Local Server Research Articles

MP-Net: A Multi-Center Privacy-Preserving Network for Medical Image Segmentation.

In this paper, we present the Multi-Center Privacy-Preserving Network (MP-Net), a novel framework designed for secure medical image segmentation in multi-center collaborations. Our methodology offers a new approach to multi-center collaborative learning, capable of reducing the volume of data transmission and enhancing data privacy protection. Unlike federated learning, which requires the transmission of model data between the central server and local servers in each round, our method only necessitates a single transfer of encrypted data. The proposed MP-Net comprises a three-layer model, consisting of encryption, segmentation, and decryption networks. We encrypt the image data into ciphertext using an encryption network and introduce an improved U-Net for image ciphertext segmentation. Finally, the segmentation mask is obtained through a decryption network. This architecture enables ciphertext-based image segmentation through computable image encryption. We evaluate the effectiveness of our approach on three datasets, including two cardiac MRI datasets and a CTPA dataset. Our results demonstrate that the MP-Net can securely utilize data from multiple centers to establish a more robust and information-rich segmentation model.

Multi-Agent Deep Reinforcement Learning-Based Inference Task Scheduling and Offloading for Maximum Inference Accuracy under Time and Energy Constraints

The journey towards realizing real-time AI-driven IoT applications is facing a significant hurdle caused by the limited resources of IoT devices. Particularly for battery-powered edge devices, the decision between performing task inference locally or by offloading to edge servers, all while ensuring timely results and conserving energy, is a critical issue. This problem is further complicated when an edge device houses multiple local inference models. The challenge of effectively allocating inference models to tasks between local models and edge server models under strict time and energy constraints while maximizing overall accuracy is recognized as a strongly NP-hard problem and has not been addressed in the literature. Therefore, in this work we propose MASITO, a novel multi-agent deep reinforcement learning framework designed to address this intricate problem. By dividing the problem into two sub-problems namely task scheduling and edge server selection we propose a cooperative multi-agent system for addressing each sub-problem. MASITO’s design allows for faster training and more robust schedules using cooperative behavior where agents compensate for each other’s sub-optimal actions. Moreover, MASITO dynamically adapts to different network configurations which allows for high-mobility edge computing applications. Experiments on the ImageNet-mini dataset demonstrate the framework’s efficacy, outperforming genetic algorithms (GAs), simulated annealing (SA), and particle swarm optimization (PSO) in scheduling times by providing lower times ranging from 60% up to 90% while maintaining comparable average accuracy in worst-case scenarios and superior accuracy in best-case scenarios.

Framework for Designing of Wireless Sensor Network Using OPNET and Effect of Transport Protocols on Simulation

A Wireless sensor network can be defined as a network of devices that can communicate the information gathered from a monitored field through wireless links. The data is forwarded through multiple nodes, and with a gateway, the data is connected to other networks like wireless Ethernet. It is intended for a general application and should be able to collect data from many nodes, every node connected to several sensors. One possible application for such a network is in the medical area. At first the network will be used to display the evolution of blood pressure; the body temperature, the ambient temperature and pressure and the level of the transfusion liquid can be collected as well. The network coordinator will transmit the data to a local server for further processing. The simulation will be used to evaluate the general parameters of the wireless network and to optimize it. In this paper, we aim to evaluate the performance of a ZigBee wireless sensor network using OPNET and also study the effects of TCP and UDP on the performance of the application based on OPNET simulation software. Keywords-Sensor, wireless sensor network, ZigBee, OPNET, TCP, UDP.

NIR-Based Electronic Platform for Glucose Monitoring for the Prevention and Control of Diabetes Mellitus.

The glucose level in the blood is measured through invasive methods, causing discomfort in the patient, loss of sensitivity in the area where the sample is obtained, and healing problems. This article deals with the design, implementation, and evaluation of a device with an ESP-WROOM-32D microcontroller with the application of near-infrared photospectroscopy technology that uses a diode array that transmits between 830 nm and 940 nm to measure glucose levels in the blood. In addition, the system provides a webpage for the monitoring and control of diabetes mellitus for each patient; the webpage is hosted on a local Linux server with a MySQL database. The tests are conducted on 120 people with an age range of 35 to 85 years; each person undergoes two sample collections with the traditional method and two with the non-invasive method. The developed device complies with the ranges established by the American Diabetes Association: presenting a measurement error margin of close to 3% in relation to traditional blood glucose measurement devices. The purpose of the study is to design and evaluate a device that uses non-invasive technology to measure blood glucose levels. This involves constructing a non-invasive glucometer prototype that is then evaluated in a group of participants with diabetes.

Smart Library Automation: Integrating Classification Tree-Based cataloging with XAMPP Server Environment

Various sectors, including libraries, have experienced a revolution due to the swift progress of technology. This involves introducing automation and monitoring systems for more efficient operations. Hence the study Smart Library Automation and Monitoring System as an appropriate solution for these technological advancements. The proposed system integrates cutting-edge technologies to create a smart interconnected library ecosystem. Object Oriented Design Methodology was used as the software engineering technique, the proposed system leverages classification tree-based cataloging, a hierarchical organization method that enhances the accessibility and navigability of library collections. JavaScript, PHP, HTML, CSS, and XML technologies are integrated to develop an intuitive and interactive user interface for the library management system, XAMMP was later used as local server environment to utilize the automation. The system boasts various advanced functions, such as automatic lending and returning of books, shelf monitoring, and cataloging for resource accessibility assurance. By integrating these features into a comprehensive library management solution, it enables proficient utilization with intellectuality sustainability on par with the modern digital era standards.

WebCM: A Web-Based Platform for Multiuser Individual-Based Modeling of Multicellular Microbial Populations and Communities.

WebCM is a web platform that enables users to create, edit, run, and view individual-based simulations of multicellular microbial populations and communities on a remote compute server. WebCM builds upon the simulation software CellModeller in the back end and provides users with a web-browser-based modeling interface including model editing, execution, and playback. Multiple users can run and manage multiple simulations simultaneously, sharing the host hardware. Since it is based on CellModeller, it can utilize both GPU and CPU parallelization. The user interface provides real-time interactive 3D graphical representations for inspection of simulations at all time points, and the results can be downloaded for detailed offline analysis. It can be run on cloud computing services or on a local server, allowing collaboration within and between laboratories.

Establishing a Generic Geographic Information Collection Platform for Heterogeneous Data

Geographic information collection platforms are widely used for acquiring geographic information. However, existing geographic information collection platforms have limited adaptability and configurability, negatively affecting their usability. They do not support complete field collection workflows or capture data with complex nested structures. To address these limitations, this paper proposes a generic geographic information collection platform based on a comprehensive XML schema definition and a corresponding XML toolkit. This platform includes professional and non-professional versions of collection software, as well as a management system. Users can configure controls and define nested tables within this platform to collect heterogeneous and complex nested data. Moreover, the platform supports functions such as task assignment, local deployment servers, multitasking parallelism, and summary statistics of heterogeneous data, ensuring complete workflow support for field data collection. The platform has been applied in agriculture, forestry, and related fields. This paper uses the agricultural industry structure survey as a case study. Practical applications and our case study show that this platform can reduce software development costs, lower user knowledge prerequisites, and fulfill 95% of geographic information collection scenarios.

Blockchain-enabled intelligent toll management system

Abstract Road toll tax contributes significantly in the economic development of any nation. In developing countries, the toll tax collection is carried out either manually or electronically. However, both approaches suffer from various challenges, including prolonged waiting times, lack of transparency, high operational costs, and concerns regarding data security and privacy. This research aims to address these challenges using a blockchain-based system. The proposed system employs advanced image processing techniques, specifically “You Only Look Once” version 5 (YOLOv5), to accurately capture and store vehicles’ registration numbers in a local server situated at toll plazas. Subsequently, the vehicle identification, along with the driver’s credentials, is transmitted to an application server, where an Ethereum smart contract verifies the information and automatically deducts the toll charges from the driver’s account. The results from this study indicate that the proposed system effectively reduces vehicle waiting time and facilitates uninterrupted vehicular movement. Additionally, the system ensures transaction transparency, safeguards the security and privacy of vehicle details, facilitates non-stop payments, rendering unnecessary cash payments or radio-frequency identification scanning at toll booths, and incorporates a decentralized architectural framework to enhance security and mitigate potential system failures.

Off-Grid Electric Vehicle Charging Station with Integrated Local Server OCPP Protocol as a Management System

Abstract Electric vehicles are widely regarded as pivotal in driving the sustainability of transportation networks forward, thanks to their capacity to diminish carbon emissions, enhance air quality, and bolster the robustness of electricity grids. The accessibility of charging infrastructure and the subjective norms that endorse electric mobility actively shape the electric vehicles acceptance. In this study, Our main goal is to provide off-grid electric vehicle charging infrastructures and the data communication protocols that connect to servers. We analyze the specifications of the OCPP (Open Charge Point Protocol) with an emphasis on its applicabillity for electric charging stations for vehicles. Our research concludes that off-grid electric vehicle charging systems can be effectively applied to small electric vehicles such as electric motorcycles, scooters, and bicycles. The OCPP data communication protocol can also support interactions between small electric vehicle charging stations and central server management systems (CSMS). Furthermore, we tested the electric vehicle charging process for a duration of two hours, and the charging station consistently produced stable voltage, current, and power output, matching the inverter outputs and fulfilling the specifications required by electric vehicle charging adapters. Analysis of throughput data indicates a positive correlation between the number of operational ports at a charging station and the volume of data processed by the server. However, beyond a certain threshold a decline in data transactions was observed, attributable to data loss.

An enhanced image based mobile deep learning model for identification of Newcastle poultry disease

An enhanced mobile deep learning model based on images is presented in this paper to identify Newcastle poultry disease. A dataset of manually annotated and labeled images of the disease was utilized to pre-train an image-based Convolutional Neural Network (CNN). An Android smartphone app was developed to communicate with the model. A local server was integrated with the generated model to do image classification. A mobile application was developed and made available, enabling users to upload a fecal photograph to a website housed on the streamlet server and obtain the model's processed findings. The user regains control over their health status. The model achieved an accuracy of 95% on the test set and was able to correctly identify specific instances of Newcastle poultry disease. The paper discusses the advantages of a mobile-based approach in comparison to traditional methods of identification and proposes the model as an effective low-cost solution for farmers and researchers.

Exploring the Feasibility of Deploying Technology Enhanced School-Based Teacher Continuous Professional Development in Internet-Limited Environments in Tanzania

In low-income countries, the use of technology to enhance teacher continuous professional development (TCPD) activities has been increasing significantly. However, most technology initiatives related to TCPD require the installation of complex information and communications technology (ICT) infrastructure in schools or availability of reliable Internet connectivity. While installation of ICT infrastructure is costly, the cost of the Internet is unaffordable to most teachers in low-income countries. This study explored the feasibility of deploying Raspberry Pi computers and tablets as micro-servers to facilitate school-based TCPD activities via a learning management system (LMS) without Internet connectivity. Teachers in eight schools in Dar es Salaam and Lindi accessed a TCPD sample module with Raspberry Pi and tablets providing hotspotting and treated as offline local servers hosting a LMS. After the trial, data was collected through focus group discussion, observation, and LMS logs involving 69 teachers. The findings showed that both Raspberry Pi and tablets could be used as micro-servers to provide access to learning resources in offline environments, but Raspberry Pi fared more favorably. Raspberry Pi was easy to set up and connected more devices than did the tablet. However, Raspberry Pi required careful handling as it is a delicate device. Interestingly, there was no significant difference in terms of the performance and cost of the two micro-servers. This study provided further evidence that both Raspberry Pi and tablets could be cost-effective approaches to deliver TCPD activities without installing complex ICT infrastructure or in areas with limited Internet connectivity.

Optimization of Energy Efficiency for Federated Learning over Unmanned Aerial Vehicle Communication Networks

Federated learning (FL) is considered a promising machine learning technique that has attracted increasing attention in recent years. Instead of centralizing data in one location for training a global model, FL allows the model training to occur on user devices, such as smartphones, IoT devices, or local servers, thereby respecting data privacy and security. However, implementing FL in wireless communication faces a significant challenge due to the inherent unpredictability and constant fluctuations in channel characteristics. A key challenge in implementing FL over wireless communication lies in optimizing energy efficiency. This holds significant importance, especially considering user devices with restricted power resources. On the other hand, unmanned aerial vehicle (UAV) technologies present a cost-effective solution owing to flexibility and mobility compared to terrestrial base stations. Consequently, the deployment of UAV communication in FL is viewed as a potential approach to deal with the energy efficiency challenge. In this paper, we address the problem of minimizing the total energy consumption of all user equipment (UE) during the training phase of FL over a UAV communication network. Our proposed system facilitates UE to operate concurrently at the same time and frequency, thereby improving bandwidth utilization efficiently. In this paper, we address the problem of minimizing the total energy consumption during the training phase of FL over a UAV communication network. To deal with the proposed nonconvex problem, we propose a novel alternating optimization approach by dividing the problem into two suboptimal problems. We then develop iterative algorithms based on the inner approximation method, yielding at least one locally optimal solution. The numerical results demonstrate the superiority of the proposed algorithm in solving the proposed problem compared to other benchmark algorithms, particularly in determining the optimal trajectory of the UAVs. In addition, we conduct extensive experiments to evaluate how different parameter settings affect performance after implementing the proposed optimization approaches for deploying FL within the UAV communication system. These analyses yield valuable insights into the comparative effectiveness of the proposed optimization algorithms concerning overall energy consumption reduction.

Desktop as a Service using Local Computers

Abstract: Desktop-as-a-Service (DaaS) has gained prominence as a cloud-based solution for delivering desktop environments to users. However, traditional DaaS models often rely on remote data centers, posing concerns regarding data security, latency, and dependence on external infrastructure. In this paper, we propose a paradigm shift by introducing a novel approach to DaaS that leverages the untapped potential of local computing resources.Our system harnesses the idle computing power available within the user's local environment, including desktops, laptops, and servers, to create a distributed DaaS platform. By integrating virtualization technologies and dynamic resource allocation strategies, we enable the provisioning of desktop environments ondemand, effectively reducing the reliance on centralized data centers. Key components of our system include a centralized management platform for orchestrating resource allocation and workload distribution, virtualization techniques for isolating and managing desktop instances, and robust security measures to safeguard sensitive data. Through experimental validation, we demonstrate the feasibility and performance of our approach, showcasing improvements in data privacy, latency reduction, and resource utilization compared to traditional DaaS models. Our research presents a significant step towards decentralized and resilient computing ecosystems, offering users greater control over their desktop environments while maintaining the scalability and accessibility inherent to DaaS paradigms

Performance analysis of a blockchain enabled domestic power consumption monitoring and forecasting system

Purpose The purpose of this paper is to develop a blockchain-based data capture and transmission system that will collect real-time power consumption data from a household electrical appliance and transfer it securely to a local server for energy analytics such as forecasting. Design/methodology/approach The data capture system is composed of two current transformer (CT) sensors connected to two different electrical appliances. The CT sensors send the power readings to two Arduino microcontrollers which in turn connect to a Raspberry-Pi for aggregating the data. Blockchain is then enabled onto the Raspberry-Pi through a Java API so that the data are transmitted securely to a server. The server provides real-time visualization of the data as well as prediction using the multi-layer perceptron (MLP) and long short term memory (LSTM) algorithms. Findings The results for the blockchain analysis demonstrate that when the data readings are transmitted in smaller blocks, the security is much greater as compared with blocks of larger size. To assess the accuracy of the prediction algorithms data were collected for a 20 min interval to train the model and the algorithms were evaluated using the sliding window approach. The mean average percentage error (MAPE) was used to assess the accuracy of the algorithms and a MAPE of 1.62% and 1.99% was obtained for the LSTM and MLP algorithms, respectively. Originality/value A detailed performance analysis of the blockchain-based transmission model using time complexity, throughput and latency as well as energy forecasting has been performed.

Multi-cell content caching: Optimization for cost and information freshness

In multi-access edge computing (MEC) systems, there are multiple local cache servers caching contents to satisfy the users’ requests, instead of letting the users download via the remote cloud server. In this paper, a multi-cell content scheduling problem (MCSP) in MEC systems is considered. Taking into account jointly the freshness of the cached contents and the traffic data costs, we study how to schedule content updates along time in a multi-cell setting. Different from single-cell scenarios, a user may have multiple candidate local cache servers, and thus the caching decisions in all cells must be jointly optimized. We first prove that MCSP is NP-hard, then we formulate MCSP using integer linear programming, by which the optimal scheduling can be obtained for small-scale instances. For problem solving of large scenarios, via a mathematical reformulation, we derive a scalable optimization algorithm based on repeated column generation. Our performance evaluation shows the effectiveness of the proposed algorithm in comparison to an off-the-shelf commercial solver and a popularity-based caching.

SMART BUILDING CONTROL THROUGH INTERNET OF THINGS/MACHINE-TO-MACHINE DEVICE MANAGEMENT VIA HETEROGENEOUS WIRELESS NETWORKS

The increasing use of wireless communication technologies has made IoT and machine-to-machine (M2M) connections crucial to a wide range of industries. Smart buildings are an excellent example of an IoT/M2M application. Issues such as a lack of a convergent solution, high costs, restricted wireless transmission range, user-unfriendly interfaces, and the inability to integrate IoT and M2M technologies. Consequently, this article suggests a more effective method for for Machine-to-Machine (M2M) and The Internet of things smart building systems: heterogeneous wireless networks that include both WSNs and MCNs. The suggested system is a cost-effective embedded system that includes Several functional actuators, sensors, and modules for Arduino and NodeMCU, ESP32CAM boards allow for data collection and control across a variety of heterogeneous communication methods like Bluetooth, Wi-Fi, and global system for Mobile (GSM). All collected data is issued to the ThingSpeak platform, allowing the building system to be monitored via the Thing Speak webpage or the UR Smarthome app. One of the researchs most important results is that it can give the server precise information with extremely little delay, allowing users to quickly control and monitor remotely the proposed system that consists of several innovative services names indoor applications(fire detection and gas leakage detection, intrusion alarm by ultrasonic, medicine reminder by RTC module, light and fan control, smart door) and outdoor applications(garden irrigation by soil moisture and DHT11, air quality, smart parking ). Our free mobile application UR Smarthome, which is a local server that controls and monitors the building from a distance, is used to plan and execute all of these services that provides remote control and monitor of the building via Bluetooth/ Cellular networks and Wi-Fi access. With its customizable features, this IoT/M2M smart building system can be tailored to the demands of its users, enhancing their quality of life and safety while using less energy. In addition, identifying and lowering risks, it assists in preventing the loss of resources and human lives. KEYWORDS— Converged networks, heterogeneous networks (HetNets), Internet of Things (IoT)/machine-to-machine (M2M), mobile application, mobile cellular networks (MCNs), smart building, wireless sensor networks (WSNs)

Designing an Internet of Things solution for monitoring vital signs

The object of study is the process of monitoring vital signs using an automated system based on an Internet of Things (IoT) solution. The study investigates and analyses the best existing solutions for continuous monitoring of human health. The research is important in the context of a possible pandemic and general health monitoring. An IoT model of a solution for monitoring and analyzing vital signs in patients is proposed. The project involves the creation of hardware and software for tracking vital signs. The interaction of the two parts will ensure that the main task is to obtain the result and analyze the indicators of vital functions of the human body. The hardware is implemented using devices for scanning data on heart rate, temperature, saturation, and the ability to track electrocardiograms. It is possible to transmit data on the state of the body. The position of the sensors attached to the body is taken into account in case they come off. The device itself should be placed on the human body in the area of the front chest wall, wrists, and ankles. The device is also programmed to respond to sudden changes in these values. The software implementation is based on a web-based interface. The design of the final solutions for the interaction between the local and intermediate server was implemented using Django and Python. The ability to administer the intermediate server of the client's time zone was written using HTML, CSS, and JavaScript. The use of the IoT solution allows monitoring the indicators of vital functions of the body and their analysis. A scheme of information exchange in the system for monitoring health indicators has been built.

The Red Cross Red Crescent Health Information System (RCHIS): an electronic medical records and health information management system for the red cross red crescent emergency response units

BackgroundThe Red Cross and Red Crescent Movement (RCRC) utilizes specialized Emergency Response Units (ERUs) for international disaster response. However, data collection and reporting within ERUs have been time-consuming and paper-based. The Red Cross Red Crescent Health Information System (RCHIS) was developed to improve clinical documentation and reporting, ensuring accuracy and ease of use while increasing compliance with reporting standards.Case presentationRCHIS is an Electronic Medical Record (EMR) and Health Information System (HIS) designed for RCRC ERUs. It can be accessed on Android tablets or Windows laptops, both online and offline. The system securely stores data on Microsoft Azure cloud, with synchronization facilitated through a local ERU server. The functional architecture covers all clinical functions of ERU clinics and hospitals, incorporating user-friendly features. A pilot study was conducted with the Portuguese Red Cross (PRC) during a large-scale event. Thirteen super users were trained and subsequently trained the staff. During the four-day pilot, 77 user accounts were created, and 243 patient files were documented. Feedback indicated that RCHIS was easy to use, requiring minimal training time, and had sufficient training for full utilization. Real-time reporting facilitated coordination with the civil defense authority.ConclusionsThe development and pilot use of RCHIS demonstrated its feasibility and efficacy within RCRC ERUs. The system addressed the need for an EMR and HIS solution, enabling comprehensive clinical documentation and supporting administrative reporting functions. The pilot study validated the training of trainers’ approach and paved the way for further domestic use of RCHIS. RCHIS has the potential to improve patient safety, quality of care, and reporting efficiency within ERUs. Automated reporting reduces the burden on ERU leadership, while electronic compilation enhances record completeness and correctness. Ongoing feedback collection and feature development continue to enhance RCHIS’s functionality. Further trainings took place in 2023 and preparations for international deployments are under way. RCHIS represents a significant step toward improved emergency medical care and coordination within the RCRC and has implications for similar systems in other Emergency Medical Teams.

DRL-empowered joint batch size and weighted aggregation adjustment mechanism for federated learning on non-IID data

To address the accuracy degradation as well as prolonged convergence time due to the inherent data heterogeneity among end-devices in federated learning (FL), we introduce the joint batch size and weighted aggregation adjustment problem, which is non-convex problem. To adjust optimal hyperparameters, we develop deep reinforcement learning (DRL) to empower a mechanism known as Batch size and Weighted aggregation Adjustment (BWA). Experimental evaluation demonstrates that BWA not only outperforms methods optimized solely from either a local training or server perspective but also achieves higher accuracy, with an increase of up to 5.53% compared to FedAvg, and additionally accelerates convergence speeds.

A deep learning-based approach for predicting COVID-19 diagnosis

This paper focuses on forecasting the total count of confirmed COVID-19 cases in Saudi Arabia through a range of methodologies, including ARIMA, mathematical modeling, and deep learning network (DQN) techniques. Its primary aim is to anticipate the verified COVID-19 cases in Saudi Arabia, aiding in decision-making for life-saving interventions by enhancing awareness of COVID-19 infection. Mathematical modeling and ARIMA are employed for their efficacy in forecasting, while DQN approaches, particularly through comparative analysis, are utilized for prediction. This comparative analysis evaluates the predictive capacities of ARIMA, mathematical modeling, and DQN techniques, aiming to pinpoint the most reliable method for forecasting positive COVID-19 cases. The modeling encompasses COVID-19 cases in Saudi Arabia, the United Kingdom (UK), and Tunisia (TU) spanning from 2020 to 2021. Predicting the number of individuals likely to test positive for COVID-19 poses a challenge, requiring adherence to fundamental assumptions in mathematical and ARIMA projections. The proposed methodology was implemented on a local server. The DQN algorithm formulates a reward function to uphold target functional performance while balancing training and testing periods. The findings indicate that DQN technology surpasses conventional approaches in efficiency and accuracy for predictions.