Climate change has been causing certain impacts on the environment and public health, especially in large urban areas, where the population density is dense and the green area is not enough. Trees play an important ro...
详细信息
Software system admins depend on log data for understanding system beliavior, monitoring anomalies, tracking software bugs, and malfunctioning detection. Log analysis based on machine learning techniques enables to tr...
详细信息
Current edge cloud providers offer a wide range of on-demand private and public cloud services for customers. Predictive demand monitoring and supply optimisation are necessary to deliver truly elastic distributed edg...
详细信息
ISBN:
(纸本)9781665458702
Current edge cloud providers offer a wide range of on-demand private and public cloud services for customers. Predictive demand monitoring and supply optimisation are necessary to deliver truly elastic distributed edge cloud services with resizable resource and compute capacity to adapt to dynamically changing customer requirements. However, current state-of-the-art monitoring and provisioning systems remain reactive which often results in over or under service provisioning, incurring unnecessary costs for customers or deterioration in the quality of service for the end-user. this paper proposes an adaptive protocol, ARPP, that enables distributed real-time demand monitoring and automatic resource provision based on the dynamically changing spatial-temporal workload patterns. ARPP leverages distributed predictive analytics and deep reinforcement learning at the edges to predict the dynamically changing spatial-temporal demand and allocate the appropriate amount of resources at the right times and right locations. We show that ARPP outperforms benchmark and state of the art algorithms across a range of criteria in the face of dynamically changing mobile real-world topologies and user interest patterns.
the proceedings contain 93 papers. the topics discussed include: novel four-dimensional chaotic oscillator for Sub1GHz chaos-based communication systems;new measurement method for respiration and heartbeat estimation ...
ISBN:
(纸本)9781728131566
the proceedings contain 93 papers. the topics discussed include: novel four-dimensional chaotic oscillator for Sub1GHz chaos-based communication systems;new measurement method for respiration and heartbeat estimation using IR-UWB radar;integration of network coding in a multi-source multi-relay cooperative wireless network;PAPR reduction in MIMO (2x2)-FBMC-OQAM systems using attenuating QAM symbols;deep reinforcement learning for real-world anomaly detection in surveillance videos;enhanced face recognition system based on deep CNN;experimental design and analysis of sound event detection systems: case studies;and vibration signal analysis for bearing fault diagnostic of asynchronous motor using HT-DWT technique.
the increasing demands of e-commerce have increased the need for efficient last-mile delivery solutions, presenting logistical challenges such as traffic congestion and high operational costs. this paper explores the ...
详细信息
Fault tolerance and energy consumption optimization are critical issues in swarm robotics. this study examines recent approaches to address these challenges, focusing on a comparative analysis between Centralized Fede...
详细信息
ISBN:
(数字)9798350350265
ISBN:
(纸本)9798350350272
Fault tolerance and energy consumption optimization are critical issues in swarm robotics. this study examines recent approaches to address these challenges, focusing on a comparative analysis between Centralized Federated Learning (CFL) and Decentralized Federated Learning (DFL). CFL requires a centralized access point for model aggregation, while DFL eliminates the need for a central server, enabling aggregation at each node according to a specific architecture. the analysis of the results reveals that other approaches, such as Hybrid Federated Learning (HFL), more effectively meet the needs of intelligent agents (swarm robots). this effectiveness is particularly enhanced when HFL is combined with Deep Reinforcement Learning (DRL), resulting in Deep Hybrid Federated Reinforcement Learning (DHFRL). the results demonstrate that, although DFL eliminates the necessity of a central server, hybrid approaches are more efficient, especially when combined with Deep Reinforcement Learning (DRL), thus forming Deep Hybrid Federated Reinforcement Learning (DHFRL).
the wireless channel often shows high complexity in the attempt to analyze theoretically the network layer parameters. A parameter of this layer is the Packet Reception Ratio (PRR). the PRR is a practical metric, whic...
the wireless channel often shows high complexity in the attempt to analyze theoretically the network layer parameters. A parameter of this layer is the Packet Reception Ratio (PRR). the PRR is a practical metric, which when analyzed theoretically, exhibits high complexity. Its optimization results in high throughput and a reduction in the interference and collisions of transmissions. In theory, PRR is described with a sigmoid function, which conveys a very hard problem to solve. In this paper, we will reduce this complexity by transforming PRR and transmission power function to a discrete concave-up one; thus, allowing fast algorithms, which locate the globally optimal solutions, to be applied. We do this transformation utilizing networking terms, which come into play to reduce the complexity of a PRR optimization process.
Integrating Al-powered applications into video conferencing systems is furtlier expected to blow up in various industrial scenarios. In this modern era of the video conferencing industry, deep learning techniques are ...
详细信息
this research introduces the design and implementation of an advanced IoT-based home security system aimed at improving both convenience and safety for homeowners. the system integrates a smart doorbell with a mobile ...
详细信息
ISBN:
(数字)9798331522667
ISBN:
(纸本)9798331522674
this research introduces the design and implementation of an advanced IoT-based home security system aimed at improving both convenience and safety for homeowners. the system integrates a smart doorbell with a mobile application, enabling real-time alerts for guest arrivals. Key features include facial recognition for automated door unlocking and notification of unrecognized visitors. When an unknown face is detected, the system sends an image along with a notification to the homeowner via a Telegram bot. the architecture incorporates the ESP32-CAM microcontroller for face detection, a solenoid lock for automatic door access, and an ultrasonic sensor to detect visitor presence. Extensive testing under various environmental conditions was conducted to assess the system's performance, particularly in terms of face recognition accuracy and notification delivery. the results indicate that the system significantly enhances home security by ensuring timely notifications and automating door access for verified individuals. While the system performs reliably in well-lit environments, challenges remain in low-light conditions. Software testing confirmed the robustness of the underlying logic. this innovative IoT solution overcomes the limitations of traditional security systems, offering a more secure, user-friendly, and efficient alternative for modern home security.
Since the evolution of digital and online text content, automatic document classification has become a significant research issue. there is a most commonly used machine learning approach to improve this task: an unsup...
详细信息
暂无评论