We study the Traveling Salesman Problem (TSP) in the Congested Clique Model (CCM) of distributedcomputing. We present a deterministic distributed algorithm that computes a tour for the TSP using O(1) rounds and O(m) ...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
We study the Traveling Salesman Problem (TSP) in the Congested Clique Model (CCM) of distributedcomputing. We present a deterministic distributed algorithm that computes a tour for the TSP using O(1) rounds and O(m) messages for a given undirected weighted complete graph of n nodes and m edges with an approximation factor 2 of the optimal. The TSP has wide applications in logistics, planning, manufacturing and testing microchips, DNA sequencing etc., and we claim that our proposed O(1)-rounds approximation algorithm to the TSP, which is fast and efficient, can also be used to minimize the energy consumption in Wireless sensor Networks.
Cyber-physical swarms represent a paradigm shift in distributedsystems, mirroring characteristics akin to natural swarms, such as self-organization, scalability, and fault tolerance. This paper delves into these comp...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
Cyber-physical swarms represent a paradigm shift in distributedsystems, mirroring characteristics akin to natural swarms, such as self-organization, scalability, and fault tolerance. This paper delves into these complex systems, characterized by vast networks of cyber-physical entities with limited environmental awareness, yet capable of exhibiting emergent collective behaviors. These systems encompass a diverse array of scenarios, ranging from swarm robotics to the interconnectivity in smart cities, as well as the collaboration among augmented humans. The engineering of such systems presents unique challenges, primarily due to their intricate complexity and the spontaneous nature of their collective behaviors. This paper aims to dissect these challenges, offering a clear delineation of potential approaches. We present a comprehensive analysis, shedding light on the intricacies of engineering cyberphysical swarms and discussing modern solutions in engineering collective applications for such systems.
In modern post-disaster rescue missions, the deployment of Multi-Robot systems (MRSs) plays a key role in minimizing injuries and deaths among rescue personnel and civilians involved in the disaster. Achieving optimal...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
In modern post-disaster rescue missions, the deployment of Multi-Robot systems (MRSs) plays a key role in minimizing injuries and deaths among rescue personnel and civilians involved in the disaster. Achieving optimal MRS efficiency requires the implementation of a well-suited task allocation mechanism and a highly efficient pathfinding algorithm. However, due to inconsistent communication and low bandwidth, traditional frameworks in the mentioned domains may be impractical or may not work well. To address these problems, a novel Bi-Layer Joint Training Reinforcement (BJoT-RL) framework is proposed where, in the first layer, a Multi-Head Deep Q-Learning (MHDQN) is designed to perform task allocation;whereas, in the second layer, a Condition-Constrained Q-Learning (CCQ) is proposed to perform pathfinding. Noticeably, the output of each layer is used in the training of the other layer to realize a tight coupling, hence the innovative joint training. Thorough simulations show that the BJoT-RL framework performs better than state-of-the-art solutions in such applications.
This paper presents a distributed learning approach designed to assist physicians in diagnosing diseases based on a patient's current health status, clinical history, and test results. The methodology relies on ne...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
This paper presents a distributed learning approach designed to assist physicians in diagnosing diseases based on a patient's current health status, clinical history, and test results. The methodology relies on neural network models and supervised classifiers to identify illnesses. It utilizes word embedding to capture semantic relationships among hospital admissions, symptoms, and diagnoses. Additionally, it introduces a method to evaluate the connection between different diagnoses based on symptom similarity, aiding in prediction tasks. Experimental results on a real-world Electronic Health Records (EHR) dataset showcase the effectiveness and accuracy of the proposed technique, providing clinically relevant interpretations. These findings suggest promising avenues for future enhancements of the framework as a valuable diagnostic tool.
This research paper aims to evaluate the efficiency and effectiveness of FLIDS in detecting multiple jamming attacks. The study conducted experiments by placing two jammers at sixteen different positions to examine th...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
This research paper aims to evaluate the efficiency and effectiveness of FLIDS in detecting multiple jamming attacks. The study conducted experiments by placing two jammers at sixteen different positions to examine the system's performance. The experiments were carried out in various scenarios of Contiki 3.1 OS and the Cooja Simulator tool using the Routing Protocol for Low-Power and Lossy Networks (RPL). Furthermore, the optimal time frame for the solution to detect real-time jamming attacks was determined after analyzing the data. The simulation results demonstrate that Fuzzy Logic is an effective technique for recognizing multiple jamming attacks with high accuracy, precision, and recall rate in different scenarios.
In wireless sensor networks, post-deployment issues persist despite extensive testing, primarily due to unpredictable environmental factors and limited debugging tools for resource-constrained end nodes. This challeng...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
In wireless sensor networks, post-deployment issues persist despite extensive testing, primarily due to unpredictable environmental factors and limited debugging tools for resource-constrained end nodes. This challenge is particularly pronounced in remote applications such as extraterrestrial habitats. To address this, we propose a runtime anomaly detection and diagnosis method for resource-constrained sensor nodes. A key advantage of our approach is its ability to learn expected behavior from historical data, eliminating the need for explicit behavior modeling, unlike other runtime fault detection methods. Our method comprises three main components: logging, detection, and diagnosis. We log event traces on the sensor nodes, enabling activity tracking down to the variable level. For anomaly detection, we explore various methods, including state transition, execution interval analysis, and clustering. Subsequently, diagnosis is performed using the logged event traces.
Occupancy refers to the presence of people in rooms and buildings. It is an essential input for IoT applications, including controlling lighting, heating, access, and monitoring space limitation policies. Occupancy in...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
Occupancy refers to the presence of people in rooms and buildings. It is an essential input for IoT applications, including controlling lighting, heating, access, and monitoring space limitation policies. Occupancy information can also be used to improve users' comfort and to reduce energy waste in buildings. This paper evaluates the performance and resource consumption of recent machine learning techniques for occupancy detection and measurement by exploiting data from distributed environmental sensors. This evaluation is founded on a dataset captured by our dedicated sensor network for indoor monitoring, comprising temperature, humidity, and carbon dioxide (CO2) sensors. Using different sensor modalities and spatio-temporal data selections, we compare eight classification algorithms based on the accuracy achieved and the required runtimes. Binary classification for occupancy detection (OD) achieves accuracies over 90% for individual modalities and close to 100% for modality combinations. Multi-class classification for occupancy measurements (OM) shows as clear ranking of the sensor modalities, and gradient boosting algorithms are superior when combining sensor modalities and fusing data from multiple sensors.
Smart lighting solutions bring benefits in terms of energy usage and users' well-being. However, their use is not widespread due to high installation and maintenance costs. The current manual commissioning procedu...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
Smart lighting solutions bring benefits in terms of energy usage and users' well-being. However, their use is not widespread due to high installation and maintenance costs. The current manual commissioning procedure is one of the main human and time-consuming tasks, so its automation is expected to reduce the overall installation cost. Considering this, we propose the Lite4More device, a Bluetooth Low Energy (BLE) based sensor platform that supports the commissioning procedure and is backwards compatible with Digital Addressable Lighting Interface (DALI) devices. The Lite4More device produces sensor data that can feed algorithms to automate the commissioning of lighting infrastructures, namely luminaire localisation and groups and scene creation. The hardware platform was validated in both lab and real office environments. The preliminary results show that Lite4More device sensors are suitable for feeding luminaire localisation and group creation algorithms, and the considered communication technology is viable for smart lighting solutions.
The Internet of Things (IoT) is a breakthrough technology that interconnects and empowers numerous smart devices allowing them to communicate, collect, and exchange data. The most challenging issue in IoT networks is ...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
The Internet of Things (IoT) is a breakthrough technology that interconnects and empowers numerous smart devices allowing them to communicate, collect, and exchange data. The most challenging issue in IoT networks is securing exchanged data. Virtual Private Networks (VPNs) have a significant impact on ensuring security within IoT systems. So implementing a VPN-based solution can bring multiple security values to IoT systems, especially for exchanged data. However, most VPN-based solutions rely on a single central server responsible for managing all VPN connections. This presents a major problem when the number of managed VPNs increases because it will lead to the performance deterioration of the VPN server and can even lead to a single point of failure problem. We propose in this paper a distributed VPN-based solution that relies on distributed fog nodes playing the role of VPN servers. To determine the VPN server responsible for a specific communication, a fully decentralized and efficient search is guaranteed within the fog nodes through the utilization of the DHT-based Chord protocol. To enforce security and immutability, blockchain is used to verify the different criteria of a new requester to join a specific VPN. The performance evaluations have shown that our solution is efficient in terms of cost, time, and complexity.
This paper presents a service model for structural health monitoring (SHM) by leveraging on-device AI techniques. Unlike conventional SHM systems relying on server-based diagnostics, our approach incorporates recent a...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
This paper presents a service model for structural health monitoring (SHM) by leveraging on-device AI techniques. Unlike conventional SHM systems relying on server-based diagnostics, our approach incorporates recent advancements in lightweight AI platforms to enable real-time diagnostics directly on the sensor nodes. This integration enhances both real-time performance and accuracy while significantly reducing network load by minimizing the need for data transfer to centralized servers. Through the experimentation using real data collected from a pedestrian bridge, we demonstrate the feasibility and efficacy of the on-device AI approach for SHM. By seamlessly integrating on-device AI into IoT infrastructure, our approach not only offers improved real-time performance and accuracy but also showcases the potential of AI in optimizing SHM systems.
暂无评论