Pub Date : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573644
Jason Lowell Jitolis, A. Ali, I. Saad, N. A. Taha, J. Idris, N. Bolong
In recent years, the popularity of optimization of bioretention systems through statistical experimental design had increased due to rapid urbanization, which directly impacted the water quality and quantity of stormwater runoff from an increasing area of impervious surface. Experimental design is necessary for developing interaction between two or more responses with various affecting factors. Due to this significant possibility of combining several variables in optimizing experimentation results, statistical analysis is essential to observe the process and optimize the responses data accurately. Response Surface Methodology (RSM) is the most commonly used statistical analysis method. There is a wide range of RSM applications from science to industrial practice. The RSM method can handle multiple factors and responses in a short amount of time compared to conventional analysis. Hence, this paper highlights the significance of RSM in optimizing pollutants rate and regulation effects in bioretention cells. From the analytical literature observation, optimization of improved and conventional bioretention system shows positive interaction effect and responses value through various bioretention design factors manipulation. The validity of the regression model also shows adequate results and well-matched between experimental and statistical predicted values.
{"title":"Utilization of Response Surface Methodology and Regression Model in Optimizing Bioretention Performance","authors":"Jason Lowell Jitolis, A. Ali, I. Saad, N. A. Taha, J. Idris, N. Bolong","doi":"10.1109/IICAIET51634.2021.9573644","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573644","url":null,"abstract":"In recent years, the popularity of optimization of bioretention systems through statistical experimental design had increased due to rapid urbanization, which directly impacted the water quality and quantity of stormwater runoff from an increasing area of impervious surface. Experimental design is necessary for developing interaction between two or more responses with various affecting factors. Due to this significant possibility of combining several variables in optimizing experimentation results, statistical analysis is essential to observe the process and optimize the responses data accurately. Response Surface Methodology (RSM) is the most commonly used statistical analysis method. There is a wide range of RSM applications from science to industrial practice. The RSM method can handle multiple factors and responses in a short amount of time compared to conventional analysis. Hence, this paper highlights the significance of RSM in optimizing pollutants rate and regulation effects in bioretention cells. From the analytical literature observation, optimization of improved and conventional bioretention system shows positive interaction effect and responses value through various bioretention design factors manipulation. The validity of the regression model also shows adequate results and well-matched between experimental and statistical predicted values.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114739929","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573713
M. Gordan, Khaled Ghaedi, Z. Ismail, Hamed Benisi, Huzaifa Hashim, H. H. Ghayeb
Computer-based technologies and their applications pervade everywhere in real life, especially in different fields of civil engineering. For example, conventional structural health monitoring (SHM) has been rapidly upgraded to sustainable SHM using artificial intelligence. It is because conventional approaches are challenged by real-time, low-cost, and quality-guaranteed SHM. In this direction, a number of innovative researches have been carried out in the Department of Civil Engineering, University of Malaya. This paper attempts to present the latest developments of SHM-based artificial intelligence in Structural Health Monitoring Research Group (StrucHMRSGroup) and Advance Shock and Vibration Research Group (ASVR). To this end, the applications of artificial neural networks, fuzzy logic, genetic algorithm, data mining, and regression analysis in SHM are presented with the aim of showing the efficiency of these methods.
{"title":"From Conventional to Sustainable SHM: Implementation of Artificial Intelligence in The Department of Civil Engineering, University of Malaya","authors":"M. Gordan, Khaled Ghaedi, Z. Ismail, Hamed Benisi, Huzaifa Hashim, H. H. Ghayeb","doi":"10.1109/IICAIET51634.2021.9573713","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573713","url":null,"abstract":"Computer-based technologies and their applications pervade everywhere in real life, especially in different fields of civil engineering. For example, conventional structural health monitoring (SHM) has been rapidly upgraded to sustainable SHM using artificial intelligence. It is because conventional approaches are challenged by real-time, low-cost, and quality-guaranteed SHM. In this direction, a number of innovative researches have been carried out in the Department of Civil Engineering, University of Malaya. This paper attempts to present the latest developments of SHM-based artificial intelligence in Structural Health Monitoring Research Group (StrucHMRSGroup) and Advance Shock and Vibration Research Group (ASVR). To this end, the applications of artificial neural networks, fuzzy logic, genetic algorithm, data mining, and regression analysis in SHM are presented with the aim of showing the efficiency of these methods.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115123010","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573970
Daniel Hofer, P. K. Prasad, Markus Schneider
The concept of anomaly detection is a majorly investigated problem in the service robotics domain. The motivation of this work is to enable household service robots to detect abnormalities in the environment and solve them. This paper investigates two approaches using knowledge-based systems to detect and solve anomalies in a household environment. Both methods use knowledge graphs as a knowledge representation format. The first approach is a classical approach that records absolute positions of objects and performs clustering to solve positional anomalies. In the second approach, we perform deep learning methods on knowledge graphs using graph neural networks to detect and solve anomalies. These approaches fall at the intersection between anomaly detection and problem-solution strategies for the service robotics domain. Finally, the paper also presents a comparison between the two approaches highlighting their advantages and disadvantages.
{"title":"Comparison of Anomaly Detection and Solution Strategies for Household Service Robotics using Knowledge Graphs","authors":"Daniel Hofer, P. K. Prasad, Markus Schneider","doi":"10.1109/IICAIET51634.2021.9573970","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573970","url":null,"abstract":"The concept of anomaly detection is a majorly investigated problem in the service robotics domain. The motivation of this work is to enable household service robots to detect abnormalities in the environment and solve them. This paper investigates two approaches using knowledge-based systems to detect and solve anomalies in a household environment. Both methods use knowledge graphs as a knowledge representation format. The first approach is a classical approach that records absolute positions of objects and performs clustering to solve positional anomalies. In the second approach, we perform deep learning methods on knowledge graphs using graph neural networks to detect and solve anomalies. These approaches fall at the intersection between anomaly detection and problem-solution strategies for the service robotics domain. Finally, the paper also presents a comparison between the two approaches highlighting their advantages and disadvantages.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124152068","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573866
H. Adamu, Mat Jasri Bin Mat Jiran, Gan Keng Hoon, Nur-Hana Samsudin
The global pandemic of the novel Coronavirus in 2019, known by the World Health Organisations (WHO) as Covid-19, has put various governments in a vulnerable situation around the world. For virtually every nation in the world, the effects of the Covid-19 pandemic, previously experienced by the people of China alone, has now become a matter of great concern. This research highlights its impact on the global economy, in addition to the immediate health consequences associated with the Covid-19 pandemic. The study further discussed the use of Text Analytics and Sentiment Analysis in Natural Language Processing (NLP) based on Twitter text to analyse public sentiment and derive insights regarding Covid-19 vaccines in the healthcare domain. Two machine learning algorithms were employed: Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) to classify and evaluate the results. Various pre-processing techniques were adopted to help in detecting the public sentiment based on the three sentiment polarity classes: positive, negative, and neutral. The result of the sentiment class distribution reveals that 31% of the public sentiment regarding Covid-19 vaccines is positive, 22% is negative while the remaining 47% were classified as neutral sentiment. The experimented machine learning algorithms reveals that SVM produced 88% accuracy which surpasses KNN with 78% accuracy.
{"title":"Text Analytics on Twitter Text-based Public Sentiment for Covid-19 Vaccine: A Machine Learning Approach","authors":"H. Adamu, Mat Jasri Bin Mat Jiran, Gan Keng Hoon, Nur-Hana Samsudin","doi":"10.1109/IICAIET51634.2021.9573866","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573866","url":null,"abstract":"The global pandemic of the novel Coronavirus in 2019, known by the World Health Organisations (WHO) as Covid-19, has put various governments in a vulnerable situation around the world. For virtually every nation in the world, the effects of the Covid-19 pandemic, previously experienced by the people of China alone, has now become a matter of great concern. This research highlights its impact on the global economy, in addition to the immediate health consequences associated with the Covid-19 pandemic. The study further discussed the use of Text Analytics and Sentiment Analysis in Natural Language Processing (NLP) based on Twitter text to analyse public sentiment and derive insights regarding Covid-19 vaccines in the healthcare domain. Two machine learning algorithms were employed: Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) to classify and evaluate the results. Various pre-processing techniques were adopted to help in detecting the public sentiment based on the three sentiment polarity classes: positive, negative, and neutral. The result of the sentiment class distribution reveals that 31% of the public sentiment regarding Covid-19 vaccines is positive, 22% is negative while the remaining 47% were classified as neutral sentiment. The experimented machine learning algorithms reveals that SVM produced 88% accuracy which surpasses KNN with 78% accuracy.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"5 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113975336","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573795
S. Chai, Kok Luong Goh, Hui-Hui Wang, Wee Bui Lin
The revealed analysis studies on pair programming so far indicate that pair programming has produced affirmative effects on some aspects of students” performance. In the academic field, the usual practice of pair programming would be pairing the students in line with the programming skills of the students by the respective lecturers. This means, compatibility of the students in terms of their programming skills is the main focus when the pairing was done by the lecturers. Yet, research on elements that the students are looking into when they are given the liberty to decide on their partner in pair programming is lacking. In this study, a multi-layer perceptron (MLP) is developed to predict the preference of opting pair programming over solo programming. The Bayesian Information Criterion was used to select the best features in the prediction. The potential of unstructured text entered by the participants as comments in the questionnaire is incorporated in the MLP model to verify its capabilities towards prediction accuracy, i.e., to verify whether their comments are connected to their preference for pair programming versus solo programming. It was found that, when the students are given the freedom to choose their partner in pair programming, in the context of Malaysia, the students would pay attention to the ethnic criterion. This also suggests that the unstructured texts in the form of comments submitted by the participants in the questionnaire did not contribute to their choices on whether to undertake solo or pair programming.
{"title":"Incorporating Unstructured Text in Multi-Layer Perceptron (MLP) Network: Factors Affecting Partner Selection in Pair Programming","authors":"S. Chai, Kok Luong Goh, Hui-Hui Wang, Wee Bui Lin","doi":"10.1109/IICAIET51634.2021.9573795","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573795","url":null,"abstract":"The revealed analysis studies on pair programming so far indicate that pair programming has produced affirmative effects on some aspects of students” performance. In the academic field, the usual practice of pair programming would be pairing the students in line with the programming skills of the students by the respective lecturers. This means, compatibility of the students in terms of their programming skills is the main focus when the pairing was done by the lecturers. Yet, research on elements that the students are looking into when they are given the liberty to decide on their partner in pair programming is lacking. In this study, a multi-layer perceptron (MLP) is developed to predict the preference of opting pair programming over solo programming. The Bayesian Information Criterion was used to select the best features in the prediction. The potential of unstructured text entered by the participants as comments in the questionnaire is incorporated in the MLP model to verify its capabilities towards prediction accuracy, i.e., to verify whether their comments are connected to their preference for pair programming versus solo programming. It was found that, when the students are given the freedom to choose their partner in pair programming, in the context of Malaysia, the students would pay attention to the ethnic criterion. This also suggests that the unstructured texts in the form of comments submitted by the participants in the questionnaire did not contribute to their choices on whether to undertake solo or pair programming.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132670072","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573878
Qaisar Khan, Hui Na Chua
It is essential to understand what topics related to the COVID19 pandemic forms informative and uninformative content on social networks instead of general information (which contains both informative and uninformative). Uninformative content is mainly based on personal opinions and is more suitable for sentimental analysis. Whereas informative content is based on facts, figures, and reports; therefore, it is beneficial to gain a more in-depth understanding for a better strategic response to COVID-19. Despite knowing this fact, there is still a lack of study performed to investigate the aspects of informative content to gain an in-depth understanding of COVID-19 discussed topics. We aim to fill this gap through the study presented in this paper. We used the dataset containing 4719 “informative” and 5281 “uninformative” labeled tweets to realize informative aspects. Latent Dirichlet Allocation (LDA) and Latent Semantic Analysis (LSA) are popular topic modeling techniques. However, since both are based on an unsupervised approach, it is still unknown whether LDA or LSA effectively categorizes documents and how an appropriate number of topics can be determined. Therefore, we used both techniques to analyze tweets' content. Results show that LDA outperforms LSA by achieving a topic coherence score of 0.619 on uninformative and 0.599 on informative. In addition, based on LDA's results, it is also observed that most of the words that form informative content are death, case, coronavirus, people, confirmed, total, positive, tested, number, reported indicating tested, and death cases are the most concerned topics. On the other hand, words like immunity, fatality, protocol, thread, tourist, queue, blockade, eradication, prediction, detention, concerned are most likely to form uninformative content.
{"title":"Comparing Topic Modeling Techniques for Identifying Informative and Uninformative Content: A Case Study on COVID-19 Tweets","authors":"Qaisar Khan, Hui Na Chua","doi":"10.1109/IICAIET51634.2021.9573878","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573878","url":null,"abstract":"It is essential to understand what topics related to the COVID19 pandemic forms informative and uninformative content on social networks instead of general information (which contains both informative and uninformative). Uninformative content is mainly based on personal opinions and is more suitable for sentimental analysis. Whereas informative content is based on facts, figures, and reports; therefore, it is beneficial to gain a more in-depth understanding for a better strategic response to COVID-19. Despite knowing this fact, there is still a lack of study performed to investigate the aspects of informative content to gain an in-depth understanding of COVID-19 discussed topics. We aim to fill this gap through the study presented in this paper. We used the dataset containing 4719 “informative” and 5281 “uninformative” labeled tweets to realize informative aspects. Latent Dirichlet Allocation (LDA) and Latent Semantic Analysis (LSA) are popular topic modeling techniques. However, since both are based on an unsupervised approach, it is still unknown whether LDA or LSA effectively categorizes documents and how an appropriate number of topics can be determined. Therefore, we used both techniques to analyze tweets' content. Results show that LDA outperforms LSA by achieving a topic coherence score of 0.619 on uninformative and 0.599 on informative. In addition, based on LDA's results, it is also observed that most of the words that form informative content are death, case, coronavirus, people, confirmed, total, positive, tested, number, reported indicating tested, and death cases are the most concerned topics. On the other hand, words like immunity, fatality, protocol, thread, tourist, queue, blockade, eradication, prediction, detention, concerned are most likely to form uninformative content.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131302164","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573754
Fahim S. Rahman, Md. Istiyak Ahmed, Saif Shahnewaz Saad, M. Ashrafuzzaman, Sharita Shehnaz Mogno, Rafeed Rahman, M. Parvez
The significance and urgency of detecting the cognitive load of a Visually Impaired Person (VIP) are essential when perception comes while designing an automated navigation aid for them in unfamiliar indoor environments. Our paper presents a novel and robust framework based on the iterative feature pooling technique which recursively selects paramount features that maintains relationships with the change in the cognitive load of the brain. We took the well-established Event-Related Desynchronization and Synchronization (ERDS) method for indexing the cognitive load and further developed the work by operating with the band power of not only the Alpha wave but the Alpha Beta band power ratio and Alpha Theta band power ratio. The supervised machine learning classifier, Gradient Boost outperformed all other classifiers reaching 94% accuracy in the best case. When provided with the most reliable features and proper tuning, this turns out to perform 7% to 8% better than the other classifiers like the Support Vector Machine (SVM), K-nearest neighbor, Naive Bayes, and Multilayer perceptron. We considered some performance parameters like the accuracy, null-accuracy, recall, precision, F1 Score, and False Alarm rate to evaluate the performance of all available supervised Machine learning classifiers. Our paper marks out the estimation of cognitive load based on Electroencephalogram (EEG) signals analysis with the existing literature, background, leeway, features, and machine learning techniques.
{"title":"Prediction And Detection In Change Of Cognitive Load For VIP's By A Machine Learning Approach","authors":"Fahim S. Rahman, Md. Istiyak Ahmed, Saif Shahnewaz Saad, M. Ashrafuzzaman, Sharita Shehnaz Mogno, Rafeed Rahman, M. Parvez","doi":"10.1109/IICAIET51634.2021.9573754","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573754","url":null,"abstract":"The significance and urgency of detecting the cognitive load of a Visually Impaired Person (VIP) are essential when perception comes while designing an automated navigation aid for them in unfamiliar indoor environments. Our paper presents a novel and robust framework based on the iterative feature pooling technique which recursively selects paramount features that maintains relationships with the change in the cognitive load of the brain. We took the well-established Event-Related Desynchronization and Synchronization (ERDS) method for indexing the cognitive load and further developed the work by operating with the band power of not only the Alpha wave but the Alpha Beta band power ratio and Alpha Theta band power ratio. The supervised machine learning classifier, Gradient Boost outperformed all other classifiers reaching 94% accuracy in the best case. When provided with the most reliable features and proper tuning, this turns out to perform 7% to 8% better than the other classifiers like the Support Vector Machine (SVM), K-nearest neighbor, Naive Bayes, and Multilayer perceptron. We considered some performance parameters like the accuracy, null-accuracy, recall, precision, F1 Score, and False Alarm rate to evaluate the performance of all available supervised Machine learning classifiers. Our paper marks out the estimation of cognitive load based on Electroencephalogram (EEG) signals analysis with the existing literature, background, leeway, features, and machine learning techniques.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115691399","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573732
H. S. Chuo, Christina Y.Y. Lo, M. K. Tan, H. Tham, S. Kumaresan, K. Teo
This paper proposes genetic algorithm (GA) to optimize the productivity of yeast fermentation process. The proposed optimizer aims to maximize yeast productivity while minimizing the by-product of ethanol. Various initial glucose concentrations will affect yeast productivity and influence the performance of yeast fermentation. Yeast has relatively high ethanol production as compared with other microorganisms. Since the excessive ethanol formation in the yeast fermentation process will have a negative impact on quality of the product, it is needed to optimize glucose feeding rate at optimal level for maximizing the yeast productivity. The conventional open-loop feeding system is inadequate to minimize the growth of byproduct as the system will not regulate the glucose feeding rate based on the instant needs. Thus, GA is proposed to optimize the glucose feeding profile based on the instant concentration of yeast, glucose, oxygen and ethanol inside the fermentation tank. The results show the proposed GA can obtain a higher yield production of 95.3% as compared to the conventional open-loop system with 92.5% yield production. The results reveal that the optimal glucose feeding rate using GA is achieved satisfyingly and successfully.
{"title":"Optimization of Yeast Fermentation Process using Genetic Algorithm","authors":"H. S. Chuo, Christina Y.Y. Lo, M. K. Tan, H. Tham, S. Kumaresan, K. Teo","doi":"10.1109/IICAIET51634.2021.9573732","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573732","url":null,"abstract":"This paper proposes genetic algorithm (GA) to optimize the productivity of yeast fermentation process. The proposed optimizer aims to maximize yeast productivity while minimizing the by-product of ethanol. Various initial glucose concentrations will affect yeast productivity and influence the performance of yeast fermentation. Yeast has relatively high ethanol production as compared with other microorganisms. Since the excessive ethanol formation in the yeast fermentation process will have a negative impact on quality of the product, it is needed to optimize glucose feeding rate at optimal level for maximizing the yeast productivity. The conventional open-loop feeding system is inadequate to minimize the growth of byproduct as the system will not regulate the glucose feeding rate based on the instant needs. Thus, GA is proposed to optimize the glucose feeding profile based on the instant concentration of yeast, glucose, oxygen and ethanol inside the fermentation tank. The results show the proposed GA can obtain a higher yield production of 95.3% as compared to the conventional open-loop system with 92.5% yield production. The results reveal that the optimal glucose feeding rate using GA is achieved satisfyingly and successfully.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121237343","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573549
Ferdous Zeaul Islam, Ashfaq Jamil, S. Momen
Popularity of android platform has made it a prime target for security threats. Third party app stores are getting flooded with malware apps. An effective way of detecting and therefore preventing the spread of malware is deemed necessary. In this paper we apply and evaluate machine learning approaches using static features to detect presence of malware in Android OS. We applied correlation based feature selection techniques and trained each classifier on the train set by hyperparameter tuning with stratified 10-fold cross validation and evaluated their performance on the unseen test set. Our experimental results reveal that it is possible to detect android malware with high reliability.
{"title":"Evaluation of Machine Learning Methods for Android Malware Detection using Static Features","authors":"Ferdous Zeaul Islam, Ashfaq Jamil, S. Momen","doi":"10.1109/IICAIET51634.2021.9573549","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573549","url":null,"abstract":"Popularity of android platform has made it a prime target for security threats. Third party app stores are getting flooded with malware apps. An effective way of detecting and therefore preventing the spread of malware is deemed necessary. In this paper we apply and evaluate machine learning approaches using static features to detect presence of malware in Android OS. We applied correlation based feature selection techniques and trained each classifier on the train set by hyperparameter tuning with stratified 10-fold cross validation and evaluated their performance on the unseen test set. Our experimental results reveal that it is possible to detect android malware with high reliability.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129381800","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 : 2021-09-13DOI: 10.1109/IICAIET51634.2021.9573963
Mark P. Melegrito, A. Alon, Sammy V. Militante, Yolanda D. Austria, Myriam J. Polinar, Maria Concepcion A. Mirabueno
Nowadays, seeing a large number of shopping carts abandoned in the parking lot is a typical occurrence at every supermarket. After being used by customers who left their shopping carts in the parking lot and never returned. This study presents a technique for detecting abandoned carts in parking lots. The proposed identification of abandoned shopping carts in parking areas enables supermarket management to quickly respond to consumer requirements for shopping carts while also providing enough parking space for vehicles. In this study, the YOLOv3 model, a state-of-the-art deep transfer learning object identification method, is utilized to construct a shopping cart detection model. Upon the result of the study, the detection model has a training and validation accuracy of 92.17 % and 93.80 %, respectively, with an mAP value of 93.00 %, according to the study's findings. Because of its outstanding performance, the proposed model is suitable for video surveillance equipment. The system achieved a total testing accuracy of 100 %, with detection per frame accuracy ranging from 40.03 % to 65.03 %.
{"title":"Abandoned-Cart-Vision: Abandoned Cart Detection Using a Deep Object Detection Approach in a Shopping Parking Space","authors":"Mark P. Melegrito, A. Alon, Sammy V. Militante, Yolanda D. Austria, Myriam J. Polinar, Maria Concepcion A. Mirabueno","doi":"10.1109/IICAIET51634.2021.9573963","DOIUrl":"https://doi.org/10.1109/IICAIET51634.2021.9573963","url":null,"abstract":"Nowadays, seeing a large number of shopping carts abandoned in the parking lot is a typical occurrence at every supermarket. After being used by customers who left their shopping carts in the parking lot and never returned. This study presents a technique for detecting abandoned carts in parking lots. The proposed identification of abandoned shopping carts in parking areas enables supermarket management to quickly respond to consumer requirements for shopping carts while also providing enough parking space for vehicles. In this study, the YOLOv3 model, a state-of-the-art deep transfer learning object identification method, is utilized to construct a shopping cart detection model. Upon the result of the study, the detection model has a training and validation accuracy of 92.17 % and 93.80 %, respectively, with an mAP value of 93.00 %, according to the study's findings. Because of its outstanding performance, the proposed model is suitable for video surveillance equipment. The system achieved a total testing accuracy of 100 %, with detection per frame accuracy ranging from 40.03 % to 65.03 %.","PeriodicalId":234229,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131958229","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}