Search

A multiphase induction machine model using vector space decomposition provides insights into many space harmonics through decoupled reference frames. In order to utilize this potential of the multiphase machine, the parameters of each vector space must be identified. These parameters are usually identified using standard no-load and locked rotor tests of each torque-producing vector space. However, these tests do not provide a method for identifying stator leakage inductances, which have comparable magnitudes to the magnetizing inductances for higher-order vector spaces. Thus, the magnetizing current cannot be neglected during the locked-rotor test. This paper proposes an accurate method for identifying the T-model parameters of a multiphase induction machine, which can be conveniently translated into the model of choice. The proposed method use harmonic relations to segregate the stator leakage inductance from the total stator inductance, enabling accurate locked-rotor and partial-load tests for the measurement of rotor side parameters. Lastly, a 9-phase induction machine is used for the evaluation of the proposed parameter measurement method. These measured parameters are used for the field-oriented control of each torque-producing vector space, whose performances are analyzed by quantifying the measured output torque error and linearity.

Network slicing presents new opportunities for cost-effective implementations of next-generation communication networks that target diverse service requirements. Deploying vertical use cases on shared resources is the main motivation for network slicing. Recently, network function (NF) sharing has been proposed in the literature in order to further exploit unused resources and lower the costs for network operators. However, such optimizations through NF sharing expose new security threats and need appropriate defense mechanisms. In this paper, we describe new attack vectors that arise due to NF sharing and list some of the possible defense strategies and security precautions. Furthermore, we propose an NF sharing-aware and network slice-oriented distributed denial of service (DDoS) filtering mechanism, SliceScore, that successfully mitigates the threat of resource exhaustion. We prove by simulations that SliceScore outperforms previous filtering mechanisms, which did not focus on differences among network slices. In this regard, we encourage researchers to investigate slice-oriented approaches to improve defense mechanisms in next-generation communication networks.

Obstructive sleep apnea syndrome (OSAS) is a life-threatening disease characterized by upper airway narrowing or obstruction. The diagnostic process is difficult, costly, and time-consuming. Many individuals with OSAS do not apply for a diagnosis or are unaware of their disease. This study aimed to develop a practical, fast, and reliable diagnostic system for early diagnosis and treatment of OSAS. For the first time, features were extracted from flow-volume curves obtained using a Pulmonary Function Test (PFT), and an Artificial Intelligence (AI)-based algorithm was developed to diagnose OSAS. Spearman correlation coefficients determined the degree of influence of the features in determining OSAS. Several models were created using different features and AI methods according to their effect levels. The models obtained by hyperparameter optimization and cross-validation were tested with unseen data, and their performance was evaluated using seven different criteria. Using only five features extracted from the flow-volume curve (TLC/PIF, PIF/PEF, TLC/FIF50, TLC/FIF25, and FIF25/FEF25), OSAS was diagnosed with 97.1% accuracy using the Neural Network (NN) algorithm. The results showed that OSAS can be diagnosed quickly and reliably using PFT available at every hospital. The features extracted from the flow-volume curve could be used as biomarkers for diagnosing OSAS. The proposed method can be adapted to PC-based spirometry devices without additional hardware developments. This is a significant innovation in both literature and practice. This method will enable early diagnosis for patients and many people unaware of their disease. This will shed light on several future studies.

Sudden Infant Death Syndrome (SIDS) presents a significant challenge, necessitating ongoing research and preventive measures. The intricate landscape of lipid metabolism plays a crucial role in SIDS, with disruptions in key lipid components like Short Chain Fatty Acids (SCFA), alongside other lipids such as triglycerides (TG) and phospholipids (PL), being significant. In this context, SCFA are essential products of the fermentation process by gut microbiota, hold particular interest. SCFA are integral to energy regulation and metabolism, influencing overall well-being. Their unique characteristics, such as chain length and saturation level, provide insights into their potential effects. Alterations in SCFA metabolism can disrupt energy balance, adding to the complexity of SIDS. Leveraging machine learning (ML) presents a promising avenue for unraveling the intricate profiles of SCFA and decoding patterns indicative of heightened SIDS risk. Ensuring interpretability in healthcare is essential for building trust and developing effective prevention strategies. This research delves into understanding SIDS, with a specific focus on SCFA and their role in metabolic health. The application of ML, particularly the Artificial Neural Network (ANN) and Stacking model, demonstrated exceptional accuracy of 94% and 96.15% with a recall of 100% and 92.31%, respectively. The models also demonstrated strong classification capabilities, as indicated by a high True Positive Rate (TPR) in the AUC, a low Root Mean Square Error (RMSE) of 0.20, Mean Absolute Error (MAE) of 0.04 and Standard deviation (SD) of 0.10, emphasizing the robustness and precision of the approach. These results underscore the potential of ML in the early assessment of SIDS risk, highlighting the critical role of SCFA and advancing the prospects for preventative healthcare.

The rapid advancement of fifth-generation (5G)-and-beyond networks coupled with unmanned aerial vehicles (UAVs) has opened up exciting possibilities for diverse applications and cutting-edge technologies, revolutionizing the way connections, communications, and innovations unfold in the digital age. This paper presents a comprehensive survey of the deployment scenarios, applications, emerging technologies, regulatory aspects, research trends, and challenges associated with the use of UAVs in 5G-and-beyond networks. It begins with a succinct background and motivation, followed by a systematic UAV classification and a review of relevant works. The survey covers UAV deployment scenarios, including single and multiple UAV configurations. The categorization of UAV applications in 5G is presented, along with investigations into emerging technologies for enhancing UAV communications. Regulatory considerations encompassing flight guidelines, spectrum allocation, privacy, and safety are discussed. Moreover, light is shed on the latest research trends and open challenges in the field, with promising directions for future investigations identified, concluding with a summary of key findings and contributions. This survey serves as a valuable resource for researchers, practitioners, and policymakers in the UAV and communication domains. Additionally, it offers a comprehensive foundation for informed decision-making, fostering collaboration, and driving advancements in UAV and communication technologies to address the evolving needs of our interconnected world.

The concept of Prosumer has enabled consumers to actively participate in Peer-to-Peer (P2P) energy trading, particularly as Renewable Energy Source (RES)s and Electric Vehicle (EV)s have become more accessible and cost-effective. In addition to the P2P energy trading, prosumers benefit from the relatively high energy capacity of EVs through the integration of Vehicle-to-X (V2X) technologies, such as Vehicle-to-Home (V2H), Vehicle-to-Load (V2L), and Vehicle-to-Grid (V2G). Optimization of an Energy Management System (EMS) is required to allocate the required energy efficiently within the cluster, due to the complex pricing and energy exchange mechanism of P2P energy trading and multiple EVs with V2X technologies. In this paper, Deep Reinforcement Learning (DRL) based EMS optimization method is proposed to optimize the pricing and energy exchanging mechanisms of the P2P energy trading without affecting the comfort of prosumers. The proposed EMS is applied to a small-scale cluster-based environment, including multiple (6) prosumers, P2P energy trading with novel hybrid pricing and energy exchanging mechanisms, and V2X technologies (V2H, V2L, and V2G) to reduce the overall energy costs and increase the Self-Sufficiency Ratio (SSR)s. Multi Double Deep Q-Network (DDQN) agents based DRL algorithm is implemented and the environment is formulated as a Markov Decision Process (MDP) to optimize the decision-making process. Numerical results show that the proposed EMS reduces the overall energy costs by 19.18%, increases the SSRs by 9.39%, and achieves an overall 65.87% SSR. Additionally, numerical results indicates that model-free DRL, such as DDQN agent based Deep Q-Network (DQN) Reinforcement Learning (RL) algorithm, promise to eliminate the energy management complexities with multiple uncertainties.

In distributed multiple-input multiple-output (D-MIMO) networks, beam selection is necessary to predict the best beam and radio units (RUs) to serve the users in an optimum way. Finding the best RU and beam requires measuring the downlink channel for all possible RU/beam pairs, which becomes a resource-heavy operation, especially at the millimeter Wave band. To overcome this problem, artificial intelligence (AI) solutions are investigated which aim to infer the best RU/beam from sounding the channel for a subset of RUs and beams. While fairly accurate AI models can be obtained, these models have some intrinsic vulnerabilities to adversarial attacks where carefully designed perturbations are applied to the input of the AI model. In this study, we consider four different adversarial attack methods that craft perturbations using gradients of the AI cost function under two different beam reporting scenarios considering sequential and one-shot reporting of reference signal received power values for all RUs and demonstrate their effectiveness over traditional methods by extensive simulations, showing the necessity of smart defense techniques. To this aim, we propose an effective mitigation solution based on scrambling of RUs against these kinds of adversarial attack threats and verify the efficacy of our solution via detailed simulations. The proposed defense method provides up to 10 dB better signal strengths at the user side by selecting more accurate RU/beam pairs under adversarial attacks.

Computer-aided interpreting(CAI) systems are software applied to one or more stages of interpreting tasks, which can directly promote the work of interpreters and improve the interpreting quality. Until now, studies on CAI in simultaneous interpretation(SI) have been limited, primarily focusing on the design and development of manual extraction models. Moreover, what’s particularly noteworthy is the lack of thorough investigation into the development of fully automated CAI models for extracting terms (SI difficulties) and other related aspects. Based on the experimental research of existing ones, this study puts forward some new methods based on automatic speech recognition(ASR) and develops a CAI system–InterpretSIMPLE with user-friendly interface, which implements automatic retrieval and display of terms (pre-imported), numbers, etc. as well as other functions specialized for conference interpreters. Through the setting of three-line label control and underline panel control, the system realizes the attention allocation and positioning of the source text content at different levels. One-click import of commonly-used Excel glossary gives simple operation with no additional format conversion. Terminologies and numbers are displayed below the corresponding position while displaying the source text, so that interpreters could locate and solve these recognized SI difficulties. Through the “exact matching” or “partial matching” setting, it could meet the personalized requirements of terms matching. The experiment shows that after the system receives text information from Tencent Cloud, the real-time display rate of the pre-imported glossary reaches 98.92%. The research results could provide references for the research and development of in-process automated CAI tools.

As the complexity of wireless mobile networks increases significantly, artificial intelligence (AI) and machine learning (ML) have become key enablers for radio resource management and orchestration. In this paper, we propose a multi-agent reinforcement learning (RL) method for allocating radio resources to mobile users under random traffic arrivals, in which Ultra-Reliable Low-Latency Communications (URLLC) and enhanced Mobile Broad-Band (eMBB) services are jointly considered in the same radio access network (RAN). The proposed system includes hierarchically placed RL agents, where the main-agent residing on the upper hierarchy performs inter-slice resource allocation between the URLLC and eMBB slices. The URLLC and eMBB sub-agents are responsible for the resource allocation within their own slice, where the objective is to maximize the eMBB throughput while satisfying the latency requirements of the URLLC slice. In the RL algorithm, the state space includes the queue occupancy and the channel quality information of mobile users while the action space specifies the resource allocation to the users. For a computationally efficient RL training, the state space is significantly reduced by quantizing the queue occupancy and grouping the users according to their channel qualities. The numerical results for the URLLC show that the proposed RL-based approach provides the average delay results of lower than 1 ms for all experiments while the worst case eMBB throughput degradation is limited to 4%.

Given the continually rising frequency of cyberattacks, the adoption of artificial intelligence methods, particularly Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL), has become essential in the realm of cybersecurity. These techniques have proven to be effective in detecting and mitigating cyberattacks, which can cause significant harm to individuals, organizations, and even countries. Machine learning algorithms use statistical methods to identify patterns and anomalies in large datasets, enabling security analysts to detect previously unknown threats. Deep learning, a subfield of ML, has shown great potential in improving the accuracy and efficiency of cybersecurity systems, particularly in image and speech recognition. On the other hand, RL is again a subfield of machine learning that trains algorithms to learn through trial and error, making it particularly effective in dynamic environments. We also evaluated the usage of ChatGPT-like AI tools in cyber-related problem domains on both sides, positive and negative. This article provides an overview of how ML, DL, and RL are applied in cybersecurity, including their usage in malware detection, intrusion detection, vulnerability assessment, and other areas. The paper also specifies several research questions to provide a more comprehensive framework to investigate the efficiency of AI and ML models in the cybersecurity domain. The state-of-the-art studies using ML, DL, and RL models are evaluated in each Section based on the main idea, techniques, and important findings. It also discusses these techniques’ challenges and limitations, including data quality, interpretability, and adversarial attacks. Overall, the use of ML, DL, and RL in cybersecurity holds great promise for improving the effectiveness of security systems and enhancing our ability to protect against cyberattacks. Therefore, it is essential to continue developing and refining these techniques to address the ever-evolving nature of cyber threats. Besides, some promising solutions that rely on machine learning, deep learning, and reinforcement learning are susceptible to adversarial attacks, underscoring the importance of factoring in this vulnerability when devising countermeasures against sophisticated cyber threats. We also concluded that ChatGPT can be a valuable tool for cybersecurity, but it should be noted that ChatGPT-like tools can also be manipulated to threaten the integrity, confidentiality, and availability of data.

This research addresses a significant gap in power system protection methodologies by developing a dedicated simulation environment that supports the communication of protection relays via the IEC 61850 protocol. Current studies have focused on hardware-in-the-loop approaches, but there is a lack of research in the software-in-the-loop domain. This limitation means that manufacturer-independent simulations cannot be performed, restricting testing to the capabilities provided by the manufacturer. By introducing a relay capable of communicating within a Simulink-modeled power system through socket programming, this study harnesses the capabilities of the IEC 61850 GOOSE protocol and sampled values. This work aims to eliminate the manufacturer dependencies present in hardware-in-the-loop approaches, thereby enabling the independent development of new protection and control strategies in an academic context. Furthermore, by facilitating advanced communication strategies through a detailed simulation framework, this research contributes to the broader field of electrical engineering by offering a robust tool for developing, testing, and validating new relay communication techniques and protection schemes. This approach not only fills a critical gap in simulation capabilities but also paves the way for future advancements in power system protection and management regarding the IEC 61850 protocol.

The increasing complexity of software development demands efficient automated bug report priority classification, and recent advancements in deep learning hold promise. This paper presents a comparative study of contemporary learning paradigms, including BERT, vector databases, large language models (LLMs), and a simple novel learning paradigm, contrastive learning for BERT. Utilizing datasets from bug reports, movie reviews, and app reviews, we evaluate and compare the performance of each approach. We find that transformer encoder-only models outperform in classification tasks measured by the precision, recall, and F1 score transformer decoder-only models despite an order of magnitude gap between the number of parameters. The novel use of contrastive learning for BERT demonstrates promising results in capturing subtle nuances in text data. This work highlights the potential of advanced NLP techniques for automated bug report priority classification and underscores the importance of considering multiple factors when developing models for this task. The paper’s main contributions are a comprehensive evaluation of various learning paradigms, such as vector databases and LLMs, an introduction of contrastive learning for BERT, an exploration of applicability to other text classification tasks, and a contrastive learning procedure that exploits ordinal information between classes.

Fuzzy logic controls (FLCs) have emerged as a promising solution for speed regulation in induction motor (IM) drives, offering adaptability to non-linearities, parameter variations, and external disturbances. However, conventional FLCs with fixed parameters and a huge number of rules can limit adaptiveness and increase system complexity, leading to deteriorated performance and high computational requirements. Moreover, reliance on costly encoders in traditional sensor-based IM drives introduces measurement errors and contributes toward the overall cost. To tackle these challenges, this paper proposes an integrated sensorless IM drive with a simplified self-tuning FLC (ST-FLC) and data-driven reinforcement learning (RL) for speed estimation. By employing a simplified 9-rule FLC instead of an intensive 49-rule counterpart and integrating a simple self-tuning mechanism based on mathematical equations, adaptiveness is maintained while computational overhead is reduced. Furthermore, the adoption of RL-based sensorless speed estimation eliminates reliance on encoder data, offering a cost-effective and computationally efficient alternative. Unlike conventional sensorless methods, the proposed sensorless-RL approach is data-driven and does not rely on motor parameters, leveraging a pre-trained policy for efficient speed estimation. Validation through simulation and experimentation on the dSPACE DS1104 platform demonstrates the efficacy of the proposed ST-FLC Sim 9-rule with sensorless RL. The method showcases accurate speed estimation, with simulation results comparable to standard 49-rule FLC and superior experimental performance. Significant computational time reduction is achieved with the proposed approach, resulting in a notable improvement in experimental performance metrics. Specifically, reductions of 50.5%, 20.4%, 15%, and 14.9% in settling time, current ripples, torque ripples, and current harmonics, respectively, underscore the practical benefits of the proposed integrated ST-FLC Sim 9-rule with sensorless-RL IM drive system.