Pub Date : 2023-03-05DOI: 10.24018/ejai.2023.2.2.18
Ajah C. Ogbonnaya, Emmanuel M. Eronu, F. Shaibu, Ikechukwu N. Amalu, B. G. Najashi
With the advent of several fault detection techniques in modern control systems design, this paper adopted the Artificial Neural Network (ANN) Fault Detection scheme for the Fault Detection of the Attitude Control System for a Communication Satellite. In satellite applications, telemetry data can be very large, and ANN is best suited for network modeling involving large sets of data. The availability of real satellite data from Nigcomsat-1R communication satellite provided a practical platform to assess the fault detection algorithm. Results obtained showed a good correlation between raw satellite telemetry data and Neural Network model-generated results for subsequent fault detection. The fault detection models were able to detect faults, log them and provide a notification to enhance subsequent isolation and rectification. Momentum Wheel Speed and Torque were used to investigate the performance of the wheels while the Momentum Wheel Voltage and Current helped to monitor the wheel’s health state. A fault is detected if the absolute difference between original output (MW Torque) and the NN Torque output is greater than 0.012. With this, an accuracy of 100% and mean squared error of 9.8489e-6 were achieved.
{"title":"Fault Diagnosis for Momentum Wheels of Communication Satellite Based on Artificial Neural Network","authors":"Ajah C. Ogbonnaya, Emmanuel M. Eronu, F. Shaibu, Ikechukwu N. Amalu, B. G. Najashi","doi":"10.24018/ejai.2023.2.2.18","DOIUrl":"https://doi.org/10.24018/ejai.2023.2.2.18","url":null,"abstract":"With the advent of several fault detection techniques in modern control systems design, this paper adopted the Artificial Neural Network (ANN) Fault Detection scheme for the Fault Detection of the Attitude Control System for a Communication Satellite. In satellite applications, telemetry data can be very large, and ANN is best suited for network modeling involving large sets of data. The availability of real satellite data from Nigcomsat-1R communication satellite provided a practical platform to assess the fault detection algorithm. Results obtained showed a good correlation between raw satellite telemetry data and Neural Network model-generated results for subsequent fault detection. The fault detection models were able to detect faults, log them and provide a notification to enhance subsequent isolation and rectification. Momentum Wheel Speed and Torque were used to investigate the performance of the wheels while the Momentum Wheel Voltage and Current helped to monitor the wheel’s health state. A fault is detected if the absolute difference between original output (MW Torque) and the NN Torque output is greater than 0.012. With this, an accuracy of 100% and mean squared error of 9.8489e-6 were achieved.","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131109242","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 : 2023-02-08DOI: 10.24018/ejai.2023.2.1.16
Shinji Kawakura, M. Hirafuji, S. Ninomiya, R. Shibasaki
In this study, we use explainable artificial intelligence (XAI) based on class activation map (CAM) techniques. Specifically, we use Grad-CAM, Grad-CAM++, and ScoreCAM to analyze outdoor physical agricultural (agri-) worker image datasets. In previous studies, we developed body-sensing systems to analyze human dynamics with the aim of enhancing agri-techniques, training methodologies, and worker development. These include distant, visual data-based sensing systems that capture image and movie datasets related to agri-worker motion and posture. For this study, we first obtained the aforementioned image datasets for researcher review. Then, we developed and executed Python programs with Open-Source Computer Vision (OpenCV) libraries and PyTorch to run XAI-oriented systems based on CAM techniques and obtained heat map-pictures of the visual explanations. Besides, we implement optical flow-based image analyses using our Visual C++ programs with OpenCV libraries, automatically set and chase the characteristic points related to the video datasets. Next, we analyze the dataset features and compare experienced and inexperienced subject groups. We investigate the output’s features, accuracies, and robustness to be able to make recommendations for real agri-workers, managers, product-developers, and researchers. Our findings indicate that the visualized output datasets are especially useful and may support further development of applied methods for these groups.
{"title":"Visual Analysis of Agricultural Workers using Explainable Artificial Intelligence (XAI) on Class Activation Map (CAM) with Characteristic Point Data Output from OpenCV-based Analysis","authors":"Shinji Kawakura, M. Hirafuji, S. Ninomiya, R. Shibasaki","doi":"10.24018/ejai.2023.2.1.16","DOIUrl":"https://doi.org/10.24018/ejai.2023.2.1.16","url":null,"abstract":"In this study, we use explainable artificial intelligence (XAI) based on class activation map (CAM) techniques. Specifically, we use Grad-CAM, Grad-CAM++, and ScoreCAM to analyze outdoor physical agricultural (agri-) worker image datasets. In previous studies, we developed body-sensing systems to analyze human dynamics with the aim of enhancing agri-techniques, training methodologies, and worker development. These include distant, visual data-based sensing systems that capture image and movie datasets related to agri-worker motion and posture. For this study, we first obtained the aforementioned image datasets for researcher review. Then, we developed and executed Python programs with Open-Source Computer Vision (OpenCV) libraries and PyTorch to run XAI-oriented systems based on CAM techniques and obtained heat map-pictures of the visual explanations. Besides, we implement optical flow-based image analyses using our Visual C++ programs with OpenCV libraries, automatically set and chase the characteristic points related to the video datasets. Next, we analyze the dataset features and compare experienced and inexperienced subject groups. We investigate the output’s features, accuracies, and robustness to be able to make recommendations for real agri-workers, managers, product-developers, and researchers. Our findings indicate that the visualized output datasets are especially useful and may support further development of applied methods for these groups.","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117276454","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 : 2022-12-02DOI: 10.24018/ejai.2022.1.3.14
Shinji Kawakura, M. Hirafuji, S. Ninomiya, R. Shibasaki
We use explainable artificial intelligence (XAI) based on Explain Like I’m 5 (ELI5), Partial Dependency Plot box (PDPbox), and Skater to analyze diverse physical agricultural (agri-) worker datasets. We have developed various promising body-sensing systems to enhance agri-technical advancement, training and worker development, and security. This includes wearable sensing systems (WSSs) that can capture real-time three-axis acceleration and angular velocity data related to agri-worker motion by analyzing human dynamics and statistics in different agri-environments, such as fields, meadows, and gardens. After investigating the obtained time-series data using a novel program written in Python, we discuss our findings and recommendations with real agri-workers and managers. In this study, we use XAI and visualization to analyze diverse data of experienced and inexperienced agri-workers to develop an applied method for agri-directors to train agri-workers.
我们使用基于Explain Like I 'm 5 (ELI5)、Partial Dependency Plot box (PDPbox)和Skater的可解释人工智能(XAI)来分析各种物理农业(agri-)工人数据集。我们开发了各种有前途的身体传感系统，以促进农业技术进步、培训和工人发展以及安全。这包括可穿戴传感系统(wss)，它可以通过分析不同农业环境(如田地、草地和花园)中的人体动力学和统计数据，捕获与农业工人运动相关的实时三轴加速度和角速度数据。在使用Python编写的新程序调查获得的时间序列数据后，我们与真正的农业工人和管理人员讨论了我们的发现和建议。在本研究中，我们使用XAI和可视化分析不同的数据，有经验和没有经验的农业工人，以开发一种适用于农业主管培训农业工人的方法。
{"title":"Adaptations of Explainable Artificial Intelligence (XAI) to Agricultural Data Models with ELI5, PDPbox, and Skater using Diverse Agricultural Worker Data","authors":"Shinji Kawakura, M. Hirafuji, S. Ninomiya, R. Shibasaki","doi":"10.24018/ejai.2022.1.3.14","DOIUrl":"https://doi.org/10.24018/ejai.2022.1.3.14","url":null,"abstract":"We use explainable artificial intelligence (XAI) based on Explain Like I’m 5 (ELI5), Partial Dependency Plot box (PDPbox), and Skater to analyze diverse physical agricultural (agri-) worker datasets. We have developed various promising body-sensing systems to enhance agri-technical advancement, training and worker development, and security. This includes wearable sensing systems (WSSs) that can capture real-time three-axis acceleration and angular velocity data related to agri-worker motion by analyzing human dynamics and statistics in different agri-environments, such as fields, meadows, and gardens. After investigating the obtained time-series data using a novel program written in Python, we discuss our findings and recommendations with real agri-workers and managers. In this study, we use XAI and visualization to analyze diverse data of experienced and inexperienced agri-workers to develop an applied method for agri-directors to train agri-workers.","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131911784","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 : 2022-11-30DOI: 10.24018/ejai.2022.1.3.13
Md. Julker Nayeem, Sohel Rana, Md. Rabiul Islam
Heart disease has become one of the alarming issues of death. It is accountable for fatty plaques in the arteries. If this fatal condition can be identified early, we can preserve many people’s arteries. Different types of supervised machine learning algorithms are applied in our research paper in order to predict heart disease existence in patient body. Besides this, we have focused on an efficient way to improve the performance of our applied classifiers. Imputing mean value technique is applied to handle null values present in our dataset. The features which are unnecessary are removed by using the info-gain feature selection technique. In order to calculate prediction accuracy, K-Nearest Neighbors (KNN), Naive Bayes and Random Forest are applied to the heart disease dataset. Accuracy, precision, recall, F1-score, and ROC are calculated which help us to compare the performance of the classification models. Handling null values on a particular column by imputing mean values of that column and our applied info-gain feature selection technique has aided us in improving the accuracy of our prediction models. Random Forest among all has given the best classification accuracy which is 95.63% with precision, recall, F1-score and ROC are 0.93, 0.92, 0.92 and 0.9, respectively.
{"title":"Prediction of Heart Disease Using Machine Learning Algorithms","authors":"Md. Julker Nayeem, Sohel Rana, Md. Rabiul Islam","doi":"10.24018/ejai.2022.1.3.13","DOIUrl":"https://doi.org/10.24018/ejai.2022.1.3.13","url":null,"abstract":"Heart disease has become one of the alarming issues of death. It is accountable for fatty plaques in the arteries. If this fatal condition can be identified early, we can preserve many people’s arteries. Different types of supervised machine learning algorithms are applied in our research paper in order to predict heart disease existence in patient body. Besides this, we have focused on an efficient way to improve the performance of our applied classifiers. Imputing mean value technique is applied to handle null values present in our dataset. The features which are unnecessary are removed by using the info-gain feature selection technique. In order to calculate prediction accuracy, K-Nearest Neighbors (KNN), Naive Bayes and Random Forest are applied to the heart disease dataset. Accuracy, precision, recall, F1-score, and ROC are calculated which help us to compare the performance of the classification models. Handling null values on a particular column by imputing mean values of that column and our applied info-gain feature selection technique has aided us in improving the accuracy of our prediction models. Random Forest among all has given the best classification accuracy which is 95.63% with precision, recall, F1-score and ROC are 0.93, 0.92, 0.92 and 0.9, respectively.","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114088523","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 : 2022-05-25DOI: 10.24018/ejai.2022.1.3.10
Ejiofor Martins Ugwu, O. Taylor, N. Nwiabu
The role of an automatic licensed plate detection system (ALPDS) cannot be over-emphasized in the world today. The need for an automated system for vehicle license plate number recognition is important for security challenges. Therefore, this paper provides a smart system for vehicle license number recognition using Computer Vision. The system was trained using images of vehicles license numbers as training data. The training images were first annotated using the Visual Graphic Generator (VGG) annotation tool, after the annotation process, the trained images were pre-processed using the OpenCV library for conversion and masking of images. TesseractOCR was then used in extracting just texts from the images. The pre-processed and segmented images were then used in training the Mask R-CNN from a pre-trained weight. The result of the proposed system shows how the Mask R-CNN model was trained in ten training steps. The mask R-CNN model obtained accuracy and a loss value for each training step. The mask R-CNN model was evaluated using both training and test data. For the training and testing data, the Mask R-CNN was evaluated in terms of accuracy and loss. The evaluation was done using graphs. The results from the graph show that the Mask R-CNN had a better accuracy result in both training and testing data. The accuracy for training data was that of 95.25% and the accuracy for the testing data was 97.69%. For real-time vehicle license plate number recognition, we deployed our proposed model to the web. Here, we built a web application that allows real-time surveillance video. Our model was tested on different vehicles in the car park. The result of the mask R-CNN on the test shows how the Mask R-CNN model was used in not just capturing and extracting the vehicle’s license plate number but predicting the characters that appeared on the vehicle’s license plate number. We also compared our proposed system with another existing system. The comparison was done in terms of accuracy, loss, and precision. The result of our proposed model gave us an accuracy of 97.69%, which is higher than the existing system (85%). This study can further be improved by using the Internet of Things in performing live video streaming and also providing a database system that will be storing the predicted vehicle numbers for cars that are detected.
{"title":"An Improved Visual Attention Model for Automated Vehicle License Plate Number Recognition Using Computer Vision","authors":"Ejiofor Martins Ugwu, O. Taylor, N. Nwiabu","doi":"10.24018/ejai.2022.1.3.10","DOIUrl":"https://doi.org/10.24018/ejai.2022.1.3.10","url":null,"abstract":"The role of an automatic licensed plate detection system (ALPDS) cannot be over-emphasized in the world today. The need for an automated system for vehicle license plate number recognition is important for security challenges. Therefore, this paper provides a smart system for vehicle license number recognition using Computer Vision. The system was trained using images of vehicles license numbers as training data. The training images were first annotated using the Visual Graphic Generator (VGG) annotation tool, after the annotation process, the trained images were pre-processed using the OpenCV library for conversion and masking of images. TesseractOCR was then used in extracting just texts from the images. The pre-processed and segmented images were then used in training the Mask R-CNN from a pre-trained weight. The result of the proposed system shows how the Mask R-CNN model was trained in ten training steps. The mask R-CNN model obtained accuracy and a loss value for each training step. The mask R-CNN model was evaluated using both training and test data. For the training and testing data, the Mask R-CNN was evaluated in terms of accuracy and loss. The evaluation was done using graphs. The results from the graph show that the Mask R-CNN had a better accuracy result in both training and testing data. The accuracy for training data was that of 95.25% and the accuracy for the testing data was 97.69%. For real-time vehicle license plate number recognition, we deployed our proposed model to the web. Here, we built a web application that allows real-time surveillance video. Our model was tested on different vehicles in the car park. The result of the mask R-CNN on the test shows how the Mask R-CNN model was used in not just capturing and extracting the vehicle’s license plate number but predicting the characters that appeared on the vehicle’s license plate number. We also compared our proposed system with another existing system. The comparison was done in terms of accuracy, loss, and precision. The result of our proposed model gave us an accuracy of 97.69%, which is higher than the existing system (85%). This study can further be improved by using the Internet of Things in performing live video streaming and also providing a database system that will be storing the predicted vehicle numbers for cars that are detected.","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127705399","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 : 2022-05-22DOI: 10.24018/ejai.2022.1.3.8
Dusan Surdilovic, Tatjana Ille, Jovita D'souza
Artificial Intelligence (AI) and machine learning are revolutionizing the way we practice dentistry today. AI solutions have been increasingly used to support doctors’ decisions in diagnostic suggestions, therapeutic protocols, personalized medicine, patient monitoring, and predicting and tracking epidemiological diseases' expansion. The clinical Decision Support System may effectively provide medical professionals with valuable data, thus improving health outcomes for patients and the general population. Software used in dental practices is constantly getting smarter. AI enables efficient patient scheduling and staffing and can prove lucrative in dentistry's financial aspect by increasing productivity and ensuring evidence-based documentation and essentials for insurance claims. In this review, we have highlighted the current trends and future direction of Smart practices. We are at the dawn of a new era, and AI is undoubtedly the future of dental practice management.
{"title":"Artificial Intelligence and Dental Practice Management","authors":"Dusan Surdilovic, Tatjana Ille, Jovita D'souza","doi":"10.24018/ejai.2022.1.3.8","DOIUrl":"https://doi.org/10.24018/ejai.2022.1.3.8","url":null,"abstract":"Artificial Intelligence (AI) and machine learning are revolutionizing the way we practice dentistry today. AI solutions have been increasingly used to support doctors’ decisions in diagnostic suggestions, therapeutic protocols, personalized medicine, patient monitoring, and predicting and tracking epidemiological diseases' expansion. The clinical Decision Support System may effectively provide medical professionals with valuable data, thus improving health outcomes for patients and the general population. Software used in dental practices is constantly getting smarter. AI enables efficient patient scheduling and staffing and can prove lucrative in dentistry's financial aspect by increasing productivity and ensuring evidence-based documentation and essentials for insurance claims. In this review, we have highlighted the current trends and future direction of Smart practices. We are at the dawn of a new era, and AI is undoubtedly the future of dental practice management.","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122000941","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 : 2022-05-20DOI: 10.24018/ejai.2022.1.3.9
A. Zeid, Trisha Bhatt, Hayley A. Morris
Bike-ride sharing systems are the new generation of traditional bike rentals, where the entire process is automated. A user rents a bike from one location and returns it at another location. There are more than 500 bike-ride sharing systems around the world, consisting of more than 500,000 bikes. Bike-ride sharing systems are typically found in urban and large cities such as Boston, N.Y. City, Washington DC, Paris, Montreal, and Barcelona. Bike-ride sharing is particularly important due to their important impact on traffic, environment, and health. As popular as bike-ride sharing systems are, there is a lack of a reliable model to forecast (predict) bike rental demand daily. Lack of available bikes constitutes an inconvenience to individuals seeking a bike at a certain location and a loss of revenues for companies operating the bikes. This paper develops a Machine Learning (ML) model (algorithm) to forecast (predict) the number of bikes rented daily based on historical data. Moreover, the model overlays environmental and seasonal settings to study their impact on bike rental demand. We test our ML model using a real-life dataset obtained from a local bike-ride sharing company in the City of Boston in the state of Massachusetts in the United States. We also applied the model to historical dataset from New York City (NYC). In both cases, the model is accurate and reliable.
{"title":"Machine Learning Model to Forecast Demand of Boston Bike-Ride Sharing","authors":"A. Zeid, Trisha Bhatt, Hayley A. Morris","doi":"10.24018/ejai.2022.1.3.9","DOIUrl":"https://doi.org/10.24018/ejai.2022.1.3.9","url":null,"abstract":"Bike-ride sharing systems are the new generation of traditional bike rentals, where the entire process is automated. A user rents a bike from one location and returns it at another location. There are more than 500 bike-ride sharing systems around the world, consisting of more than 500,000 bikes. Bike-ride sharing systems are typically found in urban and large cities such as Boston, N.Y. City, Washington DC, Paris, Montreal, and Barcelona. Bike-ride sharing is particularly important due to their important impact on traffic, environment, and health. As popular as bike-ride sharing systems are, there is a lack of a reliable model to forecast (predict) bike rental demand daily. Lack of available bikes constitutes an inconvenience to individuals seeking a bike at a certain location and a loss of revenues for companies operating the bikes. This paper develops a Machine Learning (ML) model (algorithm) to forecast (predict) the number of bikes rented daily based on historical data. Moreover, the model overlays environmental and seasonal settings to study their impact on bike rental demand. We test our ML model using a real-life dataset obtained from a local bike-ride sharing company in the City of Boston in the state of Massachusetts in the United States. We also applied the model to historical dataset from New York City (NYC). In both cases, the model is accurate and reliable.\u0000 ","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133899177","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 : 2022-04-27DOI: 10.24018/ejai.2022.1.2.7
A. Abdulhameed, Q. Memon
UAVs also known as drones are gaining more popularity day by day and its applications keep increasing. They are being used in several areas, such as transportation, surveillance, defense, etc. They open doors for new innovative applications due to their compact design, flexibility in landing and departing, the accurate possible control of their flying methodology. As a part of expected future of extensive use of this device, a landing control system for prioritizing the landing of large number of UAVs at a certain station using support vector machine learning is proposed. The proposed system shows promising results in terms of controlling landing sequences of a large number of UAVs. Based on results, the conclusions are presented.
{"title":"Support Vector Machine Based Design and Simulation of Air Traffic Management for Prioritized Landing of Large Number of UAVs","authors":"A. Abdulhameed, Q. Memon","doi":"10.24018/ejai.2022.1.2.7","DOIUrl":"https://doi.org/10.24018/ejai.2022.1.2.7","url":null,"abstract":"UAVs also known as drones are gaining more popularity day by day and its applications keep increasing. They are being used in several areas, such as transportation, surveillance, defense, etc. They open doors for new innovative applications due to their compact design, flexibility in landing and departing, the accurate possible control of their flying methodology. As a part of expected future of extensive use of this device, a landing control system for prioritizing the landing of large number of UAVs at a certain station using support vector machine learning is proposed. The proposed system shows promising results in terms of controlling landing sequences of a large number of UAVs. Based on results, the conclusions are presented.\u0000\u0000","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133794519","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 : 2022-03-23DOI: 10.24018/ejai.2022.1.2.4
O. Taylor, P. S. Ezekiel
Over the years, malware (malicious software) has become a major challenge for computer users, organizations, and even countries. In particular, a compromise of a set of inflamed hosts (aka zombies or bots) is one of the severe threats to Internet security. Botnet is described as some computer systems or devices controlled on the Internet to carry out unintentional and malicious acts without the owner's permission. Due to the continuously progressing behavior of botnets, the conventional methods fail to identify botnets. In other to solve the stated problem, this paper presents a smart system for detecting behavioural bootnet attacks using Random Forest Classifier and Principal Component Analysis (PCA). The system starts with a botnet dataset that was used in building a robust model in detecting Bootnet attacks. The dataset was pre-processed using pandas library for data cleaning. PCA was used in reducing the dimension of the dataset, so as to avoid data imbalance. The result of the PCA was used as input to the random forest classifier. The random forest classifier was trained using the number of estimators as 1000. The result of the model shows a promising accuracy of about 99%.
{"title":"A Smart System for Detecting Behavioural Botnet Attacks using Random Forest Classifier with Principal Component Analysis","authors":"O. Taylor, P. S. Ezekiel","doi":"10.24018/ejai.2022.1.2.4","DOIUrl":"https://doi.org/10.24018/ejai.2022.1.2.4","url":null,"abstract":"Over the years, malware (malicious software) has become a major challenge for computer users, organizations, and even countries. In particular, a compromise of a set of inflamed hosts (aka zombies or bots) is one of the severe threats to Internet security. Botnet is described as some computer systems or devices controlled on the Internet to carry out unintentional and malicious acts without the owner's permission. Due to the continuously progressing behavior of botnets, the conventional methods fail to identify botnets. In other to solve the stated problem, this paper presents a smart system for detecting behavioural bootnet attacks using Random Forest Classifier and Principal Component Analysis (PCA). The system starts with a botnet dataset that was used in building a robust model in detecting Bootnet attacks. The dataset was pre-processed using pandas library for data cleaning. PCA was used in reducing the dimension of the dataset, so as to avoid data imbalance. The result of the PCA was used as input to the random forest classifier. The random forest classifier was trained using the number of estimators as 1000. The result of the model shows a promising accuracy of about 99%.","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114072907","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 : 2022-02-15DOI: 10.24018/ejai.2022.1.1.2
Dev Arastu Panchariya
In recent times, mankind is seeking for certain peculiar solutions to multiple facets containing an identically very fundamental philosophy i.e., certainly intend to have indeterminism as a primordial prerequisite; however, that indeterminism is itself like a void filled with determinism as analogous to the quantum computing as qubits and the corresponding complexity. In the meantime, there are algorithms and mathematical frameworks and those in general; yield the required distinctions in the underlying theories constructed upon principles which then give rise to respective objectifications. But, when it comes to the Artificial Intelligence and Machine Learning, then there find some mathematical gaps in order to connect other regimes in relation of one and the other. The proposed discovery in this paper is about quilting some of those gaps as like the whole structure of Artificial Intelligence is yet to be developed in the realm concerning with responsive analysis in betwixt to humans and machines or beyond to such analogy. Hence, the entire introduction & incitement of this theory is to mathematically determine the deep rationality as responsive manifestation of human brain with a designed computing and both with the highest potential degree of attributions or overlaps and both the conditions will be shown mathematically herewith as identifications that make each other separate and clear to persuade.
{"title":"The Theory of Natural-Artificial Intelligence","authors":"Dev Arastu Panchariya","doi":"10.24018/ejai.2022.1.1.2","DOIUrl":"https://doi.org/10.24018/ejai.2022.1.1.2","url":null,"abstract":"In recent times, mankind is seeking for certain peculiar solutions to multiple facets containing an identically very fundamental philosophy i.e., certainly intend to have indeterminism as a primordial prerequisite; however, that indeterminism is itself like a void filled with determinism as analogous to the quantum computing as qubits and the corresponding complexity. In the meantime, there are algorithms and mathematical frameworks and those in general; yield the required distinctions in the underlying theories constructed upon principles which then give rise to respective objectifications. But, when it comes to the Artificial Intelligence and Machine Learning, then there find some mathematical gaps in order to connect other regimes in relation of one and the other. The proposed discovery in this paper is about quilting some of those gaps as like the whole structure of Artificial Intelligence is yet to be developed in the realm concerning with responsive analysis in betwixt to humans and machines or beyond to such analogy. Hence, the entire introduction & incitement of this theory is to mathematically determine the deep rationality as responsive manifestation of human brain with a designed computing and both with the highest potential degree of attributions or overlaps and both the conditions will be shown mathematically herewith as identifications that make each other separate and clear to persuade.","PeriodicalId":360205,"journal":{"name":"European Journal of Artificial Intelligence and Machine Learning","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132601108","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：