{"title":"Analysis and Predictive Modeling of Traffic Incidents in Karachi using Machine Learning","authors":"S. Batool, M. A. Ismail, Shabbar Ali","doi":"10.1109/HONET53078.2021.9615390","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615390","url":null,"abstract":"Road traffic accidents have accounted to extremely dense road traffic and the relatively great freedom of movement given to drivers. Due to the increasing traffic accidents in Karachi, it is vital to investigate the major parameters that are causing these fatalities. For this purpose, machine learning techniques provide a greater advantage over other statistical methods. In this research, a novel approach that applies Random Forest and Support vector machine (SVM) algorithm out of many different machine learning algorithms for modeling traffic accidents prediction. Empirical results show that reasonable accuracy of the developed model. The results further showed the accuracy fluctuated according to the number of attributes in the output parameter. The results of SVM showed better predictions than that from Random Forest. The parameter with less attributes like Disposal has higher accuracy of prediction with Random Forest 83.12% whereas those with greater number of attribute have higher prediction accuracy with SVM e.g. Months with 64.98%.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122444944","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":"eBiometrics: Data acquisition and Physiological Sensing","authors":"R. Splinter","doi":"10.1109/HONET53078.2021.9615465","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615465","url":null,"abstract":"Biometric sensing has critical challenges in both mechanical design as well as sensor selection. The main issues however lie in the signal acquisition (accuracy and reproducibility) and signal processing to find the derived physiological value and at what ultimate accuracy. The association with biological parameters of clinical interest are under the influence of external factors. The external factors include electromagnetic impacts which can modify the outcome of the signal processing or may reset the operational processes of the device to a state of disorder. It is imperative to consider all factors contributing to the accuracy and validity of the output.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132200303","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":"The Performance of Deep and Conventional Machine Learning Techniques for Skin Lesion Classification","authors":"Farzad Shahabi, A. Rouhi, Reza Rastegari","doi":"10.1109/HONET53078.2021.9615400","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615400","url":null,"abstract":"Skin lesion is any abnormalities occurring to the skin's tissue in terms of size, texture, shape, and color. It can be a sign of autoimmune disorders, diabetes, etc. It can be a potentially huge threat to human health leading to skin cancer if not diagnosed early enough and treated. In this paper, we studied how machine learning algorithms can help detect Skin Lesion based on the images in Skin Legion dataset. Our study highlights the effectiveness of deep learning algorithms by utilizing the state-of-the-art CNN models which performed better in terms of classification performance than ML traditional methods comparatively.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"4174 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127566591","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}
T. Javid, M. Faris, Muhammad Danish Mujib, Tayyab Ahmed Ansari, H. Iftikhar, Tayyaba Khalid, Wardah Saadat
{"title":"Cardiac Coronary Intervention Simulator","authors":"T. Javid, M. Faris, Muhammad Danish Mujib, Tayyab Ahmed Ansari, H. Iftikhar, Tayyaba Khalid, Wardah Saadat","doi":"10.1109/HONET53078.2021.9615446","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615446","url":null,"abstract":"Simulators are used in numerous disciplines to accomplish various tasks. These simulators provide excellent and unique insights into complex environments to successfully plan improvements in typical setups. Training simulators support learning with a lower cost and focus on achieving better results. This paper presents designing and developing a cardiac coronary interventions simulator with vital functions of computing and animation. This simulator is integrated hardware that implements the compute model and a software system that deploys the animate model. The developed simulator is designed for novice cardiac surgeons that learn complex coronary intervention procedures. A plastic tube is used to mimic a catheter wire. The catheter wire movements are converted to single digits through the compute model. These values are transferred to the animate model that maps each value to a line segment for visualization. A comparison based on twenty features with recent state-of-the-art works found in literature shows the proposed simulator provides a feature-rich medical device. Additionally, the simulator with few modifications is a potential artificial intelligence internet of things device.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129494172","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":"Implementing Multilevel Inverters and Multiport DC-DC Converters for Microgrids","authors":"Miguel Herrera, Afshin Balal","doi":"10.1109/HONET53078.2021.9615472","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615472","url":null,"abstract":"Microgrids are in great demand owing to their ability to enhance generation power and distribute electricity to local loads. Microgrids include renewable energy sources, DC-DC converters, batteries, and DC-AC inverters. Multiport converters and multilevel inverters are proposed for the conversion process in this paper. The cost and size of the entire system are reduced when a multiport DC-DC converter is used. Furthermore, employing conventional inverters results in an output voltage that is unstable and unsynchronized with the power grid. A multilevel inverter using the Phase Lock Loop (PLL) method is utilized to solve this problem. The suggested approach generates a pure sinusoidal output voltage while saving money and space.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125375861","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":"Intelligent Traffic Handling System Using Point Tracker Algorithm","authors":"Wania Tahir, R. A. Wagan, Bushra Naeem","doi":"10.1109/HONET53078.2021.9615479","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615479","url":null,"abstract":"Now a days road traffic is major issue of developing and under developing countries. With the rampant increase of traffic, the society faces major traffic threats including life threats and environmental threat, thus traffic management is gruesome problem to address. The consequences of poor traffic management include road accidents, jamming of traffic, pollution and many more that can be life threatening. Keeping in view the deadlock and congestion in traffic, this work provides solution by indigently detecting and prioritizing the vehicles and non-vehicles. The research involves implementation of Point Tracker Algorithm. Further, the algorithms are enhanced by improving traffic management in terms of identifying category of transport, prioritizing the traffic which contains vehicle and non-vehicles on basis of size of vehicle, type of vehicle, emergency situation and provide the priority to resolve the deadlock. Further, the proposed enhanced Point Tracker Algorithm includes the emergency detection in case of accident and provide an alternative route to neighboring vehicles and non-vehicles.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116865167","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":"Machine Learning Approach For Classification of DHCP DoS Attacks in NIDS","authors":"Shameel Syed, Faheem Khuhawar, Shahnawaz Talpur","doi":"10.1109/HONET53078.2021.9615392","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615392","url":null,"abstract":"Network Intrusion Detection System (NIDS) is used to detect anomalous activities that occur in the network, whether the activity arises from outside or from inside. An extensive amount of studies have been done in the domain of NIDS using Machine Learning, Deep Learning, and Reinforcement Learning based techniques on publicly available datasets. The main problem lies in publicly available datasets as the datasets are un-realistic and too general for real-life events and attacks and thus the models trained may produce better results during the training and testing phase but once it is deployed in the real network, most of the attacks may go undetected. This research focuses on a specific protocol “Dynamic Host Control Protocol” which is enabled in most of networks whether the network is small, medium or large. In this research, DHCP specific dataset was generated and trained with different classifiers to analyze their performance. Random Forest classifier presented better results among other classifiers.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"261 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127101876","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":"Implement an efficient multi-loop control scheme using rapid estimating filters to compensate for a variety of voltage drops","authors":"Hossein Mirzanejad, Shahaboddin Sadeghi, Ehsan Salajegheh","doi":"10.1109/HONET53078.2021.9615448","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615448","url":null,"abstract":"In this paper, we have discussed a new control design for dynamic voltage recovery (DVR) to obtain a fast response and efficient compensation ability of voltage drop. In this design, the amplitude and phase angle of injected voltage for each phase is controlled separately. Then, phasor parameters of load and supply voltage measured by least square error (LES) filter are estimated in a short time (5 ms). These filters reduce the effect of noise, harmonics, and disorders on estimated parameters. The considered control system does not need a phase-locked loop (PLL), since the angle of measured signals is estimated by LES filters. Besides, separately controlling injected voltage for each phase, help DVR to adjust negative and zero sequence components, as well as positive sequence component. Results of simulation studies in the software environment of PSCAD/EMTDC show that considered control design, first compensate voltage drop for symmetric or unsymmetric errors in a very short time interval without phase jump. Second, perform compensation desirably under conditions of linear and nonlinear load.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130465509","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":"Internet of things Enabling Smart School: An Overview","authors":"Khaula Zeeshan, P. Neittaanmäki","doi":"10.1109/HONET53078.2021.9615391","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615391","url":null,"abstract":"Internet of things (IoT) is making its way in every field of life. Education is not an exception. IoT is making landmark achievements in its applications in the field of education. This paper presents an overview of the key IoT applications in the field of education from the perspective of school management, teachers, and learners enabling smart school concept and challenges and limitations in embarking IoT in educational settings.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130325708","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}
G. F. Mirza, A. Shah, B. S. Chowdhry, T. Hussain, Yahya Sameen Junejo
{"title":"Road Condition Monitoring Using Axle-Based Acceleration Method and K-Means Clustering Algorithm","authors":"G. F. Mirza, A. Shah, B. S. Chowdhry, T. Hussain, Yahya Sameen Junejo","doi":"10.1109/HONET53078.2021.9615460","DOIUrl":"https://doi.org/10.1109/HONET53078.2021.9615460","url":null,"abstract":"Road deterioration remains a major setback if it is not considered significant especially in Pakistan which causes human casualties and massive financial losses. Hence, road condition monitoring is helpful to ensure comfort and safety to drivers on road. The aim of this project is to design an effective low cost Axle-Based Acceleration (ABA) system for road condition monitoring to restrain road accidents and vehicle damages on roads. The prototype consists of NodeMCU (with built-in WIFI) and ADXL335 accelerometer is deployed on the wheel axle of vehicle to follow ABA method. However, the android application mapped with Google Map is designed to collect the location coordinates of the vehicle. This data using Hashmap is then continuously sent to the Firebase database using WIFI module for analysis. ABA methodology easily detects short irregularities efficiently as compared to the sensors mounted on other positions which are unable to capture low frequency vibrations. Firstly, the ABA method is validated in this paper which shows that it is 12.849 % more efficient than the Non-ABA methodology. Thereafter, the collected data (Acceleration, Speed and GPS coordinates of vehicle) on Firebase is analyzed using K-Means clustering algorithm for prediction of faulty location coordinates. Those faulty coordinates are then entered into the database so that the road authorities can fix them before the road condition becomes worst.","PeriodicalId":177268,"journal":{"name":"2021 IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121544282","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}