov model is adopted to Abstract these discrete action sequences captured by multi-modal joint sensors into an occupant’s high-level behavior—event,then structure representation models of occupant normality are modeled from large amounts of spatio-temporal data. These models are used as classifiers of normality to detect an occupant’s abnormal behavior.In order to express context information needed by reasoning and detection,multi-media ontology （MMO） is designed to annotate and reason about the media information in the smart monitoring system.A pessimistic emotion model （PEM） is improved to analyze multi-interleaving events of multi-active devices in the home.Experiments demonstrate that the PEM can enhance the accuracy and reliability for detecting active devices when these devices are in blind regions or are occlusive. The above approach has good performance in detecting abnormalities involving occupants and devices in a real-time way.

Neuronal signal detecting and stimulating circuit array for monolithic integrated MEA

A neuronal signal detecting circuit and a neuronal signal stimulating circuit designed for a monolithic integrated MEA（micro-electrode array） system are described. As a basic cell of the circuits, an OPA（ operational amplifier） is designed with low power, low noise, small size and high gain. The detecting circuit has a chip area of 290 μm × 400 μm, a power dissipation of 2.02 mW, an equivalent input noise of 17.72 nV/ Hz, a gain of 60. 5 dB, and an output voltage from - 2. 48 to ＋ 2. 5 V. The stimulating circuit has a chip area of 130 μm × 290 μm, a power dissipation of 740 μW, and an output voltage from - 2. 5 to 2. 04 V. The parameters show that two circuits are suitable for a monolithic integrated MEA system. The detecting circuit and MEA have been fabricated. The test results show that the detecting circuit works well.

FE Method of Analysing Detecting Electrode of Capacitance Proximity Fuze

The finite element method is first introduced into the design process of detecting electrodes of three electrode capacitance fuze, the mutual capacitance of the fuze and target is calculated by the finite element method, which provides the parameters for simulation circuit and design of detecting electrode. The finite element method pierces the traditional method of designing detecting electrode-design, test and adjustment. The system capacitance can be calculated accurately and the performance can be predicted in the design period of the detecting electrode, which saves a lot of research fee. The capacitances of a mortar shell fuze above ground 2 m and lower are given. After putting the computing data into simulating circuit, the demodulation voltage can be obtained, its changing trend is in agreement with the tested result.

基于改进Detection Transformer的棉花幼苗与杂草检测模型研究

基于深度学习的目标检测技术在棉花幼苗与杂草检测领域已取得一定进展。论文提出了基于改进Detection Transformer的棉花幼苗与杂草检测模型,以提高杂草目标检测的准确率和效率。首先,引入了可变形注意力模块替代原始模型中的Transformer注意力模块,提高模型对特征图目标形变的处理能力。提出新的降噪训练机制,解决了二分图匹配不稳定问题。提出混合查询选择策略,提高解码器对目标类别和位置信息的利用效率。使用Swin Transformer作为网络主干,提高模型特征提取能力。通过对比原网络,论文提出的模型方法在训练过程中表现出更快的收敛速度,并且在准确率方面提高了6.7%。