Search

Data and privacy laws, such as the GDPR, require mobile apps that collect and process the personal data of their citizens to have a legally-compliant policy. Since these mobile apps are hosted on app distribution platforms such as Google Play Store and App Store, the app publishers also require the app developers who wish to submit a new app or make changes to an existing app to be transparent about their app privacy practices regarding handling sensitive user data that requires sensitive permissions such as calendar, camera, microphone. To verify compliance with privacy regulators and app distribution platforms, the app privacy policies and permissions are investigated for consistency. However, little has been done to investigate GDPR completeness checking within the Android permission ecosystem. In this paper, we investigate the design and runtime approaches towards completeness checking of sensitive (‘dangerous’) Android permission policy declarations against GDPR. In this paper, we investigate the design and runtime approaches towards completeness checking of dangerous Android permission policy declarations against GDPR. Leveraging the MPP-270 annotated corpus that describes permission declarations in application privacy policies, six natural language processing and language modelling algorithms are developed to measure permission completeness during runtime while a proof of concept Class Unified Modeling Language Diagram (UML) tool is developed to generate GDPR-compliant permission policy declarations using UML diagrams during design time. This paper makes a significant contribution to the identification of appropriate permission policy declaration methodologies that a developer can use to target particular GDPR laws, increasing GDPR compliance by 12% in cases during runtime using BERT word embedding, measuring GDPR compliance in permission policy sentences, and a UML-driven tool to generate compliant permission declarations.

Link prediction in complex networks is a critical process aimed at uncovering hidden or potential connections among nodes. This technique is widely utilized in areas such as knowledge graphs. Current Graph Neural Networks (GNNs) often focus exclusively on determining whether nodes are connected or assessing the strength of these links by leveraging node attributes. They typically use network structure and attributes to develop node representations through neighborhood aggregation. However, these methods often overlook the intrinsic importance of the links themselves. This paper thoroughly examines the significance of link value based on network structure and introduces an innovative approach for estimating this value, and proposes a method that incorporates link value into both the formulation and training of a link prediction graph attention network. This integration not only boosts the accuracy of link predictions but also provides a theoretical basis for understanding the prediction results. We conducted extensive experiments in link prediction employing widely recognized benchmark datasets. The findings reveal that our proposed framework for link prediction exhibits commendable performance and generalization capabilities, and overall performance improved by an average of 1.2%, thereby establishing it as an effective baseline model.

The limited size of existing datasets and signal variability have hindered EEG-based emotion recognition. In this paper, we present a solution that simultaneously addresses both problems. Generative Adversarial Networks (GANs) have recently shown notable data augmentation (DA) success. Therefore, we leverage a GAN-based DA technique to enhance the robustness of our proposed emotion recognition model by synthetically increasing the size of our datasets. Moreover, we employ contrastive learning to improve the quality of the learned representations from EEG signals and mitigate the adverse impact of inter-subject and intra-subject variability in signals corresponding to the same stimuli or emotions. We do so by maximizing the similarity in the representation of such EEG signals. We perform EEG-based emotion classification using a Graph Neural Network (GNN), which learns the relationship between the extracted EEG features. We compare the proposed model with several recent state-of-the-art emotion recognition models on the DEAP and MAHNOB datasets. The experimental results demonstrate that the proposed model outperforms previous models with a 64.84% and 66.40% emotion classification accuracy on the test set of the DEAP dataset and a 66.98% and 71.69% emotion classification accuracy on the test set of the MAHNOB-HCI dataset for the valence and arousal emotional dimensions, respectively. We perform an ablation study to demonstrate how contrastive learning, GAN, and GNN contribute to improving the proposed solution’s performance.

Cognitive agents make systems autonomous through the process of decision automation by mining an existing knowledge repository at run time. These processes can often be highly compute intensive, and would thus run slowly on the low-power computing platforms typically seen in autonomous systems. This paper examines how knowledge be represented in a Q-table and proposes a novel fast algorithm to mine that knowledge based on constraints. We evaluate this approach for the knowledge mining process of a specific agent: Cognitively Enhanced Complex Event Processing (CECEP). Within CECEP, knowledge is represented using Cognitive Domain Ontologies (CDO), and is mined using situational inputs and constraints. This is a novel approach to store information and is able to accommodate CDOs with millions of solutions. To show that the approach can run on low power hardware in real-time, this algorithm was executed on two low-power minicomputing platforms - Intel’s NUC and Asus’s Tinker Board. At present, no other optimized CDO solvers can generate solutions on these platforms. The algorithm generated the same amount of solutions as a GPU-enabled optimized path-based forward checking CDO solver, while consuming around 7.7 and 5.15 times less energy (Joules) on the NUC and Tinker Board respectively.

The Partial Element Equivalent Circuit (PEEC) method has gained significant recognition as an electromagnetic computational technique known for its ability to represent electromagnetic phenomena using equivalent circuits. This feature makes it particularly valuable for addressing mixed EM-circuit problems. However, PEEC models often exhibit large dimensions, necessitating modeling techniques that can effectively reduce their size while preserving accuracy. Model order reduction (MOR) serves as a highly effective approach to accomplish this objective. This paper presents two MOR techniques based on proper orthogonal decomposition (POD) for PEEC models described by neutral delayed differential equations (NDDEs). The unique characteristics of NDDEs demand specialized MOR approaches, as their formulation is inherently more complex compared to standard quasi-static PEEC models described by non-delayed differential equations. In addition to a traditional one-shot singular value decomposition (SVD), this paper also presents an incrementally computed SVD to evaluate the orthogonal matrix needed to generate the reduced order matrices. The accuracy and efficiency of the proposed PEEC-MOR methods are demonstrated through multiple relevant numerical results in both the frequency-domain and time-domain.

With the development of cyber technology, the intelligence of power systems has increased, and cyber-physics is highly integrated and mutually constrained. In this paper, a globalized cyber-physical cooperative recovery strategy based on node importance is proposed for the failure of a cyber-physical power system under communication failure. First, the static importance of communication nodes and the importance of services are comprehensively analyzed based on the structural business transmission function characteristics of the network. Secondly, based on the fault characteristics of generators, power lines, and loads, the recovery model of the physical system is constructed by considering the safety constraints such as system frequency, node voltage, and line capacity. Finally, considering the possible delay caused by the cyber system failure to the generator output regulation, power line commissioning, and load recovery, the interaction model of physical system recovery and cyber system recovery is established and solved by using the solver after linearizing it. The results show that the cyber-physical recovery strategy can effectively reduce outage losses and improve recovery efficiency.

The goal of music genre classification is to identify the genre of given feature vectors representing certain characteristics of music clips. In addition, to improve the accuracy of music genre classification, considerable research has been conducted on extracting spectral features, which contain critical information for genre classification, from music clips and feeding these features into training models. In particular, recent studies argue that classification accuracy can be enhanced by employing multiple spectral features simultaneously. Consequently, fusing information from multiple spectral features is a critical consideration in designing music genre classification models. Hence, this paper provides a short survey of recent studies on music genre classification and compares the performance of the most recent CNN-based models with a newly devised model that employs a late fusion strategy for the multiple spectral features. Our empirical study of 12 public datasets, including Ballroom, ISMIR04, and GTZAN, showed that the late fusion CNN model outperforms other compared methods. Additionally, we performed an in-depth analysis to validate the effectiveness of the late fusion strategy in music genre classification.

Text-conditioned outfit recommendation aims to recommend a whole fashion outfit that satisfies the compatibility between the recommended items and given items and adheres to the text condition like “Paradise Tropical Vacation” or “60s Style”. Using text description as a condition can provide users with a flexible and accurate way to retrieve and recommend fashion items but this problem is underexplored by existing studies. A challenge of text-conditioned outfit recommendation is how to encode and fuse the outfit text description and fashion item images and text. To solve this, this paper proposes a framework for this task which features a hybrid attention layer that constructs the relationship between outfit text description and fashion items for condition compliance, and the relationship between fashion items for internal compatibility. To encode fashion item features, our method uses pre-trained FashionCLIP as an extractor which significantly reduces the trainable parameters compared to previous methods training CNN from scratch. The whole outfits are generated by iteratively adding compatible items based on a given partial outfit. Compared with state-of-the-art methods on polyvore disjoint and non-disjoint datasets, our approach can achieve 3% relative improvement in compatibility prediction AUC, achieve 5% relative improvement in fill-in-the-blank accuracy; achieve 19% relative improvement on complementary item retrieval recall at different ranks in average. Besides, We demonstrate that our approach can recommend a whole outfit with inner compatibility and adhere to the text description.

In a rapidly advancing world of technology, information security studies have become the backbone of the digital age, and steps in this area are critical. In this context, cryptography, in particular, plays a key role in ensuring the confidentiality, integrity and authentication of data. s-box structures provide a certain diversity and security layer in encryption algorithms, forming one of the key elements in this area. This study focuses on the design and analysis of s-box structures, examining the potential impact of chaos theory-based structures on encryption systems. First, it provides a comprehensive classification of existing s-box design proposals in the literature, and explores the contribution of chaos theory to the security features of these structures. The original contribution of the study is the results obtained with the help of the developed analysis and design program. The program optimizes levels of complexity, randomness, and resistance, and demonstrates the resistance of these new structures to cryptanalysis attacks. The paper also draws attention to open issues in the field of chaos-based s-box design and provides a road map for future research. It is estimated that all these findings will provide a common motivation for researchers in the relevant literature and constitute the basis for many practical practices.

A key feature of 5G systems is the Ultra-Reliable Low-Latency Communication (URLLC), which can be used for remote surgery, smart grids, industrial control, etc. URLLC requires millisecond-level delays and very high reliability, i.e., less than $10^{-5}$ packet loss probability. The ability to satisfy these very strict quality of service requirements depends on selecting the Modulation and Coding Schemes (MCS) for data transmissions. On the one hand, the selected MCS shall be robust enough to avoid multiple retransmissions within a small delay budget. On the other hand, the MCS shall be high-rate to reduce channel resource consumption and, thus, shall increase the system capacity for URLLC. The MCS selection problem is extremely challenging to capture the quickly varying wireless channel effects, e.g., in highly mobile scenarios, because the decision shall be made long before the actual transmission occurs. The paper proposes a novel MCS selection algorithm called ALPACA (Asymmetric Loss Prediction Algorithm for Channel Adaptation), which relies on a widely used class of convolutional-recurrent neural networks. However, in contrast to existing approaches, ALPACA explicitly considers the asymmetric error cost for channel prediction by utilizing quantile regression loss. Both real-life channel measurements and 3GPP channel models are used to evaluate the performance of ALPACA. Numerical results demonstrate the increase in the reliability and reduction in resource consumption compared with the existing MCS selection algorithms, which results in 40% growth of the network capacity.

Learning high-quality representations of users, items, and tags from historical interactive data is crucial for personalized tag recommendation (PTR) systems. Currently, most PTR models are committed to learning representations from first-order interactions without considering the exploitation of high-order interactive relations, which can be beneficial for avoiding sub-optimal learning. Although several PTR models equipped with graph neural networks (GNN) have been proposed to capture higher-order semantic relevance from raw data, they all carry out representation learning in Euclidean space, which can still easily result in sub-optimal learning due to embedding distortion. In order to further improve the quality of representation learning for PTR, the paper proposes a novel PTR model based on a lightweight GNN framework with hyperbolic embedding, namely GHPTR. GHPTR explicitly injects higher-order relevance into entity representation through the message propagation and aggregation mechanism of GNN and leverages hyperbolic embedding to alleviate the embedding distortion problem. Experimental results on real-world datasets have demonstrated the superiority of our model over its Euclidean counterparts and state-of-the-art baselines.

This paper addresses the joint design of a beamformer and user-centric clustering for scalable cell-free massive multiple-input multiple-output (CF-mMIMO) under severe quantization noise generated in backhaul links for central processing units (CPUs) cooperation. The system model comes up with a plan in which multiple CPUs exchange physical layer data under limited bandwidth to enhance performance while introducing clustering across multiple CPUs. We derive the joint optimization of the minimum mean-square error (MMSE) beamformer and user-centric clustering under quantization noise, and propose its low-complexity design. The superiority of our proposed design method is clarified by comparing its performance with cellular distributed MIMO systems. Throughout the paper, we first answer the problem of how much gain CF-mMIMO systems with multiple CPUs cooperation can obtain.

Heterogeneous cross-project defect prediction (HCPDP) aims to predict defects in new software projects using defect data from previous software projects where the source and target projects have some different metrics. Most existing methods only find linear relationships in the software defect datasets. Additionally, these methods use multiple defect datasets from different projects as source datasets. In this paper, we propose a novel method called heterogeneous cross-project defect prediction using encoder networks and transfer learning (ENTL). ENTL uses encoder networks to extract the important features from source and target datasets. Also, to minimize the negative transfer during transfer learning, we used an augmented dataset that contains pseudo-labels and the source dataset. Additionally, we have used a single dataset to train the model. To evaluate the performance of the ENTL approach, 16 datasets from four publicly available software defect projects were used. Furthermore, we compared the proposed method with four HCPDP methods namely EGW, HDP_KS, CTKCCA and EMKCA, and one WPDP method from existing literature. The proposed method on average outperforms the baseline methods in terms of PD, PF, F1-score, G-mean and AUC.

The high-speed vibration rotation of the drill bit during drilling causes the logging tool to be damaged or distorted, resulting in inaccurate or lost data collection. Traditional prediction methods such as dynamic modeling and geological modeling have problems such as incomplete data and difficult modeling, which cannot meet the accuracy and stability requirements of wellbore trajectory prediction. The long short-term memory neural network (LSTM) for predicting time series can achieve accurate prediction, but there are problems such as difficulty in adjusting the hyperparameters of the LSTM model, slow convergence speed, and easy overfitting. This paper absorbs the advantages of the LSTM algorithm, ridge regression (L2 regularization), and sparrow optimization algorithm (SSA) in machine learning and proposes a well trajectory prediction model of steerable drilling based on L2 regularization and SSA optimized LSTM (L2-SSA-LSTM). The model takes the LSTM hyperparameter as the parameter optimization goal of SSA and adds L2 regularization to the model to prevent model overfitting to complete modeling and prediction. The experiment was conducted using measured data sets from directional drilling in two different oilfields. The results show that compared with the back propagation algorithm (BP), consolidated memory gated recurrent unit (CMGRU), dual-thread gated recurrent unit (DTGRU), Attention-based Spatiotemporal Graph Recurrent Neural Network (ASTG-RNN), LSTM, and the L2-SSA-LSTM prediction model has significantly higher accuracy in predicting directional drilling trajectories than other models and has the better predictive ability.

Multi-channel FinFET ( $\text{M}_{\textbf {ch}}$ -FinFET) is an emerging device having promising use due to its excellent driving capability. In this paper, we have investigated the significance of multiple channels of FinFET configuration. We have examined the performance of the multi-channel-based step FinFET ( $\text{M}_{\textbf {ch}}$ - step FinFET) structure with spacer engineering. The results obtained from this simulation work indicate that $\text{M}_{\textbf {ch}}$ -step FinFET is a good competitor for future improvisation of CMOS technology. The proposed device has improved drain conductivity, transconductance ( ${\textbf G_{m}}$ ), intrinsic gain ( ${\textbf A_{v}}$ ), and drain conductance ( ${\textbf G_{d}}$ ) performance by introducing high-K dielectric spacer material by 38.2%, 46.12%, 88.57%, and 22.55%, respectively. The proposed device with a spacer is preferable to obtain better performance regarding ON current and device efficiency.

The fifth-generation (5G) wireless communications have been deployed in many countries with the following features: wireless networks at 20 Gbps as peak data rate, a latency of 1-ms, reliability of 99.999%, maximum mobility of 500 km/h, a bandwidth of 1-GHz, and a capacity of 106 up to Mbps/m2. Nonetheless, the rapid growth of applications, such as extended/virtual reality (XR/VR), online gaming, telemedicine, cloud computing, smart cities, the Internet of Everything (IoE), and others, demand lower latency, higher data rates, ubiquitous coverage, and better reliability. These higher requirements are the main problems that have challenged 5G while concurrently encouraging researchers and practitioners to introduce viable solutions. In this review paper, the sixth-generation (6G) technology could solve the 5G limitations, achieve higher requirements, and support future applications. The integration of multiple access techniques, terahertz (THz), visible light communications (VLC), ultra-massive multiple-input multiple-output ( $\mu {\mathrm{ m}}$ -MIMO), hybrid networks, cell-free massive MIMO, and artificial intelligence (AI)/machine learning (ML) have been proposed for 6G. The main contributions of this paper are a comprehensive review of the 6G vision, KPIs (key performance indicators), and advanced potential technologies proposed with operation principles. Besides, this paper reviewed multiple access and modulation techniques, concentrating on Filter-Bank Multicarrier (FBMC) as a potential technology for 6G. This paper ends by discussing potential applications with challenges and lessons identified from prior studies to pave the path for future research.

Next generation of wireless networks are characterized by two main features named Enhanced Mobile Broadband (eMBB) and Ultra Reliable Low Latency Communications (URLLC). These two services can be accommodated in the same wireless infrastructure so that wide range of users, demanding either massive throughput or extremely low latency and high reliability requirements, are directly benefited for providing various mission critical services. Co-existence of eMBB and URLLC services, however, demand highly efficient and less complex resource allocation schemes. In this paper, various resource allocation techniques are studied for the co-existence of eMBB and URLLC traffic to meet the heterogeneous specifications of each class of users. A detailed study on existing resource allocation schemes for simultaneous transmission of eMBB and URLLC services based on network slicing, flexible Transmit Time Interval (TTI), scheduling and distributed and federated learning are provided. Moreover, Machine Learning (ML) aided and Reconfigurable Intelligent Surface (RIS) and Unmanned Aerial Vehicle (UAV) assisted resource allocation techniques are also studied in detail. Additionally, this paper identifies some challenges for eMBB and URLLC service accommodations in the same wireless architecture, and proposes their possible solution approaches.

Federated learning (FL) is now considered a critical method for breaking down data silos. However, data encryption can significantly increase computing time, limiting its large-scale deployment. While hardware acceleration can be an effective solution, existing research has largely focused on a single hardware type, which hinders the acceleration of FL across the various heterogeneous hardware of the participants. In light of this challenge, this paper proposes a novel FL acceleration framework that supports diverse types of hardware. Firstly, we conduct an analysis of the key elements of FL to clarify our accelerator design goals. Secondly, a unified acceleration framework is proposed, which divides FL into four layers, providing a basis for the compatibility and implementation of heterogeneous hardware acceleration. After that, based on the physical properties of three mainstream acceleration hardware, i.e., GPU, ASIC and FPGA, the architecture design of corresponding heterogeneous accelerators under the framework is detailed. Finally, we validate the effectiveness of the proposed heterogeneous hardware acceleration framework through experiments. For specific algorithms, our implementation achieves a state of the art acceleration effect compared to previous work. For the end-to-end acceleration performance, we gain $12\times $ , $7.7\times $ and $2.2\times $ improvement on GPU, ASIC and FPGA respectively, compared to CPU in large-scale vertical linear regression training tasks.

Brain-computer interface (BCI) systems have been developed to assist individuals with neuromuscular disorders to communicate with their surroundings using their brain signals. One attractive branch of BCI is steady-state visual evoked potential (SSVEP), which has acceptable speed and accuracy and is non-invasive. However, SSVEP-based EEG signals suffer from eye-fatigue problems, resulting in artifacts that affect the accuracy of the system. Thus, researchers are still working to improve SSVEP-based BCI systems. This paper proposes robust machine-learning algorithm for single-flicker SSVEP detection. A novel approach based on fast independent component analysis and filter-bank canonical correlation analysis (fast ICA-FBCCA) is developed to extract features from the single-flicker SSVEP signal. The clean features learned by fast ICA-FBCCA are then applied to a discrete wavelet transform (DWT) technique and fed to a convolutional neural network (CNN) with only one convolutional layer and a smaller number of parameters. The effectiveness of the proposed technique is evaluated using two datasets. The results were evaluated using two datasets. The findings clearly demonstrate that the proposed method outperforms traditional methods, with average target recognition accuracy and standard deviation values of 97 ± 3.1% among 6 subjects for dataset 1 and 82.12 ± 10.7% among 12 subjects for dataset 2. Overall, these findings suggest that the proposed method is a promising approach for improving the accuracy and reliability of the single-flicker SSVEP-based BCI systems.

Advanced Driver Assistance Systems (ADAS) are advanced technologies that assist drivers with vehicle operation and navigation. Recent improvements and brisk expansion in the ADAS market, as well as an increase in the frequency of incidents such as sensor spoofing, communication interruption etc., in autonomous vehicles (AVs), have raised the need to research ADAS security technology. The security issues raised by incorporating these technologies into automobiles must be addressed to protect the privacy and safety of passengers and other road users. As a result, the purpose of this research is to investigate the security issues that arise from the integration of ADAS technologies. Addressing these challenges holds the potential to establish a foundation for enhanced safety and dependability within transportation networks amidst the ongoing advancements in vehicle technology. This paper starts by describing the vulnerabilities, threats, assaults, and defense mechanisms of the ADAS. It then delves into the attacks and countermeasures in three categories, namely VANET, Hardware, and Adversarial attacks. VANET attacks encompass threats targeting Vehicular Ad Hoc Networks, aiming to disrupt communication among vehicles or between vehicles and infrastructure. Hardware attacks focus on vulnerabilities within the physical components of ADAS, including sensors, processors, or communication modules. Adversarial attacks involve deliberate manipulations or perturbations introduced into machine learning models or algorithms utilized within ADAS. These attacks aim to deceive or undermine the functionality of AI-based systems, causing misclassification, compromising system integrity, and posing risks to user safety by exploiting vulnerabilities in the AI decision-making process. Finally, this study highlights potential areas for future research, such as the utilization of artificial intelligence (AI), the necessity of industry-wide standardization, and recommends specific future work tailored to each attack described in the corresponding sections.

Online banking has become increasingly popular in recent years, making it a target for cyberattacks. Banks have implemented various user authentication methods to protect their customers’ online accounts. This paper reviews the state-of-the-art user authentication methods used in online banking and potential cyber threats. This paper starts by exploring different user authentication methods, such as knowledge-based authentication (KBA), biometrics-based authentication (BBA), possession-based authentication (PBA), and other methods. The advantages and disadvantages of each user authentication method are then discussed. Furthermore, the paper discusses the various cyber threats that can compromise user authentication for online banking systems, such as malware attacks, social engineering, phishing attacks, man-in-the-middle (MiTM) attacks, denial of service (DoS) attacks, session hijacking, weak passwords, keyloggers, SQL injection, and replay attacks. Also, the paper explores the user authentication methods used by popular banks, which can provide insights into best practices for safeguarding online banking accounts and future user authentication methods in online banking and cyber threats. It states that the increasing use of BBA, two-factor authentication (2FA), and multi-factor authentication (MFA) will help improve the security of online banking systems. However, the paper also warns that new cyber challenges will emerge, and banks need to be vigilant in protecting their customers’ online banking accounts.

This paper proposes a new authentication approach targeted to wireline broadcast communication systems for automotive and industrial applications. The proposed approach leverages jitter amplification in wireline channels, that become stronger features for message-source authentication with higher data rate or channel loss, to provide a low-overhead physical layer authentication. The fundamentals of jitter amplification are reviewed and the use of it as a feature for authentication while maintaining high signal integrity is explored. Simulations using a Simulink model of an example automotive link with multiple electronic control units (ECUs) are used to show the efficacy of the proposed message source authentication scheme. The simulation results also show significant resilience of the proposed approach to noise. Measurement results using a bench-top setup show that the proposed feature detection approach has a high degree of authentication accuracy in a real-time application and provides a low-cost alternative to prevailing software-based approaches.

Automated screening is employed to assist skin specialists in accurately detecting skin lesions at an early stage. Multilevel thresholding is a widely popular and efficient technique for enhancing the classification of skin cancer images. This paper proposes improved PSO with a novel visit table and multiple directions search strategies to develop the performance of the multilevel thresholding. A visit table strategy has been developed that prevents unnecessary searches of the original particle swarm optimization (PSO) algorithm by allowing the discovery of new points by making fewer visits to frequently visited points and their neighbors. Besides, a multiple directions search strategy has been introduced for the PSO to increase the diversity of the population and overcome the stuck at the local optimum by enhancing exploration ability. The qualitative, quantitative, and scalability analyzes of the improved PSO (IPSO) method were carried out on 50 benchmark functions and the highest performance was achieved with the proposed method in most of these functions. Secondly, a multilevel image segmentation application is presented on skin cancer images using two-dimensional (2D) non-local means histograms, improved PSO and Renyi’s entropy. In this work, the ISIC 2017 skin cancer image dataset is used for segmentation application and various performance evaluation metrics are used. The obtained results are compared with seven state-of-the-art approaches to show the efficiency of the proposed approach. It can be noted from the obtained results that, the proposed method outperforms the compared method based on the average of evaluation metrics for all skin cancer images. The best results in SSIM value of 0.8285, FSIM value of 0.7332, and PSNR value of 19.0576 are achieved by using the proposed method in skin cancer image segmentation. Hence, our proposed method is ready to be tested with huge databases and can aid skin specialists in making an accurate diagnosis.

Sand and dust storms (SDS) are significant atmospheric phenomena that have a negative impact on wireless links operating at various frequencies. Specifically, sand and dust (SD) particles produce attenuation in propagating electromagnetic (EM) waves upon impact, which must be measured for the proper functioning of the fade mitigation strategy. The attenuation due to SDS can be reliably evaluated using specialized equipment. However, field experiments have been conducted in only a few locations and for a limited number of link geometries; therefore, the results are not immediately generalizable to all locations. Consequently, various attenuation models based on accessible meteorological data have been developed to provide sufficient inputs for system margin calculations under all environmental conditions. In this paper, we present a comprehensive review of an extensive set of Earth SDS attenuation models that differ based on various particle characteristics in terrestrial and space communication. Furthermore, we discuss how variables such as humidity and surface charges carried by the particles are addressed in the literature. We also provide the results of various field studies conducted in many parts of the world under diverse conditions to directly measure the influence of SDS on wireless communication systems. Dust is also a significant meteorological factor in the Martian atmosphere, where it affects the efficiency of the wireless sensor networks used by NASA’s Mars Exploration Project. We explore how attenuation has been extrapolated in the Martian atmosphere. Additionally, we discuss future research challenges in SDS.

Enterprises typically install firewalls at communication points to their internal networks with the primary objective of protecting their core assets from external cyber attackers. This ensures unauthorized access is controlled and prevented. However, overly permissive policies and services with vulnerabilities can be exploited by attackers, providing them with pathways into internal systems. Therefore, firewall policies must be meticulously applied and managed. Given the significant ramifications of firewall policies, they must be continuously managed with high importance. As the number of policies increases and the amount of information to be processed grows, the process becomes complex, and there are limitations to managing policies from a human cognitive perspective. An increase in unmanaged misuse policies can inadvertently introduce security risks through unintended allowance policies. In the case of large-scale network networks operating multiple firewalls, a different form of misuse policy check and management is required compared to managing a single firewall policy. The proposed tool, HSViz-II, not only visualizes misuse of a single firewall policy but also visualizes four misuse cases in a distributed firewall environment, providing a detailed breakdown based on Octets. It displays the distribution of anomalous policies by dividing the Source IP into Octet Layers. For the four anomalous policy cases, it offers five views based on dividing the Source IP into Octet Layers and three overall views for upstream firewall, downstream firewall, and both, totaling 60 views. The processing speed for each function was measured using four sets of actual upstream and downstream firewall policies, comprising eight different firewall policies in total. Firewall operators can use this tool to grasp the distribution status of misuse policies in single and multiple firewalls and check the status of misuse policies by Octet. By offering a method for firewall operators to accurately find meaningful information, this paper proposes a firewall misuse policy visualization system in a distributed firewall environment to help reduce the risk of asset exposure to cyber threats for enterprises. HSViz-II tool can be found on the web site: https://youtu.be/jvR8ZY2uapQ

In this paper, D(HE)at, a practical denial-of-service (DoS) attack targeting the finite field Diffie-Hellman (DH) key exchange protocol, is presented, allowing remote users to send non-public keys to the victim, triggering expensive server-side DH modular-exponentiation calculations. The attack was disclosed in November 2021 with an assigned CVE-2002-20001 number. Additionally, the “long exponent” issue, an implementation flaw in cryptographic libraries where unreasonably large private keys are used, deviating from the recommended NIST guidelines, and making D(HE)at more effective, is presented. This issue was disclosed in November 2022 with an assigned CVE-2022-40735 number. A thorough analysis of the D(HE)at attack, along with proof of concept code that has the potential to compromise all existing protocols employing DH key exchange, such as TLS or SSH, is presented in this paper, highlighting the necessity of additional security measures for effective safeguarding. The potential of reaching full 100% CPU utilization by the D(HE)at attack is demonstrated, even on the most up-to-date operating systems, without any significant computation on the client side. With minimal bandwidth and a low request rate per second (rps), the D(HE)at attack can be carried out against target machines from a single laptop. In this study, the consequences of these issues are explored, and a comparative security and performance analysis is conducted among the most commonly used general-purpose cryptographic libraries, including OpenSSL, BoringSSL, LibreSSL, GnuTLS, NSS, Mbed TLS, OpenJDK, Oracle JDK, and WolfSSL. Based on Shodan measurements, it has been found that 87% of servers worldwide support DH key exchange in the SSH protocol, and according to our scan, 55% of the top 1 million websites support DH in TLS. As a result of this study, it is recommended that developers and administrators consider exclusively enabling Elliptic Curve Diffie-Hellman (ECDH), a significantly more efficient protocol, in their server configurations.

This paper presents a novel 8T SRAM bitcell-based transposable (TP) memory supporting both row-wise and column-wise data access. The proposed TP-SRAM enables orthogonal data access with additional diagonal word-lines and a low-complexity addressing scheme. To reduce cell array area overhead, the proposed TP-SRAM adopts a bitcell structure that can share all aspects of layout with adjacent cells like standard 6T-SRAM. We also propose a bidirectional barrel shifter based on dynamic logic gates to minimize the hardware cost required for the TP addressing scheme. In the proposed bidirectional barrel shifter, area and delay are minimized by using two complementary dynamic inverting MUXs that can balance the number of NMOS and PMOS transistors. The proposed 16Kb TP-SRAM implemented in 28nm CMOS technology has 17% reduced power, 52% faster operation delay, and 39% smaller area compared to the state-of-the-art.

State of Charge (SOC) estimation is vital for battery management systems (BMS), impacting battery efficiency and lifespan. Accurate SOC estimation is challenging due to battery complexity and limited data for training Machine Learning based models. Transfer learning (TL) leverages pre-trained models, reducing training time and improving generalization in SOC estimation. In this paper, 8 different transfer learning techniques are examined, which were applied in four different models (LSTM, GRU, BiLSTM, and BiGRU) for SOC estimation. These transfer learning techniques have been applied to three datasets for re-training the models and results have been compared with the same models defined by Bayesian Hyperparameter Optimization. The TL4 and TL5 techniques consistently stood out as among the most efficient in both accuracy and computational time.

This paper is an attempt to extend the theory of positive systems to sampled-data systems. Even though where to take the initial time is unimportant in positivity of linear time-invariant systems, this is not the case for sampled-data systems because of their periodically time-varying nature from the perspective of the continuous-time input and output signals. Hence, we first study positivity of sampled-data systems by considering the case where a sampling instant is viewed as the initial time. We then further consider the case where an arbitrary intersample instant is viewed as the initial time, and we finally give the necessary and sufficient conditions for ultimate notions of (i.e., initial-time-independent) internal/external positivity of sampled-data systems. The arguments of this paper are then illustrated through numerical examples.

This paper reports on the use of co-simulation techniques to build prototypes of co-operative autonomous robotic cyber-physical systems. Designing such systems involves a mission-specific planner algorithm, a control algorithm to drive an agent performing its task; and the plant model to simulate the agent dynamics. An application aimed at positioning a swarm of unmanned aerial vehicles (drones) in a bounded area, exploiting a Voronoi tessellation algorithm developed in this work, is taken as a case study. The paper shows how co-simulation allows testing the complex system at the design phase using models created with different languages and tools. The paper then reports on how the adopted co-simulation platform enables control parameters calibration, by exploiting design space exploration technology. The INTO-CPS co-simulation platform, compliant with the Functional Mock-up Interface standard to exchange dynamic simulation models using various languages, was used in this work. The different software modules were written in Modelica, C, and Python. In particular, the latter was used to implement an original variant of the Voronoi algorithm to tesselate a convex polygonal region, by means of dummy points added at appropriate positions outside the bounding polygon. A key contribution of this case study is that it demonstrates how an accurate simulation of a cooperative drone swarm requires modeling the physical plant together with the high-level coordination algorithm. The coupling of co-simulation and design space exploration has been demonstrated to support control parameter calibration to optimize energy consumption and convergence time to the target positions of the drone swarm. From a practical point of view, this makes it possible to test the ability of the swarm to self-deploy in space in order to achieve optimal detection coverage and allow unmanned aerial vehicles in a swarm to coordinate with each other.

This paper reports on ongoing research, which aims to prove that features of Obstructed Sleep Apnoea (OSA) can be automatically identified from single-lead electrocardiogram (ECG) signals using a One-Dimensional Convolutional Neural Network (1DCNN) model. The 1DCNN is also compared against other machine learning (ML) classifier models, namely Support Vector Machine (SVM) and Random Forest Classifier (RFC). The 1DCNN architecture consists of 4 major parts, a Convolutional Layer, a Flattened Dense Layer, a Max Pooling Layer and a Fully Connected Multilayer Perceptron (MLP), with 1 Hidden Layer and a SoftMax output. The model repeatedly learns how to better extract prominent features from one-dimensional data and map it to the MLP for increased prediction. Training and validation are achieved using pre-processed time-series ECG signals captured from 35 ECG recordings. Using our unique windowing strategy, the data is shaped into 5 datasets of different window sizes. A total of 15 models (5 for each group, 1DCNNs, RFCs, SVMs) were evaluated using various metrics, with each being run over numerous experiments. Results show the 1DCNN-500 model delivered the greatest degree of accuracy and rapidity in comparison to the best producing RFC and SVM classifiers. 1DCNN-500 (Sensitivity 0.9743, Specificity 0.9708, Accuracy 0.9699); RFC-500 (Sensitivity/Recall (0) 0.90 / (1) 0.94, Precision (0) 0.94 / (1) 0.90, Accuracy 0.91); SVM-500 (Sensitivity (0) 0.94 / (1) 0.50, Precision (0) 0.65 / (1) 0.90, Accuracy 0.72). The model presents a novel approach that could provide support mechanisms in clinical practice to promptly diagnose patients suffering from OSA.

Traffic congestion has become an increasingly severe problem and needs to be solved urgently. Reinforcement learning (RL) is an advanced data-driven approach for large-scale adaptive traffic signal control (ATSC) in the complex urban traffic network. The decentralized multi-agent RL (MARL) framework is feasible for multi-intersection scenarios. However, the environment becomes partially observable and nonstationary without effective communication among agents from the perspective of each local agent. Previous studies solve this problem by improving the observation of each local agent and using a spatial discount factor. In this paper, we are motivated by achieving coordination among intersections in the RL settings and better performance in ATSC and solve the problem of traffic signal control at multiple intersections in large-scale networks based on RL techniques. Pressure is used as an indicator to represent the traffic conditions of an intersection considering its neighbor intersections. A new reward function with pressure and vehicle waiting time is designed to achieve coordination among intersections. The above three control policies are innovatively applied to a multi-agent Q-learning method for ATSC at multiple intersections. Experiments are carried out on a large synthetic traffic grid under simulated peak-hour traffic dynamics. Results demonstrate that our approach outperforms the state-of-the-art decentralized MARL algorithms in average queue length and intersection delay.

This paper presents the modeling, control and evaluation in a real-time simulation (RTS) of a three-phase multilevel inverter based on the modular multilevel converter (MMC) topology. The developed model for MMC includes four decoupled state variables per phase, which are instrumental for the control design, namely injected (output) current, circulating current, total energy, and energy balance between arms. Based on this model, a control scheme is proposed with the aim to regulate and balance the total energy on each converter’s phase, regulate the circulating currents, and inject a three-phase current synchronized with the grid voltage. As part of the control process, the proposed controller generates the reference for a modulation scheme to obtain the switching sequence for each converter’s cell, which, in this case, is the phase-shifted carrier-based pulse-width modulation (PSC-PWM). As it was already reported in the literature, this particular modulation guarantees self (natural) balance of all capacitor voltages, i.e., they converge to the same steady-state average value without the need of any external balancing controller.

Health monitoring systems in the home environment are safety-critical. It is necessary to evaluate the safety of health monitoring systems. Conventionally, system safety is guaranteed through conformance to related safety standards or requirements. This conformance is qualitatively demonstrated by the safety case. However, the result of the qualitative evaluation is not straightforward to review. Moreover, two problems must be considered from the viewpoint of systematic evaluation. First, if the result of the evaluation of a system is unsafe, the traceability of the result to the system safety requirements must be considered to improve system safety. Second, re-evaluation may occur in case of changes to system safety requirements or related system design. Thus, this paper proposes a framework for quantitative evaluating system safety for health monitoring systems. The framework focuses on three models, i.e., system safety requirements structure, safety case, and Bayesian network, with five steps to solve the above concerns. Finally, the framework is applied to an example health monitoring system for demonstration.

Communication of bioelectric signals, such as electroencephalography (EEG) signals, will be a key technology for smooth interaction between users and remote robots. The existing solutions use an orthogonal transform for EEG signal compression, such as Discrete Wavelet Transform (DWT) or Discrete Cosine Transform (DCT). This paper proposes a graph-based compression scheme for EEG signals to improve the quality at the given rate. The proposed scheme constructs a graph from the positions of the EEG sensors and adopts parameterized graph shift operators to obtain the graph basis functions for decorrelating the EEG signals. Graph Fourier Transform (GFT) based on the graph basis functions with the combination of quantization and entropy coding can send high quality EEG signals with fewer bits. Evaluations using the EEG signal dataset show that the proposed GFT-based compression can send better quality EEG signals than the existing DCT-based and DWT-based schemes at the same bit rates. In addition, an optimal parameter of the graph shift operator under the given rate is discussed to maximize the reconstruction quality of the graph-based scheme.

The joint optimization of spectral efficiency (SE) and energy efficiency (EE) through power allocation (PA) techniques is a critical requirement for emerging fifth-generation and beyond networks. The trade-off between SE and EE becomes challenging in the massive multiple-input-multiple-output (MIMO) equipped base stations (BSs) in multi-cell cellular networks. Various algorithmic approaches including genetic algorithms and convex optimization have been considered to optimize the trade-offs between SE and EE in cellular networks. However, these methods suffer from high computational costs. A promising deep reinforcement learning technique is capable of addressing the computational challenges of single-objective optimization problems in wireless networks. Furthermore, multi-objective reinforcement learning has been employed for multi-objective optimization problems and can be utilized to jointly enhance the SE and EE in cellular networks. In this paper, we propose a downlink (DL) transmit PA method based on a multi-objective asynchronous advantage single actor-multiple critics (MO-A3Cs) architecture. The proposed architecture aims to optimize SE and EE trade-offs in massive MIMO-assisted multi-cell networks. Furthermore, we also propose a Bayesian rule-based preference weight updating mechanism, multi-objective advantage function, and balanced-reward aggregation method to effectively train and avoid biased objective reward during the training process of the proposed model. Extensive simulations depict that the proposed model is better capable of dealing with the joint optimization of SE and EE in dynamic changing scenarios. Compared to the existing benchmarks such as Pareto front approximation-based multi-objective, reinforcement learning-based single objective, and iterative methods, the proposed approach provides a better SE-EE trade-off by achieving a higher EE in multi-cell massive MIMO networks.

In this paper, we investigate distributed online optimization over multi-agent networks, where a group of agents aim to cooperatively seek the minimum value of a time-varying global loss function that can be expressed as the sum of the local loss functions privately owned by a single agent on the network at each iteration. In addition, all agents do not know the future loss function, and information about the loss function is disclosed only after the agent has made a decision. We are interested in scenarios where the communication topology of a multi-agent network is a sequence of time-varying unbalanced graphs and the loss function of each agent is a class of non-strongly convex functions. We generalize the distributed online Newton step algorithm to a more general multi-agent network by introducing a consensual-based auxiliary estimation to rescale the contribution of each agent in optimization. Our algorithm only uses row stochastic matrices and does not require the agent to know the out-degree of its in-neighbors. The convergence of regret bound over time-varying unbalanced networks is rigorously proved. Simulation results also verify the effectiveness of the proposed algorithm, and show its advantage in convergence speed compared with the first-order algorithms.

This paper proposes a reliable data dissemination framework for edge networks, leveraging network coding combined with low-rank approximation. We consider an edge network that consists of a server and power-limited mobile devices, where the data is broadcasted by the server. In such networks, broadcasted data may be lost due to poor channel conditions or the interference caused by the mobility of edge mobile devices, particularly without a retransmission mechanism. This can cause application errors in edge devices, lower the Quality of Service (QoS), and compromise network stability. To overcome these challenges, we propose a framework for reliable edge networks in broadcasting without retransmissions. The edge network reliability can be achieved by the approximate decoding of broadcasted data. In the proposed framework, the edge server employs matrix factorization to encode data with principal components, ensuring a lower decoding error rate even with potential packet losses. Furthermore, the proposed framework can shift the computational complexity from mobile edge devices to the edge server using the low-rank approximation at the decoding stage, effectively mitigating power limitations on mobile devices. Through theoretical analysis, we demonstrate that the proposed algorithm outperforms typical broadcasting in terms of decoding accuracy, and present an upper bound error rate for the proposed algorithm. The simulation results confirm that the proposed algorithm outperforms other state-of-the-art algorithms in terms of decoding accuracy, time delay, and complexity.

This paper concerns with the finite-time filter design problem for discrete-time nonlinear networked system subject to quantization effect and denial-of-service (DoS) attacks via dynamic event-triggered scheme (DETS). The nonlinear networked system is presented by Takagi-Sugeno (T-S) fuzzy model. The dynamic event-triggered generator and logarithmic quantizer are employed to save the limited network bandwidth. A stochastic Bernoulli distribution variable is used to characterize the effect of the randomly occurring DoS attacks in communication channel. By a generalized performance index, the finite-time $H_{\infty} $ filtering and $l_{2}-l_{\infty} $ filtering problem are accessed under a unified framework. The filtering error model is well established by taking event-triggered scheme, logarithmic quantization, and DoS attacks into account. The sufficient conditions for the existence of an acceptable filter are derived such that the filtering error system is finite-time stochastic bounded with the prescribed $H_{\infty} $ or $l_{2}-l_{\infty} $ performance. The filter gains and the event-triggered communication parameter are co-designed by solving these inequality sufficient conditions. Finally, a simulation study is performed to demonstrate the effectiveness of the proposed approach.

Table structure recognition (TSR) is crucial for document analysis, particularly for medical examination report tables (MERTs), impacting efficiency and decision-making in healthcare. Most models for TSR utilize either Graph Convolution Neural Networks (GCNs) or Transformers with html sequences for structure recognition. These methods, however, face challenges with graph inductive bias and instability in training, respectively. We observe that cells within the same row or column of a table not only are closely aligned in their vertical and horizontal coordinates, respectively, but also exhibit highly similar features. In previous work, the spatial feature of coordinates was often only used for concatenation with image features, text features, etc. We believe that explicitly utilizing the unique spatial properties of tables can better encode table features. In this paper, we introduce a novel structure named Dual-Awareness Feature Aggregator (DAFA) for table, which leverages attention mechanisms to effectively extract table features. Based on it, we design an end-to-end model called DAFA-Net requiring only images as input, without the need for additional information such as texts. In addition, we try to address the prevalent challenge of recognizing cross-row and cross-column cells in TSR — a scenario frequently encountered in medical examination reports — by introducing a modified focal loss known as CRCC loss. We conduct extensive experiments on four popular datasets. This includes a dataset specifically dedicated to medical data and others that mirror the complexity typically encountered in medical tables. Experimental results show the effectiveness and potential of our DAFA-Net for TSR within the healthcare sector.

Software engineering (SE) and computer science (CS) programs in universities worldwide are marked by a gender gap, which subsequently translates into a gender gap at the industry level. However, there are positive activities that can help attract more women to these male-dominant professions. This study maps the literature related to the achievement of gender balance in SE and CS university-level education and identifies future research directions. More specifically, this article reports on a systematic mapping study of female-inclusive SE and CS tertiary education programs. The authors collected 882 publications between 2015 and 2022 from five databases (ACM, IEEE, Scopus, Web of Science, and Science Direct), selecting 143 peer-reviewed papers for further analysis. The results showed that the main academic contributors were researchers from the USA. The majority of the publications contained observations and explanations regarding the gender gap in computing education. However, an important part of the literature considered proposals and practical activities for achieving gender balance in SE and CS programs. Finally, the authors classified the literature related to female-inclusive SE and CS tertiary education programs, identified the main research focuses and regional distribution, and considered ideas for future research.

To assist gas distribution companies to effectively monitor their infrastructure and locate gas leaks, this paper considers the use of an Unmanned Aerial Vehicle (UAV) carrying a methane sensor to survey a region for gas leaks. As the UAV collects in situ measurements, it gathers evidence regarding the presence or absence of leaks in the region. To relate the UAV measurement to a region on the ground, we propose to use Upwind Survey Regions (USRs). If the UAV collects a measurement of high gas concentration, the USR represents a region that is likely to contain the leak. Likewise, if the UAV collects a measurement of low gas concentration, the USR represents a region that is likely to be clear of gas leaks. We propose a framework to process the measurements and produce a survey map indicating areas that can be reliably cleared of gas leaks and areas that may contain gas leaks. Our framework is composed of two steps: 1) mapping UAV measurements into USRs on the ground; and 2) fusing the various mapped USRs to produce the survey map. We discuss how USRs can be estimated and we test our framework using both simulated and real UAV flights.

In modern transportation, autonomous driving technology has emerged as a significant innovation, offering improved safety, efficiency, and convenience. One of its core technologies is path planning, which creates an optimal route for vehicles in various traffic situations, ensuring they arrive safely and efficiently. However, existing path planning methods suffer from inflexible and inefficient road sampling, and limitations in path expression due to curve models. In this paper, we introduce a novel path planning framework that operates from a coarse-to-optimal approach. We first introduce an adaptive sampling method to construct a three-dimensional (3D) space-aware profiling map in the Frenet frame to quantify abstract traffic scenarios. This cost map guides the generation of waypoints by incorporating obstacle distributions in the $s$ -direction and cost values in the $l$ -direction. We then design a cost function to obtain the coarse path by considering ride comfort, anti-deviation from the center of the road, and path safety. Finally, a new path model is re-established based on the Taylor series, and a quadratic programming approach is employed to fine-tune the coarse path to attain the optimal path. Experimental results show that the proposed adaptive sampling method can dynamically adjust the sampling strategy according to the change in the number and distribution of obstacles on the road, significantly improving the sampling effectiveness rate to 100%, 99.85%, 99.68% and 99.61% for one-obstacle, two-obstacle, three-obstacle, and four-obstacle scenarios. Compared with the conventional method, the generated path length is shortened by 3.48% and 8.42%, and the maximum heading angle is reduced by 18.68% and 30.21% in the scenarios with obstacles of the same and different sizes.

The similarity between arc fault current waveforms and nonlinear load currents can lead to misjudgments in arc fault identification methods that rely on arc current. In response to this issue, this paper establishes a unified fault criterion based on the conclusion that different types of loads that exhibit similar magnitudes of load side voltage sag during arc faults. Combined the voltage sag criterion with waveform criteria, this paper proposes a novel arc fault detection method. The method takes the load side voltage sag value exceeding the threshold as the detection start condition. After detection starts, the method identifies faults by calculating the degree of load side voltage waveform distortion using Hausdorff distance algorithm. Simulations are conducted on five different loads to determine the startup threshold and detection threshold. Test results show that the fault identification accuracy of the proposed method is 100% under the above thresholds.

This paper proposes a high-Q multiband waveguide filter implementation using spherical resonators and an in-band transmission zeros approach. Three prototype filters in Ku-band, one 3 $^{\mathrm{ rd}}$ order triple-band filter with a fundamental TM101 mode and two 5 $^{\mathrm{ th}}$ order dual-band filters with TM101 and TE101 modes, are designed to validate the model. Compared to the previous multiband waveguide filter model using cylindrical resonators, the presented model can realise all expected $N$ transmission zeros between the bands, where $N$ is the filter order, and has a 112% higher simulated Qu value. Meanwhile, the designed very narrowband dual-band filter using spherical resonators with TE101 mode has about 287% higher simulated Qu value than the same filter would have if using rectangular resonator with TE101 mode. For experimental validation, the 3 $^{\mathrm{ rd}}$ order triple-band filter was fabricated using Selective Laser Melting since using traditional milling techniques is not feasible for spherical resonator filters. Monolithic near-net shape fabrication eliminated assembly, improved reliability, and reduced weight. The measured results had a relatively good agreement with the simulations. The measured insertion loss was about 0.54-0.72 dB at the centre frequency of each band, which is a noticeable improvement over the 1.1 dB insertion loss of the previous cylindrical resonator triple-band filter prototype. As there were some deviations between simulated and measured results, the proposed design was inspected in detail, and several improvements for optimising the design for Additive Manufacturing were suggested.

In recent times, mostly in the Middle East region, Red Palm Weevils (RPW) are one of the most dangerous pests of palm trees worldwide. The RPW causes significant harm to several palm species. The existing detection method includes the symptoms detection of RPW through sound or visual assessment and chemical recognition of volatile signatures created by diseased palm trees. However, an effective recognition of RPW disease at earlier stages is assumed that a very complex problem for cultivating date palms. This is another reason why the use of state-of-the-art technologies is supported in the avoidance of the spread of the RPW on palm trees. Several researchers are working on determining the correct process for the localization, classification, and detection of RPW pests. Therefore, this paper presents an intelligent Red Palm Weevil Detection using the Bird Swarm Algorithm with Deep Learning (IRPWD-BSADL) model. The major aim of the IRPWD-BSADL technique focuses on the identification and classification of RPW using CV and DL models. Primarily, the bilateral filtering (BF) approach can be utilized to remove the noise that exists in the images. In the presented IRPWD-BSADL technique, an improved ShuffleNet model can be applied for feature extraction purposes. To enhance the recognition results, the IRPWD-BSADL technique makes use of BSA for the hyperparameter tuning process. For RPW detection and classification, an extreme gradient boosting (XGBoost) classifier can be used. The simulation analysis of the IRPWD-BSADL method can be tested on the RPW dataset. An extensive comparison study stated the improved performance of the IRPWD-BSADL algorithm on the RPW detection method.

Bounded suboptimal heuristic search is a family of search algorithms capable of solving hard combinatorial problems, returning suboptimal solutions within a given bound. Recent machine learning approaches have been shown to learn accurate heuristic functions. Learned heuristics, however, are slow to compute; concretely, given a single search state $s$ and a learned heuristic $h$ , evaluating $h(s)$ is typically very slow relative to expansion time, since state-of-the-art learned heuristics are implemented as neural networks. However, by using a Graphics Processing Unit (GPU), it is possible to compute heuristics using batched computation. Existing approaches to batched heuristic computation are specific to satisficing search and have not studied the problem in the context of bounded-suboptimal search. In this paper, we present K-Focal Search, a bounded suboptimal search algorithm that in each iteration expands $K$ states from the FOCAL list and computes the learned heuristic values of the successors using a GPU. We experiment over the 24-puzzle and Rubik’s Cube using DeepCubeA, a very effective and inadmissible learned heuristic. Our results show that K-Focal Search benefits both from batched computation and from the diversity in the search introduced by its expansion strategy. Over standard Focal Search, K-Focal Search improves runtime by a factor of 6, expansions by up to three orders of magnitude, and finds better quality solutions, keeping the theoretical guarantees of Focal Search.

The alarm system is an overarching component in effectively managing abnormal situations. To enhance its efficacy, we have previously developed an alarm graph modelling (AGM) that overcomes the challenges of traditional methods in alarm workshops. This paper develops an integrated platform that is used for the justification and verification of AGM and other theoretical purposes in the future. Despite the limited availability of process simulations, we successfully updated the Tennessee Eastman Process Simulink model to work seamlessly with the alarm system. The outcomes of the alarm workshop were then implemented, and the alarms were adjusted accordingly. By analyzing predefined scenarios, we were able to evaluate the AGM’s ability to accurately represent abnormal event progression, thereby validating and fine-tuning the alarm system.

The traditional half bridge sub-module (HBSM) cannot clear the DC side fault by itself. On the other hand, the clamp double sub-module (CDSM) has the ability to self-clear the fault current, but it can only output the negative level of the single capacitive voltage during reverse locking, which will affect the speed of fault removal. To address this issue, a three-level bidirectional switch sub-module (TLBSSM) based on the bidirectional switch and CDSM is proposed in this paper. The sub-module can output 3 levels when working normally and twice the negative level of the capacitive voltage when reverse locking, which greatly accelerates the fault current removal. In addition, compared with other common sub-module, TLBSSM has certain economic advantages and stronger DC fault clearing capability. Simulation results based on MATLAB/Simulink show that TLBSSM can quickly remove DC faults, and the sub-module capacitance voltage is stably near the rated voltage after the fault, which is conducive to the rapid restart of MMC. Finally, the effectiveness of TLBSSM and its DC fault clearing capability are validated by the experiment results.

Facing the quantum attack threat, a quantum-resistant version of the SSH Transport Layer protocol has been proposed and been standardized by an IETF working group. This standardization process has been motivated by the fact that if practical quantum computers become available, classical key exchange algorithms used today will no longer be safe because their security can be efficiently broken by Shor’s algorithm running on a quantum computer. In this paper, we construct a symbolic model of the proposed protocol, specify it in the specification language CafeOBJ, and conduct a formal analysis of the claimed security properties with the employment of a formal method tool called Invariant Proof Score Generator (IPSG). Three security properties are formally verified with respect to an unbounded number of protocol participants and protocol executions by employing IPSG to produce their formal proofs, the so- called proof scores in CafeOBJ. With another property, namely authentication, we find a counterexample against it, and then we propose to slightly revise the protocol. With the improved version, we formally verify that the authentication property is enjoyed, while the three properties remain secure. To model the presence of malicious participants, we extend the Dolev-Yao intruder, which is the standard intruder model used in security protocol analysis/verification, because the availability assumption of large-scale quantum computers gives the attacker some new capabilities. Under our threat model, the intruder is given capabilities of fully controlling the network as the Dolev-Yao intruder, and additionally breaking ECDH’s security as well as compromising secrets.