Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817353
Aakib Bin Nesar, Tahseena Mahmud, Fahreen Hossain
Access to sufficient water is a human right and part of human survival, health, well being and livelihoods for consumption and domestic use. However, the gendered culture of water access, use and livelihoods have remained silent in the world of water management. With this perspective, the work conducted by the Institute of Disaster Management and Vulnerability Studies (IDMVS), University of Dhaka, in collaboration with REACH project explored how gender dimensions form a nexus between water collection challenges, spatial differences and gender division of labour comparing data from water-secure and water insecure communities (mouzas) in coastal Bangladesh. In this work, our objective was to model and simulate the behaviour of women towards water accumulation for household purposes, who are residing in regions with inadequate water conservation and distribution systems. Our simulation takes into account water risks that may affect the system such as river erosion and salinity intrusion, leading to a higher level of water stress. We have conducted this work as an extension of the project already being carried by REACH, but in terms of modeling and simulation to visualize and discuss empirical results found from our work.
{"title":"Simulating the Behaviour and Displacement of Women in Water-Stressed Areas","authors":"Aakib Bin Nesar, Tahseena Mahmud, Fahreen Hossain","doi":"10.1109/aiiot54504.2022.9817353","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817353","url":null,"abstract":"Access to sufficient water is a human right and part of human survival, health, well being and livelihoods for consumption and domestic use. However, the gendered culture of water access, use and livelihoods have remained silent in the world of water management. With this perspective, the work conducted by the Institute of Disaster Management and Vulnerability Studies (IDMVS), University of Dhaka, in collaboration with REACH project explored how gender dimensions form a nexus between water collection challenges, spatial differences and gender division of labour comparing data from water-secure and water insecure communities (mouzas) in coastal Bangladesh. In this work, our objective was to model and simulate the behaviour of women towards water accumulation for household purposes, who are residing in regions with inadequate water conservation and distribution systems. Our simulation takes into account water risks that may affect the system such as river erosion and salinity intrusion, leading to a higher level of water stress. We have conducted this work as an extension of the project already being carried by REACH, but in terms of modeling and simulation to visualize and discuss empirical results found from our work.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115082896","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817164
Abel Desoto, Ethan Santos, Francis Liri, K. Faller, Devin Heng, Joshua Dodd, K. George, Julia R. Drouin
People are constantly surrounded by some form of sound, which can occasionally interfere with their daily tasks such as conversation. When sound interferes with daily activities, it becomes noise that is undesired sound. Depending on the surroundings, one may be subjected to varying levels of noise, resulting in hearing challenges especially for those with hearing disabilities. Researchers have tested how the brain interprets information and shown that the brain can be ‘primed’ to quickly tune hearing and effectively learn to understand sounds. This concept is used to propose a software-based training solution that utilizes EEG signals to identify whether or not a person with a hearing disability is learning. This can be applied for the training of those with disabilities and eliminate the need of a doctor to administer and make the process faster and simpler. An overall framework for the proposed system and outline of the essential components are presented. The research is extended by refining the testing and experiment methods, resolving some of the weaknesses of the research and performing similar studies with a larger participant pool. Furthermore, a machine learning algorithm, K-Nearest Neighbor (KNN), is applied to evaluate EEG data and predict a subject's understanding of distorted audio.
{"title":"Predicting Audio Training Learning Outcomes Using EEG Data and KNN Modeling","authors":"Abel Desoto, Ethan Santos, Francis Liri, K. Faller, Devin Heng, Joshua Dodd, K. George, Julia R. Drouin","doi":"10.1109/aiiot54504.2022.9817164","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817164","url":null,"abstract":"People are constantly surrounded by some form of sound, which can occasionally interfere with their daily tasks such as conversation. When sound interferes with daily activities, it becomes noise that is undesired sound. Depending on the surroundings, one may be subjected to varying levels of noise, resulting in hearing challenges especially for those with hearing disabilities. Researchers have tested how the brain interprets information and shown that the brain can be ‘primed’ to quickly tune hearing and effectively learn to understand sounds. This concept is used to propose a software-based training solution that utilizes EEG signals to identify whether or not a person with a hearing disability is learning. This can be applied for the training of those with disabilities and eliminate the need of a doctor to administer and make the process faster and simpler. An overall framework for the proposed system and outline of the essential components are presented. The research is extended by refining the testing and experiment methods, resolving some of the weaknesses of the research and performing similar studies with a larger participant pool. Furthermore, a machine learning algorithm, K-Nearest Neighbor (KNN), is applied to evaluate EEG data and predict a subject's understanding of distorted audio.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121241636","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 : 2022-06-06DOI: 10.1109/AIIoT54504.2022.9817297
K. Saurabh, T. kumar, Uphar Singh, O. P. Vyas, R. Khondoker
In the recent years, Distributed Denial of Service (DDoS) attacks on Internet of Things (IoT) devices have become one of the prime concerns to Internet users around the world. One of the sources of the attacks on IoT ecosystems are botnets. Intruders force IoT devices to become unavailable for its legitimate users by sending large number of messages within a short interval. This study proposes NFDLM, a lightweight and optimised Artificial Neural Network (ANN) based Distributed Denial of Services (DDoS) attack detection framework with mutual correlation as feature selection method which produces a superior result when compared with Long Short Term Memory (LSTM) and simple ANN. Overall, the detection performance achieves approximately 99% accuracy for the detection of attacks from botnets. In this work, we have designed and compared four different models where two are based on ANN and the other two are based on LSTM to detect the attack types of DDoS.
{"title":"NFDLM: A Lightweight Network Flow based Deep Learning Model for DDoS Attack Detection in IoT Domains","authors":"K. Saurabh, T. kumar, Uphar Singh, O. P. Vyas, R. Khondoker","doi":"10.1109/AIIoT54504.2022.9817297","DOIUrl":"https://doi.org/10.1109/AIIoT54504.2022.9817297","url":null,"abstract":"In the recent years, Distributed Denial of Service (DDoS) attacks on Internet of Things (IoT) devices have become one of the prime concerns to Internet users around the world. One of the sources of the attacks on IoT ecosystems are botnets. Intruders force IoT devices to become unavailable for its legitimate users by sending large number of messages within a short interval. This study proposes NFDLM, a lightweight and optimised Artificial Neural Network (ANN) based Distributed Denial of Services (DDoS) attack detection framework with mutual correlation as feature selection method which produces a superior result when compared with Long Short Term Memory (LSTM) and simple ANN. Overall, the detection performance achieves approximately 99% accuracy for the detection of attacks from botnets. In this work, we have designed and compared four different models where two are based on ANN and the other two are based on LSTM to detect the attack types of DDoS.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128022545","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817231
Mina Esmail Zadeh Nojoo Kambar, Armin Esmaeilzadeh, Maryam Heidari
Named Entity Recognition (NER) and Relation Extraction (RE) are two principal subtasks of knowledge-based systems that extract meaningful information from unstructured text. With Recent advances in Deep Learning techniques, new models use Joint Named Entities and Relation Extraction (JNERE) techniques that simultaneously accomplish NER and RE subtasks. These models avoid the drawbacks of using the traditional pipeline method. As contributions of our study to the other related works, we specifically survey JNERE techniques. The reason for not focusing on pipeline methods or other older techniques is the recent advances of JNERE methods in achieving the state-of-art results for most databases. Additionally, we provide a comprehensive report on the embedding techniques and datasets available for this task. Finally, we discuss the approaches and how they imnpoved the results.
{"title":"A Survey on Deep Learning Techniques for Joint Named Entities and Relation Extraction","authors":"Mina Esmail Zadeh Nojoo Kambar, Armin Esmaeilzadeh, Maryam Heidari","doi":"10.1109/aiiot54504.2022.9817231","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817231","url":null,"abstract":"Named Entity Recognition (NER) and Relation Extraction (RE) are two principal subtasks of knowledge-based systems that extract meaningful information from unstructured text. With Recent advances in Deep Learning techniques, new models use Joint Named Entities and Relation Extraction (JNERE) techniques that simultaneously accomplish NER and RE subtasks. These models avoid the drawbacks of using the traditional pipeline method. As contributions of our study to the other related works, we specifically survey JNERE techniques. The reason for not focusing on pipeline methods or other older techniques is the recent advances of JNERE methods in achieving the state-of-art results for most databases. Additionally, we provide a comprehensive report on the embedding techniques and datasets available for this task. Finally, we discuss the approaches and how they imnpoved the results.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130707347","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817163
Adam Borys, A. Kamruzzaman, Hasnain Nizam Thakur, Joseph C. Brickley, M. Ali, Kutub Thakur
This paper dives into the growing world of IoT botnets that have taken the world by storm in the past five years. Though alone an IP camera cannot produce enough traffic to be considered a DDoS. But a botnet that has over 150,000 connected IP cameras can generate as much as 1 Tbps in traffic. Botnets catch many by surprise because their attacks and infections may not be as apparent as a DDoS, some other cases include using these cameras and printers for extracting information or quietly mine cryptocurrency at the IoT device owner's expense. Here we analyze damages on IoT hacking and define botnet architecture. An overview of Mirai botnet and cryptojacking provided to better understand the IoT botnets.
{"title":"An Evaluation of IoT DDoS Cryptojacking Malware and Mirai Botnet","authors":"Adam Borys, A. Kamruzzaman, Hasnain Nizam Thakur, Joseph C. Brickley, M. Ali, Kutub Thakur","doi":"10.1109/aiiot54504.2022.9817163","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817163","url":null,"abstract":"This paper dives into the growing world of IoT botnets that have taken the world by storm in the past five years. Though alone an IP camera cannot produce enough traffic to be considered a DDoS. But a botnet that has over 150,000 connected IP cameras can generate as much as 1 Tbps in traffic. Botnets catch many by surprise because their attacks and infections may not be as apparent as a DDoS, some other cases include using these cameras and printers for extracting information or quietly mine cryptocurrency at the IoT device owner's expense. Here we analyze damages on IoT hacking and define botnet architecture. An overview of Mirai botnet and cryptojacking provided to better understand the IoT botnets.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130242749","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817176
Mohammad Monirujjaman Khan, Md. Farabi Alam, Shoumik Mahabub Ridoy
Stocksofcompaniesheavilyinfluencethefinancial markets around the world. These companies help tocontributeandimprovetheoverallGDPofaneconomy.Hence, the importance of having a grip on the stock market forventurecapitalistsandcompaniesisinevitablefortheirfinancial benefit and growth. It is crucial to predict the stockprice to stay at the forefront of the financial world. None of theexistingmachinelearningtechniquescanprovideaperfectpredi ction of the stock prices due to the unpredictable identityof the stock market. The stock price prediction employing twomachinelearningalgorithms,LongShort-TermMemory(LSTM)andAutoregressivelntegratedMovingAve rage(ARIMA), willbediscussedindepthinthisstudy. Theaccuracy achieved by these two algorithms was compared. Inour comparison, we found out that, generally, LSTM had ahigheraccuracyrateinthestockpriceprediction.ARIMAprovide dbetterperformancewithasmalldatatimeframe, while LSTM had better performance in predicting stock pricewhenthedatatimeframeusedwaslarge.
{"title":"ComparativeAnalysisofARIMAandLSTMM achine Learning Algorithm for Stock PricePrediction","authors":"Mohammad Monirujjaman Khan, Md. Farabi Alam, Shoumik Mahabub Ridoy","doi":"10.1109/aiiot54504.2022.9817176","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817176","url":null,"abstract":"Stocksofcompaniesheavilyinfluencethefinancial markets around the world. These companies help tocontributeandimprovetheoverallGDPofaneconomy.Hence, the importance of having a grip on the stock market forventurecapitalistsandcompaniesisinevitablefortheirfinancial benefit and growth. It is crucial to predict the stockprice to stay at the forefront of the financial world. None of theexistingmachinelearningtechniquescanprovideaperfectpredi ction of the stock prices due to the unpredictable identityof the stock market. The stock price prediction employing twomachinelearningalgorithms,LongShort-TermMemory(LSTM)andAutoregressivelntegratedMovingAve rage(ARIMA), willbediscussedindepthinthisstudy. Theaccuracy achieved by these two algorithms was compared. Inour comparison, we found out that, generally, LSTM had ahigheraccuracyrateinthestockpriceprediction.ARIMAprovide dbetterperformancewithasmalldatatimeframe, while LSTM had better performance in predicting stock pricewhenthedatatimeframeusedwaslarge.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"29 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114130061","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 : 2022-06-06DOI: 10.48550/arXiv.2206.04548
H. Nasiri, Ghazal Kheyroddin, M. Dorrigiv, Mona Esmaeili, A. Nafchi, Mohsen Ghorbani, P. Zarkesh-Ha
The COVID-19 disease was first discovered in Wuhan, China, and spread quickly worldwide. After the COVID-19 pandemic, many researchers have begun to identify a way to diagnose the COVID-19 using chest X-ray images. The early diagnosis of this disease can significantly impact the treatment process. In this article, we propose a new technique that is faster and more accurate than the other methods reported in the literature. The proposed method uses a combination of DenseNet169 and MobileNet Deep Neural Networks to extract the features of the patient's X-ray images. Using the univariate feature selection algorithm, we refined the features for the most important ones. Then we applied the selected features as input to the LightGBM (Light Gradient Boosting Machine) algorithm for classification. To assess the effectiveness of the proposed method, the ChestX-ray8 dataset, which includes 1125 X-ray images of the patient's chest, was used. The proposed method achieved 98.54% and 91.11% accuracies in the two-class (COVID-19, Healthy) and multi-class (COVID-19, Healthy, Pneumonia) classification problems, respectively. It is worth mentioning that we have used Gradient-weighted Class Activation Mapping (Grad-CAM) for future analysis.
{"title":"Classification of COVID-19 in Chest X-ray Images Using Fusion of Deep Features and LightGBM","authors":"H. Nasiri, Ghazal Kheyroddin, M. Dorrigiv, Mona Esmaeili, A. Nafchi, Mohsen Ghorbani, P. Zarkesh-Ha","doi":"10.48550/arXiv.2206.04548","DOIUrl":"https://doi.org/10.48550/arXiv.2206.04548","url":null,"abstract":"The COVID-19 disease was first discovered in Wuhan, China, and spread quickly worldwide. After the COVID-19 pandemic, many researchers have begun to identify a way to diagnose the COVID-19 using chest X-ray images. The early diagnosis of this disease can significantly impact the treatment process. In this article, we propose a new technique that is faster and more accurate than the other methods reported in the literature. The proposed method uses a combination of DenseNet169 and MobileNet Deep Neural Networks to extract the features of the patient's X-ray images. Using the univariate feature selection algorithm, we refined the features for the most important ones. Then we applied the selected features as input to the LightGBM (Light Gradient Boosting Machine) algorithm for classification. To assess the effectiveness of the proposed method, the ChestX-ray8 dataset, which includes 1125 X-ray images of the patient's chest, was used. The proposed method achieved 98.54% and 91.11% accuracies in the two-class (COVID-19, Healthy) and multi-class (COVID-19, Healthy, Pneumonia) classification problems, respectively. It is worth mentioning that we have used Gradient-weighted Class Activation Mapping (Grad-CAM) for future analysis.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"257O 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122261295","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817156
Armin Esmaeilzadeh, Mina Esmail Zadeh Nojoo Kambar, Maryam Heidari
The scale of neural language models has been increasing significantly over recent years. As a result, the time complexity of training larger language models and resource utilization has been increasing at a higher rate as well. In this research, we propose a distributed implementation of a Graph Attention Neural Network model with 120 million parameters and train it on a cluster of eight GPUs. We demonstrate three times speedup in model training while keeping the stability of accuracy and loss rates during training and testing compared to single GPU instance training.
{"title":"Graph Attention Neural Network Distributed Model Training","authors":"Armin Esmaeilzadeh, Mina Esmail Zadeh Nojoo Kambar, Maryam Heidari","doi":"10.1109/aiiot54504.2022.9817156","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817156","url":null,"abstract":"The scale of neural language models has been increasing significantly over recent years. As a result, the time complexity of training larger language models and resource utilization has been increasing at a higher rate as well. In this research, we propose a distributed implementation of a Graph Attention Neural Network model with 120 million parameters and train it on a cluster of eight GPUs. We demonstrate three times speedup in model training while keeping the stability of accuracy and loss rates during training and testing compared to single GPU instance training.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122348538","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817180
Sanskar Raj Marahata, Eman Abdelfattah, Sandra Ibrahim, Audrina Dobrevic
This study presents a thorough analysis of nuclear energy along with how it is unsuitable as a long-term replacement for the prevailing primary sources of fuel, like oil, coal, and gas. Nuclear energy was assumed to be a utopian power supply source and peaked in usage in the United States by 1990. Despite providing ten percent of the world's electricity and becoming the second largest source for low-carbon power, nuclear energy has been on a rapid decline ever since. Various factors including international diplomacy, adherence to treaty agreements, and negative public perception regarding nuclear energy have made government investment unsustainable, resulting in nuclear energy being irrelevant. It also causes much political rancor due to its high cost and trading issues in addition to concerns with nuclear meltdowns and weapons proliferation. Regardless of the instances against nuclear energy, developing countries, especially in Southeast Asia, still seem to favor a widespread adoption of nuclear energy, even though it is just theorized as of now.
{"title":"No-Clear for Nuclear","authors":"Sanskar Raj Marahata, Eman Abdelfattah, Sandra Ibrahim, Audrina Dobrevic","doi":"10.1109/aiiot54504.2022.9817180","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817180","url":null,"abstract":"This study presents a thorough analysis of nuclear energy along with how it is unsuitable as a long-term replacement for the prevailing primary sources of fuel, like oil, coal, and gas. Nuclear energy was assumed to be a utopian power supply source and peaked in usage in the United States by 1990. Despite providing ten percent of the world's electricity and becoming the second largest source for low-carbon power, nuclear energy has been on a rapid decline ever since. Various factors including international diplomacy, adherence to treaty agreements, and negative public perception regarding nuclear energy have made government investment unsustainable, resulting in nuclear energy being irrelevant. It also causes much political rancor due to its high cost and trading issues in addition to concerns with nuclear meltdowns and weapons proliferation. Regardless of the instances against nuclear energy, developing countries, especially in Southeast Asia, still seem to favor a widespread adoption of nuclear energy, even though it is just theorized as of now.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130094031","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817374
Khalid Raihan Talha, Koushik Bandapadya, Mohammad Monirujjaman Khan
Violent crime has always been a major social problem. The rise of violent behavior in public areas can be attributed to a variety of factors. Greed, frustration, and hostility among individuals, as well as social and economic anxieties, are the primary causes of increased violence. It is critical to protect our possessions, as well as our lives, from threats such as robbery or homicide. It is impossible to prevent crime and violent acts unless brain signals are studied and a certain pattern deduced from criminal ideas is detected in real-time. Due to its technological viability, it has yet to be realized. However, We can identify violent activity in public spaces by using the concepts of computer vision (a subfield of deep learning) technology. The goal of this project is to build a real-time violent activity monitoring system that will be capable of detecting violence very quickly and efficiently. The public of any city can benefit from it, as it will allow the people of the law enforcement department to take necessary actions to prevent violent activities. When the system is implemented, it will be able to detect the speed of the movements of people and their distances from other people walking in public places by using cameras. The system will mainly detect the speed of hand and leg movements of a person who will be very close to another person. If anyone is identified as a violent maker, the server-side of the system will notify the people who will be responsible for preventing violence in a very short time. The system was built using the concepts of computer vision and neural networks. The system has been developed and tested initially on the personal computing devices of the system developers. This system is very easy to design and develop, making it very easy to use for any kind of public area surveillance. At the same time, the system gives its desired output due to its high accuracy.
{"title":"Violence Detection Using Computer Vision Approaches","authors":"Khalid Raihan Talha, Koushik Bandapadya, Mohammad Monirujjaman Khan","doi":"10.1109/aiiot54504.2022.9817374","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817374","url":null,"abstract":"Violent crime has always been a major social problem. The rise of violent behavior in public areas can be attributed to a variety of factors. Greed, frustration, and hostility among individuals, as well as social and economic anxieties, are the primary causes of increased violence. It is critical to protect our possessions, as well as our lives, from threats such as robbery or homicide. It is impossible to prevent crime and violent acts unless brain signals are studied and a certain pattern deduced from criminal ideas is detected in real-time. Due to its technological viability, it has yet to be realized. However, We can identify violent activity in public spaces by using the concepts of computer vision (a subfield of deep learning) technology. The goal of this project is to build a real-time violent activity monitoring system that will be capable of detecting violence very quickly and efficiently. The public of any city can benefit from it, as it will allow the people of the law enforcement department to take necessary actions to prevent violent activities. When the system is implemented, it will be able to detect the speed of the movements of people and their distances from other people walking in public places by using cameras. The system will mainly detect the speed of hand and leg movements of a person who will be very close to another person. If anyone is identified as a violent maker, the server-side of the system will notify the people who will be responsible for preventing violence in a very short time. The system was built using the concepts of computer vision and neural networks. The system has been developed and tested initially on the personal computing devices of the system developers. This system is very easy to design and develop, making it very easy to use for any kind of public area surveillance. At the same time, the system gives its desired output due to its high accuracy.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129204625","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：