2023 International Conference on Smart Applications, Communications and Networking (SmartNets)最新文献

{"title":"Wildfire Classification Using Infrared Unmanned Aerial Vehicle Data with Convolutional Neural Networks","authors":"Rahmi Arda Aral, Cemil Zalluhoğlu, E. Sezer","doi":"10.1109/SmartNets58706.2023.10215891","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10215891","url":null,"abstract":"Forest fires can spread briskly to large-scale areas after they happen. Thus, early detection and intervention are of great importance. Unmanned aerial vehicles (UAVs) are beneficial technologies used for forest fire detection. Since flames emit very high heat and energy into their surroundings, they can be identify easily through the electro-optic infrared cameras mounted on UAVs as payloads. Detection of forest fires via UAVs has been performed by human observation in ground control stations. Convolutional Neural networks, which is effectual deep learning algorithms, are eligible for wildfire detection with UAV vision data. This paper presents a CNN based deep learning approach to the task of forest fire detection performed by human observation. We implemented state-of-art neural networks as feature extractors to the determined architecture to achieve adequate results. In the experiments, a UAV collected infrared forest fire images were used as the dataset. The experiment result clearly showed that our approach performed sufficiently on the dataset. The ResNet101-based architecture achieved the highest results in all evaluation metrics. It has confirmed itself to be the most efficient alternative with 99.20% test accuracy.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133760295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Analysis of Machine Learning Methods for Multi-Year CVD Prediction","authors":"A. A. Gozali","doi":"10.1109/SmartNets58706.2023.10215621","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10215621","url":null,"abstract":"Cardiovascular diseases (CVDs) significantly contribute to global mortality, and early detection is crucial for preventing severe complications and reducing mortality rates. Machine learning (ML) has emerged as a promising tool for predicting heart disease using various medical data sources. However, most studies have focused on predicting the risk of heart disease at a single point in time, and there is a need for a model that can predict the long-term risk of heart disease. This study aims to address this gap by comparing the performance of eight different ML algorithms for predicting heart disease over one, two, and three-year periods. The first experiment found that the decision tree machine learning technique was the most effective in terms of run-time speed compared to the other techniques. The second experiment utilized the decision tree model and found that it could predict CVD with high accuracy up to four years in advance.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"10 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139354911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparative study of machine learning approaches for heart stroke prediction","authors":"M. Das, Fatema Tabassum Liza, Partha Pratim Pandit, Fariha Tabassum, Miraz Al Mamun, Sharmistha Bhattacharjee, Md Shakil Bin Kashem","doi":"10.1109/SmartNets58706.2023.10216049","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10216049","url":null,"abstract":"The majority of strokes are triggered by the heart and brain blocking expected pathways. Today, it is the most common cause of death in the worldwide. By looking at the people affected, several risk elements that are thought to be connected to the stroke's cause have been determined. Numerous studies have been conducted for the prediction and categorization of stroke diseases using these risk variables. Similar to any diseases, an early diagnosis of a stroke can avert such occurrences and open the door to a healthy life. Machine learning (ML) techniques have been used in this study to accurately determine heart attacks. In order to determine multiple matrices like accuracy, recall, ROC, precision, and F1 score, we used nine different machine learning algorithms in this study, which include support vector machines (SVM), K-nearest neighbor (KNN), XGBoost, AdaBoost, Random Forest (RF), Decision Tree, LightGBM, and Logistic Regression. The results indicate that the Random Forest method outperformed the others with an accuracy of 98.4%.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"33 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139355148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and Implementation of Proactive Multi-Type Context-Aware Recommender System for Patients Suffering Diabetes","authors":"A. Abu-Issa, S. Hajjaj, S. Al-Jamal, D. Barghotti, A. Awad, M. Hussein, Iyad Tumar, Abualsoud Hanani","doi":"10.1109/SmartNets58706.2023.10216111","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10216111","url":null,"abstract":"This paper presents a design and implementation of a multi-type, proactive and context-aware recommender system that supports a healthy lifestyle for patients who suffer Diabetes mellitus. The main features of this recommender system includes the consideration of users’ context while generating recommendations, its ability to recommend multi-types in the same time. The recommendation types include food, drink, physical exercise, and medication. Furthermore, the proposed recommender system is proactive, where the recommendations are pushed to the users, based on the context, without explicit query by them. A prototype was developed for the system, as well as simple Android mobile application. Artificial Neural Network was used to train the system. The results show an overall accuracy of 89.5%.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123069205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable AI-Based Malicious Traffic Detection and Monitoring System in Next-Gen IoT Healthcare","authors":"Ece Gürbüz, Özlem Turgut, Ibrahim Kök","doi":"10.1109/SmartNets58706.2023.10215896","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10215896","url":null,"abstract":"In recent years, there has been a surge in IoT healthcare applications, ranging from wearable health monitors and remote patient monitoring systems to smart medical devices, telemedicine platforms, and personalized health tracking and management tools. The purpose of these applications is to improve treatment outcomes, streamline healthcare delivery, and enable data-driven decision-making. However, due to the sensitive nature of health data and the critical role that these applications play in people’s lives, ensuring their security and privacy has become a paramount concern. To address this issue, we developed an explainable malicious traffic detection and monitoring system based on Machine Learning (ML) and Deep Learning (DL) models. The proposed system involves the use of Explainable Artificial Intelligence (XAI) methods such as LIME, SHAP, ELI5, and Integrated Gradients(IG) to ensure the interpretability and explainability of the developed models. Finally, we demonstrate the high accuracy of the developed models in detecting attacks on the intensive care patient dataset. Furthermore, we ensure the transparency and interpretability of the model outcomes by presenting them through the Shapash Monitor interface, which can be easily accessed by both experts and non-experts.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122027532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Applications in MIMO Systems","authors":"Ali J. Almasadeh, Khawla A. Alnajjar, M. Albreem","doi":"10.1109/SmartNets58706.2023.10215957","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10215957","url":null,"abstract":"Deep learning has emerged as a promising approach to tackle the challenges in multiple-input and multiple-output (MIMO) systems and has demonstrated its potential to improve system performance significantly. This paper studies two main applications that can improve the MIMO system performance and spectrum utilization. The first proposed application is an algorithmic approximation used to reduce computational complexity and time taken by known algorithms. The second application is used for the inversion of unknown functions in a system and channel estimation. This paper reviews several use cases of DL in MIMO systems, including channel estimation, precoding, and beamforming. We investigate the application of deep learning through neural networks to address different challenges in MIMO systems. We highlight the benefits and enhancements of deep learning compared to conventional methods and demonstrate how it can improve the performance of MIMO systems.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121718409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A High-Capacity 4-Port MIMO Antenna for 5G and 6G Devices","authors":"K. S. Muttair, O. A. Al-Ani, Ahmed Mahmood Farhan, M. Mosleh, H. B. Taher, Ali Z. Ghazi Zahid, A. Diwan, Raed H. C. Alfilh","doi":"10.1109/SmartNets58706.2023.10215739","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10215739","url":null,"abstract":"A fundamental supporting technology for wireless systems of communication is the multi-input multi-output (MIMO) antenna. In this article, we propose a newly developed quad-element MIMO antenna design for a variety of modern applications such as mobile phones, the Internet of Things (IoT), and telecommunication technologies. So, we presented the design of this antenna in two stages. The first stage was to design the antenna simulation using CST Studio Suite. The second stage is actually manufacturing the antenna. This antenna serves all sophisticated wireless technology applications since it operates at many frequencies ranging from 1 to 20 GHz. This antenna is characterized by its small size, so its dimensions are 28×28×1.6 mm3. The antenna’s performance is good based on CST Studio Suite results and manufacturing in engineering laboratories since the antenna’s reflection coefficients resonate at six major frequencies at 4, 8, 12, 14, 18, and 20 GHz. In addition, the isolation value between elements in the MIMO configuration is ⩽ -35 dB, and the highest gain is 10 dB. While the overall efficiency is between 75% to 100%. Finally, the results indicate that the simulated antenna design matches perfectly with the real antenna manufactured due to the precision manufacturing strategy described in this article.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128015900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Low-cost IoT Mobile System for Air Quality Monitoring in Developing Countries, a Study Case in El Salvador","authors":"O. O. Flores-Cortez, Carlos Pocasangre Jimenez, Fernando Arévalo, Ricardo León López, David Peña Martínez, Oscar Rafael","doi":"10.1109/SmartNets58706.2023.10215961","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10215961","url":null,"abstract":"Air pollution is an undeniable environmental hazard that poses a severe threat to human health. Its sources are manifold, ranging from factories, and vehicles, to and burning of fossil fuels. The Ministerio de Medio Ambiente y Recursos Naturales (MARN) is the state institution responsible for monitoring air quality in El Salvador. However, the current capacity of MARN is insufficient, as it only has three stations for the entire country. The Pan American Health Organization (PAHO) has acknowledged this situation, and has categorized El Salvador as a country without the ability to monitor air quality adequately. We propose a methodology for the design and implementation of a mobile IoT system to monitor air quality. The IoT system monitors critical air quality parameters such as particle matter (PM1.0, PM2.5, PM10), Formaldehyde (HCHO), temperature, and relative humidity. Besides, we present a low-cost IoT architecture that can be implemented in developing countries. The IoT system is composed by IoT nodes for the real-time measurement of air quality parameters, and an IoT data platform. The IoT node is based on an ESP32 microcontroller, a SIM800L GSM board, and a PMS5003ST air quality sensor. Google App Services tools are utilized as the IoT web platform and cloud data storage. The outcome of this work is a prototype of a mobile IoT system to monitor four air pollutants through graphical web dashboards. The results obtained in preliminary field tests have been satisfactory and show that the proposed approach is an efficient and low-cost option. As a field test of the proposed IoT system, we deployed three IoT nodes in different cities in El Salvador, namely San Salvador, Santa Ana, and Cojutepeque for one month. Comparing PM data reported with respect to the limits of the Central American Air Quality Index (CAQI), the air quality in the studied cities is mainly in the good to moderate range.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124455503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced Edge to Cloud system architecture for Smart Real-Time water quality monitoring using cutting-edge portable IoT biosensor devices","authors":"Marios Charalampides, Theodoros Bozios, D. Tsoukalas, Sotirios Ntouskas, S. Chatzandroulis, E. Skotadis, Evangelos Aslanidis, Themistoklis Sfetsas, Georgia Dimitropoulou, G. Tsekenis, Georgios Samaras","doi":"10.1109/SmartNets58706.2023.10216198","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10216198","url":null,"abstract":"Heavy metal ions are amongst the most toxic elements that can be found in water. Dangerous contamination of water with heavy metal ions must be identified as quickly and reliably as possible and the relevant information must reach immediately and reliably those who need it (government bodies, local authorities, scientists, citizens) for prevention, taking the appropriate measures and further analysis. In this paper we present the approach of the MICSYS research project for an advanced edge to cloud system architecture for smart real-time water quality monitoring using cutting-edge portable IoT biosensor devices. The paper analyzes the implementation of this architecture, its evaluation criteria and methodology as well as its initial evaluation. The architecture ensures speed, reliability and general availability of measurements, moves processing as close as possible to the data sources, while taking advantage of the computing power on the path from the edge device to the cloud. The significant computing capabilities of the cloud can be used for further analysis of the raw data from the measuring devices using Artificial Intelligence (AI) technologies to refine the estimation algorithms of concentrations, find contamination trends in different areas and estimate future contamination risks.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124676778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Efficient Massive MIMO Detector Based on Deep Learning and Approximate Matrix Inversion Methods","authors":"Ali Ahmad Suliman, Ahmad Bassim Humaidi, Mohammed Eid Eid, M. Albreem, Samreen Ansari","doi":"10.1109/SmartNets58706.2023.10215680","DOIUrl":"https://doi.org/10.1109/SmartNets58706.2023.10215680","url":null,"abstract":"The use of massive multiple-input multiple-output (mMIMO) technology is essential for the fifth-generation (5G) and sixth-generation (6G) networks. However, the computational complexity of detection techniques and approximation methods can be high due to matrix inversion. Deep learning (DL) has been proposed as a tool to improve the efficiency of massive MIMO systems. This study proposes a hybrid-based low-complexity detector employing deep learning and approximate matrix inversion. The Richardson method and multi-scale multi-skip connection network (MMNet) form the presented hybrid detection framework. The output of the first iteration of approximate matrix inversion methods is fed into the MMNet algorithm in order to obtain superior performance. The results are compared with the MMSE-based and conventional MMNet-based detectors to determine/benchmark the performance. The simulation results and benchmarks with an MMSE-based and conventional MMNet-based detectors further designate that employing the proposed model significantly enhances the detection performance.","PeriodicalId":301834,"journal":{"name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131389382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}