Search

Preserving customers' expectations and understanding factors affecting their purchasing decisions are crucial in designing effective marketing and advertising strategies. However, constantly and swiftly changing the customers' interests and consumption behaviors make it inevitable to utilize sophisticated tools and approaches based on advanced technologies. Among them, by measuring the customers' physiological and neural signals, studying the customers' cognitive and affective responses to marketing stimuli, neuromarketing provides deep insight into the customers' motivations, preferences, and decisions. Recently, the internet of everything (IoE) has brought many new opportunities to the industry and has attracted the attention of many researchers in recent years. The main objective of this paper is to address how the IoE would empower neuromarketing techniques. Hence, an in-depth understanding of current research issues as well as emerging trends would help meet this goal. In this paper, a comprehensive review has been done by reviewing numerous journal and conference papers from various academic databases (sciencedirect.com, IEEE Xplore, Springer, Elsevier, Wiley, ACM digital library) based on applying various filtrations on specific keywords to identify and categorize the IoE devices in the neuromarketing field. In particular, we discussed the importance and the applications of IoE gadgets and devices, especially wearable medical technologies in eight neuromarketing techniques. Finally, we described critical existing challenges and limitations in neuromarketing and IoE gadgets that researchers have dealt with in this field of research. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of guiding a flexible needle from its entry point to a target location through an obstacle-laden environment. To achieve this, we propose a path planning approach grounded in an enhanced particle swarm optimization algorithm (PSO). Our method uses the number and angle of needle rotations to govern the flexible needle's movement. By optimizing for parameters such as path length, distance from obstacles, and needle rotation, we transform the flexible needle puncture path planning problem into a multi-objective optimization task. The optimal path is determined by assigning distinct weights to these four optimization objectives and solving them using the improved PSO algorithm. To demonstrate the effectiveness and practicality of our approach, we conduct MATLAB simulations and compare the results with the unimproved PSO algorithm and the rapidly-exploring random trees algorithm. [ABSTRACT FROM AUTHOR]

This paper mainly studies the retrieval and location of violence in long time sequence video. Aiming at the low accuracy of violence detection in long time sequence video, a two-stage violence time sequence location method based on DC3D network model is proposed in this paper. In the video preprocessing stage, this paper adopts the method of generating video at multiple scales. In the first stage, we first use a large number of labeled datasets for pre-training to obtain a C3D network model for generating candidate videos and finally filter out meaningless background videos. In the second stage, we use the deconvolution method to identify the candidate video accurately to the frame level, so as to determine the specific time of violence. In the first stage, this method can improve the overall accuracy by generating candidate videos. DC3D network model can accurately locate the time of violence to the level of frame. The experimental results show that the proposed method can quickly retrieve and locate the violent fighting behavior in the surveillance video under the long time sequence video. The research results of this paper can provide convenience for the surveillance personnel to quickly retrieve and locate the target segment in a large amount of video data. [ABSTRACT FROM AUTHOR]

The number of research articles published on COVID-19 has dramatically increased since the outbreak of the pandemic in November 2019. This absurd rate of productivity in research articles leads to information overload. It has increasingly become urgent for researchers and medical associations to stay up to date on the latest COVID-19 studies. To address information overload in COVID-19 scientific literature, the study presents a novel hybrid model named CovSumm, an unsupervised graph-based hybrid approach for single-document summarization, that is evaluated on the CORD-19 dataset. We have tested the proposed methodology on the scientific papers in the database dated from January 1, 2021 to December 31, 2021, consisting of 840 documents in total. The proposed text summarization is a hybrid of two distinctive extractive approaches (1) GenCompareSum (transformer-based approach) and (2) TextRank (graph-based approach). The sum of scores generated by both methods is used to rank the sentences for generating the summary. On the CORD-19, the recall-oriented understudy for gisting evaluation (ROUGE) score metric is used to compare the performance of the CovSumm model with various state-of-the-art techniques. The proposed method achieved the highest scores of ROUGE-1: 40.14%, ROUGE-2: 13.25%, and ROUGE-L: 36.32%. The proposed hybrid approach shows improved performance on the CORD-19 dataset when compared to existing unsupervised text summarization methods. [ABSTRACT FROM AUTHOR]

Arithmetic logic unit (ALU), a core component of a processor, is one of the thrust areas of the current research. Presently, ALU is designed by transistor-based CMOS technique and its individual components are placed in different layers. The current design is affected by the limitations of Moore's law and design complexity. At present, 'Quantum cellular automata electro-spin (QCA-ES)' technology is widely accepted technology as an alternative of 'CMOS' to minimize the above discussed problems. In this research paper, the design of a novel multilayer portable, dynamic, fault-tolerant, power-efficient, thermally stable reversible ALU is proposed which is explored through QCA-ES. All the arithmetic and logical components of ALU are separately placed in different layers. Area density, delay, fault tolerance and thermal stability are investigated. A specific type of gate, known as reversible gate (modified 3:3 'TSG' gate), is used in this proposed design with QCA technology to get the optimized design ALU with low occupied area, complexity, delay and power dissipation. Investigation of a fault-free design and saturated amplitude level (of output) change with respect to temperature increment in the proposed device are also discussed in this paper. Not only the thermal stability (up to 6 k temperature) but also an investigation on cell complexity of the 100% fault-free (against multiple cell-omission, cell-displacement, cell-orientation change and extra cell deposition), multilayer nano-device is represented in this work. 'QCA-Designer' software is used in this research work to design and develop layout of the proposed components in quantum-field and find out the occupied area, delay and complexity of proposed design. 'QCA-Pro' software is used for getting the value of dissipated power. [ABSTRACT FROM AUTHOR]

The aim of this special issue is to introduce the burgeoning topic of Autonomous System. Finally, in order to check the conformity of this enforcement with defined multi-cloud SLA, the authors propose an approach for multi-cloud SLA reporting inspired by conformance checking techniques. I In i I the i I paper i I authored i I by i I Jeremy i I Mechouche i , the authors propose a hierarchical representation of multi-cloud SLAs: sub-SLAs associated with a system's components deployed on distinct cloud service providers and global-SLA associated with the whole system. [Extracted from the article]

In industry, robots are widely used to solve repetitive or dangerous actions in product production, so that product production can be more efficient. However, the problem that robots are often challenged is the convenience and the efficiency of introducing the production line. Therefore, the intuitive robot guidance method is an important issue; this paper will introduce the concept of human–robot interactions (HRI) and use deep learning methods on the machine vision system to complete the robot-guided assembly operation analysis, and the assembly operation analysis requires semantic segmentation as pre-processing. Therefore, we propose a novel semantic template correlation model architecture based on zero-shot learning (ZSL) to achieve the effect of rapid deployment. The semantic template correlation model is to search for the object area offline learning through the semantic template generated by the physics engine, and when inferring online, we can directly enter the semantic template to obtain the relevant object region. Finally, this paper verifies that the MIoU can be increased by more than 5% through the verification of the general database VOC2012. [ABSTRACT FROM AUTHOR]

The Sunway TaihuLight is the first supercomputer built entirely with domestic processors in China. On Sunway Taihulight, the local data memory (LDM) of the slave core is limited, so data transmission with the main memory is frequent during calculation, and the memory access efficiency is low. On the other hand, for many scientific computing programs, how to solve the storage problem of irregular access data is the key to program optimization. Software cache (SWC) is one of the effective means to solve these problems. Based on the characteristics of Sunway TaihuLight structure and irregular access, this paper designs and implements a new software cache structure by using part of the space in LDM to simulate the cache function, which uses new cache address mapping and conflicts solution to solve high data access overhead and storage overhead in a traditional cache. At the same time, the SWC uses the register communication between the slave cores to share on the different slave core LDMs, increasing the capacity of the software cache and improving the hit rate. In addition, we adopt a double buffer strategy to access regular data in batches, which hides the communication overhead between the slave core and the main memory. The test results on the Sunway TaihuLight platform show that the software cache structure in this paper can effectively reduce the program running time, improve the software cache hit rate, and achieve a better optimization effect. [ABSTRACT FROM AUTHOR]

A. Kireeva et al. contributed another paper in the field of cellular automata: "Parallel simulation of drift-diffusion-recombination by cellular automata and global random walk algorithm". Parallel computing technologies enable the solution of large-scale numerical simulation and data processing problems in science and industry. The previously proposed contention-aware scheduling algorithm is formally described with this model, modifications of the algorithm are proposed: look-ahead technique, chunked data transfers, data caching, and peer-to-peer data transfers. [Extracted from the article]

Intelligent Transportation Systems (ITS) are a promising research area that offers a variety of applications. The objective of these applications is to enhance road safety, to optimize traffic efficiency, and to provide a better driving experience. Yet, the efficiency of ITS applications, such as safety and driver assistance applications, relies essentially on the exchanged data between different entities of the network. Accordingly, trust management models are used to guarantee the quality of the data and to eliminate malicious and selfish nodes to secure vehicular communications. In this paper, we pay a special attention to the requirements of trust management models used in the context of ITS applications. We also dissected the trust model to extract the mechanisms used in the literature to fulfil the identified requirements. Furthermore, we present the most known simulators and evaluation metrics that are used to validate the proposed models. The aim of this study is to provide a global overview of the mechanisms that may be used to fulfil the crucial requirements of trust management models. For this purpose, we employed a systematic mapping study, through which we carefully analysed 60 selected articles. Through our analysis, five main requirements were identified: scalability, accuracy, robustness, privacy preservation, appropriate response time. Different mechanisms and techniques were applied to meet with the identified requirements. Two main findings are reported: (1) The accuracy and robustness requirements are the most considered requirements. On the other hand, the privacy requirement is the least covered by the publications, (2) the majority of the reviewed papers focus on addressing two or three requirements at most. A little number of publications covered all the requirements. Based on the identified research gaps, we highlight some future directions that may be investigated. We provide general recommendations that may serve as a guideline for researchers who want to design trust models that fulfil certain requirements. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is an important virtual network that allows remote users to access linked multimedia devices. The development of IoT and its ubiquitous application across various domains of everyday life has led to continuous research efforts. Security is a perceptual concern for researchers involved in IoT as it is a key factor in the acceptance of any innovative technology. Numerous research studies have been conducted concentrating on the level of IoT security on a particular mechanism, on specific applications, or on categorizing vulnerabilities, in order to address a defined situation of securing an IoT network. This present paper aims to comprehensively review potential solutions for securing IoT, between emerging and traditional mechanisms, such as blockchain, machine learning, cryptography, and quantum computing. This study provides a comparative analysis of related papers with their characteristics, pros and cons. Accordingly, it taxonomizes relevant solutions based on their achieved security requirements. Furthermore, the potential benefits and challenges of each of the four mechanisms are discussed. [ABSTRACT FROM AUTHOR]

To improve the quality and efficiency of machine translation (MT) for low-resource languages (LRLs), this paper analyzes the application of genetic algorithm (GA) under the background of cloud computing (CC). By using GA to optimize MT for LRL, this study aims to address the limitations and challenges of traditional methods on LRL. Firstly, GA under the background of the CC platform is analyzed in detail. The CC platform offers powerful computing and storage capabilities that provide the basis for large-scale optimization using GA. GA is an optimization algorithm based on the principle of biological evolution, which seeks the optimal solution by simulating genes' genetic and evolutionary processes. In MT of LRL, GA can be used to optimize model parameters, select translation rules, and improve translation quality, thereby improving translation results. Secondly, the present situation of MT for LRL is described. Finally, the traditional LRL-oriented MT and the GA-optimized LRL-oriented MT are compared and analyzed. The results reveal that the traditional LRL-oriented MT has low accuracy and low customer satisfaction (CS). Considering the translation time, accuracy, and resource utilization rate (RUR), the highest rate is only about 47%. In contrast, GA-optimized LRL-oriented MT significantly improves translation accuracy and CS, reaching approximately 94%. The final evaluation results indicate that the accuracy of the model is usually above 70%, and up to 94%. Therefore, GA plays an important role in optimization for LRL-oriented MT. This paper provides technical support for optimizing LRL-oriented MT and contributes to the further development of MT technology. By applying GA, the limitations of traditional methods in LRL can be overcome and the quality and efficiency of translation can be improved. It is of great significance to improve the development of translation technology of LRL, enhance cross-language communication, and promote global cultural exchange. [ABSTRACT FROM AUTHOR]

Location-based skyline queries in road networks can quickly return the desired data to the user from a large amount of data according to the user's needs and location. However, there is no effective mechanism for calculating the road network distance and judging the dominant relationship between data points in the existing skyline queries algorithms in road networks. In this paper, we propose improved dynamic skyline queries in road networks, which can quickly compute all skyline points in road networks. Firstly, this paper proposes a GD-tree index, which efficiently stores the location information of the target tuple in the road network and speeds up the calculation of the road network distance. In addition, the concept of the optimal scan end point is proposed to reduce the calculation cost. The histogram of frequency statistical is proposed for the non-spatial dimension, and the nearest and farthest distance is calculated for the spatial dimension to select the optimal scan end point. Finally, extensive experiments in real road network datasets demonstrate the efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The metaverse is seen as a future generation of the Internet in which the virtual and the real merge into a common world. Technologies such as IoT, cloud computing, artificial intelligence or the reality–virtuality continuum underpin the metaverse and condition its evolution. This paper presents a bibliometric study on the WoS database (from 1995 to 2022) to obtain a comprehensive and non-subjective understanding of the metaverse. The study identifies the main subject areas and sources, the leading countries and authors. It also analyzes the evolution over time and the core and future research themes. Extended reality, blockchain, artificial intelligence and sensors are identified as core themes, while building information modeling, digital twins and governance emerge as future themes. Based on the bibliometric study, a general layered metaverse architecture is proposed that streamlines open challenges in the metaverse to assist researchers and companies in introducing innovative and disruptive improvements. [ABSTRACT FROM AUTHOR]

Collecting and analyzing data from all devices to improve the efficiency of business processes is an important task of Industrial Internet of Things (IIoT). In the age of data explosion, extensive text data generated by the IIoT have given birth to a variety of text representation methods. The task of text representation is to convert the natural language to a form that computer can understand with retaining the original semantics. However, these methods are difficult to effectively extract the semantic features among words and distinguish polysemy in natural language. Combining the advantages of convolutional neural network (CNN) and variational autoencoder (VAE), this paper proposes an intelligent CNN-VAE text representation algorithm as an advanced learning method for social big data within next-generation IIoT, which help users identify the information collected by sensors and perform further processing. This method employs the convolution layer to capture the local features of the context and uses the variational technique to reconstruct feature space to make it conform to the normal distribution. In addition, the improved word2vec model based on topical word embedding (TWE) is utilized to add topical information to word vectors to distinguish polysemy. This paper takes the social big data as an example to illustrate the way of the proposed algorithm applied in the next-generation IIoT and utilizes Cnews dataset to verify the performance of proposed method with four evaluating metrics (i.e., recall, accuracy, precision, and F1-score). Experimental results indicate that the proposed method outperforms word2vec-avg and CNN-AE in K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) classifiers and distinguishes polysemy effectively. [ABSTRACT FROM AUTHOR]

Whether it is an NLP (natural language processing) task or an NLU (natural language understanding) task, many methods are model oriented, ignoring the importance of data features. Such models did not perform well for many tasks based on feature loose, unbalanced tricky data including text classification tasks. In this regard, this paper proposes a classification method called LSTM-SN (long-short term memory RNN fusion social network) based on extremely complex datasets. The approach condenses the characteristics of the dataset. LSTM combines with social network methods derived from specific datasets to complete the classification task, and then use complex network structure evolution methods to discover dynamic social attributes. The experimental results show that this method can overcome the shortcomings of traditional methods and achieve better classification results. Finally, a method to calculate the accuracy of fusion model is proposed. The research ideas of this paper have far-reaching significance in the domain of social data analysis and relation extraction. [ABSTRACT FROM AUTHOR]

Traditional deep learning models prefer large data sets, and in reality small data sets are easier to obtain. It is more practical to build models suitable for small data sets. Based on CNN, this paper proposes the concept of union convolution to build a deep learning model Union-net that is suitable for small data sets. The Union-net has small model size and superior performance. In this paper, the model is tested based on multiple commonly used data sets. The experimental results show that Union-net outperforms most models when dealing with small datasets, and Union-net outperforms other models when dealing with complex classification tasks or dealing with few-shot datasets. The codes for this paper have been uploaded to https://github.com/yeaso/union-net. [ABSTRACT FROM AUTHOR]

Demeanor evidence refers to the authoritative opinions of experts using analytical instruments to collect and interpret the formation of external physiological symptoms of the entire human body. With the development of modern technology, the observation of demeanor has entered a new stage of multimodal quantification. The quantifiable results of demeanor observation with the help of scientific and technological instruments play an important role in judicial work such as search, interrogation, and evidence review. The use of man-made reasoning in the field of legal settling has become increasingly broad. Specialists are giving increasingly more consideration to the securing of modular proof. This paper proposes the development of a component examination model for modular proof examination applications. The technique for this paper is to apply the guileless Bayes strategy, propose a superior information mining calculation, and lay out a model for proof observation and examination. The function of these methods is to systematically explore the basic theoretical issues of demeanor evidence based on the status quo of judicial application of demeanor evidence. Through the prediction of individual demeanor based on data mining algorithm, the evidence analysis model is designed, the neurobiological experiment is carried out, and the demeanor evidence animal stress model is constructed to verify the scientific basis of multidemeanor evidence observation. The experimental results showed that after repeated stimulation of SD rats, the maximum changes in the expression of HSP70 gene and SAA gene were 10.77 and 14.1 respectively, reflecting the high reliability of demeanor evidence biological experiments. The model can improve the accuracy of evidence use, and the correct use of demeanor evidence can realize the true litigation value of intelligent justice and the concept of human rights protection, and promote the construction of intelligent justice. [ABSTRACT FROM AUTHOR]

In the multi-domain network scenario, in order to improve the survivability of service function chain (SFC) in the face of network failure, most methods solve this problem through virtual network function (VNF) backup mechanism. However, the traditional multi-domain SFC deployment method lacks a SFC partition mechanism for backup resource consumption and does not consider the isolation and privacy requirements between different network domains. In view of the above problems, this paper proposes a reliability partition scheme based on reinforcement learning in SFC partition stage, which can ensure that VNF is backed up while maintaining good load balancing and low inter-domain transmission delay, and improve the reliability of SFC. Then, this paper proposes a VNF backup mechanism with minimum resource fluctuation in the VNF mapping stage and uses the integer linear programming (ILP) model to determine the backup scheme of each VNF, so as to ensure the minimum fluctuation of resource occupancy of the entire network. Finally, this paper proposes a multi-domain SFC deployment and backup algorithm based on Federated learning (FA-MSDB). The experimental results indicate that FA-MSDB can effectively improve the survival rate of SFC, reduce the overall transmission delay, and ensure good inter-domain and intra-domain load balance. [ABSTRACT FROM AUTHOR]

This paper discusses radio resource management in the telecommunications industry that utilizes opportunistic scheduling approaches and methods. It proposes a new scheduler called IFMR (Improved Fairness of MaxRate) to extend the opportunistic approach with the proposition of a new scheduling solution that enables to significantly maximize the system throughput. Our goal is to ensure better results that maximize system throughput, ensure perfect fairness at three levels and maximize the number of satisfied users who have achieved their desired throughput. Similarly, the performance of the proposed algorithm is evaluated and compared with reference algorithms: round robin, MaxSNR and proportional fair (PF). The focus of this study is to evaluate and analyze the quality of service guaranteed to each network subscriber, considering the heterogeneous data traffic based on simulations. The algorithms presented in this paper are programmed and simulated using the MATLAB simulation software. The study aims to effectively analyze the impact of radio resource management algorithms and schedulers, including the round robin algorithm, MaxSNR and PF, among others, with the main objective of evaluating the performance of the schedulers used by telecommunication and cellphone network operators. The scheduling phase, which precedes resource allocation and assignment, is a critical aspect of the study. The impact of these schedulers on throughput and fairness will also be evaluated and analyzed based on specific criteria. [ABSTRACT FROM AUTHOR]

Patient data are susceptible and vulnerable when collected through open channels. Since these data are collected through various IoT (Internet of Things) devices, mobile applications, and web-based applications, their security is more important. Many hackers and attackers can be found between the patient, the cloud server, and the data collector. Blockchain is a secure, immutable, and transparent method of collecting and storing data. In this paper, a novel scheme for telehealth data sharing is proposed. In this proposed scheme, we use a property mapping function to map the common properties of participating blockchains. The data-sharing case is decided based on the property mapping score, and a temporary blockchain TempChain is created. Data sharing is done using the safe search data and sharing only the required data with the requester blockchain. This proposed scheme improves the security and privacy of telehealth data sharing. The results of the proposed scheme in different cases show the proposed scheme's efficiency with respect to the available state-of-the-art system. The proposed scheme's security is also examined in this paper. [ABSTRACT FROM AUTHOR]

Channel pruning has recently become a widely used model compression method. However, most existing channel pruning methods only prune to decrease the model size, such as the number of parameters or FLOPs, and hence the decrease in model size does not effectively lead to an improvement in inference performance. To address this problem, this paper proposes a latency-optimized channel pruning method for CNN inference acceleration on GPU platforms by latency stair-step discrimination, two-stage benefit assessment and latency-sharing channel pruning. Compared with recent state-of-the-art model compression methods, it can achieve significant improvements in inference performance with comparable compression rates and model accuracy. The contributions of this paper include the following: first, a three-point latency stair-step discrimination method is proposed for determining the candidate prunable coordinates with the best latency performance adapted to the current hardware. Then, a two-stage benefit assessment method based on interlayer dependencies is proposed for determining the optimal channel pruning rate of each layer in the network. Finally, a latency-sharing channel pruning framework is proposed to accelerate the model pruning adaptation process. The method proposed in this paper can significantly reduce the model inference latency on multiple types of GPU platforms. To verify the effectiveness, we use three general-purpose GPU platforms and two embedded GPU platforms to evaluate the algorithm performance. The experimental results show that for recent state-of-the-art CNNs, the proposed method can achieve a 22.0–6.6% latency reduction and a 1.3 –3.0 inference performance improvement as well as a 1.2–4.3 pruning adaptation speedup with high model accuracy. [ABSTRACT FROM AUTHOR]

OP2 is a domain-specific language-based programming framework for unstructured mesh applications. It supports automatic code generation targeting multiple parallel modes, with CUDA included. However, using OP2 to generate efficient CUDA code for real-world applications is a challenging task. This paper reports our efforts optimizing the CUDA code performance when refactoring an unstructured high-order CFD application (namely HOUR2D) based on OP2. A series of novel methods are realized, including utilizing appropriate execution strategies, using local arrays, and optimizing the OP2 data transfer function, etc. Performance evaluation shows that our optimizations significantly improve the performance of the finally generated CUDA code. The overall performance of our optimized OP2-CUDA code is 13.2 times higher than the unoptimized OP2-CUDA code and 2.4 times higher than the manual CUDA code. Meanwhile, these optimizations do not affect the portability of HOUR2D as an OP2 application. [ABSTRACT FROM AUTHOR]

The reliable prediction of solar energy production and surplus is crucial for the stability of the electricity grid and effective energy distribution, particularly during peak consumption periods. Encouraging solar adoption by customers is also important despite fluctuations in solar energy generation. This paper addresses the need for an intelligent surplus solar energy prediction model, referred to as the Green Model, which aims to accurately predict surplus electrical energy that can be returned to the distribution grid. The Green Model utilizes a combination of a developed long short-term memory (LSTM) neural network and a novel optimization technique called deterministic selection network by gain sharing knowledge (DSN-GSK). The DSN-GSK optimizes the structure of LSTM by determining the optimal number of hidden layers, nodes in each layer, biases, weights, and activation functions based on the most important features that represent the relationship between generated solar energy and weather factors. The Green Model was evaluated and analysed, demonstrating high accuracy in the short-term prediction of surplus electrical energy with a minimal percentage of error. The model shows promising prospects for the development of returned electrical energy prediction. The main novelty of this paper lies in the development of the Green Model, which combines LSTM and DSN-GSK to enhance the accuracy of surplus solar energy prediction. The benefits of the Green Model include improved stability and efficiency of the electricity grid, effective utilization of renewable energy sources, and the reduction of negative environmental impacts. The contributions of this paper include advancing the field of intelligent energy prediction, optimizing the structure of LSTM, and providing valuable insights for the integration of renewable energy into the existing energy infrastructure. [ABSTRACT FROM AUTHOR]

A blockchain is one distributed ledger system and keeps the high redundancy of ledger copies to make the assurance of network security. However, the continuously duplicated full copies also impose a tremendous amount of demand on some nodes for data storage. The development of blockchain technologies in the Internet of things (IoT) application scenario is hampered by the restricted storage capacities of terminal devices used in the IoT edge computing scenario, which makes it difficult to load the full copy with infinite growth. Our paper suggests a collaborative ledger storing model based on Chord Ring to address the issues with lightweight blockchains in data storage. On-chain blocks are split by Chord Ring structure and stored in various node clusters in a decentralized manner, and off-chain blocks at various levels are provided with proof-of-work consensus asynchronously and archived centrally to the cloud storage on a regular basis. The theoretical and experimental analysis indicates that this model can reduce the data storage redundancy of blockchains while ensuring the high availability of data and the high decentralization of the network. [ABSTRACT FROM AUTHOR]

The early and effective diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI) has received increasing attention in recent years. However, currently available deep learning methods often ignore the contextual spatial information contained in structural MRI images used for early diagnosis and classification of Alzheimer's disease. This may lead us to miss important structural details by failing to adequately capture the potential connections between each slice and its neighboring slices. This lack of contextual information may cause the accuracy of the network model to suffer, which in turn affects its generalization ability and application in real-life scenarios. To explore deeper the connection between spatial context slices, this research is designed to develop a new network model to effectively detect or predict AD by digging into the deeper spatial contextual structural information. In this paper, we design a spatial context network based on 3D convolutional neural network to learn the multi-level structural features of brain MRI images for AD classification. The experimental results show that the model has good stability, accuracy and generalization ability. Our experimental method had a classification accuracy of 92.6% in the AD/CN comparison, 74.9% in the AD/MCI comparison, and 76.3% in the MCI/CN comparison. In addition, this paper demonstrates the effectiveness of the proposed network model through ablation experiments. [ABSTRACT FROM AUTHOR]

Hardware/software (HW/SW) partitioning is a vital aspect of HW/SW co-design. With the development of the design complexity in heterogeneous computing systems, existing partitioning algorithms have demonstrated inadequate performance in addressing problems relating to large-scale task nodes. This paper presents a novel HW/SW partitioning algorithm based on node resource attributes hovering swarm particle swarm optimization (HSPSO). First, the system task graph is initialized via the node resource urgency partitioning algorithm; then, the iterative solution produced by HSPSO algorithm yields the partitioning result. We present new initialization by combining node resource attribute information and introduce two improvements to the learning strategy of HSPSO algorithm. For the main swarm, a directed sample set and the addition of perturbation particles are designed to direct the main swarm's particle search process. For the secondary swarm, a dynamic particle update equation is formulated. Iterative updates are performed based on previous rounds' prior information using adaptive inertia weight. The experimental results illustrate that, in large-scale systems task graph partitioning with more than 400 nodes, when compared with mainstream partitioning algorithms, the proposed algorithm improves partitioning performance by no less than 10% for compute-intensive task graphs and no <5% for communication-intensive task graphs, with higher solution stability. [ABSTRACT FROM AUTHOR]

The presence of haze results in diminished image clarity, the loss of image details, color alterations, and a decline in image visibility. This paper proposes an efficient multi-stage feature fusion defogging network based on the attention mechanism for effective defogging in complex environments. To create a multi-branch defogging network, the model integrates several attention techniques to create various sorts of branching network architectures. The image's spatial details and contextual information are supplemented and merged based on the recovered image feature information of different network branches to increase the effectiveness of the network model. The stage attention fusion mechanism created among several network branches can lessen the loss of image data during feature extraction and improve the effectiveness of the image-defogging operation. The experimental results demonstrate that the proposed algorithm has superior defogging performance in both synthetic and real-world scene datasets and performs more admirably in terms of accuracy compared to other sophisticated algorithms, particularly in the RESIDE and O-Haze datasets. The PSNR metrics on the RESIDE and O-Haze datasets are improved by 1.58 dB and 1.61 dB, respectively, compared to the best-advanced technique suggested in this study, and the SSIM metrics on the O-Haze dataset are improved by 3.4%. [ABSTRACT FROM AUTHOR]

This paper solves the task of unsupervised video object segmentation (UVOS) that segments the objects of interest through the entire videos without any annotation. In recent years, many unsupervised video object segmentation (UVOS) methods have been proposed. Although these methods perform well, they rely on networks with heavy weights, often leading to large model size. In order to reduce the model size while keeping a competitive performance, we propose a saliency-based dual-attention (SDA) method for UVOS in this paper. In our method, we take optical flow and video frames as inputs and extract the appearance information and motion information from optical flow and video frames. We design a two-branch network with appearance information and motion information. The information from these two branches is fused via a saliency-based dual-attention module to segment the primary object in one path. The saliency-based dual-attention module is composed of saliency attention and saliency-based reverse attention. To demonstrate the effectiveness of our network, we tested it on the DAVIS-2016 and SegtrackV2 datasets. Experimental results demonstrate that our method can achieve competitive results in terms of accuracy and model size. [ABSTRACT FROM AUTHOR]

The scarcity of defect samples and the imbalance of defect types lead to the fact that achieving defect detection in color-patterned fabrics remains a challenge in the textile industry. Defect detection methods based on traditional auto-encoder are difficult to solve the problem of defect detection in complex color-patterned fabrics. In order to solve the problem of weak feature representation of traditional auto-encoders, this paper proposes an unsupervised method based on triplet attention multi-scale U-shape denoising convolutional auto-encoder (TA_MSUDCAE). The method further enhances the feature representation capability of the auto-encoder by introducing a triplet attention mechanism based on utilizing the multi-scale information of the image. Firstly, the defect-free samples that are added with Gaussian noise are used as inputs to the model in the training stage. The model is trained to reconstruct and repair the defective regions. Secondly, the test image is input to the trained model to obtain a normal reconstructed image, and the residual image is obtained by calculating the difference between the input image and the reconstructed image. Finally, the defect detection and localization results are obtained by threshold segmentation and mathematical morphology processing of the residual image. A large number of experiments have been carried out on a variety of representative color-patterned fabrics, and the results prove the effectiveness of the proposed method in fabric defect detection. [ABSTRACT FROM AUTHOR]

In recent years, the combination of deep learning and side-channel analysis has received extensive attention. Previous research has shown that the key recovery problem can be transformed into a classification problem. The performance of these models strongly depends on the size of the dataset and the number of instances in each target class. The training time is very long. In this paper, the key recovery problem is transformed into a similarity measurement problem in Siamese neural networks. We use simulated power traces and true power traces to form power pairs to augment data and simplify key recovery steps. The trace pairs are selected based on labels and added to the training to improve model performance. The model adopts a Siamese, CNN-based architecture, and it can evaluate the similarity between the inputs. The correct key is revealed by the similarity of different trace pairs. In experiments, three datasets are used to evaluate our method. The results show that the proposed method can be successfully trained with 1000 power traces and has excellent attack efficiency and training speed. [ABSTRACT FROM AUTHOR]

To address the path planning problem for unmanned combat aerial vehicle (UCAV) more effectively, a novel two-stage path planning model is proposed. The first stage involves a longitudinal search primarily aimed at predicting the initial path, while the second stage is a horizontal search designed to correct the initial path. Furthermore, to tackle the UCAV path planning issue more effectively, this paper designs an improved elephant clan optimization (IECO) algorithm based on the average sample learning strategy, opposition-based learning, and Lévy flight disturbance strategy. Subsequently, IECO is integrated with the two-stage model (TSIECO) to address the UCAV path planning problem. Additionally, numerical experiments across 15 test functions reveal that IECO outperforms other algorithms in terms of optimization capability and convergence speed. Finally, the UCAV path planning experimental results indicate that the two-stage model based on IECO, as proposed in this paper, has significant advantages over traditional path planning models based on other swarm intelligence algorithms. Specifically, in three different simulated environments, the TSIECO has been tested on a total of 9 maps with varying parameters, yielding paths that are optimal in terms of cost and stability. [ABSTRACT FROM AUTHOR]

The Type-2 fuzzy set is a fuzzy set with fuzzy membership degrees. This set is used when accurately determining the membership degree of a fuzzy set is challenging. It has been observed that higher-type fuzzy sets improve accuracy. However, to use fuzzy sets of higher types in deterministic space, the type needs to be reduced. Another critical challenge is ensuring hardware implementation capability and optimal performance in real-time applications while using fuzzy techniques. Memristor structures are emerging hardware platforms with biological similarities to the human nervous system, and its nanoscale implementation and low power consumption, making them suitable for hardware implementation. This paper introduces various approaches to implementing a fuzzy system with type-2 membership fuzzy sets, and for the first time, demonstrates the utilization of memristor structures to reduce the type. The suggested circuits allow the membership functions to have any shape and resolution, and the implementation results demonstrate the efficiency of the proposed hardware. The main goal of this paper was to showcase a hardware implementation that incorporates on-chip training, allowing adaptability to the environment without dependence on the host system (In-Situ Training). The ArC One hardware platform is used to demonstrate the results experimentally. In modelling and classification, the simulation and experimental results show an increase in accuracy more than 2% has been achieved, compared to previous works. [ABSTRACT FROM AUTHOR]

In the last decade, the smart grid has utilized many modern technologies and applications compared with the conventional grid. Cloud computing offers numerous managed services and storage solutions for smart grid data. To balance security, privacy, efficiency, and utility, more efforts should be made to keep up with the rapid evolution of technology. Searchable encryption techniques are widely considered an intelligent solution to ensure data privacy and security while maintaining the functionality to search over encrypted data. In this paper, we propose a more reliable and efficient searchable symmetric encryption scheme for smart grid data. It is a dynamic keyword searchable scheme that uses a symmetric cipher based on a key hashing algorithm (DKS-SCKHA) to generate a secure index. This scheme eliminates the false-positive issue associated with the use of bloom filters and narrows the scope of the retrieved search results. Additionally, it efficiently supports both partial and exact query processing on the encrypted database. Both theoretical and security analyses demonstrate the efficiency and security of the DKS-SCKHA scheme compared to other previous schemes. Comprehensive experiments on a smart grid dataset showed that the DKS-SCKHA scheme is 35–68% more efficient than the schemes compared in this paper. The DKS-SCKHA scheme supports three keyword search scenarios: single, conjunctive, and disjunctive. Furthermore, the DKS-SCKHA scheme is extended to support dynamic fuzzy keyword search on the encrypted database (DEFKS-SCKHA). We evaluated the security and efficiency of the DEFKS-SCKHA scheme through security analysis and experimental evaluation. Theoretical analysis shows that the proposed scheme is secure against known-ciphertext and known-background attacks. [ABSTRACT FROM AUTHOR]

The connectivity of a network is an important indicator for assessing its reliability and fault-tolerability. In this paper, we study a novel measurement, which is the h-faulty-block connectivity. Given a connected graph G and a nonnegative integer h, let C ⊂ V (G) and G[C] be a connected subgraph. Then, C is called an h-faulty-block of G if G - C is disconnected, and every remaining component of G - C has at least h + 1 nodes. The minimum cardinality over all h-faulty-blocks of G is called h-faulty-block connectivity of G, denoted by F B k h (G) . In this paper, we focus on the alternating group graphs and split-star networks. We study the { 0 , 1 , 2 } -faulty-block connectivity of the two kinds of graphs and show that F B k 0 (A G n) = 3 n - 7 for n ≥ 4 , F B k 1 (A G n) = 5 n - 14 for n ≥ 5 , F B k 2 (A G n) = 7 n - 22 for n ≥ 6 , and F B k 0 (S n 2) = 3 n - 5 for n ≥ 4 , F B k 1 (S n 2) = 5 n - 11 for n ≥ 5 , F B k 2 (S n 2) = 7 n - 18 for n ≥ 6 . [ABSTRACT FROM AUTHOR]

Most implicit sentiment sentences in aspect level implicit sentiment analysis lack emotional words, but there are still potential emotional clues. Current research mainly utilizes contextual information and external knowledge of text for semantic enhancement, thereby improving implicit sentiment analysis. However, in these models, the semantic correlation between words decays as the distance between the two increases, leading to weak and difficult to capture emotional cues at long distances, presenting ambiguity in emotional polarity and reducing the performance of sentiment analysis. To solve this problem, in this paper, we propose aspect-level implicit sentiment analysis model based on semantic wave and knowledge enhancement. Firstly, the semantic wave-based aspect word context information enhancement method uses the fluctuation property of semantic wave to perform weight adaptive enhancement of semantically related long-distance context information. This method essentially utilizes a sine wave function to significantly reduce the weight of words that are close but semantically unrelated, thereby allowing the weight of words that are close and semantically similar to be relatively reflected, in order to solve the problem of hiding emotional clues at long distances. Then, the implicit sentiment analysis method based on supervised contrastive pre-training is used to capture potential sentiment cues from context information and embed them into the sentence vector by weak feature learning of implicit sentiment. Finally, multi-feature interaction-based knowledge enhancement method is used to focus on the context content of sentences that are more related to background knowledge in a feature interaction way, and the information scaling factor is combined to enhance the dependency between aspect words and sentiment cues, thereby solving the problem of weak features in long-distance emotional clues and accurately identifying the emotional polarity of aspect words. The experiment shows that the model proposed in this paper has made significant improvements on the Restaurant and Laptop datasets in SemEval 2014 Task 4, with an accuracy increase of 3.38% and 4.57% in implicit emotions, respectively, achieving the best performance so far. At the same time, generalization and robustness testing experiments were conducted on the model, achieving preferable performance improvement. [ABSTRACT FROM AUTHOR]

Blockchain technology has unlocked the doors of building decentralized applications, where security plays a vital role. Any transaction ever created in a blockchain is recorded permanently. With the increasing usage of social media modalities today, many non-reputable sources create and publish fake and luring news. Due to the easy availability of the internet and excessive use of social media, fake news can spread like a flash. It causes the need to eliminate fake news posted on social media platforms. The main motive of the paper is to develop an ensemble model that assists in the automated identification of fake news. This paper addresses the identified gaps in detecting multi-modal fake news. We propose Fake News Network (FNNet) as a novel secure blockchain-based deep learning model to detect fake news. It uses blockchain and deep learning to assure data integrity and learn data representations, respectively. The proposed model consists of four layers: the node layer, the deep learning layer, the blockchain layer, and the network layer. This is an ensemble deep-learning model that leverages Bi-LSTM and CNN models, where the Bi-LSTM model captures the sequential data in both directions, and CNN captures the hidden features. We use Pheme, CrisisLexT6, and ISOT datasets to train the model. FNNet achieves an average accuracy of 86.93%, 92.22%, and 98.53% on Pheme, CrisisLexT9, and ISOT datasets, respectively. Our results show that the proposed model is robust and applicable to real-time datasets and social media networks to detect fake news effectively. [ABSTRACT FROM AUTHOR]

The growing depletion of fossil fuels has led to the use of distributed renewable energy sources. This shift has altered the grid structure from centralized to distributed, where energy flows from multiple sources through multiple paths, besides producing a more competitive and dynamic energy market, posing new problems to power system management. To tackle the issue of effectively utilizing renewable energy sources, the energy internet (EI) was developed, in which devices are connected by energy routers. Therefore, efficiently transmitting energy within the EI has become a prominent topic in research. Despite the existence of algorithms and reviews in the literature on energy routing, there is still a lack of a thorough and comprehensive comparison of these existing algorithms. This paper classifies current energy routers and discusses and categorizes energy routing algorithms based on their methods. Additionally, the paper conducts extensive simulations to compare several energy routing algorithms in detail. [ABSTRACT FROM AUTHOR]

Within the realm of social networks, most research efforts have concentrated on identifying crucial nodes in networks, with little attention paid to identifying critical edges. Nevertheless, edges, serving as conduits for information dissemination, hold significant importance. Mining critical edges in networks can serve as a valuable target for both network disassembly as an attack strategy and network preservation as a defensive measure. This paper introduces the k -sup structure by taking into account the strength of relationships between nodes and investigates the critical subgraph based on the k -sup structure. Furthermore, this paper distinguishes between the significance of inter-community edges and intra-community edges, proposing an importance indicator based on the k -sup structure. To validate the effectiveness of the proposed indicator, comparative experiments are conducted with seven classic edge importance indicators on eight real-world network datasets and three synthetic network datasets. The experimental results demonstrate that the proposed indicator assesses their importance, exhibiting superiority over alternative methods in terms of network connectivity. [ABSTRACT FROM AUTHOR]

Controller placement issue (CPI) in software-defined networks (SDNs) describes the controllers' number, location, and assigning of forwarding devices to controllers. Recently, mathematical formulations and algorithms have been proposed to solve various problems in SDNs and software-defined wide area networks. The comprehensive literature review can be divided into four groups according to objectives: (i) minimizing latency between forwarding devices or switches and their corresponding controllers, and minimizing latency between controllers, (ii) improving network resilience and stability, (iii) minimizing energy consumption and installation costs and (iv) using multi-objective approaches. In addition to the objectives of each research, the importance of this paper is to examine the CPI in terms of reducing the network search space in order to optimally place the controller and how to assign switches to the controllers. In this paper, first the mathematical formulations in previous studies will be examined and then, for solving CPI, the existing algorithms will be discussed. Different classifications of CPIs and related formulas/algorithms, descriptions, advantages and disadvantages will be separately provided. A comprehensive comparison of proposed approaches with their advantages and disadvantages in the summarized tables will be provided. Also, a comparative discussion of different statistics of CPIs will be presented in terms of some technical features such as objective-oriented problems and parameters in four categories, estimated environments, and efficient estimating factors in CPIs. Finally, we explained the future studies' challenges, problems related to CPIs, ideas and following orientations in this field. [ABSTRACT FROM AUTHOR]

As the foundation of circuits and electronic systems, the quality of printed circuit boards (PCBs) is directly related to the reliability of the whole system. At present, deep learning-based target detection technology has a broad application prospect in PCB defect detection. However, there are still some shortcomings in the process of detection. For example, the detection speed is slow, and the detection accuracy is not ideal for defects with small size. Therefore, this paper proposes an improved algorithm based on the YOLOv5s model to improve the detection of PCB defects. The algorithm enhances the connection between the shallow and high layers of the network by improving the backbone network structure. Meanwhile, a self-attention mechanism is introduced into YoloHead to enhance the feature extraction and the ability to focus on the global information of the feature map, and the self-attention mechanism is optimized by combining the computational characteristics of the SENet, the CBAM and the residual unit. While improving the accuracy of PCB defect detection, better computational efficiency is ensured. In subsequent experiments, this paper trains and tests the improved YOLOv5s algorithm using publicly available PCB defect datasets. The results show that the algorithm achieves a detection rate of 39.7 frames per second and a maximum average precision of 96.14%, which is a 4.68% improvement over the original YOLOv5s. [ABSTRACT FROM AUTHOR]

Community detection is a significant research area in social networks. Most methods use network topology, but combining it with user interactions improves accuracy. This paper proposes a robust method to identify communities based on the improved user interaction degree, the weighted quasi-local structural similarity measure, and the frequent pattern mining on user interactions. In the community creation phase, influential users are identified based on eigenvector centrality and users who interact with them the most are extracted based on frequent pattern mining. In the community expansion phase, we introduce a measure to calculate the degree of user interactions based on the local clustering coefficient improved by interactions between common neighbors. We present two strategies to expand the community. The first strategy, a direct connection, exists between a user outside and a user inside the community. Their similarity is calculated based on the combined measure of improved user interaction degree and user degrees. The second strategy is if two users do not have a direct connection, we consider their communication paths. Therefore, we present a similarity measure combining a quasi-local path-based measure and an improved user interaction degree. Analysis of Higgs Twitter and Flickr datasets using internal density, Normalized Mutual Information, and Adjusted Rand Index shows that this paper's method outperforms the other five community detection methods. Furthermore, our method has more robustness than other relevant methods. [ABSTRACT FROM AUTHOR]

Gait recognition has become an important biometric feature for human identification, in addition to data such as face, iris, and fingerprint. The goal of human gait recognition is to identify people based on walking images. Artificial intelligence technologies have revolutionized the field of gait recognition by enabling computers to automatically learn and extract intricate patterns. These techniques examine video recordings to determine key features in an individual's gait, and these features are used to identify the person. This paper examines the existing appearance-based gait recognition methods that have been published in recent years. The primary objective of this paper is to provide an informative survey of the state-of-the-art in appearance-based gait recognition techniques, highlighting their applications, strengths, and limitations. Through our analysis, we aim to highlight the significant advance that has been made in this field, draw attention to the challenges that have been faced, and identify areas of prospective future research and advances in technology. Furthermore, we comprehensively examine common datasets used in gait recognition research. By analyzing the latest developments in appearance-based gait recognition, our study aims to be a helpful resource for researchers, providing an extensive overview of current methods and guiding future attempts in this dynamic field. [ABSTRACT FROM AUTHOR]

This paper introduces a sophisticated approach to network security, with a primary emphasis on utilizing deep learning for intrusion detection. In real-world scenarios, the high dimensionality of training data poses challenges for simple deep learning models and can lead to vanishing gradient issues with complex neural networks. Additionally, uploading network traffic data to a central server for training raises privacy concerns. To tackle these issues, the paper introduces a Residual Network (ResNet)-based deep learning model trained using a federated learning approach. The ResNet effectively tackles the vanishing gradient problem, while federated learning enables multiple Internet Service Providers (ISPs) or clients to engage in joint training without sharing their data with third parties. This approach enhances accuracy through collaborative learning while maintaining privacy. Experimental results on the X-IIoTID dataset indicate that the proposed model outperforms conventional deep learning and machine learning methods in terms of accuracy and other metrics used for evaluation. Specifically, the proposed methodology achieved 99.43% accuracy in a centralized environment and 99.16% accuracy in a federated environment. [ABSTRACT FROM AUTHOR]

The target detection algorithm has a high accuracy rate for the detection of general objects. However, for specific kinds of objects, especially those with complex application scenarios and high requirements on recognition rates, the accuracy and real-time performance are still far behind the actual application requirements. Meanwhile, the high real-time performance of most current target detection algorithm depends on high-performance computers or Graphics Processing Units (GPUs), which limits their application in low-performance embedded system. In this paper, an embedded vehicle detection algorithm was proposed. Compared to the existing general detection algorithms, the network structure of the proposed algorithm has been improved in many aspects. Firstly, the overall network structure of YOLOv3-tiny has been improved, and the way of feature extraction has been modified to increase the network in terms of detection speed and recognition accuracy. Secondly, a spatial pyramid pooling structure is introduced into the network to enhance the learning capability, and the spatial pyramid pooling structure is also improved by increasing the number of pooling layers in the structure and cascading multiple groups of pooling layers of different sizes. Thirdly, to speed up target detection process, the original clustering algorithm is replaced by Kmean++ clustering algorithm, and the original IoU (The Intersection over Union) loss function is replaced by GIoU (Generalized IoU). Fourthly, according to the scale factor of batch normalization layer, the model is compressed and trimmed to remove redundant channels, and a small model more suitable for embedded system application is obtained. Finally, Raspberry Pi 4B and Inter NCS2 neural computing stick are used as the embedded system with the input image size of 416 × 416. Experimental tests on UA-DETRAC dataset obtain higher mAP than other advanced existing methods, indicating that the network model proposed in this paper could effectively improve the real time and accuracy of multi-vehicle target detection. [ABSTRACT FROM AUTHOR]

Inverse Synthetic Aperture Radar (ISAR) is widely used as an all-weather imaging radar system in military and civilian fields. However, for complex moving targets, the presence of their velocity, acceleration, and jerk leads to range migration and Doppler shift, which causes difficulties in imaging, especially in multi-target scenarios. In this paper, the adjacent cross-correlation function (ACCF) is used to reduce the migration order. Based on the idea of Lv transform and Hough transform (HT), an ISAR imaging algorithm for complex maneuvering multi-target is proposed. The algorithm proposed in this paper is simple and fast and can be accomplished by complex multiplication, fast Fourier transform (FFT) and inverse fast Fourier transform (IFFT) without the searching process. The simulation results show that the proposed algorithm can effectively compensate for the range migration (RM) and Doppler migration (DM) caused by the target motion parameters, and form a focused ISAR image. Compared with the existing methods, the algorithm has lower computational complexity and achieves ideal results in both anti-noise performance and imaging. [ABSTRACT FROM AUTHOR]

Actual trends in the real-time system field consists of migration towards complex central processing unit (CPU) architectures with enhanced execution predictability and rapid CPU contexts switch, thus obtaining high-performant control systems. The main objective of this paper is to present the results obtained following the implementation of real-time operating systems (RTOS) functions in hardware. Based on the CPU resource multiplication concept, actual researches has been focused on synthesizing in field-programmable gate array (FPGA) and implementing innovative solutions to improve RTOS performance. The results are materialized by validating an efficient hardware scheduler micro-architecture, from which a remarkable efficiency and a plus of performance and predictability are obtained. The experimental results, the FPGA resource requirements for implementation of the processor in different configurations, and the comparisons with other similar processor architectures are presented in order to verify theoretical aspects proposed through this paper. [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) prediction is critical for industrial equipment status detection, and the accurate prediction results provide decision-makers with actionable information. Preventive maintenance can be carried out to prevent the sudden failure of the equipment effectively based on the predicted results. However, as Industry 4.0 technologies develop, the amount of data collected by sensors is also rapidly increasing. The existing RUL prediction methods are gradually unable to cope with complex industrial equipment data, and deep learning methods gradually come to the fore. In this background, this paper proposes a transformer-based model with a multi-layer encoder–decoder structure to extract domain-invariant features. The decoder in the traditional transformer structure only obtains a single piece of information from the last layer of the encoder, and this paper uses an integrated layer-cross decoding strategy to compensate. Based on the encoder–decoder cross-connection, each decoder layer is provided with global view information from the final encoder layer simultaneously, improving the model's performance. The validity and superiorities of the proposed method are evaluated through several experiments on the publicly available C-MAPSS dataset provided by NASA. As can be seen from the results, the proposed method gets higher prediction accuracy than other network architectures and state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

With the gradual expansion of microservice architecture-based applications, the complexity of system operation and maintenance is also growing significantly. With the advent of AIOps, it is now possible to automatically detect the state of the system, allocate resources, warn, and detect anomalies using machine learning models. Given the dynamic nature of online workloads, the running state of a microservice system in production is constantly in flux. Therefore, it is necessary to continuously train, encapsulate, and deploy models based on the current system status for the AIOps model to dynamically adapt to the system environment. This paper proposes a model update and management pipeline framework for AIOps models in microservices systems in order to accomplish the aforementioned objectives and simplify the process. In addition, a prototype system based on Kubernetes and Gitlab is designed to provide preliminary framework implementation and validation. The system consists of three components: model training, model packaging, and model deploying. Parallelization and parameter search are incorporated into the model training procedure in order to facilitate rapid training of multiple models and automated model hyperparameter tuning. We automate the packaging and deployment process using technology for continuous integration. Experiments are conducted to validate the prototype system, and the results demonstrate the feasibility of the proposed framework. This work serves as a useful resource for constructing an integrated and streamlined AIOps model management system. [ABSTRACT FROM AUTHOR]

Intelligent Transportation System (ITS) aims to strengthen the connection between vehicles, roads, and people. As the important road information in ITS, intelligent detection of traffic signs has become an important part in the intelligent vehicle. In this paper, a lightweight vehicle mounted multi-scale traffic sign detector is proposed. First, guided by the attention fusion algorithm, an improved feature pyramid network is proposed, named AFPN. Assign weights according to the importance of information and fuse multi-dimensional attention maps to improve feature extraction and information retention capabilities. Second, a multi-head detection structure is designed to improve the positioning and detection capability of the detector. According to the target scale, the corresponding detection head is constructed to improve the target detection accuracy. The experimental results show that compared with other state-of-the-art methods, the proposed method not only has excellent detection accuracy with 50.3% for small targets and 64.8% for large targets but also can better trade-off detection speed and detection accuracy. Furthermore, the proposed detector is deployed on the Jetson Xavier NX and integrated with the vehicle-mounted camera, inverter, and LCD to realize real-time traffic sign detection on the vehicle terminal, and the speed reaches 25.6 FPS. [ABSTRACT FROM AUTHOR]