{"title":"Robotic System Control using Embedded Machine Learning and Speech Recognition","authors":"Joseph M. Phillips, J. Conrad","doi":"10.1109/HONET56683.2022.10019106","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019106","url":null,"abstract":"The focus of this work is to control a computing-resource-constrained robotics system using embedded machine learning (also known as tiny machine learning). The objective of this effort was to develop a potential lab exercise for students in a robotics class, with the goal of giving them a better understanding of how artificial intelligence applications can be used to control a robotics system. This paper discusses the fundamentals of embedded machine learning and the convolution neural network training process used for this project. The dataset used for this project and its preparation for use with the machine learning model is also discussed. An overview of the technology and data used for this project is provided describing hardware features used to control two motors on a robotic system using speech recognition by keyword spotting. Data validation and future improvements of the project related to the speech-controlled system are also discussed.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115838336","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":"Energy Efficient Wireless Communication Utilizing Reinforcement Based Learning","authors":"S. Chakravarty, Madhushri Banerjee, S. Agarwal","doi":"10.1109/HONET56683.2022.10019077","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019077","url":null,"abstract":"IoT devices and battery technology have come to the forefront of a society that acknowledges the need for better, cleaner power management and generation. As these technologies improve, better and more efficient means of wireless communication can extend the longevity of battery power devices and networks. The use of reinforcement learning can spur an even greater improvement in these protocols than traditional means. Experiments show the efficacy of the approach as well as the efficiency achieved using the RL process.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125173900","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":"Modeling of Artificial Intelligence Enabled Crowd Density Classification for Smart Communities","authors":"Mohamed Yasin Noor Mohamed","doi":"10.1109/HONET56683.2022.10019032","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019032","url":null,"abstract":"Smart cities are a contemporary phenomenon to involve information and communication technologies (ICTs) in the advancement of large urban cities. It will be helpful in determining the movement of a city through observing general flow of visitors and traffic jams. Crowd management can be one key aspect of smart cities, assisting in enjoyable and safety experiences for visitors and residents. As crowd density (CD) classification methods encounter difficulties such as inter-scene and intra-scene deviations, non-uniform density, occlusion and convolutional neural network (CNN) methods were valuable. This manuscript designs a wolf pack algorithm with deep learning enabled crowd density classification (WPADL-CDC) model for smart communities. The presented WPADL-CDC technique assists in improving the quality of life in smart community environment. In addition, the presented WPADL-CDC model employs deep convolutional neural network (DCNN) based densely connected network (DenseNet) model for feature extraction purposes. Moreover, the WPA is exploited for the optimal hyper parameter tuning of the DenseNet201 method. Furthermore, fuzzy radial basis neural network (FRBNN) model can be utilized for the identification and classification of CDs in the video surveillance system. For examining the enhanced CD classification outcomes of the presented WPADL-CDC method, a detailed experimental analysis is performed. The experimental values demonstrate the promising performance of the WPADL-CDC model.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127997747","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}
M. Abrishami, S. Dadkhah, Euclides Carlos Pinto Neto, Pulei Xiong, Shahrear Iqbal, S. Ray, A. Ghorbani
{"title":"Label Noise Detection in IoT Security based on Decision Tree and Active Learning","authors":"M. Abrishami, S. Dadkhah, Euclides Carlos Pinto Neto, Pulei Xiong, Shahrear Iqbal, S. Ray, A. Ghorbani","doi":"10.1109/HONET56683.2022.10019152","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019152","url":null,"abstract":"Classification is an essential and important task in Machine Learning (ML). The existence of label noise in training datasets can negatively impact the performance of supervised classification. Due to the growing interest in the data-centric AI that aims at improving the quality of training data without enhancing the complexity of models, there have been a variety of research works to tackle the label noise problem. However, few works have investigated this problem in the IoT network intrusion detection domain. This paper addresses the issue of label noise in the intrusion detection domain by presenting a framework to detect the samples with noisy labels. The decision tree classification algorithm and active learning are the main components of the proposed framework. The use of the framework is composed of two steps: making a decision tree robust against the label noise in a dataset and then using this robust model with the help of active learning with uncertainty sampling to detect noisy samples effectively. In this way, the inherent resiliency of the decision tree algorithm against label noise is utilized to tackle this issue in datasets. Based on the results of our experiments, the proposed framework can detect a considerable number of noisy samples in the training dataset, with up to 98% noise reduction.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126183773","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":"Cybersecurity Risk with Wearable Technology in Sports: Why Should We Care?","authors":"Stefan Andjelić, Callum Doyle, G. Hossain","doi":"10.1109/HONET56683.2022.10019146","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019146","url":null,"abstract":"With technology becoming ever more prevalent in the world of sports, with collecting of data also becoming essential for analysis, the use of wearable medical technology in sports has increased drastically. Take a professional athlete as an example, their use is to track their biodata and optimize their performance. Compared to people who participate in recreational activities, they may simply want to view their BMI, calories burned, and heart rate to help guide them towards a healthier lifestyle. The purpose of this study is to explore the possibilities and limitations due to cybersecurity of wearable technology in sports, and in what, way can it influence athletes, trainers, and an organization. This technology is not limited to performance and health, as it can also help predict sudden cardiac arrests which could ultimately even prevent deaths. Despite all the benefits, like any industry with a large market, there is always the issue of conflicting motives and conflict of interests. This could result in unethical behavior and hinder the research and development of wearable technology for all users including one in the sports, with cyber-risks. Implementing a data governance council who has the best interest for a sports individual's security and privacy is key to formulating a successful risk management framework in sports. To protect wearable technologies in sports, this research took the novel initiative.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133670447","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 Analysis of a Novel Plasmonic Power Splitter Based on an Air-Slot Coupler","authors":"R. Wahsheh","doi":"10.1109/HONET56683.2022.10019085","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019085","url":null,"abstract":"Power splitters are used to achieve high density and cost effective optical integrated circuits. Based on an air-slot coupler, we introduce a plasmonic power splitter that achieves high coupling efficiency over a broad frequency range which entails lower-precision fabrication processes to align its two-branches to the conventional dielectric waveguide (CDW). We found that tapering the width of the two CDWs not only increases the coupling efficiency into and out of the MDM plasmonic waveguides, but also reduces the oscillations in the measured transmitted coupling efficiency into the output CDW and increases the fabrication tolerance when placing the two MDM branches between the two CDWs. Our results show that the proposed power splitter has potential applications in the optical data communications.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128545256","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":"Accuracy-Aware Data Reduction for Internet of Things","authors":"Taimur Hafeez, G. Mcardle","doi":"10.1109/HONET56683.2022.10019133","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019133","url":null,"abstract":"The Internet of Things (IoT) generates an enormous amount of data. Usually, either in real-time or after their collection, these data are passed to already trained machine learning and deep learning models for making predictions. Sometimes these data are used for retraining models. While efforts for data reduction have been made, little attention has been given to the effects of data reduction on machine learning models in the IoT context. Furthermore, the works that have explored how accurately data is reduced have no mechanism to use the result as feedback for future data reduction. In this paper, we propose a new reduction technique that depends on feedback from machine learning and deep learning models. As a result, data is as much reduced as required to achieve the desired results for the models. When machine learning model feedback reports low performance, the reduction algorithm increases the amount of data sent. Similarly, when the feedback indicates that the data being sent is sufficient to achieve the desired level of performance, the proposed reduction algorithm attempts to reduce the amount of data further to explore the opportunity that a similar level of performance might be achieved with a comparatively smaller amount of data. Experiments on NASA's turbofan engine data revealed that the algorithm's reduction rate can be integrated with feedback from the machine learning model without significantly affecting the performance of the model.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129257008","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}
Rija Tariq, Hareem Ashraf, Maira Sohail, Hasan Ali Khattak
{"title":"Optimization Techniques for Scheduling IoT tasks in Fog-based Environments","authors":"Rija Tariq, Hareem Ashraf, Maira Sohail, Hasan Ali Khattak","doi":"10.1109/HONET56683.2022.10019213","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019213","url":null,"abstract":"Cloud computing has been around us for a while now, and everywhere we look around, data surrounds us. Data is transferred over a network and computed over some cloud platform. The concept of the fog layer has also been around, and there have been multiple implementations of how these two sets of layers can work together and implement an excellent and optimized structure. Numerous factors are involved in creating an architecture like that, including time, energy, network bandwidth, etc. Every solution presented tries to cater to most of these factors and gives the best possible outcome. But there has been a trade-off always. Such architecture has been here for many years. These solutions and many new ones are implemented to find a common optimal point. Such solutions can be divided into categories like bio-inspired algorithms, evolution-based algorithms, etc. There can also be a division based on these algorithms' heuristic and metaheuristic nature. This paper focuses on all these techniques and compares the objectives and limitations of previous implementations. This paper also pointed out majorly used algorithms repeatedly seen during this research and simulated on the same set of parameters to determine which solution presents a more efficient performance.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"78 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120813054","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":"Study of Zero Trust Architecture for Applications and Network Security","authors":"Farhan Qazi","doi":"10.1109/HONET56683.2022.10019186","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019186","url":null,"abstract":"As a result of globalization, the COVID-19 pandemic and the migration of data to the cloud, the traditional security measures where an organization relies on a security perimeter and firewalls do not work. There is a shift to a concept whereby resources are not being trusted, and a zero-trust architecture (ZTA) based on a zero-trust principle is needed. Adapting zero trust principles to networks ensures that a single insecure Application Protocol Interface (API) does not become the weakest link comprising of Critical Data, Assets, Application and Services (DAAS). The purpose of this paper is to review the use of zero trust in the security of a network architecture instead of a traditional perimeter. Different software solutions for implementing secure access to applications and services for remote users using zero trust network access (ZTNA) is also summarized. A summary of the author's research on the qualitative study of “Insecure Application Programming Interface in Zero Trust Networks” is also discussed. The study showed that there is an increased usage of zero trust in securing networks and protecting organizations from malicious cyber-attacks. The research also indicates that APIs are insecure in zero trust environments and most organization are not aware of their presence.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115285980","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}
Sam J. Slate, Cole C Tryon, Fernando E Uribe, William Howland, Matt Marshall, Razvan Cristian Voicu
{"title":"Improving Biomedical Systems With Robotics & Automation","authors":"Sam J. Slate, Cole C Tryon, Fernando E Uribe, William Howland, Matt Marshall, Razvan Cristian Voicu","doi":"10.1109/HONET56683.2022.10019253","DOIUrl":"https://doi.org/10.1109/HONET56683.2022.10019253","url":null,"abstract":"In biomedical processes, there are a wide variety of operations that require the use of pipetting and transferring liq-uids into a specialized dish known as a microplate. For example, researchers and scientists utilize Enzyme-Linked Immunosorbent Assay (ELIZA) to test for specific antigens within a testing solution. Researchers use a handheld, manual pipette during most ELISA tests to move solutions into microplates. While the entire ELISA process often incorporates machines/automation at different steps along the way, the pipetting process usually remains manual. Integrating an automated pipetting system into one such biomedical process can enhance repeatability and optimize time and accuracy. This paper presents the design and implementation of a custom biomedical pipetting system that uses stepper motors along three Cartesian axes to allow precise placement and control of the pipette end effector into individual bays of a microplate. The results show promising improvement both in time and equal volume distribution.","PeriodicalId":293446,"journal":{"name":"2022 IEEE 19th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130729741","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}