Accurately predicting extreme stock market fluctuations at the right time will allow traders and investors to make better-informed investment decisions and practice more efficient financial risk management. However, extreme stock market events are particularly hard to model because of their scarce and erratic nature. Moreover, strong trading strategies, market stress tests, and portfolio optimization largely rely on sound data. While the application of generative adversarial networks (GANs) for stock forecasting has been an active area of research, there is still a gap in the literature on using GANs for extreme market movement prediction and simulation. In this study, we proposed a framework based on GANs to efficiently model stock prices’ extreme movements. By creating synthetic real-looking data, the framework simulated multiple possible market-evolution scenarios, which can be used to improve the forecasting quality of future market variations. The fidelity and predictive power of the generated data were tested by quantitative and qualitative metrics. Our experimental results on S&P 500 and five emerging market stock data show that the proposed framework is capable of producing a realistic time series by recovering important properties from real data. The results presented in this work suggest that the underlying dynamics of extreme stock market variations can be captured efficiently by some state-of-the-art GAN architectures. This conclusion has great practical implications for investors, traders, and corporations willing to anticipate the future trends of their financial assets. The proposed framework can be used as a simulation tool to mimic stock market behaviors.
{"title":"Predicting extreme events in the stock market using generative adversarial networks","authors":"Badre Labiad, A. Berrado, L. Benabbou","doi":"10.26555/ijain.v9i2.898","DOIUrl":"https://doi.org/10.26555/ijain.v9i2.898","url":null,"abstract":"Accurately predicting extreme stock market fluctuations at the right time will allow traders and investors to make better-informed investment decisions and practice more efficient financial risk management. However, extreme stock market events are particularly hard to model because of their scarce and erratic nature. Moreover, strong trading strategies, market stress tests, and portfolio optimization largely rely on sound data. While the application of generative adversarial networks (GANs) for stock forecasting has been an active area of research, there is still a gap in the literature on using GANs for extreme market movement prediction and simulation. In this study, we proposed a framework based on GANs to efficiently model stock prices’ extreme movements. By creating synthetic real-looking data, the framework simulated multiple possible market-evolution scenarios, which can be used to improve the forecasting quality of future market variations. The fidelity and predictive power of the generated data were tested by quantitative and qualitative metrics. Our experimental results on S&P 500 and five emerging market stock data show that the proposed framework is capable of producing a realistic time series by recovering important properties from real data. The results presented in this work suggest that the underlying dynamics of extreme stock market variations can be captured efficiently by some state-of-the-art GAN architectures. This conclusion has great practical implications for investors, traders, and corporations willing to anticipate the future trends of their financial assets. The proposed framework can be used as a simulation tool to mimic stock market behaviors.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86762331","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}
Abu Kowshir Bitto, Md. Hasan Imam Bijoy, S. Yesmin, Imran Mahmud, Md. Jueal Mia, Khalid Been Md. Badruzzaman Biplob
Abnormal brain tissue or cell growth is known as a brain tumor. One of the body's most intricate organs is the brain, where billions of cells work together. As a head tumor grows, the brain suffers damage due to its increasingly dense core. Magnetic resonance imaging, or MRI, is a type of medical imaging that enables radiologists to view the inside of body structures without the need for surgery. The image-based medical diagnosis expert system is crucial for a brain tumor patient. In this study, we combined two Magnetic Resonance Imaging (MRI)-based image datasets from Figshare and Kaggle to identify brain tumor MRI using a variety of convolutional neural network designs. To achieve competitive performance, we employ several data preprocessing techniques, such as resizing and enhancing contrast. The image augmentation techniques (E.g., rotated, width shifted, height shifted, shear shifted, and horizontally flipped) are used to increase data size, and five pre-trained models employed, including VGG-16, VGG-19, ResNet-50, Xception, and Inception-V3. The model with the highest accuracy, ResNet-50, performs at 96.76 percent. The model with the highest precision overall is Inception V3, with a precision score of 98.83 percent. ResNet-50 performs at 96.96% for F1-Score. The prominent accuracy of the implemented model, i.e., ResNet-50, compared with several earlier studies to validate the consequence of this introspection. The outcome of this study can be used in the medical diagnosis of brain tumors with an MRI-based expert system.
{"title":"Tumor-Net: convolutional neural network modeling for classifying brain tumors from MRI images","authors":"Abu Kowshir Bitto, Md. Hasan Imam Bijoy, S. Yesmin, Imran Mahmud, Md. Jueal Mia, Khalid Been Md. Badruzzaman Biplob","doi":"10.26555/ijain.v9i2.872","DOIUrl":"https://doi.org/10.26555/ijain.v9i2.872","url":null,"abstract":"Abnormal brain tissue or cell growth is known as a brain tumor. One of the body's most intricate organs is the brain, where billions of cells work together. As a head tumor grows, the brain suffers damage due to its increasingly dense core. Magnetic resonance imaging, or MRI, is a type of medical imaging that enables radiologists to view the inside of body structures without the need for surgery. The image-based medical diagnosis expert system is crucial for a brain tumor patient. In this study, we combined two Magnetic Resonance Imaging (MRI)-based image datasets from Figshare and Kaggle to identify brain tumor MRI using a variety of convolutional neural network designs. To achieve competitive performance, we employ several data preprocessing techniques, such as resizing and enhancing contrast. The image augmentation techniques (E.g., rotated, width shifted, height shifted, shear shifted, and horizontally flipped) are used to increase data size, and five pre-trained models employed, including VGG-16, VGG-19, ResNet-50, Xception, and Inception-V3. The model with the highest accuracy, ResNet-50, performs at 96.76 percent. The model with the highest precision overall is Inception V3, with a precision score of 98.83 percent. ResNet-50 performs at 96.96% for F1-Score. The prominent accuracy of the implemented model, i.e., ResNet-50, compared with several earlier studies to validate the consequence of this introspection. The outcome of this study can be used in the medical diagnosis of brain tumors with an MRI-based expert system.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78247057","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 : 2023-03-31DOI: 10.26555/ijain.v9i1.1076
Noor Aini Mohd Roslan, N. Diah, Z. Ibrahim, Yuda Munarko, A. E. Minarno
Herbs are an important nutritional source for humans since they provide a variety of nutrients. Indigenous people have employed herbs, in particular, as traditional medicines since ancient times. Malaysia has hundreds of plant species; herb detection may be difficult due to the variety of herb species and their shape and color similarities. Furthermore, there is a scarcity of support datasets for detecting these plants. The main objective of this paper is to investigate the performance of convolutional neural network (CNN) on Malaysian medicinal herbs datasets, real data and augmented data. Malaysian medical herbs data were obtained from Taman Herba Pulau Pinang, Malaysia, and ten kinds of native herbs were chosen. Both datasets were evaluated using the CNN model developed throughout the research. Overall, herbs real data obtained an average accuracy of 75%, whereas herbs augmented data achieved an average accuracy of 88%. Based on these findings, herbs augmented data surpassed herbs actual data in terms of accuracy after undergoing the augmentation technique.
{"title":"Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation","authors":"Noor Aini Mohd Roslan, N. Diah, Z. Ibrahim, Yuda Munarko, A. E. Minarno","doi":"10.26555/ijain.v9i1.1076","DOIUrl":"https://doi.org/10.26555/ijain.v9i1.1076","url":null,"abstract":"Herbs are an important nutritional source for humans since they provide a variety of nutrients. Indigenous people have employed herbs, in particular, as traditional medicines since ancient times. Malaysia has hundreds of plant species; herb detection may be difficult due to the variety of herb species and their shape and color similarities. Furthermore, there is a scarcity of support datasets for detecting these plants. The main objective of this paper is to investigate the performance of convolutional neural network (CNN) on Malaysian medicinal herbs datasets, real data and augmented data. Malaysian medical herbs data were obtained from Taman Herba Pulau Pinang, Malaysia, and ten kinds of native herbs were chosen. Both datasets were evaluated using the CNN model developed throughout the research. Overall, herbs real data obtained an average accuracy of 75%, whereas herbs augmented data achieved an average accuracy of 88%. Based on these findings, herbs augmented data surpassed herbs actual data in terms of accuracy after undergoing the augmentation technique.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76115827","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 : 2023-03-31DOI: 10.26555/ijain.v9i1.1077
Nur Aliah Khairina Mohd Haris, S. Mutalib, A. Malik, S. Abdul-Rahman, Siti Nur Kamaliah Kamarudin
User-generated content is critical for tourism destination management as it could help them identify their customers' opinions and come up with solutions to upgrade their tourism organizations as it could help them identify customer opinions. There are many reviews on social media and it is difficult for these organizations to analyse the reviews manually. By applying sentiment classification, reviews can be classified into several classes and help ease decision-making. The reviews contain noisy contents, such as typos and emoticons, which could affect the accuracy of the classifiers. This study evaluates the reviews using Support Vector Machine and Random Forest models to identify a suitable classifier. The main phases in this study are data collection, data preparation, data labelling and modelling phases. The reviews are labelled into three sentiments; positive, neutral, and negative. During pre-processing, steps such as removing the missing value, tokenization, case folding, stop words removal, stemming, and applying n-grams are performed. The result of this research is evaluated by looking at the performance of the models based on accuracy where the result with the highest accuracy is chosen as the solution. In this study, data is data from TripAdvisor and Google reviews using web scraping tools. The findings show that the Support Vector Machine model with 5-fold cross-validation the most suitable classifier with an accuracy of 67.97% compared to Naive Bayes with 61.33% accuracy and Random Forest classifier with 63.55% accuracy. In conclusion, the result of this paper could provide important information in tourism besides determining the suitable algorithm to be used for Sentiment Analysis related to the tourism domain.
{"title":"Sentiment classification from reviews for tourism analytics","authors":"Nur Aliah Khairina Mohd Haris, S. Mutalib, A. Malik, S. Abdul-Rahman, Siti Nur Kamaliah Kamarudin","doi":"10.26555/ijain.v9i1.1077","DOIUrl":"https://doi.org/10.26555/ijain.v9i1.1077","url":null,"abstract":"User-generated content is critical for tourism destination management as it could help them identify their customers' opinions and come up with solutions to upgrade their tourism organizations as it could help them identify customer opinions. There are many reviews on social media and it is difficult for these organizations to analyse the reviews manually. By applying sentiment classification, reviews can be classified into several classes and help ease decision-making. The reviews contain noisy contents, such as typos and emoticons, which could affect the accuracy of the classifiers. This study evaluates the reviews using Support Vector Machine and Random Forest models to identify a suitable classifier. The main phases in this study are data collection, data preparation, data labelling and modelling phases. The reviews are labelled into three sentiments; positive, neutral, and negative. During pre-processing, steps such as removing the missing value, tokenization, case folding, stop words removal, stemming, and applying n-grams are performed. The result of this research is evaluated by looking at the performance of the models based on accuracy where the result with the highest accuracy is chosen as the solution. In this study, data is data from TripAdvisor and Google reviews using web scraping tools. The findings show that the Support Vector Machine model with 5-fold cross-validation the most suitable classifier with an accuracy of 67.97% compared to Naive Bayes with 61.33% accuracy and Random Forest classifier with 63.55% accuracy. In conclusion, the result of this paper could provide important information in tourism besides determining the suitable algorithm to be used for Sentiment Analysis related to the tourism domain.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87422580","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}
Hanafi Hanafi, A. Pranolo, Yingchi Mao, T. Hariguna, Leonel Hernandez, Nanang F Kurniawan
An Intrusion Detection System (IDS) is essential for automatically monitoring cyber-attack activity. Adopting machine learning to develop automatic cyber attack detection has become an important research topic in the last decade. Deep learning is a popular machine learning algorithm recently applied in IDS applications. The adoption of complex layer algorithms in the term of deep learning has been applied in the last five years to increase IDS detection effectiveness. Unfortunately, most deep learning models generate a large number of false negatives, leading to dominant mistake detection that can affect the performance of IDS applications. This paper aims to integrate a statistical model to remove outliers in pre-processing, SDAE, responsible for reducing data dimensionality, and LSTM-Attention, responsible for producing attack classification tasks. The model was implemented into the NSL-KDD dataset and evaluated using Accuracy, F1, Recall, and Confusion metrics measures. The results showed that the proposed IDSX-Attention outperformed the baseline model, SDAE, LSTM, PCA-LSTM, and Mutual Information (MI)-LSTM, achieving more than a 2% improvement on average. This study demonstrates the potential of the proposed IDSX-Attention, particularly as a deep learning approach, in enhancing the effectiveness of IDS and addressing the challenges in cyber threat detection. It highlights the importance of integrating statistical models, deep learning, and dimensionality reduction mechanisms to improve IDS detection. Further research can explore the integration of other deep learning algorithms and datasets to validate the proposed model's effectiveness and improve the performance of IDS.
{"title":"IDSX-Attention: Intrusion detection system (IDS) based hybrid MADE-SDAE and LSTM-Attention mechanism","authors":"Hanafi Hanafi, A. Pranolo, Yingchi Mao, T. Hariguna, Leonel Hernandez, Nanang F Kurniawan","doi":"10.26555/ijain.v9i1.942","DOIUrl":"https://doi.org/10.26555/ijain.v9i1.942","url":null,"abstract":"An Intrusion Detection System (IDS) is essential for automatically monitoring cyber-attack activity. Adopting machine learning to develop automatic cyber attack detection has become an important research topic in the last decade. Deep learning is a popular machine learning algorithm recently applied in IDS applications. The adoption of complex layer algorithms in the term of deep learning has been applied in the last five years to increase IDS detection effectiveness. Unfortunately, most deep learning models generate a large number of false negatives, leading to dominant mistake detection that can affect the performance of IDS applications. This paper aims to integrate a statistical model to remove outliers in pre-processing, SDAE, responsible for reducing data dimensionality, and LSTM-Attention, responsible for producing attack classification tasks. The model was implemented into the NSL-KDD dataset and evaluated using Accuracy, F1, Recall, and Confusion metrics measures. The results showed that the proposed IDSX-Attention outperformed the baseline model, SDAE, LSTM, PCA-LSTM, and Mutual Information (MI)-LSTM, achieving more than a 2% improvement on average. This study demonstrates the potential of the proposed IDSX-Attention, particularly as a deep learning approach, in enhancing the effectiveness of IDS and addressing the challenges in cyber threat detection. It highlights the importance of integrating statistical models, deep learning, and dimensionality reduction mechanisms to improve IDS detection. Further research can explore the integration of other deep learning algorithms and datasets to validate the proposed model's effectiveness and improve the performance of IDS.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"88 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81343965","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}
Person re-identification is one of the problems in the computer vision field that aims to retrieve similar human images in some image collections (or galleries). It is very useful for people searching or tracking in a closed environment (like a mall or building). One of the highlighted things on person re-identification problems is that the model is usually designed only for performance instead of performance and computing power consideration, which is applicable for devices with limited computing power. In this paper, we proposed a lightweight residual network with pyramid attention for person re-identification problems. The lightweight residual network adopted from the residual network (ResNet) model used for CIFAR dataset experiments consists of not more than two million parameters. An additional pyramid features extraction network and attention module are added to the network to improve the classifier's performance. We use CPFE (Context-aware Pyramid Features Extraction) network that utilizes atrous convolution with different dilation rates to extract the pyramid features. In addition, two different attention networks are used for the classifier: channel-wise and spatial-based attention networks. The proposed classifier is tested using widely use Market-1501 and DukeMTMC-reID person re-identification datasets. Experiments on Market-1501 and DukeMTMC-reID datasets show that our proposed classifier can perform well and outperform the classifier without CPFE and attention networks. Further investigation and ablation study shows that our proposed classifier has higher information density compared with other person re-identification methods.
{"title":"Lightweight pyramid residual features with attention for person re-identification","authors":"R. F. Rachmadi, I. Purnama, S. M. S. Nugroho","doi":"10.26555/ijain.v9i1.702","DOIUrl":"https://doi.org/10.26555/ijain.v9i1.702","url":null,"abstract":"Person re-identification is one of the problems in the computer vision field that aims to retrieve similar human images in some image collections (or galleries). It is very useful for people searching or tracking in a closed environment (like a mall or building). One of the highlighted things on person re-identification problems is that the model is usually designed only for performance instead of performance and computing power consideration, which is applicable for devices with limited computing power. In this paper, we proposed a lightweight residual network with pyramid attention for person re-identification problems. The lightweight residual network adopted from the residual network (ResNet) model used for CIFAR dataset experiments consists of not more than two million parameters. An additional pyramid features extraction network and attention module are added to the network to improve the classifier's performance. We use CPFE (Context-aware Pyramid Features Extraction) network that utilizes atrous convolution with different dilation rates to extract the pyramid features. In addition, two different attention networks are used for the classifier: channel-wise and spatial-based attention networks. The proposed classifier is tested using widely use Market-1501 and DukeMTMC-reID person re-identification datasets. Experiments on Market-1501 and DukeMTMC-reID datasets show that our proposed classifier can perform well and outperform the classifier without CPFE and attention networks. Further investigation and ablation study shows that our proposed classifier has higher information density compared with other person re-identification methods.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"2 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72390222","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}
The popular modified graph clustering ant colony optimization (ACO) algorithm (MGCACO) performs feature selection (FS) by grouping highly correlated features. However, the MGCACO has problems in local search, thus limiting the search for optimal feature subset. Hence, an enhanced feature clustering with ant colony optimization (ECACO) algorithm is proposed. The improvement constructs an ACO feature clustering method to obtain clusters of highly correlated features. The ACO feature clustering method utilizes the ability of various mechanisms, such as local and global search to provide highly correlated features. The performance of ECACO was evaluated on six benchmark datasets from the University California Irvine (UCI) repository and two deoxyribonucleic acid microarray datasets, and its performance was compared against that of five benchmark metaheuristic algorithms. The classifiers used are random forest, k-nearest neighbors, decision tree, and support vector machine. Experimental results on the UCI dataset show the superior performance of ECACO compared with other algorithms in all classifiers in terms of classification accuracy. Experiments on the microarray datasets, in general, showed that the ECACO algorithm outperforms other algorithms in terms of average classification accuracy. ECACO can be utilized for FS in classification tasks for high-dimensionality datasets in various application domains such as medical diagnosis, biological classification, and health care systems.
{"title":"Enhanced feature clustering method based on ant colony optimization for feature selection","authors":"Hassan Almazini, K. Ku-Mahamud, Hassan Almazini","doi":"10.26555/ijain.v9i1.987","DOIUrl":"https://doi.org/10.26555/ijain.v9i1.987","url":null,"abstract":"The popular modified graph clustering ant colony optimization (ACO) algorithm (MGCACO) performs feature selection (FS) by grouping highly correlated features. However, the MGCACO has problems in local search, thus limiting the search for optimal feature subset. Hence, an enhanced feature clustering with ant colony optimization (ECACO) algorithm is proposed. The improvement constructs an ACO feature clustering method to obtain clusters of highly correlated features. The ACO feature clustering method utilizes the ability of various mechanisms, such as local and global search to provide highly correlated features. The performance of ECACO was evaluated on six benchmark datasets from the University California Irvine (UCI) repository and two deoxyribonucleic acid microarray datasets, and its performance was compared against that of five benchmark metaheuristic algorithms. The classifiers used are random forest, k-nearest neighbors, decision tree, and support vector machine. Experimental results on the UCI dataset show the superior performance of ECACO compared with other algorithms in all classifiers in terms of classification accuracy. Experiments on the microarray datasets, in general, showed that the ECACO algorithm outperforms other algorithms in terms of average classification accuracy. ECACO can be utilized for FS in classification tasks for high-dimensionality datasets in various application domains such as medical diagnosis, biological classification, and health care systems.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"26 62","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72396326","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}
Human environments are designed and managed by humans for humans. Thus, adding robots to interact with humans and perform specific tasks appropriately is an essential topic in robotics research. In recent decades, object recognition, human skeletal, and face recognition frameworks have been implemented to support the tasks of robots. However, recognition of activities and interactions between humans and surrounding objects is an ongoing and more challenging problem. Therefore, this study proposed a graph neural network (GNN) approach to directly recognize human activity at home using vision and speech teaching data. Focus was given to the problem of classifying three activities, namely, eating, working, and reading, where these activities were conducted in the same environment. From the experiments, observations, and analyses, this proved to be quite a challenging problem to solve using only traditional convolutional neural networks (CNN) and video datasets. In the proposed method, an activity classification was learned from a 3D detected object corresponding to the human position. Next, human utterances were used to label the activity from the collected human and object 3D positions. The experiment, involving data collection and learning, was demonstrated by using human-robot communication. It was shown that the proposed method had the shortest training time of 100.346 seconds with 6000 positions from the dataset and was able to recognize the three activities more accurately than the deep layer aggregation (DLA) and X3D networks with video datasets.
{"title":"An efficient activity recognition for homecare robots from multi-modal communication dataset","authors":"Mohamad Yani, Yamada Nao, Chyan Zheng Siow, Kubota Naoyuki","doi":"10.26555/ijain.v9i1.903","DOIUrl":"https://doi.org/10.26555/ijain.v9i1.903","url":null,"abstract":"Human environments are designed and managed by humans for humans. Thus, adding robots to interact with humans and perform specific tasks appropriately is an essential topic in robotics research. In recent decades, object recognition, human skeletal, and face recognition frameworks have been implemented to support the tasks of robots. However, recognition of activities and interactions between humans and surrounding objects is an ongoing and more challenging problem. Therefore, this study proposed a graph neural network (GNN) approach to directly recognize human activity at home using vision and speech teaching data. Focus was given to the problem of classifying three activities, namely, eating, working, and reading, where these activities were conducted in the same environment. From the experiments, observations, and analyses, this proved to be quite a challenging problem to solve using only traditional convolutional neural networks (CNN) and video datasets. In the proposed method, an activity classification was learned from a 3D detected object corresponding to the human position. Next, human utterances were used to label the activity from the collected human and object 3D positions. The experiment, involving data collection and learning, was demonstrated by using human-robot communication. It was shown that the proposed method had the shortest training time of 100.346 seconds with 6000 positions from the dataset and was able to recognize the three activities more accurately than the deep layer aggregation (DLA) and X3D networks with video datasets.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90747534","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}
Muhammad Munsarif, E. Noersasongko, P. Andono, M. Soeleman
Convolutional Neural Networks (CNNs) perform well compared to other deep learning models in image recognition, especially in handwritten alphabetic numeral datasets. CNN's challenging task is to find an architecture with the right hyperparameters. Usually, this activity is done by trial and error. A genetic algorithm (GA) has been widely used for automatic hyperparameter optimization. However, the original GA with fixed chromosome length allows for suboptimal solution results because CNN has a variable number of hyperparameters depending on the depth of the model. Previous work proposed variable chromosome lengths to overcome the drawbacks of native GA. This paper proposes a variable length GA by adding global hyperparameters, namely optimizer and learning speed, to systematically and automatically tune CNN hyperparameters to improve performance. We optimize seven hyperparameters, such as the learning rate. Optimizer, kernel, filter, activation function, number of layers and pooling. The experimental results show that a population of 25 produces the best fitness value and average fitness. In addition, the comparison results show that the proposed model is superior to the basic model based on accuracy. The experimental results show that the proposed model is about 99.18% higher than the baseline model.
{"title":"Improving convolutional neural network based on hyperparameter optimization using variable length genetic algorithm for english digit handwritten recognition","authors":"Muhammad Munsarif, E. Noersasongko, P. Andono, M. Soeleman","doi":"10.26555/ijain.v9i1.881","DOIUrl":"https://doi.org/10.26555/ijain.v9i1.881","url":null,"abstract":"Convolutional Neural Networks (CNNs) perform well compared to other deep learning models in image recognition, especially in handwritten alphabetic numeral datasets. CNN's challenging task is to find an architecture with the right hyperparameters. Usually, this activity is done by trial and error. A genetic algorithm (GA) has been widely used for automatic hyperparameter optimization. However, the original GA with fixed chromosome length allows for suboptimal solution results because CNN has a variable number of hyperparameters depending on the depth of the model. Previous work proposed variable chromosome lengths to overcome the drawbacks of native GA. This paper proposes a variable length GA by adding global hyperparameters, namely optimizer and learning speed, to systematically and automatically tune CNN hyperparameters to improve performance. We optimize seven hyperparameters, such as the learning rate. Optimizer, kernel, filter, activation function, number of layers and pooling. The experimental results show that a population of 25 produces the best fitness value and average fitness. In addition, the comparison results show that the proposed model is superior to the basic model based on accuracy. The experimental results show that the proposed model is about 99.18% higher than the baseline model.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88919571","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}
One study whose importance has significantly grown in recent years is lip-reading, particularly with the widespread of using deep learning techniques. Lip reading is essential for speech recognition in noisy environments or for those with hearing impairments. It refers to recognizing spoken sentences using visual information acquired from lip movements. Also, the lip area, especially for males, suffers from several problems, such as the mouth area containing the mustache and beard, which may cover the lip area. This paper proposes an automatic lip-reading system to recognize and classify short English sentences spoken by speakers using deep learning networks. The input video extracts frames and each frame is passed to the Viola-Jones to detect the face area. Then 68 landmarks of the facial area are determined, and the landmarks from 48 to 68 represent the lip area extracted based on building a binary mask. Then, the contrast is enhanced to improve the quality of the lip image by applying contrast adjustment. Finally, sentences are classified using two deep learning models, the first is AlexNet, and the second is VGG-16 Net. The database consists of 39 participants (32 males and 7 females). Each participant repeats the short sentences five times. The outcomes demonstrate the accuracy rate of AlexNet is 90.00%, whereas the accuracy rate for VGG-16 Net is 82.34%. We concluded that AlexNet performs better for classifying short sentences than VGG-16 Net.
{"title":"An automatic lip reading for short sentences using deep learning nets","authors":"M. Rajab, Kadhim M. Hashim","doi":"10.26555/ijain.v9i1.920","DOIUrl":"https://doi.org/10.26555/ijain.v9i1.920","url":null,"abstract":"One study whose importance has significantly grown in recent years is lip-reading, particularly with the widespread of using deep learning techniques. Lip reading is essential for speech recognition in noisy environments or for those with hearing impairments. It refers to recognizing spoken sentences using visual information acquired from lip movements. Also, the lip area, especially for males, suffers from several problems, such as the mouth area containing the mustache and beard, which may cover the lip area. This paper proposes an automatic lip-reading system to recognize and classify short English sentences spoken by speakers using deep learning networks. The input video extracts frames and each frame is passed to the Viola-Jones to detect the face area. Then 68 landmarks of the facial area are determined, and the landmarks from 48 to 68 represent the lip area extracted based on building a binary mask. Then, the contrast is enhanced to improve the quality of the lip image by applying contrast adjustment. Finally, sentences are classified using two deep learning models, the first is AlexNet, and the second is VGG-16 Net. The database consists of 39 participants (32 males and 7 females). Each participant repeats the short sentences five times. The outcomes demonstrate the accuracy rate of AlexNet is 90.00%, whereas the accuracy rate for VGG-16 Net is 82.34%. We concluded that AlexNet performs better for classifying short sentences than VGG-16 Net.","PeriodicalId":52195,"journal":{"name":"International Journal of Advances in Intelligent Informatics","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89799365","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：