Pub Date : 2023-06-08DOI: 10.1109/HORA58378.2023.10156729
Faris Ali Jasim Shaban
At 2019, China had a large number of severe cases of pneumonia, particularly in Wuhan. A SARS virus was detected after a thorough realization of sample from the sick people. Due to the form of the virus, which resembled a crown, it was given the name CORONA; the abbreviation COVID-19 stands for 2019 CORONA VIRUS. The World Health Organization WHO classified it as COVID-19, a pandemic, on March, 2020. In this study, artificial neural networks—which function similarly to the network of human neurons—are built to imitate how the human brain functions. Due to this, neural networks were used to connect the diagnosis to the symptoms, where the platform and knowledge-based system were found to be compatible, the symptoms that depend on the diagnosed disease were represented as numerical data, and after the network had been trained, the system was found to be appropriate for the accurate diagnosis of the disease. Our current study includes two primary phases: the training phase of neurons, which includes inputting the training data and generating random weights whose value is less than 1 for each of these inputs, and applying the neural network algorithm to them. The testing phase, where the two inputs were entered without the results to assess how well the proposed system works. Three statistical calculations R, RMSE, MAPE were made in order to evaluate the performance of the existing system and its findings.
{"title":"NNA and Activation Equation-Based Prediction of New COVID-19 Infections","authors":"Faris Ali Jasim Shaban","doi":"10.1109/HORA58378.2023.10156729","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156729","url":null,"abstract":"At 2019, China had a large number of severe cases of pneumonia, particularly in Wuhan. A SARS virus was detected after a thorough realization of sample from the sick people. Due to the form of the virus, which resembled a crown, it was given the name CORONA; the abbreviation COVID-19 stands for 2019 CORONA VIRUS. The World Health Organization WHO classified it as COVID-19, a pandemic, on March, 2020. In this study, artificial neural networks—which function similarly to the network of human neurons—are built to imitate how the human brain functions. Due to this, neural networks were used to connect the diagnosis to the symptoms, where the platform and knowledge-based system were found to be compatible, the symptoms that depend on the diagnosed disease were represented as numerical data, and after the network had been trained, the system was found to be appropriate for the accurate diagnosis of the disease. Our current study includes two primary phases: the training phase of neurons, which includes inputting the training data and generating random weights whose value is less than 1 for each of these inputs, and applying the neural network algorithm to them. The testing phase, where the two inputs were entered without the results to assess how well the proposed system works. Three statistical calculations R, RMSE, MAPE were made in order to evaluate the performance of the existing system and its findings.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114280749","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 : 2023-06-08DOI: 10.1109/HORA58378.2023.10156761
Usman Ahmad Usmani, A. Happonen, J. Watada
Human-Centered Artificial Intelligence (AI) focuses on AI systems prioritizing user empowerment and ethical considerations. We explore the importance of usercentric design principles and ethical guidelines in creating AI technologies that enhance user experiences and align with human values. It emphasizes user empowerment through personalized experiences and explainable AI, fostering trust and user agency. Ethical considerations, including fairness, transparency, accountability, and privacy protection, are addressed to ensure AI systems respect human rights and avoid biases. Effective human AI collaboration is emphasized, promoting shared decision-making and user control. By involving interdisciplinary collaboration, this research contributes to advancing human-centered AI, providing practical recommendations for designing AI systems that enhance user experiences, promote user empowerment, and adhere to ethical standards. It emphasizes the harmonious coexistence between humans and AI, enhancing well-being and autonomy and creating a future where AI technologies benefit humanity. Overall, this research highlights the significance of human-centered AI in creating a positive impact. By centering on users' needs and values, AI systems can be designed to empower individuals and enhance their experiences. Ethical considerations are crucial to ensure fairness and transparency. With effective collaboration between humans and AI, we can harness the potential of AI to create a future that aligns with human aspirations and promotes societal well-being.
{"title":"Human-Centered Artificial Intelligence: Designing for User Empowerment and Ethical Considerations","authors":"Usman Ahmad Usmani, A. Happonen, J. Watada","doi":"10.1109/HORA58378.2023.10156761","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156761","url":null,"abstract":"Human-Centered Artificial Intelligence (AI) focuses on AI systems prioritizing user empowerment and ethical considerations. We explore the importance of usercentric design principles and ethical guidelines in creating AI technologies that enhance user experiences and align with human values. It emphasizes user empowerment through personalized experiences and explainable AI, fostering trust and user agency. Ethical considerations, including fairness, transparency, accountability, and privacy protection, are addressed to ensure AI systems respect human rights and avoid biases. Effective human AI collaboration is emphasized, promoting shared decision-making and user control. By involving interdisciplinary collaboration, this research contributes to advancing human-centered AI, providing practical recommendations for designing AI systems that enhance user experiences, promote user empowerment, and adhere to ethical standards. It emphasizes the harmonious coexistence between humans and AI, enhancing well-being and autonomy and creating a future where AI technologies benefit humanity. Overall, this research highlights the significance of human-centered AI in creating a positive impact. By centering on users' needs and values, AI systems can be designed to empower individuals and enhance their experiences. Ethical considerations are crucial to ensure fairness and transparency. With effective collaboration between humans and AI, we can harness the potential of AI to create a future that aligns with human aspirations and promotes societal well-being.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131386068","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 : 2023-06-08DOI: 10.1109/HORA58378.2023.10156736
Jetnipat Thongprasith, Poom Separattananan, Phumrpee Meyer, R. Chanchareon
Food is an essential part of human life and plays a crucial role in maintaining good health and well-being. In various industries, such as food processing and packaging, it is essential to ensure that raw materials are divided equally to optimize the production process and reduce waste. However, traditional methods of food processing and packaging can be time-consuming and prone to errors. Hence, we are interested in developing a method for accurately portion materials into equal sizes using the Intel RealSense D435i 3D camera to capture point cloud images of object, which are then processed using Python code, running on a Raspberry Pi 4, to generate cutting planes. In the experiment on object size variations, three sizes of plasticine weighing 50 g, 150 g, and 250 g. resulting in errors of 10.2%, 8.8%, and 7.3%, respectively. In the experiment on the number of cutting plane variations, keeping the object weight fixed at 150 g at 150 g, and divided into 2, 3, 4, and 5 pieces. The resulting errors were 1.3%, 8.8%, 10.7%, and 18.2%, respectively, according to the number of pieces. Our algorithm can generate precise cutting planes to partition the volume of an object. The primary cause of errors is the shape resolution of the object's point cloud that the camera can collect and the use of human hands for cutting the object.
{"title":"Portioning Algorithm Using the Bisection Method for Slicing Food","authors":"Jetnipat Thongprasith, Poom Separattananan, Phumrpee Meyer, R. Chanchareon","doi":"10.1109/HORA58378.2023.10156736","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156736","url":null,"abstract":"Food is an essential part of human life and plays a crucial role in maintaining good health and well-being. In various industries, such as food processing and packaging, it is essential to ensure that raw materials are divided equally to optimize the production process and reduce waste. However, traditional methods of food processing and packaging can be time-consuming and prone to errors. Hence, we are interested in developing a method for accurately portion materials into equal sizes using the Intel RealSense D435i 3D camera to capture point cloud images of object, which are then processed using Python code, running on a Raspberry Pi 4, to generate cutting planes. In the experiment on object size variations, three sizes of plasticine weighing 50 g, 150 g, and 250 g. resulting in errors of 10.2%, 8.8%, and 7.3%, respectively. In the experiment on the number of cutting plane variations, keeping the object weight fixed at 150 g at 150 g, and divided into 2, 3, 4, and 5 pieces. The resulting errors were 1.3%, 8.8%, 10.7%, and 18.2%, respectively, according to the number of pieces. Our algorithm can generate precise cutting planes to partition the volume of an object. The primary cause of errors is the shape resolution of the object's point cloud that the camera can collect and the use of human hands for cutting the object.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"57 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131521500","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 : 2023-06-08DOI: 10.1109/HORA58378.2023.10156700
D. Satyanarayana, Nadir Kamal Salih Idries, Abdullah Said Al Kalbani, Gopal Rathinam
The robot path identification towards a specific destination is an important problem for robot movement applications such as logistics, warehousing, and inventorying systems. The Global Positioning System based robot tracking is one of the solutions. However, when it comes to the accuracy of robot movement towards the destination, it is not advisable the GPS based robot movement, because the small-scale robots generally move inside the buildings where it has the signaling problem, and/or travel small distances, where it has accuracy problem. In addition, many algorithms for path identification of mobile robots in the literature need centralized systems to control the mobile robots from collisions. In this paper, we propose a new method for robot path identification with Radio Frequency Identification technology. The simulation is carried out to analyze the performance of the proposed method.
{"title":"A Method for Path Identification of Wheel Robot using UHF RFID Technology","authors":"D. Satyanarayana, Nadir Kamal Salih Idries, Abdullah Said Al Kalbani, Gopal Rathinam","doi":"10.1109/HORA58378.2023.10156700","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156700","url":null,"abstract":"The robot path identification towards a specific destination is an important problem for robot movement applications such as logistics, warehousing, and inventorying systems. The Global Positioning System based robot tracking is one of the solutions. However, when it comes to the accuracy of robot movement towards the destination, it is not advisable the GPS based robot movement, because the small-scale robots generally move inside the buildings where it has the signaling problem, and/or travel small distances, where it has accuracy problem. In addition, many algorithms for path identification of mobile robots in the literature need centralized systems to control the mobile robots from collisions. In this paper, we propose a new method for robot path identification with Radio Frequency Identification technology. The simulation is carried out to analyze the performance of the proposed method.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121639586","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 : 2023-06-08DOI: 10.1109/HORA58378.2023.10156789
Omer Kayan, H. Yalcin
Knee orthoses aim to treat problems in the knees by customizing them in order to support the joint externally, protect the joint, provide bio-mechanical balance, eliminate dysfunctions, reduce pain, and strengthen weakened muscles. Since each case is different from each other, individual treatment is required. For this reason, measuring the performance of orthoses in a simulated environment before they are applied to the patients increases efficiency during the treatment. Musculoskeletal model simulations allow estimating how the orthosis will affect the patient's motions. In this paper, the deep reinforcement learning (DRL) method, which imitates the reference walking motion, is used in simulations for the model to learn to walk. The walking performance and muscle activation of four different musculoskeletal models that are healthy, injured in the knee but not wearing an orthosis, wearing passive orthosis, and wearing active orthosis are compared.
{"title":"Learning to Walk on a Human Musculoskeletal Model Wearing a Knee Orthosis via Deep Reinforcement Learning","authors":"Omer Kayan, H. Yalcin","doi":"10.1109/HORA58378.2023.10156789","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156789","url":null,"abstract":"Knee orthoses aim to treat problems in the knees by customizing them in order to support the joint externally, protect the joint, provide bio-mechanical balance, eliminate dysfunctions, reduce pain, and strengthen weakened muscles. Since each case is different from each other, individual treatment is required. For this reason, measuring the performance of orthoses in a simulated environment before they are applied to the patients increases efficiency during the treatment. Musculoskeletal model simulations allow estimating how the orthosis will affect the patient's motions. In this paper, the deep reinforcement learning (DRL) method, which imitates the reference walking motion, is used in simulations for the model to learn to walk. The walking performance and muscle activation of four different musculoskeletal models that are healthy, injured in the knee but not wearing an orthosis, wearing passive orthosis, and wearing active orthosis are compared.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132619200","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 : 2023-06-08DOI: 10.1109/HORA58378.2023.10155782
U. Yıldıran
Reinforcement Learning (RL) based methods have became popular for control and motion planning of robots, recently. Unlike sampling based motion planners, optimal policies computed by them provide feedback motion plans which eliminates the need for re-computing (optimal) trajectories when a robot starts from a different initial configuration each time. In related studies, an optimal policy (actor) and the associated value function (critic) are usually calculated preforming training in a simulation environment. During training, RL allows learning by interactions with the environment in a physically realistic manner. However, in a simulation system, it is possible to make physically unimplementable moves. Thus, instead of RL, one can make use of Dynamic Programming approaches such as Value Iteration for computing optimal policies, which does not require an exploration component and known to have better convergence properties. In addition, dimension of a value function is smaller than that of a Q-fuction, thereby lessening the severity of the curse of dimensionality. Motivated by these facts, the aim of this paper is to employ Value Iteration algorithm for motion planning of robot manipulators and elaborate its effectiveness compared to a popular RL method, Q-learning.
{"title":"Dynamic Programming vs Q-learning for Feedback Motion Planning of Manipulators","authors":"U. Yıldıran","doi":"10.1109/HORA58378.2023.10155782","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10155782","url":null,"abstract":"Reinforcement Learning (RL) based methods have became popular for control and motion planning of robots, recently. Unlike sampling based motion planners, optimal policies computed by them provide feedback motion plans which eliminates the need for re-computing (optimal) trajectories when a robot starts from a different initial configuration each time. In related studies, an optimal policy (actor) and the associated value function (critic) are usually calculated preforming training in a simulation environment. During training, RL allows learning by interactions with the environment in a physically realistic manner. However, in a simulation system, it is possible to make physically unimplementable moves. Thus, instead of RL, one can make use of Dynamic Programming approaches such as Value Iteration for computing optimal policies, which does not require an exploration component and known to have better convergence properties. In addition, dimension of a value function is smaller than that of a Q-fuction, thereby lessening the severity of the curse of dimensionality. Motivated by these facts, the aim of this paper is to employ Value Iteration algorithm for motion planning of robot manipulators and elaborate its effectiveness compared to a popular RL method, Q-learning.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"33 5‐6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132340942","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 : 2023-06-08DOI: 10.1109/HORA58378.2023.10156756
Salma Abdullah Aswad
The central theme for this thesis is the design of an aspect-based sentiment analysis model for the classification of online Italian automotive forums' comments. The work starts with designing a strategy for collecting information about target forums to make it possible to develop a machine learning-based sentiment classification model. The study involved applying the CNN and LTSM model, a state-of-the-art solution based on a parametric model that will improve the performance of a baseline algorithm, especially in case of very noisy data like the ones where this tool is supposed to be to work on. This work has been designed as a two-stage CNN and LTSM classifier in all its parts. It was compared with a one-step classifier to detect the pertinence about some topics, and eventually, the sentiment achieved an accuracy of 96.78% for all comments. The current problem passed from a typical three degrees' polarity sentiment analysis to a four labels text classification, where it will be introduced an additional category for determining whether the text is pertinent to a particular topic or not. Presenting this information, the models must be enhanced, and a cascade classification solution will be proposed. The final model is then utilized for a real-world use case. New data have been classified concerning some selected topics, finally presented exploiting a data visualization but still not satisfactory, thus making sentiment analysis an ongoing and open research subject.
{"title":"Evaluation and Analysis Data from Twitter Data By Using Hybrid CNN & LTSM","authors":"Salma Abdullah Aswad","doi":"10.1109/HORA58378.2023.10156756","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156756","url":null,"abstract":"The central theme for this thesis is the design of an aspect-based sentiment analysis model for the classification of online Italian automotive forums' comments. The work starts with designing a strategy for collecting information about target forums to make it possible to develop a machine learning-based sentiment classification model. The study involved applying the CNN and LTSM model, a state-of-the-art solution based on a parametric model that will improve the performance of a baseline algorithm, especially in case of very noisy data like the ones where this tool is supposed to be to work on. This work has been designed as a two-stage CNN and LTSM classifier in all its parts. It was compared with a one-step classifier to detect the pertinence about some topics, and eventually, the sentiment achieved an accuracy of 96.78% for all comments. The current problem passed from a typical three degrees' polarity sentiment analysis to a four labels text classification, where it will be introduced an additional category for determining whether the text is pertinent to a particular topic or not. Presenting this information, the models must be enhanced, and a cascade classification solution will be proposed. The final model is then utilized for a real-world use case. New data have been classified concerning some selected topics, finally presented exploiting a data visualization but still not satisfactory, thus making sentiment analysis an ongoing and open research subject.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133880322","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}
Women's opportunities are in the uptrend in recent days with recent laws, obligations, rules, regulations, and government promulgations in favor of women's participation in the global space. With emerging technologies and rising market competition, these opportunities are critical to women's societal development. Adding to this, various technology and IT companies are encouraging their female employees to take part in women-led events and seminars actively. After a score of deliberate perusals by the authors into the matter, it is found that a large proportion of women are least knowledgeable about these opportunities resulting in the persistence of poor outcomes. This paper takes these issues into consideration, where the authors performed data analysis on the existing women's opportunities, tabled them, and designed an analytical solution for the same. With the existence of powerful technologies like Power BI, this paper explores using power bi for visualizing the trends of opportunities in numbers and their impact on female societies. The research involves the basic requirements and salient features of Women related events, scholarships, and contributions as a result of the same. In this paper, we discuss the relevance and impact of such opportunities for women and the development of appropriate technical solutions for the same. The result of this research work contributes to the systematic aversion to the situations mentioned above and provides a valid solution by data-driven applications throughout the procedure of development. The solutions enable the users to have a clear idea about the statistics of women's opportunities in recent years and provide a clear visualization of the current scenarios involving the impact and statistical influence of these opportunities on the female society scaled to the global level.
{"title":"Data Analytics on Opportunities for Women in the Field of Technology","authors":"L. Pallavi, Sailaja Kosuru, Abhinav Goud Dulam, Kaushik Varma Datla, Kousthubha Debbata, Raghuveer Chaitanya Gangavarapu","doi":"10.1109/HORA58378.2023.10156790","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156790","url":null,"abstract":"Women's opportunities are in the uptrend in recent days with recent laws, obligations, rules, regulations, and government promulgations in favor of women's participation in the global space. With emerging technologies and rising market competition, these opportunities are critical to women's societal development. Adding to this, various technology and IT companies are encouraging their female employees to take part in women-led events and seminars actively. After a score of deliberate perusals by the authors into the matter, it is found that a large proportion of women are least knowledgeable about these opportunities resulting in the persistence of poor outcomes. This paper takes these issues into consideration, where the authors performed data analysis on the existing women's opportunities, tabled them, and designed an analytical solution for the same. With the existence of powerful technologies like Power BI, this paper explores using power bi for visualizing the trends of opportunities in numbers and their impact on female societies. The research involves the basic requirements and salient features of Women related events, scholarships, and contributions as a result of the same. In this paper, we discuss the relevance and impact of such opportunities for women and the development of appropriate technical solutions for the same. The result of this research work contributes to the systematic aversion to the situations mentioned above and provides a valid solution by data-driven applications throughout the procedure of development. The solutions enable the users to have a clear idea about the statistics of women's opportunities in recent years and provide a clear visualization of the current scenarios involving the impact and statistical influence of these opportunities on the female society scaled to the global level.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130373170","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 : 2023-06-08DOI: 10.1109/HORA58378.2023.10156803
Turgut Özseven, M. Arpacioglu
The increase in the rate of urbanization in recent years has led to an increase in environmental sound sources and, accordingly, an increase in noise pollution. Street noises, especially in big cities, pose some health problems. In terms of smart cities, accurate detection of street sounds is important in detecting unwanted sounds and responding to emergencies. In this study, research was carried out to select acoustic features of street sounds with meta-heuristic methods. In the experimental study, using the Urbansound8k dataset, feature extraction was done through openSMILE software, then feature selection was performed with PSO and WO algorithms. SVM and k-NN methods were applied for the classification process. Accuracy rates were obtained with SVM and k-NN classifiers as 88.12%, 69.32% in the PSO algorithm, 88.39%, and 70.51% in the WO algorithm, respectively.
{"title":"Classification of Urban Sounds with PSO and WO Based Feature Selection Methods","authors":"Turgut Özseven, M. Arpacioglu","doi":"10.1109/HORA58378.2023.10156803","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156803","url":null,"abstract":"The increase in the rate of urbanization in recent years has led to an increase in environmental sound sources and, accordingly, an increase in noise pollution. Street noises, especially in big cities, pose some health problems. In terms of smart cities, accurate detection of street sounds is important in detecting unwanted sounds and responding to emergencies. In this study, research was carried out to select acoustic features of street sounds with meta-heuristic methods. In the experimental study, using the Urbansound8k dataset, feature extraction was done through openSMILE software, then feature selection was performed with PSO and WO algorithms. SVM and k-NN methods were applied for the classification process. Accuracy rates were obtained with SVM and k-NN classifiers as 88.12%, 69.32% in the PSO algorithm, 88.39%, and 70.51% in the WO algorithm, respectively.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"25 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114007682","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 : 2023-06-08DOI: 10.1109/HORA58378.2023.10156747
S. Mahmood, Swash Sami Mohammed, Ayad Ghany Ismaeel, Hülya Gükalp Clarke, Iman Nozad Mahmood, D. Aziz, Sameer Alani
This research presents a deep convolutional neural network (CNN) as a solution for identifying malarial cells that are infected. The AI model suggested in this work comprises a three-layered CNN and a two-layered dense neural network. The model can capture both minor and significant features by utilizing CNN, thereby extracting a maximum amount of information from the input data. The model is trained over 20 epochs and evaluated using the binary cross entropy loss function and accuracy metric to assess its performance. Remarkably, the proposed model achieved an impressive accuracy of 96% and maintained a loss value below 0.2 for both the training and validation datasets. Ultimately, this research demonstrates promising potential for automating the detection of malaria through parasite cell counting.
{"title":"Improved Malaria Cells Detection Using Deep Convolutional Neural Network","authors":"S. Mahmood, Swash Sami Mohammed, Ayad Ghany Ismaeel, Hülya Gükalp Clarke, Iman Nozad Mahmood, D. Aziz, Sameer Alani","doi":"10.1109/HORA58378.2023.10156747","DOIUrl":"https://doi.org/10.1109/HORA58378.2023.10156747","url":null,"abstract":"This research presents a deep convolutional neural network (CNN) as a solution for identifying malarial cells that are infected. The AI model suggested in this work comprises a three-layered CNN and a two-layered dense neural network. The model can capture both minor and significant features by utilizing CNN, thereby extracting a maximum amount of information from the input data. The model is trained over 20 epochs and evaluated using the binary cross entropy loss function and accuracy metric to assess its performance. Remarkably, the proposed model achieved an impressive accuracy of 96% and maintained a loss value below 0.2 for both the training and validation datasets. Ultimately, this research demonstrates promising potential for automating the detection of malaria through parasite cell counting.","PeriodicalId":247679,"journal":{"name":"2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115382839","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：