Search

This paper presents a novel hierarchical control scheme for solving the data-driven optimal cooperative tracking control problem of heterogeneous multi-agent systems. Considering that followers cannot communicate with the leader, a prescribed-time fully distributed observer is devised to estimate the leader's state for each follower. Then, the data-driven decentralized controller is designed to ensure that the follower's output can track the leader's one. Compared with the existing results, the advantages of the designed distributed observer are that the prescribed convergence time is completely predetermined by the designer, and the design of the observer gain is independent of the global topology information. Besides, the advantages of the designed decentralized controller are that neither the follower's system model nor a known initial stabilizing control policy is required. Finally, simulation results exemplify the advantage of the proposed method. • Compared with the existing methods, the advantage of our proposed prescribed-time fully distributed observer is that the leader's state can be accurately estimated within the designer's predetermined time; • Unlike the existing RL-based algorithms that rely on the initial stabilizing control policy associated with the accurate system matrices, the proposed new RL-based algorithm not only does not require a known initial stabilizing control policy, but also ensures the optimal tracking control in a data-driven manner. • Different from the homotopy-based policy iteration algorithm, an improved counterpart is presented, where the design parameter can be directly designed in the data-driven manner. [ABSTRACT FROM AUTHOR]

In the application of interval type-2 (IT2) Takagi–Sugeno–Kang (TSK) fuzzy logic systems (FLSs), the center-of-sets (COS) type-reduction (TR) is more advantageous than the centroid TR. This paper proposes three types of discrete non-iterative algorithms to solve the problem of COS TR in IT2 TSK FLSs. Multiple simulation experiments are carried out for the IT2 TSK FLSs with different fuzzy rule numbers. Experimental results show that the computational efficiencies of the three discrete non-iterative algorithms are better than that of Karnik–Mendel (KM) algorithms, which provides latent value for the application of type-2 FLSs. [ABSTRACT FROM AUTHOR]

Concept-cognitive learning (CCL) has been an active topic in artificial intelligence and cognitive computing. Two-way concept-cognitive learning (TCCL), an efficient cognitive mechanism to discover knowledge from an arbitrary information granule, has attracted attention to the problems of concept learning. Although TCCL has been widely adopted for cognitive and learning concepts, the existing studies still have some issues: learning concepts can only from the standard formal context, i.e., extent with discrete information, and ignoring the fuzziness of object information that is also important to precise cognitive and learning concepts. Hence, this paper proposes a novel L-fuzzy concept learning method via two-way concept-cognitive learning and fuzzy residual implication, namely, L-fuzzy concept-cognitive learning (LF-CCL). Specifically, we give the theoretical underpinnings of the L-fuzzy CCL method and a pair of dual cognitive operators are presented based on residual implication. Then L-fuzzy two-way granule spaces are constructed to explore the transformation of information granules and the generation of knowledge granules from arbitrary cognitive clues. Meanwhile, we analyze the CCL progress using L-fuzzy operators based on fixed points. Moreover, the corresponding algorithms are designed, and the decision value of this method in financial investment applications is explored through experimental analysis. Finally, numerical experiments verify the effectiveness and flexibility of the proposed method. [ABSTRACT FROM AUTHOR]

The predicted Bridge Condition Index (BCI) is a guiding indicator for formulating preventive maintenance strategies for bridges and is hardly available even if using the most advanced neural network prediction model, owing to the few measured BCIs and neural network model defects. In this paper, an improved Back-Propagation Neural Network (BPNN) model named CPSO-BP-MC is proposed to predict BCI, which has a BPNN as its core, combined with the Coordinated Particle Swarm Optimization (CPSO) algorithm aims to faster convergence and avoid local optimal solution even with less training sample, and the Markov Chain (MC) algorithm aims to further revise the fluctuation of CPSO-BP prediction output due to maintenance and reinforcement. A case study is presented to demonstrate the efficiency of CPSO-BP-MC predicting BCI with fewer training samples. Comparing the predicted BCI of CPSO-BP-MC with the measured BCI and other models, the results show that CPSO-BP-MC converges faster than other models, and can predict the BCI more stably and accurately, and the error between prediction and measured BCI is less than 3 %. [ABSTRACT FROM AUTHOR]

In recent years, synthetic aperture radar (SAR) vehicle detection has become a research hotspot. However, algorithms using horizontal bounding boxes can lead to redundant detection areas due to the varying aspect ratio and arbitrary orientation of vehicle targets. This paper proposes a morphology-based feature extraction network (MFE-Net), which fully uses the prior shape knowledge of the vehicle targets. Specifically, we adopt rotatable bounding boxes to predict the targets, and a novel rectangular rotation-invariant coordinate convolution (RRICC) is proposed to extract the feature, which can determine more accurately the convolutional sampling location of the vehicles. The adaptive thresholding denoising module (ATDM) is designed to suppress background clutter. Furthermore, inspired by the convolutional neural networks (CNNs) and selfattention, we propose the hybrid representation enhancement module (HREM) to highlight the vehicle target features. The experiment results show that the proposed model obtains an average precision (AP) of 93.1% on the SAR vehicle detection data set (SVDD). [ABSTRACT FROM AUTHOR]

With the continuous advancements in malicious code polymorphism and obfuscation techniques, the performance of traditional machine learning-based detection methods for malware variant detection has gradually declined. Additionally, conventional pre-trained models could adequately capture the contextual semantic information of malicious code and appropriately represent polysemous words. To enhance the efficiency of malware variant detection, this paper proposes the MalEXLNet intelligent semantic analysis and detection architecture for malware. This architecture leverages malware API call sequences and employs an improved pre-training model for semantic vector representation, effectively utilizing the semantic information of API call sequences. It constructs a hybrid deep learning model, CBAM+AttentionBiLSTM, for training and classification prediction. Furthermore, incorporating the KMeansSMOTE algorithm achieves balanced processing of small sample data, ensuring the model maintains robust performance in detecting malicious variants from rare malware families. Comparative experiments on generalized datasets, Ember and Catak, the results show that the proposed MalEXLNet architecture achieves excellent performance in malware classification and detection tasks, with accuracies of 98.85% and 94.46% in the two datasets, and macro-averaged and micro-averaged metrics exceeding 98% and 92%, respectively. [ABSTRACT FROM AUTHOR]

The particle swarm optimization (PSO) path planning algorithm often suffers from low population diversity and rapid early convergence, which can lead to the algorithm easily falling into local optima and affecting its stability. This paper proposes an improved PSO algorithm with two key enhancements: (1) the introduction of a particle reactivation module during the iteration process, and (2) the incorporation of the Simulated Annealing (SA) concept during the global optimal solution update phase. These improvements enhance the diversity of the particle population, slow down the early convergence rate of the algorithm, reduce the probability of the algorithm getting trapped in local optima, and increase its overall stability. Experiments were conducted to compare the proposed algorithm with the standard PSO algorithm, genetic algorithms, and other improved PSO path planning algorithms. The results indicate that the improved algorithm shows superior performance in both average path length and algorithm stability. [ABSTRACT FROM AUTHOR]

Siamese-based segmentation and tracking algorithms improve accuracy and stability for video object segmentation and tracking tasks simultaneously. Although effective, variability in target appearance and background clutter can still affect segmentation accuracy and further influence the performance of tracking. In this paper, we present a memory propagation-based target- aware and mask-attention decision network for robust object segmentation and tracking. Firstly, a mask propagation-based attention module (MPAM) is constructed to explore the inherent correlation among image frames, which can mine mask information of the historical frames. By retrieving a memory bank (MB) that stores features and binary masks of historical frames, target attention maps are generated to highlight the target region on backbone features, thus suppressing the adverse effects of background clutter. Secondly, an attention refinement pathway (ARP) is designed to further refine the segmentation profile in the process of mask generation. A lightweight attention mechanism is introduced to calculate the weight of low- level features, paying more attention to low-level features sensitive to edge detail so as to obtain segmentation results. Finally, a mask fusion mechanism (MFM) is proposed to enhance the accuracy of the mask. By utilizing a mask quality assessment decision network, the corresponding quality scores of the “initial mask” and the “previous mask” can be obtained adaptively, thus achieving the assignment of weights and the fusion of masks. Therefore, the final mask enjoys higher accuracy and stability. Experimental results on multiple benchmarks demonstrate that our algorithm performs outstanding performance in a variety of challenging tracking tasks. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is facing growing security challenges due to its vulnerability. It is imperative to address the security issues using lightweight and efficient encryption schemes in resource-limited IoT. In this paper, we propose an enhanced message authentication encryption (MAE) scheme based on physical-layer key generation (PKG), which uses the random nature of wireless channels to generate and negotiate keys, and simultaneously encrypts the messages and authenticates the source. The proposed enhanced MAE scheme can greatly improve the security performance via dynamic keyed primitives construction while consuming very few resources. The enhanced MAE scheme is an efficient and lightweight secure communication solution, which is very suitable for resource-limited IoT. Theoretical analysis and simulations are carried out to confirm the security of the enhanced MAE scheme and evaluate its performance. A one-bit flipping in the session key or plain texts will result in a 50%-bit change in the ciphertext or message authentication code. The numerical results demonstrate the good performance of the proposed scheme in terms of diffusion and confusion. With respect to the typical advanced encryption standard (AES)- based scheme, the performance of the proposed scheme improves by 80.5% in terms of algorithm execution efficiency. [ABSTRACT FROM AUTHOR]

Existing sea surface small target detection methods typically rely on intricate feature extraction techniques on transformed radar returns. However, these approaches suffer from issues of high computational complexity and low real-time performance. Temporal Convolutional Network (TCN) can enable direct processing of radar time-series echo data without the need for elaborate feature extraction, thus substantially improving computational efficiency. Building upon this, this paper presents a novel target detection algorithm based on Multi-layer Attention Temporal Convolutional Network (MA-TCN). The proposed algorithm processes the amplitude information in the original echo signals, and comprehensively extracts sequence feature information through the construction of stacked residual modules. Additionally, it integrates multi-layer attention mechanisms to adaptively adjust the output weights of each residual module, thereby further enhancing detection accuracy. Experimental results demonstrate that the proposed approach achieves significant improvements in both detection performance and efficiency compared to existing methods. [ABSTRACT FROM AUTHOR]

The detection algorithms of small objects in remote sensing images is often challenging due to the complex background and limited pixels. This can lead to reduced accuracy in detection and an increased number of missed small objects. So this paper introduces YOLOFNC, an enhanced network based on YOLOv7. To improve the model's ability to capture features of small objects, an enhanced C3-Faster module based on the C3 module is designed and integrated into the YOLOv7 network. This module helps extract more features related to small objects. Additionally, we employ Normalized Wasserstein Distance (NWD) fusion GIoU as a novel loss function to refine the accuracy of network optimization weights and the small object regression framework. Furthermore, a coordinated attention (CA) mechanism is incorporated at strategic locations in the model to reduce redundant information in the feature layer and prevent the loss of important small object features. we conduct comparison experiments between YOLO-FNC and other commonly used object detection algorithms on DIOR, AITOD, and VisDrone datasets. The experimental results show that YOLO-FNC achieves 84.4% mAP on the DIOR dataset, 35.9% mAP on the AI-TOD dataset, and 52.6% mAP on the VisDrone dataset. Compared to YOLOv7 and other remote sensing object detection models, YOLO-FNC demonstrates better performance in object detection. [ABSTRACT FROM AUTHOR]

Star identification algorithms can be applied to resident space object (RSO) surveillance, which includes a large number of stars and false stars. This paper proposes an efficient, robust star identification algorithm for RSO surveillance based on a neural network. First, a feature called equal-frequency binning radial feature (EFB-RF) is proposed for guide stars, and a superficial neural network is constructed for feature classification. Then the training set is generated based on EFB-RF. Finally, the remaining stars are identified using a residual star matching method. The simulation experiment and results show that the identification rate of our algorithm can reach 99.82% under 1 pixel position noise, and it can reach 99.54% under 5% false stars. When the percentage of missing stars is 15%, it can reach 99.40%. The algorithm is verified by RSO surveillance. [ABSTRACT FROM AUTHOR]

The paper discusses the possibility of increasing the effectiveness of strategic management of research and development activities in higher education institutions. To achieve this goal, the authors proposed an algorithm for selecting competencies, which allows for the distribution of university employees and students among research and development teams in accordance with their individual competencies for carrying out research and development work. The paper covers the problem statement of competence selection, an overview of natural language processing methods for algorithm development, problematic areas of the algorithm, and prospects for its implementation in university management. [ABSTRACT FROM AUTHOR]

A sensorless control method of permanent magnet synchronous motor (PMSM) based on adaptive super-twisting algorithm sliding mode observer (STASMO) is proposed in this paper. The traditional sliding mode observer (SMO) algorithm has the problem of inherent high-frequency chattering due to the use of switching function. The phase delay will be caused by using low-pass filter to deal with the problem of high-frequency buffeting. In this paper, the chattering of the system is effectively suppressed by combining the super-twisting algorithm and the SMO algorithm. The chattering suppression ability of the algorithm is further improved by adding an adaptive coefficient associated with speed in front of the higher-order integral term of the observer. At the same time, the speed and rotor position information are extracted by normalized phase-locked loop (PLL), which avoids the use of low-pass filter and phase compensation module. In order to overcome the influence of the change of motor parameters on the control system, an online estimation method of motor parameters is proposed. The values of stator resistance and stator inductance are estimated online in real time, and the estimated values are fed back to the SMO, which improves the system performance and estimation accuracy. Through simulations and experiments, it is proved that the proposed algorithm can effectively suppress high-frequency chattering, effectively improve the estimation performance of PMSM sensorless control system, and obtain more accurate speed and rotor position information. [ABSTRACT FROM AUTHOR]

In order to improve the effect of intelligent fusion recommendation under the background of social network, this paper combines the fuzzy perception algorithm to research the intelligent fusion recommendation algorithm of social network. Moreover, this paper proposes a task offloading scheme that relies on V2V communication to utilize idle computing resources in a "resource pool". In addition, this paper formulates the computational task execution time as a min-max problem to reduce the storage overhead to optimize the total task execution time. Numerical results show that the proposed scheme greatly reduces the task execution time. The introduced particle swarm optimization algorithm also proves the convergence speed and accuracy of the optimization problem. The research verifies that the intelligent fusion recommendation algorithm for social network based on fuzzy perception has good social network data fusion effect and can effectively improve the effect of intelligent fusion recommendation. [ABSTRACT FROM AUTHOR]

Federated learning is a distributed machine learning framework that solves data security and data island problems faced by artificial intelligence. However, federated learning frameworks are not always secure, and attackers can attack customer privacy information by analyzing parameters in the training process of federated learning models. To solve the problems of data security and availability during federated learning training, this paper proposes an Efficient Differential Privacy Federated Learning Algorithm based on early stopping mechanism (EfficientDP-FL). This method inherits the advantages of differential privacy and federated learning and improves the performance of model training while protecting the parameter information uploaded by the client during the training process. Specifically, in the federated learning framework, this article uses an adaptive DP-FL method for gradient descent training, which makes the model converge faster than traditional stochastic gradient descent. In addition, due to model convergence, noise should be reduced accordingly. This paper introduces an early stopping mechanism to improve data availability. This paper demonstrates the performance improvement of the Efficient DP-FL algorithm through simulation experiments on real MNIST and Fashion-MNIST datasets. Experimental showthat the efficient DP-FL algorithm is significantly superior to other algorithms. [ABSTRACT FROM AUTHOR]

Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies making different compromises among conflicting objectives. The recent surge of interest in MORL has led to diverse studies and solving methods, often drawing from existing knowledge in multi-objective optimization based on decomposition (MOO/D). Yet, a clear categorization based on both RL and MOO/D is lacking in the existing literature. Consequently, MORL researchers face difficulties when trying to classify contributions within a broader context due to the absence of a standardized taxonomy. To tackle such an issue, this paper introduces multi-objective reinforcement learning based on decomposition (MORL/D), a novel methodology bridging the literature of RL and MOO. A comprehensive taxonomy for MORL/D is presented, providing a structured foundation for categorizing existing and potential MORL works. The introduced taxonomy is then used to scrutinize MORL research, enhancing clarity and conciseness through well-defined categorization. Moreover, a flexible framework derived from the taxonomy is introduced. This framework accommodates diverse instantiations using tools from both RL and MOO/D. Its versatility is demonstrated by implementing it in different configurations and assessing it on contrasting benchmark problems. Results indicate MORL/D instantiations achieve comparable performance to current state-of-the-art approaches on the studied problems. By presenting the taxonomy and framework, this paper offers a comprehensive perspective and a unified vocabulary for MORL. This not only facilitates the identification of algorithmic contributions but also lays the groundwork for novel research avenues in MORL. [ABSTRACT FROM AUTHOR]

In this paper, a pipeline leakage detection algorithm based on information fusion of pressure and flow is proposed, and its core work is the construction of BPA based on discount factors. The wavelet packet decomposition is carried out for the original signals, and the processed signals are used to train different SVM classifiers to achieve the first identification results. For the samples whose initial classification results are not completely consistent, BPA is calculated according to the confusion matrixes of the initial SVM classifiers. In this paper, static discount factors and dynamic discount factors are constructed using different methods, and dynamic discount factors are modified when decisions fail. Then comprehensive discount factors are constructed based on the combination of different static discount factors and dynamic discount factors. The Shafer discount rule is used to modify BPA. Finally, D-S evidence theory is used to fuse the BPA results of all classifiers under different discount combinations. Experiments show that this algorithm can effectively use the correlation of evidences to reasonably fuse the decision results of multiple sensors, overcome the problem that the accuracy of a single sensor is not high enough for leakage identification, and improve the identification accuracy of pipeline leakage. [ABSTRACT FROM AUTHOR]

As urbanization progresses, urban road congestion has intensified, highlighting the need for effective vehicle and pedestrian detection as a cornerstone of public safety transportation. This area holds significant relevance in video surveillance and public safety domains. Despite its importance, achieving precise vehicle and pedestrian detection in complex road environments remains challenging. This paper presents a vehicle-pedestrian detection algorithm based on the improved YOLOv5. Key modifications include the integration of a small target detection layer and alterations to the feature pyramid using the feature fusion technique inherent to the weighted Bidirectional Feature Pyramid Network (BIFPN). This ensures efficient multi-scale feature fusion. A coordinated attention mechanism is introduced to preserve accurate target location data. Furthermore, the paper incorporates the SIOU metric to refine the localization loss function, bolstering both speed and edge regression accuracy. Experimental outcomes indicate that our improved YOLOv5 algorithm augments detection accuracy by 1.9% and achieves a detection speed of 67 FPS, which surpasses many competing target detection algorithms. [ABSTRACT FROM AUTHOR]

The substantial surge in users has adversely impacted the performance of the present IP-based Internet. Named data networking (NDN) emerges as a future alternative, given its distributed content caching system, where data can be cached in multiple routers and retrieved from the closest one instead of the original producer, enhancing content availability, reducing latency, and minimizing data loss. This paper introduces the less popular content eviction (LPCE) policy, a novel cache replacement scheme designed to enhance the caching performance of the conventional LFU (least frequently used) policy in NDN routers, thereby improving overall network efficiency. The proposed method subsumes LFU and FIFO (first in first out) policies and employs an additional list controlled by the LRU (least recently used) policy. Utilizing the ccnSim simulator, we conduct a comparison of LPCE’s performance with that of the LFU technique and other competing caching techniques, considering variations in several simulation parameters. Experimental results reveal that the proposed LPCE algorithm excels over others across a majority of performance metrics, such as cache hit ratio, content delivery delay, upstream hop count, network traffic, and producers’ load. Besides, the findings indicate that LPCE outperforms LFU, with an increase in cache hit ratio ranging from 1.32% to 5.75%. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Graph Neural Network (GNN) directly inherits the captured collaborative information and there is no determination of whether the captured collaborative information benefits user preferences. Therefore, this paper propose the RCGCN model to solve that issue. First, we detect the level of interaction between a specific neighbor of the target node and other neighbors by the common interaction ratio (CIR), and the experimental results show that the collaboration information propagated by neighbors with higher CIR is more favorable to user preferences. Second, we introduce structural neighborhood contrastive learning to mine the association between users and items by comparing them with their structural neighbors. Finally, we use a joint training approach to optimize the learning objectives. The experimental results indicated that the RCGCN model is superior than the current benchmark models in both Recall@20 and NDCG@20 evaluation metrics. [ABSTRACT FROM AUTHOR]

The paper proposes a modification of the existing distributed forward-backward algorithm for finding strongly connected components in directed graphs. The modification aims at improving the parallelism of the algorithm by increasing the branching factor while dividing the workload. Instead of randomly picking the pivot vertex, a heuristic technique is used which allows more sub-tasks to be generated, on average, for the subsequent step of the algorithm. The work describes suitable algorithm modifications and presents empirical results, proving suitability of the approach in question. [ABSTRACT FROM AUTHOR]

To overcome the limitations of the Fourier nonlinearfilter and even mirror Fourier nonlinear filter-based adaptive algorithms for active noise control, this paper introduces boosted Fourier nonlinear filter and boosted even mirror Fourier nonlinear filter algorithms. Weight updating equations for the proposed algorithms are derived. Their performance is compared with Fourier nonlinear filter and even mirror Fourier nonlinear filter. Experimentally recorded bandsawand compressor noises are utilized for the analysis. The analysis is carried out for (a) linear primary and linear secondary paths, and (b) nonlinear primary path and linear secondary path. Visual inspection of residual noises after control and dB values of residual noises are utilized to understand the performance of the developed algorithms. [ABSTRACT FROM AUTHOR]

The growth of Internet of Things (IoT) devices has created opportunities in multiple sectors, but has also created the threat of growing attacks. Malicious actors are taking advantages of the lightweight nature of IoT devices and targeting them to perform attacks. This paper presents a novel approach to detect malicious traffic at an early stage to block attacks at the entry point of network so devices could be protected from getting infected. An optimized Machine Learning(ML) based algorithm is proposed specifically designed for light weighted IoT devices. The IoT- 23 dataset is used in this study to create a model and test the performance. The proposed model detects diverse categories of IoT malwares, creating security threats and challenges to IoT systems. MQTT (Message Queuing Telemetry Transport) is utilized to simulate behavior of IoT devices. Attack and normal traffic is passed to the IoT network to record latency and throughput in both scenarios. Performance of five different classifiers is compared with the proposed algorithm and had outstanding results with an accuracy 99.98%. The detection model takes around 52.89 seconds and processes 3965.27 samples per second. Utilization of CPU during the entire process is observed around 3.5%. Future research directions and suggestions have also been given to enhance the security of IoT environment. [ABSTRACT FROM AUTHOR]

There are many instances of intellectual property rights violations due to the common usage of digital data on the Internet, including unauthorised use, copying, and theft of digital content. Intellectual property rights of digital photos must be upheld, as they are very valuable materials. Digital watermarking is a more modern method to do this. By using a watermark (WM), the owner's information is included into the content, which may then be shared or saved. When required, this technology will retrieve the encoded WM information to prove ownership. Different technologies have been investigated and created on the basis of existing technologies, fields of use, etc. This paper proposes a novel approach to digital watermarking based on a neural network. First, the trigger data set and noise data set are generated from the binary encoding and random cutting of the original training samples. Then, the pattern with higher watermark trigger accuracy is obtained from the trigger set. Simulation results show that the proposed algorithm performs better in terms of accuracy and computing time cost compared to existing algorithms. [ABSTRACT FROM AUTHOR]

This paper explains the construction of a novel augmented hunger games search algorithm using a logarithmic spiral opposition-based learning technique. The proposed algorithm (LsOBL-HGS) is used as an efficient tool for both function optimization and controller design. To assess the performance of the algorithm for function optimization, benchmark functions from the CEC2017 test suite were employed and comparisons were made with available and good performing algorithms. In terms of controller design, the proposed LsOBL-HGS algorithm was utilized to design a FOPID controlled magnetic ball suspension system. Comparative assessments were also performed for FOPID controller design, as well using other state-of-the-art methods reported for the magnetic ball suspension system. The results showed that the proposed LsOBL-HGS algorithm has good capability for FOPID controller design employed in a magnetic ball suspension system as it provided an improvement of more than 13 % in terms of the transient response-related parameters and more than 34 % in terms of bandwidth compared to the best-reported approach used for comparisons. [ABSTRACT FROM AUTHOR]

• Fast, reliable signature generation, blockchain storage, and video verification. • Our method detects video forgery on any file, anytime, anywhere, by anyone. • Insignificant additional storage requirements with respect to video size. • Withstands attacks: collisions, key substitutions, side-channels, chosen messages. • Aids real-time devices, e.g., phones, CCTV, serving legal, police, medical inquiries. Within the field of forensic science, video integrity is an essential component that ensures the validity and dependability of visual evidence that is essential for court cases. Maintaining the integrity of justice in a time when digital modification tools are easily accessible requires making sure that video recordings are unaltered. Video footage is carefully inspected by forensic analysts who use advanced tools to look for indications of manipulation or change. This paper presents a novel, lightweight approach for verifying the integrity of video data. The proposed method utilizes the blockchain and the Edwards Curve Digital Signature Algorithm, coupled with the BLAKE2b hash function. Signatures are generated for video clips with a predetermined size called video segments and stored in blocks chronologically. The signature of the previous block is stored in the current block to add another layer of security. At the time of validation, these signatures are verified. Experimental results show that the proposed method outperforms state-of-the-art methods in both speed and security. Our method is capable of identifying any type of forgery on any video file, by anyone, at any given moment, with insignificant additional storage requirements. Furthermore, our security analysis shows that our method is resilient against various types of attacks, including collision attacks, key substitution attacks, side-channel attacks, and chosen message attacks. The proposed lightweight video integrity verification method is better suited for use in resource constrained devices. [ABSTRACT FROM AUTHOR]

In elastic optical networks (EONs), the slicing-and-stitching technique has emerged as a promising solution to reduce spectrum fragmentation by breaking the subcarrier consecutiveness constraint. This physical layer technology enables all-optical slicing of requests, allowing them to be accommodated in multiple lion-consecutive spectral slots within an EON. In this paper, we investigate the survivable routing problem in EONs with slicers. Specifically, we consider the dedicated path protection (DPP) scheme to address single edge failures. For each connection request, we aim to find a pair of link-disjoint lightpaths to route the request. Additionally, we propose four heuristic algorithms to determine the routing paths based on two different slicing schemes, namely source and L-shape. Through extensive simulations, we evaluate the performance of the proposed algorithms and demonstrate their effectiveness in achieving satisfactory results. [ABSTRACT FROM AUTHOR]

At present, the threats to network security are also increasing, among which abnormal traffic detection is the key link to ensure network security. Traditional detection methods based on signature or threshold are often difficult to adapt to the increasingly complex network environment and new attack methods. Therefore, this paper optimizes and improves the data processing technology, proposes a network ATD method based on particle swarm optimization (PSO) algorithm, and explores in detail the traffic data collection and pre-processing, the feature recognition of abnormal traffic, the application of PSO algorithm, real-time monitoring and response mechanism. The results of two sets of simulation experiments are as follows: compared with the traditional model, the accuracy rate of ATD of the improved algorithm is increased by 7.2% on average, and the detection time is reduced by 7.35s on average. This method not only enhances the adaptability of the model to new attacks, but also improves the degree of automation of detection. [ABSTRACT FROM AUTHOR]

One of the most dangerous threats in WSNs is botnet attacks, in which attackers use mutual communications between IoT devices to launch large-scale malicious activities. In this regard, developments in the field of effective and reliable means of defence against this type of threat, in particular, reliable methods for detecting, identifying, and countering botnet attacks, are becoming increasingly important and relevant. This paper presents a comprehensive study that applies machine learning techniques, namely Random Forest and XGBoost, to identify botnet attacks on IoT effectively. These algorithms are analyzed, compared, and shown to be highly effective in detecting complex patterns indicative of botnet activity, thus achieving a significant improvement in IoT security. The conducted research aims to make a useful contribution to the problem of securing WSNs and IoT in general. The results of the study demonstrated high accuracy in detecting attacks with an accuracy of 99.18% for XGBoost and Random Forest showed an accuracy of 99.21%. Thus, it was shown that the significance of applying machine learning techniques such as Random Forest and XGBoost can be one of the key approaches in combating botnet attacks and securing the IoT. The results of the work emphasize the promising application of machine learning techniques for effective defense against cyber threats and highlight the importance of further. [ABSTRACT FROM AUTHOR]

Intellectual analysis of small and middle-sized datasets through machine learning tools presents challenges in various application domains. Existing methods fail to provide sufficient accuracy, and their utilization is accompanied by a range of issues during data analysis. This paper proposes the improvement of the input doubling method for middle-sized data analysis. The existing method employs an augmentation procedure where the augmented data sample increases quadratically. This imposes several limitations on the method's usage for middle-sized data analysis. The authors propose enhancing this method by introducing an additional clustering procedure during data augmentation. The training algorithms and application methods are described, and a visualization of the main steps of its operation is provided. Modeling is performed on two medium-sized datasets. Optimal parameters for the improved method are selected, demonstrating its high efficiency. Specifically, significant reductions in the volumes of augmented datasets (8-9 times for both datasets respectively) are achieved, accompanied by substantial reductions in the training procedure duration of the method (more than 100 and 260 times for both datasets respectively), while maintaining high accuracy. [ABSTRACT FROM AUTHOR]

Software-based technical indicators have been widely used for the stock market forecasting, aiming to predict market direction. Even though many algorithms for the software based technical indicators are presented, there are almost no hardware implementations reported in the literature. In this paper, the hardware implementation is presented for three commonly used technical indicators: Moving Average Convergence/Divergence (MACD), Relative Strength Index (RSI), and Aroon. Latency evaluation is conducted for Bitcoin and Ethereum within a single-day timeframe, utilizing the Xilinx Zynq-7000 programmable SoC XC7Z020-CLG484-1 platform. Additionally, various hardware/software (HW/SW) partitioning strategies are explored to leverage the flexibility of software alongside the performance advantages of hardware via the Zynq SoC platform. The results show that the best performing technical indicator is MACD with a speedup of 30 times over its software only counterpart. Furthermore, a hybrid design integrating multiple technical indicators is proposed, pairing MACD with RSI due to their competitive throughput values, differing by only 0.38 microseconds. This hybrid approach capitalizes on the parallel processing capabilities of hardware, enabling multiple systems to operate simultaneously. • Proposed SoC framework boosts HFT system efficiency. • HW/SW partitioning on Zynq-7000 SoC enhances flexibility. • MACD, RSI, Aroon indicators implemented for forecasting. • MACD outperforms others on ZYNQ SoC, 30x faster than software. • MACD and RSI combination optimal for hybrid designs. [ABSTRACT FROM AUTHOR]

Semantic segmentation of glioma and its subregions plays a critical role in the entirely clinical workflow of brain cancer diagnosis, monitoring, and treatment planning. Recently, automatic tumor segmentation has attracted a lot of attention, especially supervised learning methods based on neural networks, and the popular “Ushaped” network architecture has achieved state-of-the-art performance in many fields of medical image segmentation. Despite the success of these models, the commonly used small convolution kernel can only extract local features, and more global contextual features cannot be learned, resulting in the disappointing performance of modeling long-range information. At the same time, due to the difficulty of obtaining medical image data, and the imbalance of tumor data in which tumor usually occupies a relatively small volume compared with the background, the adverse influence on the training of the model occurs. In this paper, a novel segmentation framework including TensorMixup data augmentation, improved Receptive Field Expansion UNet (RFE-UNet) and hybrid loss function is designed. Specifically, the TensorMixup algorithm in the data preprocessing phase is used to provide more high-quality training data. In the training phase, both a RFE-UNet network and a hybrid loss function are proposed respectively. RFE-UNet network adds Receptive field expansion module based on Dilated convolution in the first three stages of skip connection, which is used to learn more local and global features. In addition, hybrid loss function is mainly composed of focal loss and focal Tversky loss, focal loss increasing the weight of fewer samples and focal Tversky loss focusing on learning the characteristics of samples with incorrect predictions, which is adopted to alleviate data imbalance. The experimental results on the BraTs2019 dataset show that the average Dice value of the proposed algorithm in the intact tumor, tumor core, and enhanced tumor region can reach 91.55%, 89.23%, and 84.16% respectively, which proves the feasibility and effectiveness of using the proposed architecture. [ABSTRACT FROM AUTHOR]

In Currently, research in the field of infrared road object detection is primarily focused on enhancing model performance and robustness to address the challenges posed by complex real-world driving scenarios. In response to these challenges, this paper proposes an infrared road object detection algorithm based on an attention mechanism. By incorporating the CPCA module, which utilizes attention mechanisms, into the YOLOv8s model, the algorithm enhances the model's focus on unobstructed areas and highly illuminated sections, extracting crucial feature information to improve both accuracy and robustness. Additionally, the original model's downsampling layer is replaced with the Context Grided Network Block Downsampling (CGBD) module, which not only preserves feature edge information but also effectively handles local and contextual features, thereby enhancing the overall feature capturing capabilities of the model. To address the issue of equal aspect ratios in the model's original loss function, the proposed algorithm adopts the superior Weighted Intersection over Union (WIoU). This not only addresses the shortcomings of the original loss function (CIoU) but also demonstrates increased sensitivity in classification tasks. Experimental results show that the improved algorithm, compared to YOLOv8s, achieves a 1.4% increase in mean average precision (mAP), along with notable improvements in precision and recall. Furthermore, when compared to mainstream model algorithms, the enhanced model significantly outperforms in infrared road object detection tasks, providing validation of its effectiveness. [ABSTRACT FROM AUTHOR]

Images captured under severe weather conditions, such as haze and fog, suffer from image quality degradation caused by atmospheric particle diffusion. This degradation manifests as color fading, reduced contrast, and adversely affects the performance of various computer vision tasks. To address this, this paper presents an end-to-end feature fusion attention network (FFA-Net) designed to directly restore haze-free images. By incorporating the SSIM loss into the original loss function, the proposed method effectively captures the visual disparities between the estimated defogged image and the authentic haze-free image. Additionally, it mitigates the color distortion problem inherent in the original algorithm. To address the challenge of low brightness in input images, a low illumination enhancement module is introduced, seamlessly integrated with the FFA-Net defogging method. Subsequently, a comparative analysis of different defogging algorithms is conducted using two distinct foggy datasets. Multiple evaluation metrics are employed to assess the performance of these algorithms. The findings indicate that our algorithm significantly outperforms others in terms of objective indicators such as PSNR and SSIM, as well as visual effects. [ABSTRACT FROM AUTHOR]

Network function virtualization can increase the versatility of computing and network platforms, enabling them to provide more flexible services. In terms of a softwaredefined network and network function virtualization environment, this paper explores the joint virtual network function (VNF) deployment and traffic routing in multisource multicast for VNF service chain deployment to minimize the deployment overhead, transmission delay. Firstly, a multi-objective optimization model, which minimizes the deployment overhead and transmission delay, is established to tackle this challenge problem. Then, a highly efficient coding scheme, crossover, and mutation operators are designed. Based on these, an improved genetic algorithm in multi-objective evolutionary algorithm based on decomposition (MOEA/D) framework (GA-MOEA/D) is proposed to solve this multi-objective problem. Finally, simulation experiments are conducted using two widely used network topologies in order to demonstrate the performance of the proposed algorithm. The simulation results demonstrate that the proposed algorithm can obtain the smaller deployment overhead, transmission delay, load degree and energy consumption 5.2%-15.61%, 11.2%-26.4%, 8.3%-17.6% and 7.8%-14.4% than that of the compared algorithm, respectively. [ABSTRACT FROM AUTHOR]

In the modern era, industrial automation ofers significant competitive advantages. Replacing human labor with robots allows processes to be carried out much faster and more efficiently, with lower waste rates and the possibility of scheduling production 24/7. However, this also presents new challenges and opportunities in optimizing these automated processes. This paper proposes a hybrid algorithm BRKGA (Biased Random Key Genetic Algorithm) to optimize fexible job shop scheduling (FJSSP) problems in automated manufacturing systems. The algorithm is applied to a real-world case study in the Cinvestav Intelligent Manufacturing Laboratory, seeking to optimize the production of a four-piece product. The results demonstrate that the proposed algorithm outperforms previous results in terms of both, solution quality and computational efficiency. [ABSTRACT FROM AUTHOR]

Dataset distillation refers to the process of constructing a smaller dataset based on a larger dataset, so that the training model with the smaller dataset can obtain similar results to the larger dataset. In this paper, we first briefly review the basic methods and some recent advances in this field from the perspectives of meta-learning framework and data matching framework, including the backpropagation through time(BPTT), kernel ridge regression(KRR), decoupled techniques, gradient matching(DC), trajectory matching(MTT) and distribution matching(DM). The results of the plug-and-play approach in recent years are then presented. Finally, we discuss possible future developments from the perspectives of data distillation algorithms on large datasets, the relationship between compress ratio and information contained, more tasks and data modalities, and the use of generative models to improve the distillation results of datasets. [ABSTRACT FROM AUTHOR]

With the rapid development of e-commerce platforms, how to better identify and filter fake reviews has become an urgent issue for the healthy development of the e-commerce industry. However, traditional fake review identification methods cannot effectively solve this problem. They are easily affected by text changes, language differences, and context, and fake reviewers may take measures to blur their behavioral characteristics, making them difficult to detect by behavior-based algorithms. Large language models can capture the contextual relationships of the entire text through self-attention mechanisms, thereby understanding the overall meaning and emotional tendency of the review, which enables them to more effectively judge the authenticity of the review. In addition, large models have strong generalization ability and a certain degree of interpretability, which also makes them suitable for research on fake review text identification. Since fake reviews have an asymmetric distribution feature, this paper uses the RoBERTa model to extract information and combine it with the behavioral features in traditional research for model training. Compared with traditional methods, the accuracy rate is improved by nearly 3%. [ABSTRACT FROM AUTHOR]

In this paper, we explore how to use a Nvidia Jetson Nano and Python to create a system that detects weariness in a person's face using computer vision and machine learning techniques. The system captures the person's face in real time, preprocesses the picture to cut noise, then detects the face using Haar cascades. Next, using computer vision algorithms, characteristics associated with weariness, such as the eyes, are retrieved. These characteristics are then used to build a machine learning model that can predict weariness in the live stream feed. Lastly, using a graphical user interface, the findings are shown, and the system may be fine-tuned to increase accuracy. This device might be used in applications such as driver monitoring and traffic safety. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Donghua University (English Edition) is the property of Journal of Donghua University Editorial Board and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The growing need for high-performance folded cascode CMOS OTAs in various fields, such as electronics and communications, requires them to operate with wide bandwidth, high voltage gain, compact devices, and low power consumption. Recent research indicates that implementing the water cycle algorithm (WCA) can greatly improve the performance of the folded cascode CMOS operational transconductance amplifier (OTA). This is due to the WCA's ability to perform both global search and local exploration efficiently. Notably, the OTA in question is constructed using 0.18µm TSMC technology and operates with a voltage supply of ±1.8V. The results of the simulation were collected using PSPICE software (version 17.4). These design solutions demonstrate exceptional efficiency, delivering significant amplification, high frequency, and minimal power usage. In addition, the paper demonstrates the implementation and simulation outcomes of a folded cascode CMOS operational transconductance amplifier utilizing the water cycle algorithm, MATLAB was employed for this purpose. Using WCA in the design of an OTA for folded cascode CMOS OTA results in significant improvements in performance metrics. Experiences a significant increase in voltage gain, with an increase in gain bandwidth by a factor of five compared to the algorithm-free design. In addition, power consumption is reduced by 15.5%, and the common mode rejection ratio is improved by 15.18% compared to the non-WCA folded cascode CMOS OTA design. The results highlight the effectiveness of the WCA technique as a powerful optimization strategy to improve the performance of folded cascode CMOS OTA. [ABSTRACT FROM AUTHOR]

The utilization of a supporting tool in Double-Sided Incremental Forming (DSIF) imposes a stabilizing compressive stress through the sheet’s thickness, increasing, thereby, the material’s formability and fatigue life. However, these favorable effects strongly depend on a steady tool-metal contact condition. This work presents a general DSIF control scheme, which augments the conventional position servo-loop with explicit force feedback control. The algorithm is examined for its robustness and effectiveness using complex geometries with varying curvatures and wall angles. The resulting parts have demonstrated enhanced material formability and geometric accuracy. [ABSTRACT FROM AUTHOR]

Block cipher (BC) is a type of symmetric cipher used to encrypt data. Despite its advantages, it faces a substantial challenge. Writing the script code for the BC scheme accurately using General-Purpose Programming Languages (GPPLs) poses a significant challenge for programmers. The aim of this paper is to present the first graphical domain-specific modeling language (DSML) for designing and implementing BC algorithms, called BCLang. It is an extension to our previous DSML that was developed for Stream cipher. Programming efficiency and expressiveness were increased by reducing grammar and runtime errors and providing a high level of abstraction. BCLang provides the fundamental components of the BC three structures, which enable the programmer to design and implement BC algorithms in a graphical manner. Two keystream generation methods, performance analysis, and tests of the National Institute of Standards and Technology (NIST) for randomness analysis were provided. The presented language was evaluated based on five subjective metrics specific to graphical DSML evaluation. The design, evaluation details, and properties are explained in depth in this paper. [ABSTRACT FROM AUTHOR]

To serve various tasks requested by various end devices with different requirements, end-edge-cloud (E2C) has attracted more and more attention from specialists in both academia and industry, by combining both benefits of edge and cloud computing. But nowadays, E2C still suffers from low service quality and resource efficiency, due to the geographical distribution of edge resources and the high dynamic of network topology and user mobility. To address these issues, this paper focuses on task offloading, which makes decisions that which resources are allocated to tasks for their processing. This paper first formulates the problem into binary non-linear programming and then proposes a particle swarm optimization (PSO)-based algorithm to solve the problem. The proposed algorithm exploits an imbalance mutation operator and a task rescheduling approach to improve the performance of PSO. The proposed algorithm concerns the resource heterogeneity by correlating the probability that a computing node is decided to process a task with its capacity, by the imbalance mutation. The task rescheduling approach improves the acceptance ratio for a task offloading solution, by reassigning rejected tasks to computing nodes with available resources. Extensive simulated experiments are conducted. And the results show that the proposed offloading algorithm has an 8.93%-37.0% higher acceptance ratio than ten of the classical and up-to-date algorithms, and verify the effectiveness of the imbalanced mutation and the task rescheduling. [ABSTRACT FROM AUTHOR]

Information and communication technologies are spreading rapidly due to their fast proliferation in many fields. The number of Internet users has led to a spike in cyber-attack incidents. E-commerce applications, such as online banking, marketing, trading, and other online businesses, play an integral role in our lives. Network Intrusion Detection System (NIDS) is essential to protect the network from unauthorized access and against other cyber-attacks. The existing NIDS systems are based on the Backward Oracle Matching (BOM) algorithm, which minimizes the false alarm rate and causes of high packet drop ratio. This paper discussed the existing NIDS systems and different used pattern-matching techniques regarding their weaknesses and limitations. To address the existing system issues, this paper proposes an enhanced version of the BOM algorithm by using multiple pattern-matching methods for the NIDS system to improve the network performance. The proposed solution is tested in simulation with existing solutions using the Snort and NSL-KDD datasets. The experimental results indicated that the proposed solution performed better than the existing solutions and achieved a 5.17% detection rate and a 0.22% lower false alarm rate than the existing solution. [ABSTRACT FROM AUTHOR]

Intelligent transportation systems (ITSs) are becoming increasingly popular as they support efficient coordinated transport. ITSs aim to improve the safety, efficiency and reliability of road transportation through integrated approaches to the exchange of relevant information. Mobile adhoc networks (MANETs) and vehicle ad-hoc networks (VANETs) are integral components of ITS. The VANET is composed of interconnected vehicles with sensitivity capabilities to exchange traffic, positioning, weather and emergency information. One of the main challenges in VANET is the reliable and timely dissemination of information between vehicular nodes to improve decision-making processes. This paper illustrates challenges in VANET and reviews possible solutions to improve road safety control and management using V2V and V2I communications. This paper also summarizes existing rules-based and optimized-based solutions, including reducing the effect of mixed environments, obstacles, malfunctions and short wireless ranges on transportation efficiency and reducing false messages that cause unintended vehicle actions and unreliable transportation systems. Additionally, an event simulation algorithm was designed to maximize the benefits of exchangeable messages among vehicles. Furthermore, simulatedVANETenvironmentswere developed to demonstrate how the algorithm can be used for transformable messages. Experimental results show that coupling of both V2V and V2I messages yielded better results in terms of end-to-end delay and average time. Future research directions were highlighted to be taken into account in the development of ITS and intelligent routing mechanisms. [ABSTRACT FROM AUTHOR]

3D models are essential in virtual reality, game development, architecture design, engineering drawing, medicine, and more. Compared to digital images, 3D models can provide more realistic visual effects. In recent years, significant progress has been made in the field of digital image encryption, and researchers have developed new algorithms that are more secure and efficient. However, there needs to be more research on 3D model encryption. This paper proposes a new 3D model encryption algorithm, called the 1D map with sin and logistic coupling (1D-MWSLC), because existing digital image encryption algorithms cannot be directly applied to 3D models. Firstly, this paper introduce 1D-MWSLC, which has a wider range of parameters compared to traditional 1D chaotic systems. When the parameter exceeds a specific range, the chaotic phenomenon does not weaken. Additionally, 1D-MWSLC has two control parameters, which increases the cryptosystem's parameter space. Next, 1D-MWSLC generates keystreams for confusion and diffusion. In the confusion stage, this paper use random confusion, and the keystream generates an index matrix that confuses the integer and decimal parts of the 3D model simultaneously. In the diffusion stage, this paper use parallel bidirectional diffusion to simultaneously diffuse the integer parts of the three coordinates of the 3D model. Finally, this paper verify the proposed algorithm through statistical analysis, and experimental results demonstrate that the proposed 3D model encryption algorithm has robust security. [ABSTRACT FROM AUTHOR]

Due to the anonymity of blockchain, frequent security incidents and attacks occur through it, among which the Ponzi scheme smart contract is a classic type of fraud resulting in huge economic losses. Machine learningbased methods are believed to be promising for detecting ethereum Ponzi schemes. However, there are still some flaws in current research, e.g., insufficient feature extraction of Ponzi scheme smart contracts, without considering class imbalance. In addition, there is room for improvement in detection precision. Aiming at the above problems, this paper proposes an ethereum Ponzi scheme detection scheme through opcode context analysis and adaptive boosting (AdaBoost) algorithm. Firstly, this paper uses the n-gram algorithm to extract more comprehensive contract opcode features and combine them with contract account features, which helps to improve the feature extraction effect. Meanwhile, adaptive synthetic sampling (ADASYN) is introduced to deal with class imbalanced data, and integrated with the Adaboost classifier. Finally, this paper uses the improved AdaBoost classifier for the identification of Ponzi scheme contracts. Experimentally, this paper tests our model in real-world smart contracts and compares it with representative methods in the aspect of F1-score and precision. Moreover, this article compares and discusses the state of art methods with our method in four aspects: data acquisition, data preprocessing, feature extraction, and classifier design. Both experiment and discussion validate the effectiveness of our model. [ABSTRACT FROM AUTHOR]