Pub Date : 2022-11-24DOI: 10.1109/iotais56727.2022.9975933
{"title":"IoTaIS 2022 Cover Page","authors":"","doi":"10.1109/iotais56727.2022.9975933","DOIUrl":"https://doi.org/10.1109/iotais56727.2022.9975933","url":null,"abstract":"","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127830888","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975984
Albert Budi Christian, Chih-Yu Lin, Y. Tseng, Lan-Da Van, Wan-Hsun Hu, Chia-Hsuan Yu
In this paper, we present accuracy-time efficient hyperparameter optimization (HPO) using advantage actor-critic (A2C)-based reinforcement learning (RL) and early stopping in OpenAI Gym environment. The A2C RL can improve the hyperparameter selection such that the resulting accuracy of machine learning (ML) algorithms including XGBoost, support vector classifier (SVC), random forest shows comparable. According to the specified accuracy of the ML algorithms, the early stopping scheme can save the computation cost. Ten standard datasets are used to valid the accuracy-time efficient HPO. Experimental results show that the presented accuracy-efficient HPO architecture can improve 0.77% accuracy on average compared with default hyperparameter for random forest. The early stopping can save 64% computation cost on average compared to without early stopping for random forest.
{"title":"Accuracy-Time Efficient Hyperparameter Optimization Using Actor-Critic-based Reinforcement Learning and Early Stopping in OpenAI Gym Environment","authors":"Albert Budi Christian, Chih-Yu Lin, Y. Tseng, Lan-Da Van, Wan-Hsun Hu, Chia-Hsuan Yu","doi":"10.1109/IoTaIS56727.2022.9975984","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975984","url":null,"abstract":"In this paper, we present accuracy-time efficient hyperparameter optimization (HPO) using advantage actor-critic (A2C)-based reinforcement learning (RL) and early stopping in OpenAI Gym environment. The A2C RL can improve the hyperparameter selection such that the resulting accuracy of machine learning (ML) algorithms including XGBoost, support vector classifier (SVC), random forest shows comparable. According to the specified accuracy of the ML algorithms, the early stopping scheme can save the computation cost. Ten standard datasets are used to valid the accuracy-time efficient HPO. Experimental results show that the presented accuracy-efficient HPO architecture can improve 0.77% accuracy on average compared with default hyperparameter for random forest. The early stopping can save 64% computation cost on average compared to without early stopping for random forest.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121512484","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975888
M. Mavroforakis, H. Georgiou
Genetic profiling via biomarkers in the food industry is a technology that gains momentum in the context of quality assurance and protection against fraud, as well as securing commercial assets like designation of origin. However, current solutions are based on methods that require significant computational resources and management of large data volumes, making them unsuitable for applications in the context of Internet-of-Things (IoT), edge computing and microcontrollers (MCU). This study presents a novel, computationally efficient and robust approach for fully field-integrated, low-complexity and high-accuracy classification of olives variety and location of origin, based on genetic ‘fingerprinting’ via a minimal set of information-rich features. The method is tested with real-world datasets, achieving accuracy rates above 96% and 99%, respectively, using various instance-based and tree ensemble classification models.
{"title":"Genetic profiling of olives for location of origin and variety discrimination using Machine Learning","authors":"M. Mavroforakis, H. Georgiou","doi":"10.1109/IoTaIS56727.2022.9975888","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975888","url":null,"abstract":"Genetic profiling via biomarkers in the food industry is a technology that gains momentum in the context of quality assurance and protection against fraud, as well as securing commercial assets like designation of origin. However, current solutions are based on methods that require significant computational resources and management of large data volumes, making them unsuitable for applications in the context of Internet-of-Things (IoT), edge computing and microcontrollers (MCU). This study presents a novel, computationally efficient and robust approach for fully field-integrated, low-complexity and high-accuracy classification of olives variety and location of origin, based on genetic ‘fingerprinting’ via a minimal set of information-rich features. The method is tested with real-world datasets, achieving accuracy rates above 96% and 99%, respectively, using various instance-based and tree ensemble classification models.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122567079","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975896
Revanth Reddy Kontham, Akhilesh Kumar Kondoju, M. Fouda, Z. Fadlullah
Deep learning-based predictive models, for identifying malign tumor data in various cancer types, emerged as a hot research topic in the Internet of Medical Things (IoT). Such models can be deployed onto biomedical machines acting as IoMT devices to provide highly accurate breast cancer screening. While there has been a significant advancement in deep learning models for classifying cancer imaging data, a key shortcoming exists in terms of their use as blackbox algorithms rendering them unexplainable or non-interpretable. Caregivers, such as oncologists and radiologists, however, need to understand the nature of the model outcome. We address this in this paper by providing an end-to-end explainable AI framework for analyzing breast cancer prediction models based on a publicly available mammography dataset. In addition, we demonstrate how the various methods in such an end-to-end system can be effectively evaluated with appropriate performance measures.
{"title":"An End-To-End Explainable AI System for Analyzing Breast Cancer Prediction Models","authors":"Revanth Reddy Kontham, Akhilesh Kumar Kondoju, M. Fouda, Z. Fadlullah","doi":"10.1109/IoTaIS56727.2022.9975896","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975896","url":null,"abstract":"Deep learning-based predictive models, for identifying malign tumor data in various cancer types, emerged as a hot research topic in the Internet of Medical Things (IoT). Such models can be deployed onto biomedical machines acting as IoMT devices to provide highly accurate breast cancer screening. While there has been a significant advancement in deep learning models for classifying cancer imaging data, a key shortcoming exists in terms of their use as blackbox algorithms rendering them unexplainable or non-interpretable. Caregivers, such as oncologists and radiologists, however, need to understand the nature of the model outcome. We address this in this paper by providing an end-to-end explainable AI framework for analyzing breast cancer prediction models based on a publicly available mammography dataset. In addition, we demonstrate how the various methods in such an end-to-end system can be effectively evaluated with appropriate performance measures.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130891992","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975966
Aya Farrag, Z. Fadlullah, M. Fouda
While traditional medical informatics focus primarily on disease classification problems, the disease survivability prediction for patients suffering from multi-stage conditions (e.g., congestive cardiac disorders, cancer types, diabetes, chronic kideny disorder, and so forth) surprisingly remains as an overlooked research topic. In this paper, we address this topic, and among the numerous multi-stage chronic diseases, we select the breast cancer use-case due to the importance of breast cancer patients survivability analysis and prediction for healthcare providers to make informed decisions on recommended treatment pathways for different patients. Then, we combine two main strategies in solving the breast cancer survivability prediction problem using Machine Learning techniques. In the first strategy, we model the survivability prediction task as a two-step problem, namely 1) a classification problem to predict whether or not a patient survives for five years, and 2) a regression problem to forecast the number of remaining months for those who are predicted to not survive for five years. The second strategy is to develop stage-specific models, where each model is trained on instances belonging to a certain cancer stage, instead of using all stages together, in order to predict survivability of patients from the same stage. We investigate the impact of adapting these strategies along with applying different balancing techniques over the model performance using the National Cancer Institute’s Surveillance, Epidemiology, and End Results (SEER) dataset. The obtained results demonstrate that the proposed methods prove effective in both survivability classification and regression.
{"title":"A Two-Step Machine Learning Model for Stage-Specific Disease Survivability Prediction","authors":"Aya Farrag, Z. Fadlullah, M. Fouda","doi":"10.1109/IoTaIS56727.2022.9975966","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975966","url":null,"abstract":"While traditional medical informatics focus primarily on disease classification problems, the disease survivability prediction for patients suffering from multi-stage conditions (e.g., congestive cardiac disorders, cancer types, diabetes, chronic kideny disorder, and so forth) surprisingly remains as an overlooked research topic. In this paper, we address this topic, and among the numerous multi-stage chronic diseases, we select the breast cancer use-case due to the importance of breast cancer patients survivability analysis and prediction for healthcare providers to make informed decisions on recommended treatment pathways for different patients. Then, we combine two main strategies in solving the breast cancer survivability prediction problem using Machine Learning techniques. In the first strategy, we model the survivability prediction task as a two-step problem, namely 1) a classification problem to predict whether or not a patient survives for five years, and 2) a regression problem to forecast the number of remaining months for those who are predicted to not survive for five years. The second strategy is to develop stage-specific models, where each model is trained on instances belonging to a certain cancer stage, instead of using all stages together, in order to predict survivability of patients from the same stage. We investigate the impact of adapting these strategies along with applying different balancing techniques over the model performance using the National Cancer Institute’s Surveillance, Epidemiology, and End Results (SEER) dataset. The obtained results demonstrate that the proposed methods prove effective in both survivability classification and regression.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114253646","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975889
Xin-Wen Wu, Yongtao Cao, Richard Dankwa
Anomaly detection is an important security mechanism for the Internet of Things (IoT). Existing works have been focused on developing accurate anomaly detection models. However, due to the resource-constrained nature of IoT networks and the requirement of real-time security operation, cost efficient (regarding computational efficiency and memory-consumption efficiency) approaches for anomaly detection are highly desirable in IoT applications. In this paper, we investigated machine learning (ML) enabled anomaly detection models for the IoT with regard to multi-objective optimization (Pareto optimization) that minimizes the detection error, execution time, and memory consumption simultaneously. Making use of well-known datasets consisting of network traffic traces captured in an IoT environment, we studied a variety of machine learning algorithms through the world-class H2O AI platform. Our experimental results show that the Gradient Boosting Machine, Random Forest, and Deep Learning models are the most accurate and fastest anomaly detection models; the Gradient Boosting Machine and Random Forest are the most accurate and memory-efficient models. These ML models form the Pareto-optimal set of anomaly detection models. Our results can be used by the industry to facilitate their selection of ML models for anomaly detection on various IoT networks based on their security requirements and system constraints.
{"title":"Accuracy vs Efficiency: Machine Learning Enabled Anomaly Detection on the Internet of Things","authors":"Xin-Wen Wu, Yongtao Cao, Richard Dankwa","doi":"10.1109/IoTaIS56727.2022.9975889","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975889","url":null,"abstract":"Anomaly detection is an important security mechanism for the Internet of Things (IoT). Existing works have been focused on developing accurate anomaly detection models. However, due to the resource-constrained nature of IoT networks and the requirement of real-time security operation, cost efficient (regarding computational efficiency and memory-consumption efficiency) approaches for anomaly detection are highly desirable in IoT applications. In this paper, we investigated machine learning (ML) enabled anomaly detection models for the IoT with regard to multi-objective optimization (Pareto optimization) that minimizes the detection error, execution time, and memory consumption simultaneously. Making use of well-known datasets consisting of network traffic traces captured in an IoT environment, we studied a variety of machine learning algorithms through the world-class H2O AI platform. Our experimental results show that the Gradient Boosting Machine, Random Forest, and Deep Learning models are the most accurate and fastest anomaly detection models; the Gradient Boosting Machine and Random Forest are the most accurate and memory-efficient models. These ML models form the Pareto-optimal set of anomaly detection models. Our results can be used by the industry to facilitate their selection of ML models for anomaly detection on various IoT networks based on their security requirements and system constraints.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124919822","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975975
Enrico Fernandez, Anderies, Michael Gilbert Winata, Fadly Haikal Fasya, A. A. Gunawan
Recently, more people access mobile stock trading apps and investors send messages, comments, and posts. Interest in performing sentiment analysis of these messages to predict stock price changes requires ever-improving machine learning models, though, this requires identifying Bahasa Indonesian slang phrases in comments and posts. For developing the model to perform a sentiment analysis on stock price changes, we retrieved data from comments and posts on third-party applications. In the current paper, we presented such a model and test data acquisition using datasets manually labelled by the authors. Our sentiment analysis approach was implemented with a fine-tuned IndoBERT model and achieved 60.35% accuracy predicting the sentiment of 1289 records comments, and posts which better than previous research study. By testing the model, it can do a sentiment analysis on stock price changes and is also capable of identifying the number of slang phrases in the comments and posts by Indonesian traders.
{"title":"Improving IndoBERT for Sentiment Analysis on Indonesian Stock Trader Slang Language","authors":"Enrico Fernandez, Anderies, Michael Gilbert Winata, Fadly Haikal Fasya, A. A. Gunawan","doi":"10.1109/IoTaIS56727.2022.9975975","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975975","url":null,"abstract":"Recently, more people access mobile stock trading apps and investors send messages, comments, and posts. Interest in performing sentiment analysis of these messages to predict stock price changes requires ever-improving machine learning models, though, this requires identifying Bahasa Indonesian slang phrases in comments and posts. For developing the model to perform a sentiment analysis on stock price changes, we retrieved data from comments and posts on third-party applications. In the current paper, we presented such a model and test data acquisition using datasets manually labelled by the authors. Our sentiment analysis approach was implemented with a fine-tuned IndoBERT model and achieved 60.35% accuracy predicting the sentiment of 1289 records comments, and posts which better than previous research study. By testing the model, it can do a sentiment analysis on stock price changes and is also capable of identifying the number of slang phrases in the comments and posts by Indonesian traders.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127826874","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975988
Kemal Cagri Serdaroglu, S. Baydere, Boonyarith Saovapakhiran
Fog computing has the benefits to handle and reduce data traffic load towards the central cloud in IoT systems. These benefits are facilitated with the help of offloaded fog services that participate in the decision making processes. Besides, fog-based systems have the potential to mitigate scalability bottlenecks that occur in cloud-based systems. In this study, we elaborate on fog based design for a scalable real time air quality monitoring and alert generation system. We established an emulation test bed with real data collected from air quality sensing nodes deployed around Bangkok and vicinity areas to understand the behavior of the proposed solution in terms of waiting time characteristics. We analyzed the performance of the system in two design scenarios; first scenario is built with the proposed fog solution and the second one is the cloud-based approach. We present the performance results revealing the advantages of the proposed model, for the number of air box nodes scaling up to 120 and the number of client nodes up to 200.
{"title":"Real time air quality monitoring with fog computing enabled IoT system: an experimental study","authors":"Kemal Cagri Serdaroglu, S. Baydere, Boonyarith Saovapakhiran","doi":"10.1109/IoTaIS56727.2022.9975988","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975988","url":null,"abstract":"Fog computing has the benefits to handle and reduce data traffic load towards the central cloud in IoT systems. These benefits are facilitated with the help of offloaded fog services that participate in the decision making processes. Besides, fog-based systems have the potential to mitigate scalability bottlenecks that occur in cloud-based systems. In this study, we elaborate on fog based design for a scalable real time air quality monitoring and alert generation system. We established an emulation test bed with real data collected from air quality sensing nodes deployed around Bangkok and vicinity areas to understand the behavior of the proposed solution in terms of waiting time characteristics. We analyzed the performance of the system in two design scenarios; first scenario is built with the proposed fog solution and the second one is the cloud-based approach. We present the performance results revealing the advantages of the proposed model, for the number of air box nodes scaling up to 120 and the number of client nodes up to 200.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130234171","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975885
Somayya Avadut, S. Udgata
Around the world, the number of senior citizens is increasing and shall continue to increase, and it is expected to be around 20 percent by 2050. Realizing its importance, the United Nations has identified Health and Wellness as one of the Sustainable Development Goals (SDG). The unfortunate pandemic situation due to the COVID-19 outbreak opened up new challenges for contact-less interactions and control of devices for ensuring the well being of citizens. In this paper, our main aim is to develop an intelligent framework based on a gesture-based interface that will help the senior citizens and physically challenged people interact and control different devices using only gestures. We focus on dynamic gesture recognition using a deep learning-based Convolutional Neural Network (CNN) model. The proposed system records continuous real-time data streams from non-invasive wearable sensors. This real-time continuous data stream is fragmented into data segments that are most likely to contain meaningful gesture data frames using the Adaptive Threshold Setting algorithm. The segmented data frames are provided as input to the CNN model to train, test, validate, and then classify it into predefined clusters, which are gestures. We have used the MPU6050 Inertial Measurement Unit based sensor model for collecting the data of the hand/ finger movement. The popular and widely used ESP8266 controller is used for data gathering, processing, and communicating. We created a dataset for 36 gestures, which includes ten digits and 26 English alphabets. For each gesture, a dataset of 300 samples has been created from 5 subjects of age group between 21-30. Thus, the final dataset consists of a total of 10800 samples belonging to 36 gestures. A total of six features comprising linear accelerations and angular rotation in 3-dimensional axes are used for training and validation. The proposed model can segment 93.75% of data segments correctly using the adaptive threshold selection algorithm, and the CNN classification algorithm can classify 98.67% gestures correctly.
{"title":"A Deep Learning based IoT Framework for Assistive Healthcare using Gesture Based Interface","authors":"Somayya Avadut, S. Udgata","doi":"10.1109/IoTaIS56727.2022.9975885","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975885","url":null,"abstract":"Around the world, the number of senior citizens is increasing and shall continue to increase, and it is expected to be around 20 percent by 2050. Realizing its importance, the United Nations has identified Health and Wellness as one of the Sustainable Development Goals (SDG). The unfortunate pandemic situation due to the COVID-19 outbreak opened up new challenges for contact-less interactions and control of devices for ensuring the well being of citizens. In this paper, our main aim is to develop an intelligent framework based on a gesture-based interface that will help the senior citizens and physically challenged people interact and control different devices using only gestures. We focus on dynamic gesture recognition using a deep learning-based Convolutional Neural Network (CNN) model. The proposed system records continuous real-time data streams from non-invasive wearable sensors. This real-time continuous data stream is fragmented into data segments that are most likely to contain meaningful gesture data frames using the Adaptive Threshold Setting algorithm. The segmented data frames are provided as input to the CNN model to train, test, validate, and then classify it into predefined clusters, which are gestures. We have used the MPU6050 Inertial Measurement Unit based sensor model for collecting the data of the hand/ finger movement. The popular and widely used ESP8266 controller is used for data gathering, processing, and communicating. We created a dataset for 36 gestures, which includes ten digits and 26 English alphabets. For each gesture, a dataset of 300 samples has been created from 5 subjects of age group between 21-30. Thus, the final dataset consists of a total of 10800 samples belonging to 36 gestures. A total of six features comprising linear accelerations and angular rotation in 3-dimensional axes are used for training and validation. The proposed model can segment 93.75% of data segments correctly using the adaptive threshold selection algorithm, and the CNN classification algorithm can classify 98.67% gestures correctly.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116417314","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975916
Onur Önder, G. Ghinea, Tor-Morten Grønli, T. Serif
The proliferation of smart devices has dramatically changed how people live their daily lives. Today, on top of their initial communicator role, smart devices act as guides, companions, and aids. For a long time, people have been using navigation systems and mobile phones as navigators in their cars. Indeed, there have been interests in implementing similar indoor navigation systems using technologies such as Wi-Fi, Bluetooth, and ultra-wideband. However, the proposed indoor navigation solutions were either too expensive to implement and maintain, or not accurate enough for a wider acceptance. Accordingly, this paper proposes a hybrid pedestrian dead reckoning (PDR) for indoor navigation, which utilizes the built-in sensors of smart devices. As part of this study, the authors implement three approaches to pedestrian dead-reckoning namely PDR, Personal PDR, and Hybrid P-PDR-and evaluate in a real-world setting. The findings of the the evaluation shows that the Hybrid P-PDR approach, which harnesses the user’s walking pattern and signals from low-energy beacons, can navigate users in an indoor environment with a minimum of 0.77 and maximum of 1.35-meter average distance error.
智能设备的普及极大地改变了人们的日常生活方式。如今，智能设备除了最初的传播者角色之外，还扮演着向导、伙伴和辅助的角色。很长一段时间以来，人们一直在使用导航系统和移动电话作为他们汽车的导航仪。事实上，人们对使用Wi-Fi、蓝牙和超宽带等技术实现类似的室内导航系统很感兴趣。然而，拟议的室内导航解决方案要么过于昂贵，无法实施和维护，要么不够精确，无法得到更广泛的接受。据此，本文提出了一种利用智能设备内置传感器的混合行人航位推算(PDR)方法。作为本研究的一部分，作者实施了三种行人航位推算方法，即PDR、Personal PDR和Hybrid p -PDR，并在现实环境中进行评估。评估结果表明，混合P-PDR方法利用用户的行走模式和低能信标信号，可以在室内环境中为用户导航，平均距离误差最小为0.77米，最大为1.35米。
{"title":"Indoor Navigation Using Hybrid Personal Pedestrian Dead Reckoning (Hybrid P-PDR)","authors":"Onur Önder, G. Ghinea, Tor-Morten Grønli, T. Serif","doi":"10.1109/IoTaIS56727.2022.9975916","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975916","url":null,"abstract":"The proliferation of smart devices has dramatically changed how people live their daily lives. Today, on top of their initial communicator role, smart devices act as guides, companions, and aids. For a long time, people have been using navigation systems and mobile phones as navigators in their cars. Indeed, there have been interests in implementing similar indoor navigation systems using technologies such as Wi-Fi, Bluetooth, and ultra-wideband. However, the proposed indoor navigation solutions were either too expensive to implement and maintain, or not accurate enough for a wider acceptance. Accordingly, this paper proposes a hybrid pedestrian dead reckoning (PDR) for indoor navigation, which utilizes the built-in sensors of smart devices. As part of this study, the authors implement three approaches to pedestrian dead-reckoning namely PDR, Personal PDR, and Hybrid P-PDR-and evaluate in a real-world setting. The findings of the the evaluation shows that the Hybrid P-PDR approach, which harnesses the user’s walking pattern and signals from low-energy beacons, can navigate users in an indoor environment with a minimum of 0.77 and maximum of 1.35-meter average distance error.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116537293","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：