Hasil untuk "Cybernetics"

Yi Liu, Hongda Zhang, Zhongxue Gan et al.

Ant Colony Optimization (ACO) is a prominent swarm intelligence algorithm extensively applied to path planning. However, traditional ACO methods often exhibit shortcomings, such as blind search behavior and slow convergence within complex environments. To address these challenges, this paper proposes the Pheromone-Focused Ant Colony Optimization (PFACO) algorithm, which introduces three key strategies to enhance the problem-solving ability of the ant colony. First, the initial pheromone distribution is concentrated in more promising regions based on the Euclidean distances of nodes to the start and end points, balancing the trade-off between exploration and exploitation. Second, promising solutions are reinforced during colony iterations to intensify pheromone deposition along high-quality paths, accelerating convergence while maintaining solution diversity. Third, a forward-looking mechanism is implemented to penalize redundant path turns, promoting smoother and more efficient solutions. These strategies collectively produce the focused pheromones to guide the ant colony's search, which enhances the global optimization capabilities of the PFACO algorithm, significantly improving convergence speed and solution quality across diverse optimization problems. The experimental results demonstrate that PFACO consistently outperforms comparative ACO algorithms in terms of convergence speed and solution quality.

Ting-Wei Ou, Jia-Hao Jiang, Guan-Lin Huang et al.

The COVID-19 pandemic has severely affected public health, healthcare systems, and daily life, especially amid resource shortages and limited workers. This crisis has underscored the urgent need for automation in hospital environments, particularly disinfection, which is crucial to controlling virus transmission and improving the safety of healthcare personnel and patients. Ultraviolet (UV) light disinfection, known for its high efficiency, has been widely adopted in hospital settings. However, most existing research focuses on maximizing UV coverage while paying little attention to the impact of human activity on virus distribution. To address this issue, we propose a mobile robotic system for UV disinfection focusing on the virus hotspot. The system prioritizes disinfection in high-risk areas and employs an approach for optimized UV dosage to ensure that all surfaces receive an adequate level of UV exposure while significantly reducing disinfection time. It not only improves disinfection efficiency but also minimizes unnecessary exposure in low-risk areas. In two representative hospital scenarios, our method achieves the same disinfection effectiveness while reducing disinfection time by 30.7% and 31.9%, respectively. The video of the experiment is available at: https://youtu.be/wHcWzOcoMPM.

Jayavani Vankara , Muddada Murali Krishna , Sekharamahanti S. Nandhini et al.

Due to the lack of precise medical testing for autism, such as blood tests to detect the illness, diagnosing autism spectrum disorder (ASD) has proven to be challenging. The prevalence of restrictive and/or repetitive behaviors and difficulties and impairments in social communication are hallmarks of autism spectrum disorders. This behavioral condition has been identified. Doctors assess the child's developmental history and behavior to make a diagnosis. Research results. This research used a hybrid Multi Label-Graph Convolutional Network (ML-GCN) with label-attentive neighborhood convolution to categorize the autism spectrum disorder. It offers a clear and effective graph wrapper module in particular for collecting the local attribute data of a specific node to produce a logical representation of node functioning. Additionally, the homeopathic theory recommends developing a taxonomy for attention-related terms. Furthermore, developed an adaptive graph technique that allows the model to learn the kernel for each layer dynamically and uniquely, allowing the model to acquire more valuable and efficient features. On three frequently used reference datasets, including customized and non-specialized networks, comprehensive tests were conducted to validate the neural network-based approach to multi-label classification.

William Villegas-Ch, Alexandra Maldonado Navarro, Santiago Sanchez-Viteri

This study presents implementing and evaluating a computer vision platform to optimize warehouse inventory management. Integrating machine learning and computer vision technologies, this solution addresses critical challenges in inventory accuracy and operational efficiency, overcoming the limitations of traditional methods and pre-existing automated systems. The platform uses convolutional neural networks and open-source libraries such as TensorFlow and PyTorch to recognize and accurately classify products from images captured in real time. Practical implementation in a natural warehouse environment allowed the proposed platform to be compared with traditional systems, highlighting significant improvements, such as a 45% reduction in the time required for inventory counting and a 9% increase in inventory accuracy. Despite facing challenges such as staff resistance to change and technical limitations on image quality, these difficulties were overcome through effective change management strategies and algorithm improvements. The findings of this study identify the potential for computer vision technology to transform warehouse operations, offering a practical and adaptable solution for inventory management.

Saif AlDeen AlSharman, Osama Al-Khaleel, Mahmoud Al-Ayyoub

The growing use of the Internet of Things (IoT) across a vast number of sectors in our daily life noticeably exposes IoT internet-connected devices, which generate, share, and store sensitive data, to a wide range of cyber threats. Software Defined Networks (SDNs) can play a significant role in enhancing the security of IoT networks against any potential attacks. The goal of the SDN approach to network administration is to enhance network performance and monitoring. This is achieved by allowing more dynamic and programmatically efficient network configuration; hence, simplifying networks through centralized management and control. There are many difficulties for manufacturers to manage the risks associated with evolving technology as the technology itself introduces a variety of vulnerabilities and dangers. Therefore, Intrusion Detection Systems (IDSs) are an essential component for keeping tabs on suspicious behaviors. While IDSs can be implemented with more simplicity due to the centralized view of an SDN, the effectiveness of modern detection methods, which are mainly based on machine learning (ML) or deep learning (DL), is dependent on the quality of the data used in their modeling. Anomaly-based detection systems employed in SDNs have a hard time getting started due to the lack of publicly available data, especially on the data layer. The large majority of existing literature relies on data from conventional networks. This study aims to generate multiple types of Distributed Denial of Service (DDoS) and Denial of Service (DoS) attacks over the data plane (Southbound) portion of an SDN implementation. The cutting-edge virtualization technology is used to simulate a real-world environment of Docker Orchestration as a distributed system. The collected dataset contains examples of both benign and suspicious forms of attacks on the data plane of an SDN infrastructure. We also conduct an experimental evaluation of our collected dataset with well-known machine learning-based techniques and statistical measures to prove their usefulness. Both resources we build in this work (the dataset we create and the baseline models we train on it) can be useful for researchers and practitioners working on improving the security of IoT networks by using SDN technologies.

Mohammad Mahdi Chegini, Farhad Pourkeyvan

SUBJECT & OBJECTIVES: This article examines the moral principles and norms required by legislators, particularly parliamentarians, from the perspective of Islamic teachings, which is significant for crafting appropriate codes of conduct. It aims to differentiate the unique professional ethics requirements for parliamentarians within a religious democratic context like the Islamic Republic of Iran. Additionally, it identifies potential conflicts or synergies between Islamic ethics and global ethical standards. METHOD & FINDING: The approach includes a comparative analysis, looking at contemporary practices of ethical code development, alongside a focused review of Islamic religious texts and their interpretations regarding moral governance. Key findings suggest that trustworthiness, confidentiality, consultation, and adherence to the law stand out as crucial ethical obligations. Moreover, the article highlights the potential pitfalls of not adhering to these ethical standards, such as the loss of public trust and the erosion of the legislative body's effectiveness. The approach includes a comparative analysis, looking at contemporary practices of ethical code development, alongside a focused review of Islamic religious texts and their interpretations regarding moral governance. Key findings suggest that trustworthiness, confidentiality, consultation, and adherence to the law stand out as crucial ethical obligations. Moreover, the article highlights the potential pitfalls of not adhering to these ethical standards, such as the loss of public trust and the erosion of the legislative body's effectiveness.CONCLUSION: The development of a comprehensive moral framework for parliamentarians is not only a foundational step in enhancing the integrity of governance but also crucial for maintaining public trust and accountability. Islamic teachings provide a robust foundation for these ethical norms, emphasizing the importance of moral conduct in leadership roles. By adhering to these principles, legislators can ensure more effective governance and a greater alignment with the public's interests, which ultimately strengthens the overall democratic structure.

Hanyi Xu, Wensheng Gan, Zhenlian Qi et al.

Artificial intelligence (AI) has a profound impact on traditional education. In recent years, large language models (LLMs) have been increasingly used in various applications such as natural language processing, computer vision, speech recognition, and autonomous driving. LLMs have also been applied in many fields, including recommendation, finance, government, education, legal affairs, and finance. As powerful auxiliary tools, LLMs incorporate various technologies such as deep learning, pre-training, fine-tuning, and reinforcement learning. The use of LLMs for smart education (LLMEdu) has been a significant strategic direction for countries worldwide. While LLMs have shown great promise in improving teaching quality, changing education models, and modifying teacher roles, the technologies are still facing several challenges. In this paper, we conduct a systematic review of LLMEdu, focusing on current technologies, challenges, and future developments. We first summarize the current state of LLMEdu and then introduce the characteristics of LLMs and education, as well as the benefits of integrating LLMs into education. We also review the process of integrating LLMs into the education industry, as well as the introduction of related technologies. Finally, we discuss the challenges and problems faced by LLMEdu, as well as prospects for future optimization of LLMEdu.

Ryan Hare, Ying Tang

In the search for more effective education, there is a widespread effort to develop better approaches to personalize student education. Unassisted, educators often do not have time or resources to personally support every student in a given classroom. Motivated by this issue, and by recent advancements in artificial intelligence, this paper presents a general-purpose framework for personalized student support, applicable to any virtual educational system such as a serious game or an intelligent tutoring system. To fit any educational situation, we apply ontologies for their semantic organization, combining them with data collection considerations and multi-agent reinforcement learning. The result is a modular system that can be adapted to any virtual educational software to provide useful personalized assistance to students.

Fan Ding, Xuewen Luo, Gaoxuan Li et al.

To tackle the twin challenges of limited battery life and lengthy charging durations in electric vehicles (EVs), this paper introduces an Energy-efficient Hybrid Model Predictive Planner (EHMPP), which employs an energy-saving optimization strategy. EHMPP focuses on refining the design of the motion planner to be seamlessly integrated with the existing automatic driving algorithms, without additional hardware. It has been validated through simulation experiments on the Prescan, CarSim, and Matlab platforms, demonstrating that it can increase passive recovery energy by 11.74\% and effectively track motor speed and acceleration at optimal power. To sum up, EHMPP not only aids in trajectory planning but also significantly boosts energy efficiency in autonomous EVs.

Chengyan Wu, Bolei Ma, Zheyu Zhang et al.

Aspect-based sentiment analysis (ABSA), a sequence labeling task, has attracted increasing attention in multilingual contexts. While previous research has focused largely on fine-tuning or training models specifically for ABSA, we evaluate large language models (LLMs) under zero-shot conditions to explore their potential to tackle this challenge with minimal task-specific adaptation. We conduct a comprehensive empirical evaluation of a series of LLMs on multilingual ABSA tasks, investigating various prompting strategies, including vanilla zero-shot, chain-of-thought (CoT), self-improvement, self-debate, and self-consistency, across nine different models. Results indicate that while LLMs show promise in handling multilingual ABSA, they generally fall short of fine-tuned, task-specific models. Notably, simpler zero-shot prompts often outperform more complex strategies, especially in high-resource languages like English. These findings underscore the need for further refinement of LLM-based approaches to effectively address ABSA task across diverse languages.

Dhruv Nandakumar, Sathvik Murli, Ankur Khosla et al.

The increasing reliance on the internet has led to the proliferation of a diverse set of web-browsers and operating systems (OSs) capable of browsing the web. User agent strings (UASs) are a component of web browsing that are transmitted with every Hypertext Transfer Protocol (HTTP) request. They contain information about the client device and software, which is used by web servers for various purposes such as content negotiation and security. However, due to the proliferation of various browsers and devices, parsing UASs is a non-trivial task due to a lack of standardization of UAS formats. Current rules-based approaches are often brittle and can fail when encountering such non-standard formats. In this work, a novel methodology for parsing UASs using Multi-Headed Attention Based transformers is proposed. The proposed methodology exhibits strong performance in parsing a variety of UASs with differing formats. Furthermore, a framework to utilize parsed UASs to estimate the vulnerability scores for large sections of publicly visible IT networks or regions is also discussed. The methodology present here can also be easily extended or deployed for real-time parsing of logs in enterprise settings.

Maxime Adjigble, Rustam Stolkin, Naresh Marturi

This paper presents an assisted telemanipulation framework for reaching and grasping desired objects from clutter. Specifically, the developed system allows an operator to select an object from a cluttered heap and effortlessly grasp it, with the system assisting in selecting the best grasp and guiding the operator to reach it. To this end, we propose an object pose estimation scheme, a dynamic grasp re-ranking strategy, and a reach-to-grasp hybrid force/position trajectory guidance controller. We integrate them, along with our previous SpectGRASP grasp planner, into a classical bilateral teleoperation system that allows to control the robot using a haptic device while providing force feedback to the operator. For a user-selected object, our system first identifies the object in the heap and estimates its full six degrees of freedom (DoF) pose. Then, SpectGRASP generates a set of ordered, collision-free grasps for this object. Based on the current location of the robot gripper, the proposed grasp re-ranking strategy dynamically updates the best grasp. In assisted mode, the hybrid controller generates a zero force-torque path along the reach-to-grasp trajectory while automatically controlling the orientation of the robot. We conducted real-world experiments using a haptic device and a 7-DoF cobot with a 2-finger gripper to validate individual components of our telemanipulation system and its overall functionality. Obtained results demonstrate the effectiveness of our system in assisting humans to clear cluttered scenes.

Ziyue Li, Yuchen Fang, You Li et al.

A timely detection of seizures for newborn infants with electroencephalogram (EEG) has been a common yet life-saving practice in the Neonatal Intensive Care Unit (NICU). However, it requires great human efforts for real-time monitoring, which calls for automated solutions to neonatal seizure detection. Moreover, the current automated methods focusing on adult epilepsy monitoring often fail due to (i) dynamic seizure onset location in human brains; (ii) different montages on neonates and (iii) huge distribution shift among different subjects. In this paper, we propose a deep learning framework, namely STATENet, to address the exclusive challenges with exquisite designs at the temporal, spatial and model levels. The experiments over the real-world large-scale neonatal EEG dataset illustrate that our framework achieves significantly better seizure detection performance.

Panagiotis Petropoulakis, Ludwig Gräf, Mohammadhossein Malmir et al.

Choosing an appropriate representation of the environment for the underlying decision-making process of the reinforcement learning agent is not always straightforward. The state representation should be inclusive enough to allow the agent to informatively decide on its actions and disentangled enough to simplify policy training and the corresponding sim2real transfer. Given this outlook, this work examines the effect of various representations in incentivizing the agent to solve a specific robotic task: antipodal and planar object grasping. A continuum of state representations is defined, starting from hand-crafted numerical states to encoded image-based representations, with decreasing levels of induced task-specific knowledge. The effects of each representation on the ability of the agent to solve the task in simulation and the transferability of the learned policy to the real robot are examined and compared against a model-based approach with complete system knowledge. The results show that reinforcement learning agents using numerical states can perform on par with non-learning baselines. Furthermore, we find that agents using image-based representations from pre-trained environment embedding vectors perform better than end-to-end trained agents, and hypothesize that separation of representation learning from reinforcement learning can benefit sim2real transfer. Finally, we conclude that incentivizing the state representation with task-specific knowledge facilitates faster convergence for agent training and increases success rates in sim2real robot control.

Yaosheng Deng, Aiyi Li, Masaki Ogura et al.

The shepherding problem refers to guiding a group of agents (called sheep) to a specific destination using an external agent with repulsive forces (called shepherd). Although various movement algorithms for the shepherd have been explored in the literature, there is a scarcity of methodologies for selective guidance, which is a key technology for precise swarm control. Therefore, this study investigates the problem of guiding a single target sheep within a swarm to a given destination using a shepherd. We first present our model of the dynamics of sheep agents and the interaction between sheep and shepherd agents. The model is shown to be well-defined with no collision if the interaction magnitude between sheep and shepherd is reasonably limited. Based on the analysis with Lyapunov stability principles, we design a shepherd control law to guide the target sheep to the origin while avoiding collisions among sheep agents. Experimental results demonstrate the effectiveness of the proposed method in guiding the target sheep in both small and large scale swarms.

Divij Gupta, Ali Etemad

Remote Photoplethysmography (rPPG) is the process of estimating PPG from facial videos. While this approach benefits from contactless interaction, it is reliant on videos of faces, which often constitutes an important privacy concern. Recent research has revealed that deep learning techniques are vulnerable to attacks, which can result in significant data breaches making deep rPPG estimation even more sensitive. To address this issue, we propose a data perturbation method that involves extraction of certain areas of the face with less identity-related information, followed by pixel shuffling and blurring. Our experiments on two rPPG datasets (PURE and UBFC) show that our approach reduces the accuracy of facial recognition algorithms by over 60%, with minimal impact on rPPG extraction. We also test our method on three facial recognition datasets (LFW, CALFW, and AgeDB), where our approach reduced performance by nearly 50%. Our findings demonstrate the potential of our approach as an effective privacy-preserving solution for rPPG estimation.

Zhaojun Li, Xinyan Qin, Jin Lei et al.

Abstract To address complex work conditions incredibly challenging to the stability of power line inspection robots, we design a walking mechanism and propose a variable universe fuzzy control (VUFC) method based on multi‐work conditions for flying‐walking power line inspection robots (FPLIRs). The contributions of this paper are as follows: (1) A flexible pressing component is designed to improve the adaptability of the FPLIR to the ground line slope. (2) The influence of multi‐work conditions on the FPLIR's walking stability is quantified using three condition parameters (i.e., slope, slipping degree and swing angle), and their measurement methods are proposed. (3) The VUFC method based on the condition parameters is proposed to improve the walking stability of the FPLIR. Finally, the effect of the VUFC method on walking stability of the FPLIR is teste. The experimental results show that the maximum climbing angle of the FPLIR reaches 29.1°. Compared with the constant pressing force of 30 N, the average value of slipping degree is 0.93°, increasing by 35%. The maximum and average values of robot's swing angle are reduced by 46% and 54%, respectively. By comparing with fuzzy control, the VUFC can provide a more reasonable pressing force while maintaining the walking stability of the FPLIR. The proposed walking mechanism and the VUFC method significantly improve the stability of the FPLIR, providing a reference for structural designs and stability controls of inspection robots.

Patrick Fortin, Michael R. Gerhardt, Øystein Ulleberg et al.

Electrochemical impedance spectroscopy (EIS) is a powerful technique that can be used to detect small changes in electrochemical systems and subsequently identify the source of the change. While promising, analysis is often non-intuitive and time-consuming, where collection times of a single EIS spectrum can reach several minutes. To circumvent the long collection times associated with traditional EIS measurements, a multi-sine EIS technique was proposed in which the simultaneous application of many frequencies can reduce the acquisition time to less than a minute. This shortened acquisition time opens the possibility to use multi-sine EIS as a real-time diagnostic tool for monitoring the state-of-health of commercial fuel cell systems. In this work, a single-cell proton exchange membrane fuel cell (PEMFC) was characterised using multi-sine EIS, by establishing steady-state impedance response under baseline conditions before systematically changing operating conditions and monitoring the dynamic changes of the impedance response. Our initial results demonstrate that full multi-sine EIS spectra, encompassing a frequency range from 50 kHz to 0.5 Hz, can be collected and analysed using simple equivalent circuit models in 50 s. It is shown that this timeframe is sufficiently short to capture the dynamic response of the fuel cell in response to changing operating conditions, thereby validating the use of multi-sine EIS as a diagnostic technique for in-situ monitoring and fault detection during fuel cell operation.

Rajesh Siraskar

This paper is a study of reinforcement learning (RL) as an optimal-control strategy for control of nonlinear valves. It is evaluated against the PID (proportional–integral–derivative) strategy, using a unified framework. RL is an autonomous learning mechanism that learns by interacting with its environment. It is gaining increasing attention in the world of control systems as a means of building optimal-controllers for challenging dynamic and nonlinear processes. Published RL research often uses open-source tools (Python and OpenAI Gym environments). We use MATLAB’s recently launched (R2019a) Reinforcement Learning Toolbox exttrademark to develop the valve controller; trained using the DDPG (Deep Deterministic Policy-Gradient) algorithm and Simulink® to simulate the nonlinear valve and create the experimental test-bench for evaluation. Simulink allows industrial engineers to quickly adapt and experiment with other systems of their choice. Results indicate that the RL controller is extremely good at tracking the signal with speed and produces a lower error with respect to the reference signal. The PID, however, is better at disturbance rejection and hence provides a longer life for the valves. Successful machine learning involves tuning many hyperparameters requiring significant investment of time and efforts. We introduce “Graded Learning” as a simplified, application oriented adaptation of the more formal and algorithmic “Curriculum for Reinforcement Learning”. It is shown via experiments that it helps converge the learning task of complex non-linear real world systems. Finally, experiential learnings gained from this research are corroborated against published research.

Ghassan Fadlallah, Djamal Rebaine, Hamid Mcheick

Smart, pervasive devices have recently experienced accelerated technological development in the fields of hardware, software, and wireless connections. The promotion of various kinds of collaborative mobile computing requires an upgrade in network connectivity with wireless technologies, as well as enhanced peer-to-peer communication. Mobile computing also requires appropriate scheduling methods to speed up the implementation and processing of various computing applications by better managing network resources. Scheduling techniques are relevant to the modern architectural models that support the IoT paradigm, particularly smart collaborative mobile computing architectures at the network periphery. In this regard, load-balancing techniques have also become necessary to exploit all the available capabilities and thus the speed of implementation. However, since the problem of scheduling and load-balancing, which we addressed in this study, is known to be NP-hard, the heuristic approach is well justified. We thus designed and validated a greedy scheduling and load-balancing algorithm to improve the utilization of resources. We conducted a comparison study with the longest cloudlet fact processing (LCFP), shortest cloudlet fact processing (SCFP), and Min-Min heuristic algorithms. The choice of those three algorithms is based on the efficiency and simplicity of their mechanisms, as reported in the literature, for allocating tasks to devices. The simulation we conducted showed the superiority of our approach over those algorithms with respect to the overall completion time criterion.