Traffic anomaly detection algorithm for CAN bus using similarity analysis Chao Wang,Xueqiao Xu∗,Ke Xiao,Yunhua He,Guangcan Yang School of Information Science and Technology,Traffic anomaly detection algorithm for CAN bus using similarity analysis

Recently,vehicles have experienced a rise in networking and informatization,leading to increased security concerns.As the most widely used automotive bus network,the Controller Area Network(CAN)bus is vulnerable to attacks,as security was not considered in its original design.This paper proposes SIDuBzip2,a traffic anomaly detection method for the CAN bus based on the bzip2 compression algorithm.The proposed method utilizes the pseudo-periodic characteristics of CAN bus traffic,constructing time series of CAN IDs and calculating the similarity between adjacent time series to identify abnormal traffic.The method consists of three parts:the conversion of CAN ID values to characters,the calculation of similarity based on bzip2 compression,and the optimal solution of model parameters.The experimental results demonstrate that the proposed SIDuBzip2 method effectively detects various attacks,including Denial of Service,replay,basic injection,mixed injection,and suppression attacks.In addition,existing CAN bus traffic anomaly detection methods are compared with the proposed method in terms of performance and delay,demonstrating the feasibility of the proposed method.

Reform and Practice of the Course“Introduction to Computer Science”in Universities Based on the Cultivation of Computational Thinking and Systematic Abilities

Introduction to Computer Science,as one of the fundamental courses in computer-related majors,plays an important role in the cultivation of computer professionals.However,traditional teaching models and content can no longer fully meet the needs of modern information technology development.In response to these issues,this article introduces the concept of computational creative thinking,optimizes course content,adopts exploratory teaching methods,and innovates course assessment methods,aiming to comprehensively enhance students’computational thinking and innovative abilities.By continuously improving and promoting this teaching model,it will undoubtedly promote computer education in universities to a new level.

Research on the Reform of School-Enterprise Cooperation Teaching and Education Mode for Computer Majors

This paper discusses the innovative methods of school-enterprise cooperation education mode in computer applied talent training.An innovative training model based on school-enterprise cooperation is proposed to promote the cultivation of students’practical and innovative skills,so as to better adapt to the needs of society.By analyzing the key links and influencing factors of the training mode,this paper puts forward some concrete suggestions and measures to provide guidelines for universities and enterprises in personnel training.

Vehicle Abnormal Behavior Detection Based on Dense Block and Soft Thresholding

With the rapid advancement of social economies,intelligent transportation systems are gaining increasing atten-tion.Central to these systems is the detection of abnormal vehicle behavior,which remains a critical challenge due to the complexity of urban roadways and the variability of external conditions.Current research on detecting abnormal traffic behaviors is still nascent,with significant room for improvement in recognition accuracy.To address this,this research has developed a new model for recognizing abnormal traffic behaviors.This model employs the R3D network as its core architecture,incorporating a dense block to facilitate feature reuse.This approach not only enhances performance with fewer parameters and reduced computational demands but also allows for the acquisition of new features while simplifying the overall network structure.Additionally,this research integrates a self-attentive method that dynamically adjusts to the prevailing traffic conditions,optimizing the relevance of features for the task at hand.For temporal analysis,a Bi-LSTM layer is utilized to extract and learn from time-based data nuances.This research conducted a series of comparative experiments using the UCF-Crime dataset,achieving a notable accuracy of 89.30%on our test set.Our results demonstrate that our model not only operates with fewer parameters but also achieves superior recognition accuracy compared to previous models.

Emission and capture characteristics of deep hole trap in n-GaN by optical deep level transient spectroscopy

Emission and capture characteristics of a deep hole trap(H1)in n-GaN Schottky barrier diodes(SBDs)have been investigated by optical deep level transient spectroscopy(ODLTS).Activation energy(Eemi)and capture cross-section(σ_(p))of H1 are determined to be 0.75 eV and 4.67×10^(−15)cm^(2),respectively.Distribution of apparent trap concentration in space charge region is demonstrated.Temperature-enhanced emission process is revealed by decrease of emission time constant.Electricfield-boosted trap emission kinetics are analyzed by the Poole−Frenkel emission(PFE)model.In addition,H1 shows point defect capture properties and temperature-enhanced capture kinetics.Taking both hole capture and emission processes into account during laser beam incidence,H1 features a trap concentration of 2.67×10^(15)cm^(−3).The method and obtained results may facilitate understanding of minority carrier trap properties in wide bandgap semiconductor material and can be applied for device reliability assessment.

A Tutorial on Federated Learning from Theory to Practice:Foundations,Software Frameworks,Exemplary Use Cases,and Selected Trends

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized environment.FL allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third parties.This paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data sources.By virtue of FL,models can be learned from all such distributed data sources while preserving data privacy.The aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software frameworks.Furthermore,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL landscape.The ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

The In-Flight Realtime Trigger and Localization Software of GECAM

Realtime trigger and localization of bursts are the key functions of GECAM,an all-sky gamma-ray monitor launched on 2020 December 10.We developed a multifunctional trigger and localization software operating in the CPU of the GECAM Electronic Box.This onboard software has the following features:high trigger efficiency for real celestial bursts with a suppression of false triggers caused by charged particle bursts and background fluctuation,dedicated localization algorithm optimized for both short and long bursts,and low time latency of the trigger information which is downlinked through the Global Short Message Communication service of the global BeiDou navigation system.This paper provides a detailed description of the design and development of the trigger and localization software system for GECAM.It covers the general design,workflow,the main functions,and the algorithms used in the system.The paper also includes on-ground trigger tests using simulated gamma-ray bursts generated by a dedicated X-ray tube,as well as an overview of the performance for real celestial bursts during its in-orbit operation.

Performance and Complexity Trade-Off between Short-Length Regular and Irregular LDPC

In this paper, both the high-complexity near-ML list decoding and the low-complexity belief propagation decoding are tested for some well-known regular and irregular LDPC codes. The complexity and performance trade-off is shown clearly and demonstrated with the paradigm of hybrid decoding. For regular LDPC code, the SNR-threshold performance and error-floor performance could be improved to the optimal level of ML decoding if the decoding complexity is progressively increased, usually corresponding to the near-ML decoding with progressively increased size of list. For irregular LDPC code, the SNR-threshold performance and error-floor performance could only be improved to a bottle-neck even with unlimited decoding complexity. However, with the technique of CRC-aided hybrid decoding, the ML performance could be greatly improved and approached with reasonable complexity thanks to the improved code-weight distribution from the concatenation of CRC and irregular LDPC code. Finally, CRC-aided 5GNR-LDPC code is evaluated and the capacity-approaching capability is shown.

Optimization and Innovation of the Operation Model of Mobile Social E-commerce under AI Empowerment:Taking the Female Community Platform“Little Red Book”as an Example

This article takes the female community platform“Little Red Book”as an example to explore the optimization and innovation of mobile community e-commerce operation mode under Artificial Intelligence(AI)empowerment.Firstly,the relevant concepts were defined,and then the unique attributes of mobile community e-commerce were analyzed.As a typical representative of mobile community e-commerce,Little Red Book introduces the background and characteristics of its platform,analyzes its mobile community operation mode,and focuses on exploring how to establish a mobile community e-commerce platform and effective operation mode under the empowerment of AI technology,to provide some reference and inspiration for the development and operation of Little Red Book and other e-commerce platform enterprises.

Innovation and Practice of Teaching Methods in Digital and Adaptive Learning:Taking Communication Engineering Major as an Example

This paper proposes teaching reforms in communication engineering majors,emphasizing the implementation of digital and adaptive teaching methodologies,integrating emerging technologies,breaking free from the constraints of traditional education,and fostering high-caliber talents.The reform measures encompass fundamental data collection,recognition of individual characteristics,recommendation of adaptive learning resources,process-oriented teaching management,adaptive student guidance and early warning systems,personalized evaluation,and the construction of an integrated service platform.These measures,when combined,form a comprehensive system that is expected to enhance teaching quality and efficiency,and facilitate student development.

Task Offloading and Resource Allocation for Edge-Enabled Mobile Learning

Mobile learning has evolved into a new format of education based on communication and computer technology that is favored by an increasing number of learning users thanks to the development of wireless communication networks,mobile edge computing,artificial intelligence,and mobile devices.However,due to the constrained data processing capacity of mobile devices,efficient and effective interactive mobile learning is a challenge.Therefore,for mobile learning,we propose a"Cloud,Edge and End"fusion system architecture.Through task offloading and resource allocation for edge-enabled mobile learning to reduce the time and energy consumption of user equipment.Then,we present the proposed solutions that uses the minimum cost maximum flow(MCMF)algorithm to deal with the offloading problem and the deep Q network(DQN)algorithm to deal with the resource allocation problem respectively.Finally,the performance evaluation shows that the proposed offloading and resource allocation scheme can improve system performance,save energy,and satisfy the needs of learning users.

Deep learning-based activity recognition and fine motor identification using 2D skeletons of cynomolgus monkeys

Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and prediction.However,action recognition currently used in non-human primate(NHP)research relies heavily on intense manual labor and lacks standardized assessment.In this work,we established two standard benchmark datasets of NHPs in the laboratory:Monkeyin Lab(Mi L),which includes 13 categories of actions and postures,and MiL2D,which includes sequences of two-dimensional(2D)skeleton features.Furthermore,based on recent methodological advances in deep learning and skeleton visualization,we introduced the Monkey Monitor Kit(Mon Kit)toolbox for automatic action recognition,posture estimation,and identification of fine motor activity in monkeys.Using the datasets and Mon Kit,we evaluated the daily behaviors of wild-type cynomolgus monkeys within their home cages and experimental environments and compared these observations with the behaviors exhibited by cynomolgus monkeys possessing mutations in the MECP2 gene as a disease model of Rett syndrome(RTT).Mon Kit was used to assess motor function,stereotyped behaviors,and depressive phenotypes,with the outcomes compared with human manual detection.Mon Kit established consistent criteria for identifying behavior in NHPs with high accuracy and efficiency,thus providing a novel and comprehensive tool for assessing phenotypic behavior in monkeys.

Detection and Characterization of Defects in Additive Manufacturing by Polarization-Based Imaging System

Additive manufacturing (AM) technology such as selective laser melting (SLM) often produces a high refection phenomenon that makes defect detection and information extraction challenging. Meanwhile, it is essential to establish a characterization method for defect analysis to provide sufcient information for process diagnosis and optimization. However, there is still a lack of universal standards for the characterization of defects in SLM parts. In this study, a polarization-based imaging system was proposed, and a set of characterization parameters for SLM defects was established. The contrast, defect contour information, and high refection suppression efect of the SLM part defects were analyzed. Comparative analysis was conducted on defect characterization parameters, including geometric and texture parameters. The experimental results demonstrated the efects of the polarization imaging system and verifed the feasibility of the defect feature extraction and characterization method. The research work provides an efective solution for defect detection and helps to establish a universal standard for defect characterization in additive manufacturing.

Fire Detection Algorithm Based on an Improved Strategy of YOLOv5 and Flame Threshold Segmentation

Due to the rapid growth and spread of fire,it poses a major threat to human life and property.Timely use of fire detection technology can reduce disaster losses.The traditional threshold segmentation method is unstable,and the flame recognition methods of deep learning require a large amount of labeled data for training.In order to solve these problems,this paper proposes a new method combining You Only Look Once version 5(YOLOv5)network model and improved flame segmentation algorithm.On the basis of the traditional color space threshold segmentation method,the original segmentation threshold is replaced by the proportion threshold,and the characteristic information of the flame is maximally retained.In the YOLOv5 network model,the training module is set by combining the ideas of Bootstrapping and cross validation,and the data distribution of YOLOv5 network training is adjusted.At the same time,the feature information after segmentation is added to the data set.Different from the training method that uses large-scale data sets for model training,the proposed method trains the model on the basis of a small data set,and achieves better model detection results,and the detection accuracy of the model in the validation set reaches 0.96.Experimental results show that the proposed method can detect flame features with faster speed and higher accuracy compared with the original method.

Interannual Variation and Statistical Prediction of Summer Dry and Hot Days in South China from 1970 to 2018

The frequent occurrence of dry and hot(DH)days in South China in summer has a negative impact on social development and human health.This study explored the variation characteristics of DH days and the possible reasons for this knotty problem.The findings revealed a notable increase in the number of DH days across most stations,indicating a significant upward trend.Additionally,DH events were observed to occur frequently.The number of DH days increased during 1970-1990,decreased from 1991 to 1997,and stayed stable after 1997.The key climate factors affecting the interannual variability of the number of DH days were the Indian Ocean Basin warming(IOBW)in spring and the East Asian Summer Monsoon(EASM).Compared with the negative phase of IOBW,in the positive phase of IOBW,500 hPa and 850 hPa geopotential height enhanced,the West Pacific subtropical high strengthened and extended abnormally to the west,more solar radiation reached the surface,surface outgoing longwave radiation increased,and there was an anomalous anticyclone in eastern South China.The atmospheric circulation characteristics of the positive and negative phases of ESAM were opposite to those of IOBW,and the abnormal circulation of the positive(negative)phases of ESAM was unfavorable(favorable)for the increase in the number of DH days.A long-term prediction model for the number of summer DH days was established using multiple linear regression,incorporating the key climate factors.The correlation coefficient between the observed and predicted number of DH days was 0.65,and the root-mean-square error was 2.8.In addition,independent forecasts for 2019 showed a deviation of just 1 day.The results of the independent recovery test confirmed the stability of the model,providing evidence that climatic factors did have an impact on DH days in South China.

Hybrid Chinese Information Retrieval Model Based on the Combination of Keyword and Concept

A hybrid model that is based on the Combination of keywords and concept was put forward. The hybrid model is built on vector space model and probabilistic reasoning network. It not only can exert the advantages of keywords retrieval and concept retrieval but also can compensate for their shortcomings. Their parameters can be adjusted according to different usage in order to accept the best information retrieval result, and it has been proved by our experiments.

A Survey of the Researches on Grid-Connected Solar Power Generation Systems and Power Forecasting Methods Based on Ground-Based Cloud Atlas

Photovoltaic power generating is one of the primary methods of utilizing solar energy resources,with large-scale photovoltaic grid-connected power generation being the most efficient way to fully utilize solar energy.In order to provide reference strategies for pertinent researchers as well as potential implementation,this paper tries to provide a survey investigation and technical analysis of machine learning-related approaches,statistical approaches and optimization techniques for solar power generation and forecasting.Deep learning-related methods,in particular,can theoretically handle arbitrary nonlinear transformations through proper model structural design,such as hidden layer topology optimization and objective function analysis to save information that can increase forecasting accuracy while filtering out irrelevant or less affected data for forecasting.The research’s results indicate that RBFNN-AG performed the best when applying the predetermined number of days,with an NRMSE value of 4.65%.RBFNN-AG performs better than sophisticated models like DenseNet(5.69%),SLFN-ELM(5.95%),and ANN-k-means-linear regression correction(6.11%).Additionally,scenario application and PV system investment techniques are provided to evaluate the current condition of new energy development and market trends both domestically and internationally.

Improved Variable Forgetting Factor Proportionate RLS Algorithm with Sparse Penalty and Fast Implementation Using DCD Iterations

The proportionate recursive least squares(PRLS)algorithm has shown faster convergence and better performance than both proportionate updating(PU)mechanism based least mean squares(LMS)algorithms and RLS algorithms with a sparse regularization term.In this paper,we propose a variable forgetting factor(VFF)PRLS algorithm with a sparse penalty,e.g.,l_(1)-norm,for sparse identification.To reduce the computation complexity of the proposed algorithm,a fast implementation method based on dichotomous coordinate descent(DCD)algorithm is also derived.Simulation results indicate superior performance of the proposed algorithm.

A Survey on Type-3 Fuzzy Logic Systems and Their Control Applications

In this paper,we offer a review of type-3 fuzzy logic systems and their applications in control.The main objective of this work is to observe and analyze in detail the applications in the control area using type-3 fuzzy logic systems.In this case,we review their most important applications in control and other related topics with type-3 fuzzy systems.Intelligent algorithms have been receiving increasing attention in control and for this reason a review in this area is important.This paper reviews the main applications that make use of Intelligent Computing methods.Specifically,type-3 fuzzy logic systems.The aim of this research is to be able to appreciate,in detail,the applications in control systems and to point out the scientific trends in the use of Intelligent Computing techniques.This is done with the construction and visualization of bibliometric networks,developed with VosViewer Software,which it is a free Java-based program,mainly intended to be used for analyzing and visualizing bibliometric networks.With this tool,we can create maps of publications,authors,or journals based on a co-citation network or construct maps of keywords,countries based on a co-occurrence networks,research groups,etc.

BLS-identification:A device fingerprint classification mechanism based on broad learning for Internet of Things

The popularity of the Internet of Things(IoT)has enabled a large number of vulnerable devices to connect to the Internet,bringing huge security risks.As a network-level security authentication method,device fingerprint based on machine learning has attracted considerable attention because it can detect vulnerable devices in complex and heterogeneous access phases.However,flexible and diversified IoT devices with limited resources increase dif-ficulty of the device fingerprint authentication method executed in IoT,because it needs to retrain the model network to deal with incremental features or types.To address this problem,a device fingerprinting mechanism based on a Broad Learning System(BLS)is proposed in this paper.The mechanism firstly characterizes IoT devices by traffic analysis based on the identifiable differences of the traffic data of IoT devices,and extracts feature parameters of the traffic packets.A hierarchical hybrid sampling method is designed at the preprocessing phase to improve the imbalanced data distribution and reconstruct the fingerprint dataset.The complexity of the dataset is reduced using Principal Component Analysis(PCA)and the device type is identified by training weights using BLS.The experimental results show that the proposed method can achieve state-of-the-art accuracy and spend less training time than other existing methods.