Pub Date : 2023-05-18DOI: 10.1109/eIT57321.2023.10187288
Biswaranjan Senapati, J. Talburt, Awad Bin Naeem, Venkata Jaipal Reddy Batthula
Being overweight may be caused by eating too many calories. It is a curable medical condition defined by abnormal fat accumulation in the body. Diabetes, excessive cholesterol, and heart attacks are the most common, although high blood pressure, colon cancer, and prostate cancer are also common. Computer techniques are often utilized to address such difficulties. In this work, we develop a system that detects and identifies food allergies using food photographs. To summaries, powerful computer algorithms such as transfer learning (ResNet50) have been taught to detect food type and validate the identified label in dataset food 101, as well as supply nutrients. The fundamental purpose of this study was to create a single framework capable of managing the difficult process of detecting, localizing, and classifying food allergies. Furthermore, larger weight parameter optimization using Adam and RMS Prop optimizers was attempted to increase their performance on healthy and allergic food image datasets. The Resnet-50 was trained to obtain the greatest mean average accuracy when compared to the other transfer learning meta-architectures. It achieved the best-identifying results by utilizing an Adam optimizer and obtaining 95% accuracy. The suggested technique was discovered to be novel since it detects all food types and then provides the nutrients of that meal from another dataset. In reality, employing the transfer learning technique to successfully diagnose food allergies would assist to prevent the adverse application of issues in diet management.
{"title":"Transfer Learning Based Models for Food Detection Using ResNet-50","authors":"Biswaranjan Senapati, J. Talburt, Awad Bin Naeem, Venkata Jaipal Reddy Batthula","doi":"10.1109/eIT57321.2023.10187288","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187288","url":null,"abstract":"Being overweight may be caused by eating too many calories. It is a curable medical condition defined by abnormal fat accumulation in the body. Diabetes, excessive cholesterol, and heart attacks are the most common, although high blood pressure, colon cancer, and prostate cancer are also common. Computer techniques are often utilized to address such difficulties. In this work, we develop a system that detects and identifies food allergies using food photographs. To summaries, powerful computer algorithms such as transfer learning (ResNet50) have been taught to detect food type and validate the identified label in dataset food 101, as well as supply nutrients. The fundamental purpose of this study was to create a single framework capable of managing the difficult process of detecting, localizing, and classifying food allergies. Furthermore, larger weight parameter optimization using Adam and RMS Prop optimizers was attempted to increase their performance on healthy and allergic food image datasets. The Resnet-50 was trained to obtain the greatest mean average accuracy when compared to the other transfer learning meta-architectures. It achieved the best-identifying results by utilizing an Adam optimizer and obtaining 95% accuracy. The suggested technique was discovered to be novel since it detects all food types and then provides the nutrients of that meal from another dataset. In reality, employing the transfer learning technique to successfully diagnose food allergies would assist to prevent the adverse application of issues in diet management.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130023821","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187291
Nagababu Andraju, G. Curtzwiler, Yun Ji, E. Kozliak, Prakash Ranganathan
Per- and polyfluoroalkyl substances (PFAS) are known for their persistence, toxicity, and potential to cause harm to human health and the environment. Traditional monitoring methods are often expensive and time-consuming. The paper provides a review of existing machine learning (ML) models for PFAS detection and treatment processes. The paper also highlights a ML workflow process for PFAS detection, remediation technologies, and the need for unified open-source database for PFAS assessment in water.
{"title":"Machine Learning Models for PFAS Tracking, Detection and Remediation: A Review","authors":"Nagababu Andraju, G. Curtzwiler, Yun Ji, E. Kozliak, Prakash Ranganathan","doi":"10.1109/eIT57321.2023.10187291","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187291","url":null,"abstract":"Per- and polyfluoroalkyl substances (PFAS) are known for their persistence, toxicity, and potential to cause harm to human health and the environment. Traditional monitoring methods are often expensive and time-consuming. The paper provides a review of existing machine learning (ML) models for PFAS detection and treatment processes. The paper also highlights a ML workflow process for PFAS detection, remediation technologies, and the need for unified open-source database for PFAS assessment in water.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128940499","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187303
Rasha Ghabboun, Diana W. Dawoud, Eman Abu Shabab, Shereen S. Ismail
Vehicular Visible Light Communication (VVLC) systems is considered a revolutionary solution to ensure safe autonomous driving. VVLC systems have been considered to provide vehicle to vehicle (V2V), vehicle-to-infrastructure (V2I) and vehicle to everything (V2X) communication. While V2V systems have been extensively studied, demonstrated, evaluated and tested in the literature, research work related to V2I and V2X is still limited. In this regard, this paper considers utilizing VVLC to design cheap speed limit broadcasting system that provides adaptive real-time speed limit information, unlike what is proposed in the literature. The proposed technique only modifies the currently employed electronic speed signals to smart adaptive speed signals via the use of the visible light communication link. Experimental results confirm the feasibility and effectiveness of the visible light link to convey speed limit information.
{"title":"Adaptive Real-Time Speed Limit Broadcasting for Autonomous Driving applications Using Visible Light Communication","authors":"Rasha Ghabboun, Diana W. Dawoud, Eman Abu Shabab, Shereen S. Ismail","doi":"10.1109/eIT57321.2023.10187303","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187303","url":null,"abstract":"Vehicular Visible Light Communication (VVLC) systems is considered a revolutionary solution to ensure safe autonomous driving. VVLC systems have been considered to provide vehicle to vehicle (V2V), vehicle-to-infrastructure (V2I) and vehicle to everything (V2X) communication. While V2V systems have been extensively studied, demonstrated, evaluated and tested in the literature, research work related to V2I and V2X is still limited. In this regard, this paper considers utilizing VVLC to design cheap speed limit broadcasting system that provides adaptive real-time speed limit information, unlike what is proposed in the literature. The proposed technique only modifies the currently employed electronic speed signals to smart adaptive speed signals via the use of the visible light communication link. Experimental results confirm the feasibility and effectiveness of the visible light link to convey speed limit information.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122807298","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187286
Jun Chen, Zhao-Ying Zhou
Battery cell imbalance in electric vehicles (EV) has been extensively investigated in the literature to understand its origin and mitigation control. However, the correlation between cell imbalance and EV range deserves further investigation, which can be critical in designing a balancing controller. To address this issue, this paper conducts a Monte Carlo simulation to randomly sample cell parameters with different standard deviations to analyze their impacts. More specifically, distance correlation will be utilized to measure the correlation between battery cell parameters/variations and EV driving range. Furthermore, a nonlinear model predictive controller is developed to illustrate the efficacy of balancing controls in extending EV driving range.
{"title":"Battery Cell Imbalance and Electric Vehicles Range: Correlation and NMPC-based Balancing Control","authors":"Jun Chen, Zhao-Ying Zhou","doi":"10.1109/eIT57321.2023.10187286","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187286","url":null,"abstract":"Battery cell imbalance in electric vehicles (EV) has been extensively investigated in the literature to understand its origin and mitigation control. However, the correlation between cell imbalance and EV range deserves further investigation, which can be critical in designing a balancing controller. To address this issue, this paper conducts a Monte Carlo simulation to randomly sample cell parameters with different standard deviations to analyze their impacts. More specifically, distance correlation will be utilized to measure the correlation between battery cell parameters/variations and EV driving range. Furthermore, a nonlinear model predictive controller is developed to illustrate the efficacy of balancing controls in extending EV driving range.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131335947","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187365
J. Ford, David Arnold, J. Saniie
Hands-on learning environments and cyber ranges are popular tools in cybersecurity education. These resources provide students with practical assessments to strengthen their abilities and can assist in transferring material from the classroom to real-world scenarios. Additionally, virtualization environments, such as Proxmox, provide scalability and network flexibility that can be adapted to newly discovered threats. However, due to the increasing demand for cybersecurity skills and experience, learning environments must support an even greater number of students each term. Manual provisioning and management of environments for large student populations can consume valuable time for the instructor. To address this challenge, we developed an Environment Provisioning and Management Tool for cybersecurity education. Our solution interacts with the exposed Proxmox API to automate the process of user creation, server provisioning, and server destruction for a large set of users. Remote access will be managed by a pfSense firewall. Based on our testing, a six-machine user environment could be provisioned in 14.96 seconds and destroyed in 15.06 seconds.
{"title":"Environment Provisioning and Management for Cybersecurity Education","authors":"J. Ford, David Arnold, J. Saniie","doi":"10.1109/eIT57321.2023.10187365","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187365","url":null,"abstract":"Hands-on learning environments and cyber ranges are popular tools in cybersecurity education. These resources provide students with practical assessments to strengthen their abilities and can assist in transferring material from the classroom to real-world scenarios. Additionally, virtualization environments, such as Proxmox, provide scalability and network flexibility that can be adapted to newly discovered threats. However, due to the increasing demand for cybersecurity skills and experience, learning environments must support an even greater number of students each term. Manual provisioning and management of environments for large student populations can consume valuable time for the instructor. To address this challenge, we developed an Environment Provisioning and Management Tool for cybersecurity education. Our solution interacts with the exposed Proxmox API to automate the process of user creation, server provisioning, and server destruction for a large set of users. Remote access will be managed by a pfSense firewall. Based on our testing, a six-machine user environment could be provisioned in 14.96 seconds and destroyed in 15.06 seconds.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126630060","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187265
Minakshi Arya, Shubhavi Arya, Saatvik Arya
In recent years, there has been a significant increase in malware attacks on IoT devices. As a result, there is a critical need to develop a robust malware detection model that can detect malware in real-time. This study explores different algorithms to identify the distinctions between various types of malware and develop a malware detection system based on botnets such as Mirai, Okiru, and Torii. We evaluate the performance of the malware detection system using RapidMiner and compare the results of different algorithms including Random Forest, Deep Learning, Naive Bayes, kNN, and Decision Tree. Our results show that the Random Forest algorithm outperforms the others and is the most effective at detecting malware in real-time.
{"title":"An Evaluation of Real-time Malware Detection in IoT Devices: Comparison of Machine Learning Algorithms with RapidMiner","authors":"Minakshi Arya, Shubhavi Arya, Saatvik Arya","doi":"10.1109/eIT57321.2023.10187265","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187265","url":null,"abstract":"In recent years, there has been a significant increase in malware attacks on IoT devices. As a result, there is a critical need to develop a robust malware detection model that can detect malware in real-time. This study explores different algorithms to identify the distinctions between various types of malware and develop a malware detection system based on botnets such as Mirai, Okiru, and Torii. We evaluate the performance of the malware detection system using RapidMiner and compare the results of different algorithms including Random Forest, Deep Learning, Naive Bayes, kNN, and Decision Tree. Our results show that the Random Forest algorithm outperforms the others and is the most effective at detecting malware in real-time.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115257422","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187278
Shereen S. Ismail, Diana W. Dawoud, Tamara Al-Zyoud, H. Reza
Blockchain is an emerging technology that can be utilized to enhance Wireless Sensor Networks (WSNs) security level in various Internet of Things (IoT) applications. However, the implementation of blockchain in WSNs remains a challenging task due to the high demands for processing and communication. WSNs are prone to different types of cyber-attacks and the sensor nodes can be compromised or become unreliable as they are the primary data sources. To address this issue, it is crucial to incorporate a blockchain-based trust mechanism that guarantees the selection of trusted sources of data-gathering. This paper proposes a lightweight blockchain-based adaptive trust management mechanism that maintains nodes' trust and facilitates the identification of malicious nodes. A trust smart contract is introduced to evaluate the trustworthiness of each sensor node based on its behavior during the network operation using a set of assessment metrics such as node status, Transmitted Signal Strength, Packet Sending Rate, Packet Forwarding Rate, and Forwarding Delay. The proposed mechanism is shown to help mitigate potential cyber-attacks and maintain trustworthiness among sensor nodes.
{"title":"Towards Blockchain-based Adaptive Trust Management in Wireless Sensor Networks","authors":"Shereen S. Ismail, Diana W. Dawoud, Tamara Al-Zyoud, H. Reza","doi":"10.1109/eIT57321.2023.10187278","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187278","url":null,"abstract":"Blockchain is an emerging technology that can be utilized to enhance Wireless Sensor Networks (WSNs) security level in various Internet of Things (IoT) applications. However, the implementation of blockchain in WSNs remains a challenging task due to the high demands for processing and communication. WSNs are prone to different types of cyber-attacks and the sensor nodes can be compromised or become unreliable as they are the primary data sources. To address this issue, it is crucial to incorporate a blockchain-based trust mechanism that guarantees the selection of trusted sources of data-gathering. This paper proposes a lightweight blockchain-based adaptive trust management mechanism that maintains nodes' trust and facilitates the identification of malicious nodes. A trust smart contract is introduced to evaluate the trustworthiness of each sensor node based on its behavior during the network operation using a set of assessment metrics such as node status, Transmitted Signal Strength, Packet Sending Rate, Packet Forwarding Rate, and Forwarding Delay. The proposed mechanism is shown to help mitigate potential cyber-attacks and maintain trustworthiness among sensor nodes.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129855718","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187280
S. Tasnim, Daniel Piner
Mobile sensing applications are software programs that are written for mobile devices, such as smartphones and tablets, whose collective purpose is to turn the user and the device into a sensor for data collection. These applications require the user's approval to access certain features within the device and its operating system. Mobile sensing systems have a wide variety of applications to provide researchers with real data that they can use to solve problems such as air quality monitoring, contact tracing, medical resource allocation, among others. In this paper, our goal is to analyze different mobile sensing applications (app) that are particularly developed for pandemic monitoring. We classified such apps into two groups, one that performs contact tracing and the other is non-contact tracing applications. We present detailed description of several highly used pandemic monitoring mobile applications, noting pros and cons of each.
{"title":"Analysis of Mobile Sensing Applications for Pandemic Monitoring","authors":"S. Tasnim, Daniel Piner","doi":"10.1109/eIT57321.2023.10187280","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187280","url":null,"abstract":"Mobile sensing applications are software programs that are written for mobile devices, such as smartphones and tablets, whose collective purpose is to turn the user and the device into a sensor for data collection. These applications require the user's approval to access certain features within the device and its operating system. Mobile sensing systems have a wide variety of applications to provide researchers with real data that they can use to solve problems such as air quality monitoring, contact tracing, medical resource allocation, among others. In this paper, our goal is to analyze different mobile sensing applications (app) that are particularly developed for pandemic monitoring. We classified such apps into two groups, one that performs contact tracing and the other is non-contact tracing applications. We present detailed description of several highly used pandemic monitoring mobile applications, noting pros and cons of each.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130198817","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187250
M. Sarsengeldin, Sanim Imatayeva, Nurmukhamed Abeuov, Myrzakhan Naukhanov, Abdullah Said Erdogan, Debesh Jha, Ulas Bagci
The Gastrointestinal (GI) tract is responsible for different types of cancer-related mortality worldwide. Regular screening is recommended to detect abnormalities in the GI tract early. However, studies have shown a large number of miss-rates of early GI precursors. This is mostly due to the shortage of experienced physicians and the overall clinical burden. A computer-aided diagnosis system can play a significant role in identifying abnormalities and assisting gastroenterologists during the examination. The main objective of this work is to develop a deep learning-based model for gastrointestinal tract findings classification (pathological findings, anatomical landmarks, polyp removal cases, therapeutic interventions, and the quality of mucosal views) using VGG16 and Capsule Networks. We ex-periment with two commonly available GI endoscopy datasets (Kvasir and HyperKvasir) to achieve this goal. We proposed VGG16+CapsNets-based architecture for the classification of GI abnormalities and findings. For the Kvasir dataset (5 classes), we obtained Matthew's correlation coefficient (MCC) of 89.00%. Similarly, for the HyperKvasir dataset (23 classes), we obtained an MCC of 83.00%. Overall our obtained results are good with the highly imbalanced dataset. Our experimental results on the retrospective dataset showed that the proposed model could act as a benchmark for GI endoscopy image classification tasks.
{"title":"Gastrointestinal Disease Diagnosis with Hybrid Model of Capsules and CNNs","authors":"M. Sarsengeldin, Sanim Imatayeva, Nurmukhamed Abeuov, Myrzakhan Naukhanov, Abdullah Said Erdogan, Debesh Jha, Ulas Bagci","doi":"10.1109/eIT57321.2023.10187250","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187250","url":null,"abstract":"The Gastrointestinal (GI) tract is responsible for different types of cancer-related mortality worldwide. Regular screening is recommended to detect abnormalities in the GI tract early. However, studies have shown a large number of miss-rates of early GI precursors. This is mostly due to the shortage of experienced physicians and the overall clinical burden. A computer-aided diagnosis system can play a significant role in identifying abnormalities and assisting gastroenterologists during the examination. The main objective of this work is to develop a deep learning-based model for gastrointestinal tract findings classification (pathological findings, anatomical landmarks, polyp removal cases, therapeutic interventions, and the quality of mucosal views) using VGG16 and Capsule Networks. We ex-periment with two commonly available GI endoscopy datasets (Kvasir and HyperKvasir) to achieve this goal. We proposed VGG16+CapsNets-based architecture for the classification of GI abnormalities and findings. For the Kvasir dataset (5 classes), we obtained Matthew's correlation coefficient (MCC) of 89.00%. Similarly, for the HyperKvasir dataset (23 classes), we obtained an MCC of 83.00%. Overall our obtained results are good with the highly imbalanced dataset. Our experimental results on the retrospective dataset showed that the proposed model could act as a benchmark for GI endoscopy image classification tasks.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"7 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128766548","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 : 2023-05-18DOI: 10.1109/eIT57321.2023.10187257
Rabia Emhamed Al Mamlook, Sujeet Shresth, Tasnim Gharaibeh, A. Almuflih, Wassnaa Al-Mawee, H. Bzizi
Breast cancer is a leading cause of death among women worldwide. Early detection and diagnosis are crucial to improving the chances of survival. This paper presents a study on the diagnosis of breast cancer using various machine-learning approaches. The study includes the performance evaluation of nine different techniques using confusion matrix accuracy for Sensitivity, Specificity, Precision, PME, PPV, NPV, and Model Accuracy. AdaBoost is found to have the highest Sensitivity and PME, while Random Forest and MLP gave the best Specificity and Precision. Logistic Regression is found to be the best model for accuracy with 97.8%, followed by SVM with 96.49%, Random Forest with 95.61%, and KNN & Decision Forest with 94.73%. The proposed approach is found to have the highest accuracy of 97.80% compared to other approaches studied. Our results indicate that the proposed approach using discretization can significantly improve the signal-to-noise ratio in the diagnosis of breast cancer. This approach can accurately predict and diagnose breast cancer using a subset of features.
{"title":"Machine Learning Approaches for Early Diagnosis of Breast Cancer: A Comparative Study of Performance Evaluation","authors":"Rabia Emhamed Al Mamlook, Sujeet Shresth, Tasnim Gharaibeh, A. Almuflih, Wassnaa Al-Mawee, H. Bzizi","doi":"10.1109/eIT57321.2023.10187257","DOIUrl":"https://doi.org/10.1109/eIT57321.2023.10187257","url":null,"abstract":"Breast cancer is a leading cause of death among women worldwide. Early detection and diagnosis are crucial to improving the chances of survival. This paper presents a study on the diagnosis of breast cancer using various machine-learning approaches. The study includes the performance evaluation of nine different techniques using confusion matrix accuracy for Sensitivity, Specificity, Precision, PME, PPV, NPV, and Model Accuracy. AdaBoost is found to have the highest Sensitivity and PME, while Random Forest and MLP gave the best Specificity and Precision. Logistic Regression is found to be the best model for accuracy with 97.8%, followed by SVM with 96.49%, Random Forest with 95.61%, and KNN & Decision Forest with 94.73%. The proposed approach is found to have the highest accuracy of 97.80% compared to other approaches studied. Our results indicate that the proposed approach using discretization can significantly improve the signal-to-noise ratio in the diagnosis of breast cancer. This approach can accurately predict and diagnose breast cancer using a subset of features.","PeriodicalId":113717,"journal":{"name":"2023 IEEE International Conference on Electro Information Technology (eIT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127948589","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：