Wireless sensor networks are widely valued for their effectiveness in real-time data collection. As the amount of data exchanged within such networks grows, designing a robust network topology that maximizes area cove...
详细信息
ISBN:
(数字)9798350367300
ISBN:
(纸本)9798350367317
Wireless sensor networks are widely valued for their effectiveness in real-time data collection. As the amount of data exchanged within such networks grows, designing a robust network topology that maximizes area coverage with minimal sensors has become a critical challenge. The choice of topology impacts key network metrics, including sensor coverage, communication range, connectivity, inference, and installation and management costsIn this paper, we address the Wireless Sensor Network Planning Problem with Multiple Sources/Destinations, presenting an optimization approach based on deep reinforcement learning. This problem is noteworthy, as sensors in various applications are often required to share data within distinct destinationsWe leverage deep reinforcement learning to effectively address the complex task of selecting optimal sensor locations. Our reinforcement learning agent dynamically learns network structure by iteratively adding and removing sensors, optimizing both sensor coverage and the total number of sensors used. Experiment across diverse scenarios demonstrate the effectiveness of our method for network planning problems of varying scales, achieving full coverage with fewer sensors than traditional approaches. Additionally, our approach also produce solutions for large instances where Mixed Integer programming solvers were not able to. Overall, our method was able to reduce the number of sensors used by up to 22.3% compared to other methods.
While Spatio-Temporal Graph Convolutional Networks (STGCNs) are an effective method for traffic speed fore-casting, their training and inference tend to be time-consuming. In this paper, we aim to refine these network...
详细信息
ISBN:
(数字)9798350308365
ISBN:
(纸本)9798350308372
While Spatio-Temporal Graph Convolutional Networks (STGCNs) are an effective method for traffic speed fore-casting, their training and inference tend to be time-consuming. In this paper, we aim to refine these networks by strategically reducing their number of nodes, thereby boosting computational efficiency. The nodes in these graphs represent data observed for road segments, and by analyzing the interconnections and layout of the graph, we can identify nodes with minimal contribution to overall performance. Removing these nodes can potentially decrease computation time while maintaining the prediction accuracy. We employ the Biased Random-Key Genetic Algorithm (BRKGA) to identify a good set of nodes for removal, based on a predefined percentage reduction of the original graph size (e.g., retaining 95 % of the original graph). We evaluate different graph size configurations, ranging from 95 % to 70 % node retention, to determine the least impactful node set performance. Our experiments on three real-world datasets reveal that reducing nodes can decrease computation time by up to 29%, and as a byproduct of removing noise, even improve the prediction accuracy.
Artificial Intelligence (AI) seems to be a disruptive technology that defines and reshapes the economy, more efficient industrial processes, new business models, and the service sector, becoming the development of dif...
详细信息
RFID-based mechanical vibration detection is considered a promising method for many Internet of Things (IoT) applications. However, existing methods are affected by ambient interference and leakage from the reader sig...
详细信息
In this article, we present an innovative approach to enhance the online shoe shopping experience. The convolutional neural network (CNN) image recognition technology was used to enhance shoe classification and recomm...
In this article, we present an innovative approach to enhance the online shoe shopping experience. The convolutional neural network (CNN) image recognition technology was used to enhance shoe classification and recommendations. By training the CNN model on an extensive dataset, unique shoe features and styles were learned. Integrated into a user-friendly online platform, the system offers real-time image recognition, allowing users to snap a photo of a desired shoe for instant identification, including brand, price, and availability details. Moreover, the CNN-based recommendation engine provides personalized suggestions based on style, color, and customer preferences, enriching the shopping experience. Evaluation results confirmed the system's feasibility, and user feedback highlighted its effectiveness in simplifying the shopping process and enhancing satisfaction. This innovative system presents a significant leap in merging AI and e-commerce and shows the potential of image recognition to transform online marketplaces, benefiting consumers, offering valuable insights for retailers, and ultimately reshaping the future of online shoe shopping.
In this paper we consider the filtering of partially observed multi-dimensional diffusion processes that are observed regularly at discrete times. We assume that, for numerical reasons, one has to time-discretize the ...
详细信息
According to data from Taiwan’s National Development Council in 2024, Taiwan is expected to enter a super-aged society by 2025, indicating a great acceleration in population aging. With the aging population and the i...
详细信息
ISBN:
(数字)9798350389210
ISBN:
(纸本)9798350389227
According to data from Taiwan’s National Development Council in 2024, Taiwan is expected to enter a super-aged society by 2025, indicating a great acceleration in population aging. With the aging population and the increasing prevalence of chronic diseases, the importance of rehabilitation for the elderly has become crucial. Rehabilitation aims not only to aid in recovering from illness or surgery but also to maintain health in daily life. For the elderly, appropriate rehabilitation exercises can improve physical strength, cardiopulmonary function, and overall quality of life. This not only helps restore physical function but also reduces the occurrence and progression of chronic diseases. The system includes contextual rehabilitation games, general rehabilitation training, accessible remote instruction, and physical fitness assessment. The contextual rehabilitation games utilize gamified interactive designs to enhance engagement and motivation. General rehabilitation training provides standardized guidance on rehabilitation movements. Accessible remote instruction allows patients who are unable to move due to various factors to receive professional guidance in hospitals or care centers, reducing the inconvenience of movement. Finally, physical fitness assessment provides accurate data support for medical personnel, while also reducing manual calculation errors and labor costs. Through this comprehensive assistive system, smart healthcare can not only improve the effectiveness and efficiency of rehabilitation but also provide a new approach for health management and rehabilitation of the elderly, helping to address the challenges brought by an aging society in the future.
Recent work has proven the effort of researchers to integrate small sensors and a cloud environment, delivering the Internet of Things (IoT). Sensors as a service are one of the leading research concerns in this conte...
Recent work has proven the effort of researchers to integrate small sensors and a cloud environment, delivering the Internet of Things (IoT). Sensors as a service are one of the leading research concerns in this context. Nevertheless, security is becoming one of the most significant attributes of the IoT as sensors become more human-independent and are being extensively used to monitor human lives. That way, IoT brings many key security challenges that need attention, some of which we address in this position paper. We present a cloud-based infrastructure that can deliver sensors and actuators as a service, providing secure communication between them and the control nodes on which IoT applications rely while implementing Big Data algorithms. For mapping our proposal, two scenarios related to Health Assistance are discussed, considering secure communications in a sensor network. In conclusion, we propose a scope for future research in this field considering digital twin concepts. Since domains exploiting IoT technologies can benefit from adopting Digital Twin, our goal is to evolve a virtual sensor and actuator system into this technology.
In this paper we consider the filtering problem associated to partially observed McKean-Vlasov stochastic differential equations (SDEs). The model consists of data that are observed at regular and discrete times and t...
详细信息
Mobility-on-demand (MoD) systems consist of a fleet of shared vehicles that can be hailed for one-way point-to-point trips. The total distance driven by the vehicles and the fleet size can be reduced by employing ride...
详细信息
暂无评论