Pub Date : 2023-04-03DOI: 10.32890/jict2023.22.2.2
Vanbien Le, Viet Minh Nhat Vo
Fairness is an important feature of communication networks. It is the distribution, allocation, and provision of approximately equal orequal performance parameters, such as throughput, bandwidth, loss rate, and delay. In an optical burst switched (OBS) network, fairness is considered in three aspects: distance, throughput, and delay. Studies on these three types of fairness have been conducted; however, they have usually been considered in isolation. These fairness types should be considered together to improve the communication performance of the entire OBS network. This paper proposes a combined delay-throughput fairness model, where burst assembly and bandwidth allocation are improved to achieve both delay fairness and throughput fairness at ingress OBS nodes. The delay fairness and throughput fairness indices are recommended as metrics for adjusting the assembly queue length and allocated bandwidth for priority flows. The simulation results showed that delay and throughput fairness could be achieved simultaneously, improving the overall communication performance of the entire OBS network.
{"title":"A Combined Delay-Throughput Fairness Model for Optical Burst Switched Networks","authors":"Vanbien Le, Viet Minh Nhat Vo","doi":"10.32890/jict2023.22.2.2","DOIUrl":"https://doi.org/10.32890/jict2023.22.2.2","url":null,"abstract":"Fairness is an important feature of communication networks. It is the distribution, allocation, and provision of approximately equal orequal performance parameters, such as throughput, bandwidth, loss rate, and delay. In an optical burst switched (OBS) network, fairness is considered in three aspects: distance, throughput, and delay. Studies on these three types of fairness have been conducted; however, they have usually been considered in isolation. These fairness types should be considered together to improve the communication performance of the entire OBS network. This paper proposes a combined delay-throughput fairness model, where burst assembly and bandwidth allocation are improved to achieve both delay fairness and throughput fairness at ingress OBS nodes. The delay fairness and throughput fairness indices are recommended as metrics for adjusting the assembly queue length and allocated bandwidth for priority flows. The simulation results showed that delay and throughput fairness could be achieved simultaneously, improving the overall communication performance of the entire OBS network.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75913435","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 : 2023-04-03DOI: 10.32890/jict2023.22.2.6
The digital gaming community appreciates visual style information in digital games as it facilitates information seeking. Nevertheless, learned scholars have discovered that the digital game visual style classification is inconsistent and easily modified, potentially limitingthe information and leading to inaccurate visual terminologies during information discovery. Therefore, this cross-sectional study wasperformed to assess multiple visual style classification terms and their definitions among Malaysian game developers using the closedcard sorting exercise. A total of seven professional game developers participated in an online survey that comprised thirty-five digital game case studies using a card sorting technique. They were asked to classify nineteen visual style classification terms, including psychedelic, text, illusionism, photorealism, televisualism, handicraft, caricature, celshaded, comic book (anime), watercolour, Lego, minimalism, pixel art, silhouette, bright, dark, maplike, colourful, and black and white. The Fleiss’ kappa intercoder reliability assessment was performed to measure the coders’ agreement on visual style classification, followed by the think-aloud protocol descriptive analysis to gather assessment insights into the visual style descriptions. The intercoder reliability test achieved a significantly moderate agreement based on the results. The professional game developers agreed on eighteen visual stylesand rejected the bright visual style classification due to its overlapping description with the colourful visual style. The definition of ten visual style classifications was improved from the existing Video Game Metadata Schema (VGMS) description, contributing to the digital game’s coherence and consistency. This improvement will enhance visual style classification information for machine-learning-based recommendation systems for digital game distribution platforms and digital archiving.
数字游戏社区欣赏数字游戏中的视觉风格信息，因为它有助于信息搜索。然而，学者们发现，数字游戏的视觉风格分类是不一致的，容易修改，潜在地限制了信息，并导致信息发现过程中不准确的视觉术语。因此，这项横断面研究是为了评估多种视觉风格分类术语及其在马来西亚游戏开发者中使用的定义。共有7名专业游戏开发者参与了一项在线调查，其中包括35个使用卡片分类技术的数字游戏案例研究。他们被要求对19种视觉风格分类术语进行分类，包括迷幻、文本、幻觉、照片现实主义、电视视觉主义、手工艺、漫画、光影、漫画书(动漫)、水彩、乐高、极简主义、像素艺术、剪影、明亮、黑暗、地图样、彩色和黑白。采用Fleiss kappa编码者可靠性评估来衡量编码者在视觉风格分类上的一致性，随后采用“大声思考”协议描述性分析来收集对视觉风格描述的评估见解。编码间信度测试在结果的基础上取得了显著的中等一致性。专业游戏开发者一致同意18种视觉风格，并拒绝了明亮的视觉风格分类，因为它与色彩丰富的视觉风格重叠。十种视觉风格分类的定义是基于现有的电子游戏元数据模式(Video Game Metadata Schema, VGMS)描述而改进的，这有助于数字游戏的连贯性和一致性。这一改进将增强基于机器学习的推荐系统的视觉风格分类信息，用于数字游戏分发平台和数字存档。
{"title":"Improving Visual Style Classification in Digital Games Using Intercoder Reliability Assessment","authors":"","doi":"10.32890/jict2023.22.2.6","DOIUrl":"https://doi.org/10.32890/jict2023.22.2.6","url":null,"abstract":"The digital gaming community appreciates visual style information in digital games as it facilitates information seeking. Nevertheless, learned scholars have discovered that the digital game visual style classification is inconsistent and easily modified, potentially limitingthe information and leading to inaccurate visual terminologies during information discovery. Therefore, this cross-sectional study wasperformed to assess multiple visual style classification terms and their definitions among Malaysian game developers using the closedcard sorting exercise. A total of seven professional game developers participated in an online survey that comprised thirty-five digital game case studies using a card sorting technique. They were asked to classify nineteen visual style classification terms, including psychedelic, text, illusionism, photorealism, televisualism, handicraft, caricature, celshaded, comic book (anime), watercolour, Lego, minimalism, pixel art, silhouette, bright, dark, maplike, colourful, and black and white. The Fleiss’ kappa intercoder reliability assessment was performed to measure the coders’ agreement on visual style classification, followed by the think-aloud protocol descriptive analysis to gather assessment insights into the visual style descriptions. The intercoder reliability test achieved a significantly moderate agreement based on the results. The professional game developers agreed on eighteen visual stylesand rejected the bright visual style classification due to its overlapping description with the colourful visual style. The definition of ten visual style classifications was improved from the existing Video Game Metadata Schema (VGMS) description, contributing to the digital game’s coherence and consistency. This improvement will enhance visual style classification information for machine-learning-based recommendation systems for digital game distribution platforms and digital archiving.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90545615","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 : 2023-04-03DOI: 10.32890/jict2023.22.2.4
Zi Hau Chin, Vishnu Monn Baskaran, Golnoush Abaei, I. Tan, T. Yap
Node churn, or the constant joining and leaving of nodes in a network, can impact the performance of a blockchain network. The difficulties of performing research on the actual blockchain network, particularly on a live decentralized global network like Bitcoin, pose challenges that good simulators can overcome. While various tools, such as NS-3 and OMNet++, are useful for simulating network behavior, SimBlock is specifically designed to simulate the complex Bitcoin blockchain network. However, the current implementation of SimBlock has limitations when replicating actual node churn activity. In this study, the SimBlock simulator was improved to simulate node churn more accurately by removing churning nodes and dropping their connections, and increasing additional instrumentation for validation. The methodology used in the study involved modeling the Bitcoin node churn behavior based on previous studies and using the enhanced SimBlock simulator to simulate node churn. Empirical studies were then conducted to determine the suitability and limitations of the node churn simulation. This study found that the improved SimBlock could produce results similar to observed indicators in a 100-node network. However, it still had limitations in replicating node churn behavior accurately. It was discovered that SimBlock limits all nodes to operate as mining nodes and that mining is simulated in a way that does not depict churn accurately at any time but only at specific intervals or under certain conditions. Despite these limitations, the study’simprovements to SimBlock and the identification of its limitations can be useful for future research on node churn in blockchain networks and the development of more effective simulation tools.
{"title":"Attestation of Improved SimBlock Node Churn Simulation","authors":"Zi Hau Chin, Vishnu Monn Baskaran, Golnoush Abaei, I. Tan, T. Yap","doi":"10.32890/jict2023.22.2.4","DOIUrl":"https://doi.org/10.32890/jict2023.22.2.4","url":null,"abstract":"Node churn, or the constant joining and leaving of nodes in a network, can impact the performance of a blockchain network. The difficulties of performing research on the actual blockchain network, particularly on a live decentralized global network like Bitcoin, pose challenges that good simulators can overcome. While various tools, such as NS-3 and OMNet++, are useful for simulating network behavior, SimBlock is specifically designed to simulate the complex Bitcoin blockchain network. However, the current implementation of SimBlock has limitations when replicating actual node churn activity. In this study, the SimBlock simulator was improved to simulate node churn more accurately by removing churning nodes and dropping their connections, and increasing additional instrumentation for validation. The methodology used in the study involved modeling the Bitcoin node churn behavior based on previous studies and using the enhanced SimBlock simulator to simulate node churn. Empirical studies were then conducted to determine the suitability and limitations of the node churn simulation. This study found that the improved SimBlock could produce results similar to observed indicators in a 100-node network. However, it still had limitations in replicating node churn behavior accurately. It was discovered that SimBlock limits all nodes to operate as mining nodes and that mining is simulated in a way that does not depict churn accurately at any time but only at specific intervals or under certain conditions. Despite these limitations, the study’simprovements to SimBlock and the identification of its limitations can be useful for future research on node churn in blockchain networks and the development of more effective simulation tools. ","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89180096","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 : 2023-01-19DOI: 10.32890/jict2023.22.1.2
Juho Song, Ho Lee, O-young Kwon
The purpose of this study is to identify issues related to software manpower, which became more important in the era of the FourthIndustrial Revolution in Korea. The results of this study can provide guidelines for those who establish software manpower training policies for solving the software industry’s human resource paradox. As for the research method, the quantitative text network and qualitative analyses from industry experts were used to interpret the results. A total of 14,752 news data mentioning software manpower were extracted, and data pre-processing for the synonyms and negative words were performed. The network was non-directional and consisted of 14,074 words (nodes) and 1,542,383 word combinations (edges). In addition, the network was clustered based on Modularity, and the degree of connection and eigenvector centrality were used to determine the importance of nodes. The analysis of the results showed that the government’s efforts through the Korean Ministry of Science and ICT were vital in creating jobs that fueled software innovation growth, and that software education was actively promoted to develop software talent. This study had the following implications. It was confirmed that software is making a high contribution to the expansion of business opportunities and job creation in the fields of new technology and software convergence technology. To resolve the software manpower supply-demand mismatch, it is necessary to cultivate high-quality software talent and provide mid- to long-term activities to attract competent human resources. In addition, it is necessary to develop and expand programs that link education and recruitment in terms of public-private cooperation along with government-led investment to strengthen national software competitiveness.
{"title":"Investigating Job Mismatch in Software Industry through News Big Data","authors":"Juho Song, Ho Lee, O-young Kwon","doi":"10.32890/jict2023.22.1.2","DOIUrl":"https://doi.org/10.32890/jict2023.22.1.2","url":null,"abstract":"The purpose of this study is to identify issues related to software manpower, which became more important in the era of the FourthIndustrial Revolution in Korea. The results of this study can provide guidelines for those who establish software manpower training policies for solving the software industry’s human resource paradox. As for the research method, the quantitative text network and qualitative analyses from industry experts were used to interpret the results. A total of 14,752 news data mentioning software manpower were extracted, and data pre-processing for the synonyms and negative words were performed. The network was non-directional and consisted of 14,074 words (nodes) and 1,542,383 word combinations (edges). In addition, the network was clustered based on Modularity, and the degree of connection and eigenvector centrality were used to determine the importance of nodes. The analysis of the results showed that the government’s efforts through the Korean Ministry of Science and ICT were vital in creating jobs that fueled software innovation growth, and that software education was actively promoted to develop software talent. This study had the following implications. It was confirmed that software is making a high contribution to the expansion of business opportunities and job creation in the fields of new technology and software convergence technology. To resolve the software manpower supply-demand mismatch, it is necessary to cultivate high-quality software talent and provide mid- to long-term activities to attract competent human resources. In addition, it is necessary to develop and expand programs that link education and recruitment in terms of public-private cooperation along with government-led investment to strengthen national software competitiveness.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83873866","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 : 2023-01-19DOI: 10.32890/jict2023.22.1.6
Seong-Yoon Shin, Gwanghyun Jo, Guangxing Wang
Image recognition and classification is a significant research topic in computational vision and widely used computer technology. Themethods often used in image classification and recognition tasks are based on deep learning, like Convolutional Neural Networks(CNNs), LeNet, and Long Short-Term Memory networks (LSTM). Unfortunately, the classification accuracy of these methods isunsatisfactory. In recent years, using large-scale deep learning networks to achieve image recognition and classification canimprove classification accuracy, such as VGG16 and Residual Network (ResNet). However, due to the deep network hierarchyand complex parameter settings, these models take more time in the training phase, especially when the sample number is small, which can easily lead to overfitting. This paper suggested a deep learning-based image classification technique based on a CNN model and improved convolutional and pooling layers. Furthermore, the study adopted the approximate dynamic learning rate update algorithm in the model training to realize the learning rate’s self-adaptation, ensure the model’s rapid convergence, and shorten the training time. Using the proposed model, an experiment was conducted on the Fashion-MNIST dataset, taking 6,000 images as the training dataset and 1,000 images as the testing dataset. In actual experiments, the classification accuracy of the suggested method was 93 percent, 4.6 percent higher than that of the basic CNN model. Simultaneously, the study compared the influence of the batch size of model training on classification accuracy. Experimental outcomes showed this model is very generalized in fashion clothing image classification tasks.
{"title":"A Novel Method for Fashion Clothing Image Classification Based on Deep Learning","authors":"Seong-Yoon Shin, Gwanghyun Jo, Guangxing Wang","doi":"10.32890/jict2023.22.1.6","DOIUrl":"https://doi.org/10.32890/jict2023.22.1.6","url":null,"abstract":"Image recognition and classification is a significant research topic in computational vision and widely used computer technology. Themethods often used in image classification and recognition tasks are based on deep learning, like Convolutional Neural Networks(CNNs), LeNet, and Long Short-Term Memory networks (LSTM). Unfortunately, the classification accuracy of these methods isunsatisfactory. In recent years, using large-scale deep learning networks to achieve image recognition and classification canimprove classification accuracy, such as VGG16 and Residual Network (ResNet). However, due to the deep network hierarchyand complex parameter settings, these models take more time in the training phase, especially when the sample number is small, which can easily lead to overfitting. This paper suggested a deep learning-based image classification technique based on a CNN model and improved convolutional and pooling layers. Furthermore, the study adopted the approximate dynamic learning rate update algorithm in the model training to realize the learning rate’s self-adaptation, ensure the model’s rapid convergence, and shorten the training time. Using the proposed model, an experiment was conducted on the Fashion-MNIST dataset, taking 6,000 images as the training dataset and 1,000 images as the testing dataset. In actual experiments, the classification accuracy of the suggested method was 93 percent, 4.6 percent higher than that of the basic CNN model. Simultaneously, the study compared the influence of the batch size of model training on classification accuracy. Experimental outcomes showed this model is very generalized in fashion clothing image classification tasks. ","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90498560","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 : 2023-01-19DOI: 10.32890/jict2023.22.1.5
Nur Hanis Mohamad Noor, Izzal Asnira Zolkepli, Bahiyah Omar
Contemporary technology success is frequently associated with the competitive advantage of being cool. A fitness band is one of thesmart wearable devices promoting health behaviours, which is one of the cool lifestyle trends in modern societies. Although past research established the profound effects of coolness on user technology acceptance, the influencing role in fostering health behaviour remained obscure. To bridge the existing literature gap, the current study aims to examine the perception of coolness as a higher-order construct with multiple dimensions, namely originality, attractiveness, and sub-cultural appeals, by investigating the direct effect on fitness band adoption and indirect influence on users’ health behaviour. An online survey was conducted on 280 fitness band users, and the data was subsequently analysed via the Partial Least Squares-Structural Equation Modeling (PLS-SEM). The study results demonstrated that the perceived coolness of fitness bands significantly affects users’ device adoption levels, which subsequently influence personal health behaviour. This study thus contributes to health communication research by testing the coolness concept and developing the diffusioninnovation framework from current human-computer interaction literature. The findings would guide future developers of fitness bands to emphasise the coolness functions for higher degrees of adoption and positive impact on society.
{"title":"It’s Cool to be Healthy! The Effect of Perceived Coolness on the Adoption of Fitness Bands and Health Behaviour","authors":"Nur Hanis Mohamad Noor, Izzal Asnira Zolkepli, Bahiyah Omar","doi":"10.32890/jict2023.22.1.5","DOIUrl":"https://doi.org/10.32890/jict2023.22.1.5","url":null,"abstract":"Contemporary technology success is frequently associated with the competitive advantage of being cool. A fitness band is one of thesmart wearable devices promoting health behaviours, which is one of the cool lifestyle trends in modern societies. Although past research established the profound effects of coolness on user technology acceptance, the influencing role in fostering health behaviour remained obscure. To bridge the existing literature gap, the current study aims to examine the perception of coolness as a higher-order construct with multiple dimensions, namely originality, attractiveness, and sub-cultural appeals, by investigating the direct effect on fitness band adoption and indirect influence on users’ health behaviour. An online survey was conducted on 280 fitness band users, and the data was subsequently analysed via the Partial Least Squares-Structural Equation Modeling (PLS-SEM). The study results demonstrated that the perceived coolness of fitness bands significantly affects users’ device adoption levels, which subsequently influence personal health behaviour. This study thus contributes to health communication research by testing the coolness concept and developing the diffusioninnovation framework from current human-computer interaction literature. The findings would guide future developers of fitness bands to emphasise the coolness functions for higher degrees of adoption and positive impact on society.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85707405","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 : 2023-01-19DOI: 10.32890/jict2023.22.1.1
F. Okwonu, N. Ahad, Hashibah Hamid, N. Muda, Olimjon Shukurovich Sharipov
The robustness of some classical univariate classifiers is hampered if the data are contaminated. Overfitting is another hiccup when the data sets are uncontaminated with a considerable sample size. The performance of the classification models can be easily biased by the outliers’ problems, of which the constructed model tends to be overfitted. Previous studies often used the Bayes Classifier (BC) and the Predictive Classifier (PC) to address two groups of univariate classification problems. Unfortunately for substantial large sample sizes and uncontaminated data, the BC method overfits when the Optimal Probability of Exact Classification (OPEC) is used as an evaluation benchmark. Meanwhile, for small sample sizes, the BC and PC methods are extremely susceptible to outliers. To overcome these two problems, we proposed two methods: the Smart Univariate Classifier (SUC) and the hybrid classifier. The latter is a combination of the SUC and the BC methods, known as the Smart Univariate Bayes Classifier (SUBC). The performance of the new classification methods was evaluated and compared with the conventional BC and PC methods using the OPEC as a benchmark value. To validate the performance of these classification methods, the Probability of Exact Classification (PEC) was compared with the OPEC value. The results showed that the proposed methods outperformed the conventional BC and PC methods based on the real data sets applied. Numerical results also revealed that the SUC method could solve the overfitting problem. The results further indicated that the two proposed methods were robust against outliers. Therefore, these new methods are helpful when practitioners are confronted with overfitting and data contamination problems.
{"title":"Enhanced Robust Univariate Classification Methods for Solving Outliers and Overfitting Problems","authors":"F. Okwonu, N. Ahad, Hashibah Hamid, N. Muda, Olimjon Shukurovich Sharipov","doi":"10.32890/jict2023.22.1.1","DOIUrl":"https://doi.org/10.32890/jict2023.22.1.1","url":null,"abstract":"The robustness of some classical univariate classifiers is hampered if the data are contaminated. Overfitting is another hiccup when the data sets are uncontaminated with a considerable sample size. The performance of the classification models can be easily biased by the outliers’ problems, of which the constructed model tends to be overfitted. Previous studies often used the Bayes Classifier (BC) and the Predictive Classifier (PC) to address two groups of univariate classification problems. Unfortunately for substantial large sample sizes and uncontaminated data, the BC method overfits when the Optimal Probability of Exact Classification (OPEC) is used as an evaluation benchmark. Meanwhile, for small sample sizes, the BC and PC methods are extremely susceptible to outliers. To overcome these two problems, we proposed two methods: the Smart Univariate Classifier (SUC) and the hybrid classifier. The latter is a combination of the SUC and the BC methods, known as the Smart Univariate Bayes Classifier (SUBC). The performance of the new classification methods was evaluated and compared with the conventional BC and PC methods using the OPEC as a benchmark value. To validate the performance of these classification methods, the Probability of Exact Classification (PEC) was compared with the OPEC value. The results showed that the proposed methods outperformed the conventional BC and PC methods based on the real data sets applied. Numerical results also revealed that the SUC method could solve the overfitting problem. The results further indicated that the two proposed methods were robust against outliers. Therefore, these new methods are helpful when practitioners are confronted with overfitting and data contamination problems.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86602694","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 : 2023-01-18DOI: 10.32890/jict2023.22.1.3
Y. Bhanusree, Samayamantula Srinivas Kumar, Anne Koteswara Rao
Speech Emotion Detection (SER) is a field of identifying human emotions from human speech utterances. Human speech utterancesare a combination of linguistic and non-linguistic information. Nonlinguistic SER provides a generalized solution in human–computerinteraction applications as it overcomes the language barrier. Machine learning and deep learning techniques were previously proposed for classifying emotions using handpicked features. To achieve effective and generalized SER, feature extraction can be performed using deep neural networks and ensemble learning for classification. The proposed model employed a time-distributed attention-layered convolution neural network (TDACNN) for extracting spatiotemporal features at the first stage and a random forest (RF) classifier, which is an ensemble classifier for efficient and generalized classification of emotions, at the second stage. The proposed model was implemented on the RAVDESS and IEMOCAP data corpora and compared with the CNN-SVM and CNN-RF models for SER. The TDACNN-RF model exhibited test classification accuracies of 92.19 percent and 90.27 percent on the RAVDESS and IEMOCAP data corpora, respectively. The experimental results proved that the proposed model is efficient in extracting spatiotemporal features from time-series speech signals and can classify emotions with good accuracy. The class confusion among the emotions was reduced for both data corpora, proving that the model achieved generalization.
{"title":"Time-Distributed Attention-Layered Convolution Neural Network with Ensemble Learning using Random Forest Classifier for Speech Emotion Recognition","authors":"Y. Bhanusree, Samayamantula Srinivas Kumar, Anne Koteswara Rao","doi":"10.32890/jict2023.22.1.3","DOIUrl":"https://doi.org/10.32890/jict2023.22.1.3","url":null,"abstract":"Speech Emotion Detection (SER) is a field of identifying human emotions from human speech utterances. Human speech utterancesare a combination of linguistic and non-linguistic information. Nonlinguistic SER provides a generalized solution in human–computerinteraction applications as it overcomes the language barrier. Machine learning and deep learning techniques were previously proposed for classifying emotions using handpicked features. To achieve effective and generalized SER, feature extraction can be performed using deep neural networks and ensemble learning for classification. The proposed model employed a time-distributed attention-layered convolution neural network (TDACNN) for extracting spatiotemporal features at the first stage and a random forest (RF) classifier, which is an ensemble classifier for efficient and generalized classification of emotions, at the second stage. The proposed model was implemented on the RAVDESS and IEMOCAP data corpora and compared with the CNN-SVM and CNN-RF models for SER. The TDACNN-RF model exhibited test classification accuracies of 92.19 percent and 90.27 percent on the RAVDESS and IEMOCAP data corpora, respectively. The experimental results proved that the proposed model is efficient in extracting spatiotemporal features from time-series speech signals and can classify emotions with good accuracy. The class confusion among the emotions was reduced for both data corpora, proving that the model achieved generalization.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78756334","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 : 2023-01-18DOI: 10.32890/jict2023.22.1.4
Yonghan Jung, Chang-heon Oh
Demand for more accurate particulate matter forecasts is accumulating owing to the increased interest and issues regarding particulate matter. Incredibly low concentration particulate matter, which accounts for most of the overall particulate matter, is often underestimated when a particulate matter prediction model based on machine learning is used. This study proposed a concentration-specific separation prediction model to overcome this shortcoming. Three prediction models based on Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM), commonly used for performance evaluation of the proposed prediction model, were used as comparative models. Root mean squared error (RMSE), mean absolute percentage error (MAPE), and accuracy were utilized for performance evaluation. The results showed that the prediction accuracy for all Air Quality Index (AQI) segments was more than 80 percent in the entire concentration spectrum. In addition, the study confirmed that the over-prediction phenomenon of single neural network models concentrated in the ‘normal’ AQI region was alleviated.
{"title":"Concentration Separation Prediction Model to Enhance Prediction Accuracy of Particulate Matter","authors":"Yonghan Jung, Chang-heon Oh","doi":"10.32890/jict2023.22.1.4","DOIUrl":"https://doi.org/10.32890/jict2023.22.1.4","url":null,"abstract":"Demand for more accurate particulate matter forecasts is accumulating owing to the increased interest and issues regarding particulate matter. Incredibly low concentration particulate matter, which accounts for most of the overall particulate matter, is often underestimated when a particulate matter prediction model based on machine learning is used. This study proposed a concentration-specific separation prediction model to overcome this shortcoming. Three prediction models based on Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM), commonly used for performance evaluation of the proposed prediction model, were used as comparative models. Root mean squared error (RMSE), mean absolute percentage error (MAPE), and accuracy were utilized for performance evaluation. The results showed that the prediction accuracy for all Air Quality Index (AQI) segments was more than 80 percent in the entire concentration spectrum. In addition, the study confirmed that the over-prediction phenomenon of single neural network models concentrated in the ‘normal’ AQI region was alleviated.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80178628","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}
{"title":"Fusion deep capsule-network based facial expression recognition","authors":"Tusongjiang Kari, Guohang Zhuang, Yilihamu YaErmaimaiti","doi":"10.1504/ijict.2023.10059350","DOIUrl":"https://doi.org/10.1504/ijict.2023.10059350","url":null,"abstract":"","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135653470","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：