Pub Date : 2022-08-22DOI: 10.51548/joctec-2022-009
Z. W. Taylor, Linda Eguiluz, P. Wheeler
Colleges continue to use technology to connect students to information, but a research gap exists regarding how colleges use a ubiquitous technology in the business world: chatbots. Moreover, no work has addressed whether chatbots address Spanish-speaking students seeking higher education in the form of automated (AI) chatbot responses in Spanish or Spanish-programmed chatbots. This study randomly sampled 331 United States institutions of higher education to learn if these institutions embed chatbots on their undergraduate admissions websites and if these chatbots have been programmed to speak Spanish. Results suggest 21% of institutions (n=71) embed chatbots into their admissions websites and only 28% of those chatbots (n= 20) were programmed to provide Spanish-language admissions information. Implications for college access and equity for English learners and L1 Spanish speakers are addressed.
{"title":"Ni máquina, ni humano ni disponible: Do College Admissions Offices Use Chatbots and Can They Speak Spanish?","authors":"Z. W. Taylor, Linda Eguiluz, P. Wheeler","doi":"10.51548/joctec-2022-009","DOIUrl":"https://doi.org/10.51548/joctec-2022-009","url":null,"abstract":"Colleges continue to use technology to connect students to information, but a research gap exists regarding how colleges use a ubiquitous technology in the business world: chatbots. Moreover, no work has addressed whether chatbots address Spanish-speaking students seeking higher education in the form of automated (AI) chatbot responses in Spanish or Spanish-programmed chatbots. This study randomly sampled 331 United States institutions of higher education to learn if these institutions embed chatbots on their undergraduate admissions websites and if these chatbots have been programmed to speak Spanish. Results suggest 21% of institutions (n=71) embed chatbots into their admissions websites and only 28% of those chatbots (n= 20) were programmed to provide Spanish-language admissions information. Implications for college access and equity for English learners and L1 Spanish speakers are addressed.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87053565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-17DOI: 10.32890/jict2022.21.3.5
Shahrizan Jamaludin, A. F. Mohamad Ayob, Syamimi Mohd Norzeli, S. Mohamed
Iris segmentation is a process to isolate the accurate iris region from the eye image for iris recognition. Iris segmentation on non-ideal and noisy iris images is accurate with active contour. Nevertheless, it is currently unclear on how active contour responds to blurry iris images or motion blur, which presents a significant obstacle in iris segmentation. Investigation on blurry iris images, especially on the initial contour position, is rarely published and must be clarified. Moreover, evolution or convergence speed remains a significant challenge for active contour as it segments the precise iris boundary. Therefore, this study carried out experiments to achieve an efficient iris segmentation algorithm in terms of accuracy and fast execution, according to the aforementioned concerns. In addition, initial contour was explored to clarify its position. In order to accomplish these goals, the Wiener filter and morphological closing were used for preprocessing and reflection removal. Next, the adaptive initial contour (AIC), δ, and stopping function were integrated to create the adaptive Chan-Vese active contour (ACVAC) algorithm. Finally, the partly -normalization method for normalization and feature extraction was designed by selecting the most prominent iris features. The findings revealed that the algorithm outperformed the other active contour-based approaches in computational time and segmentation accuracy. It proved that in blurry iris images, the accurate initial contour position could be established. This algorithm is significant to solve inaccurate segmentation on blurry iris images.
{"title":"ADAPTIVE INITIAL CONTOUR AND PARTLY-NORMALIZATION ALGORITHM FOR IRIS SEGMENTATION OF BLURRY IRIS IMAGES","authors":"Shahrizan Jamaludin, A. F. Mohamad Ayob, Syamimi Mohd Norzeli, S. Mohamed","doi":"10.32890/jict2022.21.3.5","DOIUrl":"https://doi.org/10.32890/jict2022.21.3.5","url":null,"abstract":"Iris segmentation is a process to isolate the accurate iris region from the eye image for iris recognition. Iris segmentation on non-ideal and noisy iris images is accurate with active contour. Nevertheless, it is currently unclear on how active contour responds to blurry iris images or motion blur, which presents a significant obstacle in iris segmentation. Investigation on blurry iris images, especially on the initial contour position, is rarely published and must be clarified. Moreover, evolution or convergence speed remains a significant challenge for active contour as it segments the precise iris boundary. Therefore, this study carried out experiments to achieve an efficient iris segmentation algorithm in terms of accuracy and fast execution, according to the aforementioned concerns. In addition, initial contour was explored to clarify its position. In order to accomplish these goals, the Wiener filter and morphological closing were used for preprocessing and reflection removal. Next, the adaptive initial contour (AIC), δ, and stopping function were integrated to create the adaptive Chan-Vese active contour (ACVAC) algorithm. Finally, the partly -normalization method for normalization and feature extraction was designed by selecting the most prominent iris features. The findings revealed that the algorithm outperformed the other active contour-based approaches in computational time and segmentation accuracy. It proved that in blurry iris images, the accurate initial contour position could be established. This algorithm is significant to solve inaccurate segmentation on blurry iris images.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82028345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-17DOI: 10.32890/jict2022.21.3.3
N. Ismail, U. K. Yusof
Machine learning (ML) prediction determinants based on open data (OD) are investigated in this work, which is accomplished by examining current research trends over ten years. Currently, OD is commonly regarded as the most crucial trend for users to improve their ability to make decisions, particularly to the exponential expansion of social networking sites (SNSs) and open government data (OGD).The purpose of this study was to examine if there was an increase in the usage of OD in ML prediction techniques by conducting a systematic literature review (SLR) of the results of the trends. The papers published in major online scientific databases between 2011 and 2020, including ScienceDirect, Scopus, IEEE Xplore, ACM, and Springer, were identified and analysed. After various selection and Springer, were identified and analysed. After various selection processes, according to SLR based on precise inclusion and exclusion criteria, a total of 302 articles were located. However, only 81 of them were included. The findings were presented and plotted based on the research questions (RQs). In conclusion, this research could be beneficial to organisations, practitioners, and researchers by providing information on current trends in the implementation of ML prediction using OD setting by mapping studies based on the RQs designed, the most recent growth, and the necessity for future research based on the findings.
{"title":"RECENT TRENDS OF MACHINE LEARNING PREDICTIONS USING OPEN DATA: A SYSTEMATIC REVIEW","authors":"N. Ismail, U. K. Yusof","doi":"10.32890/jict2022.21.3.3","DOIUrl":"https://doi.org/10.32890/jict2022.21.3.3","url":null,"abstract":"Machine learning (ML) prediction determinants based on open data (OD) are investigated in this work, which is accomplished by examining current research trends over ten years. Currently, OD is commonly regarded as the most crucial trend for users to improve their ability to make decisions, particularly to the exponential expansion of social networking sites (SNSs) and open government data (OGD).The purpose of this study was to examine if there was an increase in the usage of OD in ML prediction techniques by conducting a systematic literature review (SLR) of the results of the trends. The papers published in major online scientific databases between 2011 and 2020, including ScienceDirect, Scopus, IEEE Xplore, ACM, and Springer, were identified and analysed. After various selection and Springer, were identified and analysed. After various selection processes, according to SLR based on precise inclusion and exclusion criteria, a total of 302 articles were located. However, only 81 of them were included. The findings were presented and plotted based on the research questions (RQs). In conclusion, this research could be beneficial to organisations, practitioners, and researchers by providing information on current trends in the implementation of ML prediction using OD setting by mapping studies based on the RQs designed, the most recent growth, and the necessity for future research based on the findings.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73863956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-17DOI: 10.32890/jict2022.21.3.1
Kinan Keshkeh, A. Jantan, Kamal Alieyan
Transport Layer Security (TLS) based malware is one of the most hazardous malware types, as it relies on encryption to conceal connections. Due to the complexity of TLS traffic decryption, several anomaly-based detection studies have been conducted to detect TLS-based malware using different features and machine learning (ML) algorithms. However, most of these studies utilized flow features with no feature transformation or relied on inefficient flow feature transformations like frequency-based periodicity analysis and outliers percentage. This paper introduces TLSMalDetect, a TLS-based malware detection approach that integrates periodicity-independent entropy-based flow set (EFS) features generated by a flow feature transformation technique to solve flow feature utilization issues in related research. EFS features effectiveness was evaluated in two ways: (1) by comparing them to the corresponding outliers percentage and flow features using four feature importance methods, and (2) by analyzing classification performance with and without EFS features. Moreover, new Transmission Control Protocol features not explored in literature were incorporated into TLSMalDetect, and their contribution was assessed. This study’s results proved EFS features of the number of packets sent and received were superior to related outliers percentage and flow features and could remarkably increase the performance up to ~42% in the case of Support Vector Machine accuracy. Furthermore, using the basic features, TLSMalDetect achieved the highest accuracy of 93.69% by Naïve Bayes (NB) among the ML algorithms applied. Also, from a comparison view, TLSMalDetect’s Random Forest precision of 98.99% and NB recall of 92.91% exceeded the best relevant findings of previous studies. These comparative results demonstrated the TLSMalDetect’s ability to detect more malware flows out of total malicious flows than existing works. It could also generate more actual alerts from overall alerts than earlier research.Transport Layer Security (TLS) based malware is one of the most hazardous malware types, as it relies on encryption to conceal connections. Due to the complexity of TLS traffic decryption, several anomaly-based detection studies have been conducted to detect TLS-based malware using different features and machine learning (ML) algorithms. However, most of these studies utilized flow features with no feature transformation or relied on inefficient flow feature transformations like frequency-based periodicity analysis and outliers percentage. This paper introduces TLSMalDetect, a TLS-based malware detection approach that integrates periodicity-independent entropy-based flow set (EFS) features generated by a flow feature transformation technique to solve flow feature utilization issues in related research. EFS features effectiveness was evaluated in two ways: (1) by comparing them to the corresponding outliers percentage and flow features using four feature importance methods, and (
{"title":"A MACHINE LEARNING CLASSIFICATION APPROACH TO DETECT TLS-BASED MALWARE USING ENTROPY-BASED FLOW SET FEATURES","authors":"Kinan Keshkeh, A. Jantan, Kamal Alieyan","doi":"10.32890/jict2022.21.3.1","DOIUrl":"https://doi.org/10.32890/jict2022.21.3.1","url":null,"abstract":"Transport Layer Security (TLS) based malware is one of the most hazardous malware types, as it relies on encryption to conceal connections. Due to the complexity of TLS traffic decryption, several anomaly-based detection studies have been conducted to detect TLS-based malware using different features and machine learning (ML) algorithms. However, most of these studies utilized flow features with no feature transformation or relied on inefficient flow feature transformations like frequency-based periodicity analysis and outliers percentage. This paper introduces TLSMalDetect, a TLS-based malware detection approach that integrates periodicity-independent entropy-based flow set (EFS) features generated by a flow feature transformation technique to solve flow feature utilization issues in related research. EFS features effectiveness was evaluated in two ways: (1) by comparing them to the corresponding outliers percentage and flow features using four feature importance methods, and (2) by analyzing classification performance with and without EFS features. Moreover, new Transmission Control Protocol features not explored in literature were incorporated into TLSMalDetect, and their contribution was assessed. This study’s results proved EFS features of the number of packets sent and received were superior to related outliers percentage and flow features and could remarkably increase the performance up to ~42% in the case of Support Vector Machine accuracy. Furthermore, using the basic features, TLSMalDetect achieved the highest accuracy of 93.69% by Naïve Bayes (NB) among the ML algorithms applied. Also, from a comparison view, TLSMalDetect’s Random Forest precision of 98.99% and NB recall of 92.91% exceeded the best relevant findings of previous studies. These comparative results demonstrated the TLSMalDetect’s ability to detect more malware flows out of total malicious flows than existing works. It could also generate more actual alerts from overall alerts than earlier research.Transport Layer Security (TLS) based malware is one of the most hazardous malware types, as it relies on encryption to conceal connections. Due to the complexity of TLS traffic decryption, several anomaly-based detection studies have been conducted to detect TLS-based malware using different features and machine learning (ML) algorithms. However, most of these studies utilized flow features with no feature transformation or relied on inefficient flow feature transformations like frequency-based periodicity analysis and outliers percentage. This paper introduces TLSMalDetect, a TLS-based malware detection approach that integrates periodicity-independent entropy-based flow set (EFS) features generated by a flow feature transformation technique to solve flow feature utilization issues in related research. EFS features effectiveness was evaluated in two ways: (1) by comparing them to the corresponding outliers percentage and flow features using four feature importance methods, and (","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73017278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-17DOI: 10.32890/jict2022.21.3.6
F. Okwonu, N. Ahad, N. Ogini, I. Okoloko, W. Z. Wan Husin
This paper aimed to determine the efficiency of classifiers for high-dimensional classification methods. It also investigated whether an extreme minimum misclassification rate translates into robust efficiency. To ensure an acceptable procedure, a benchmark evaluation threshold (BETH) was proposed as a metric to analyze the comparative performance for high-dimensional classification methods. A simplified performance metric was derived to show the efficiency of different classification methods. To achieve the objectives, the existing probability of correct classification (PCC) or classification accuracy reported in five different articles was used to generate the BETH value. Then, a comparative analysis was performed between the application of BETH value and the well-established PCC value ,derived from the confusion matrix. The analysis indicated that the BETH procedure had a minimum misclassification rate, unlike the Optimal method. The results also revealed that as the PCC inclined toward unity value, the misclassification rate between the two methods (BETH and PCC) became extremely irrelevant. The study revealed that the BETH method was invariant to the performance established by the classifiers using the PCC criterion but demonstrated more relevant aspects of robustness and minimum misclassification rate as compared to the PCC method. In addition, the comparative analysis affirmed that the BETH method exhibited more robust efficiency than the Optimal method. The study concluded that a minimum misclassification rate yields robust performance efficiency.
{"title":"COMPARATIVE PERFORMANCE EVALUATION OF EFFICIENCY FOR HIGH DIMENSIONAL CLASSIFICATION METHODS","authors":"F. Okwonu, N. Ahad, N. Ogini, I. Okoloko, W. Z. Wan Husin","doi":"10.32890/jict2022.21.3.6","DOIUrl":"https://doi.org/10.32890/jict2022.21.3.6","url":null,"abstract":"This paper aimed to determine the efficiency of classifiers for high-dimensional classification methods. It also investigated whether an extreme minimum misclassification rate translates into robust efficiency. To ensure an acceptable procedure, a benchmark evaluation threshold (BETH) was proposed as a metric to analyze the comparative performance for high-dimensional classification methods. A simplified performance metric was derived to show the efficiency of different classification methods. To achieve the objectives, the existing probability of correct classification (PCC) or classification accuracy reported in five different articles was used to generate the BETH value. Then, a comparative analysis was performed between the application of BETH value and the well-established PCC value ,derived from the confusion matrix. The analysis indicated that the BETH procedure had a minimum misclassification rate, unlike the Optimal method. The results also revealed that as the PCC inclined toward unity value, the misclassification rate between the two methods (BETH and PCC) became extremely irrelevant. The study revealed that the BETH method was invariant to the performance established by the classifiers using the PCC criterion but demonstrated more relevant aspects of robustness and minimum misclassification rate as compared to the PCC method. In addition, the comparative analysis affirmed that the BETH method exhibited more robust efficiency than the Optimal method. The study concluded that a minimum misclassification rate yields robust performance efficiency.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81634604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-17DOI: 10.32890/jict2022.21.3.2
Nurul Aiman Abdul Rahim, M. A. Norasikin, Z. Maksom
Virtual Reality (VR) technologies create and control different virtual world instead of the actual environment, and this contributes to the feeling of control known as the sense of agency (SoA). The SoA exists from the contrast between the expected sensory consequence of one’s action from efference copy and the real sensory effects. However, the size representation of objects differs between the physical and virtual world due to certain technical limitations, such as the VR application’s virtual hand not reflecting the user’s actual hand size. A limitation that will incur low quality of perception and SoA for digital application. Here, we proposed a proof-of-concept of an interactive e-commerce application that incorporates VR capability and size calibration mechanism. The mechanism uses a calibration method based on the reciprocal scale factor from the virtual object to its real counterpart. The study of the SoA focusing on user perception and interaction was done. The proposed method was tested on twenty two participants − who are also online shopping users. Nearly half of the participants (45%) buy online products frequently, at least one transaction per day. The outcome indicates that our proposed method improves 47% of user perception and interaction compared to the conventional e-commerce application with its static texts and images. Our proposed method is rudimentary yet effective and can be easily implemented in any digital field.
{"title":"IMPROVING E-COMMERCE APPLICATION THROUGH SENSE OF AGENCY OF A CALIBRATED INTERACTIVE VR APPLICATION","authors":"Nurul Aiman Abdul Rahim, M. A. Norasikin, Z. Maksom","doi":"10.32890/jict2022.21.3.2","DOIUrl":"https://doi.org/10.32890/jict2022.21.3.2","url":null,"abstract":"Virtual Reality (VR) technologies create and control different virtual world instead of the actual environment, and this contributes to the feeling of control known as the sense of agency (SoA). The SoA exists from the contrast between the expected sensory consequence of one’s action from efference copy and the real sensory effects. However, the size representation of objects differs between the physical and virtual world due to certain technical limitations, such as the VR application’s virtual hand not reflecting the user’s actual hand size. A limitation that will incur low quality of perception and SoA for digital application. Here, we proposed a proof-of-concept of an interactive e-commerce application that incorporates VR capability and size calibration mechanism. The mechanism uses a calibration method based on the reciprocal scale factor from the virtual object to its real counterpart. The study of the SoA focusing on user perception and interaction was done. The proposed method was tested on twenty two participants − who are also online shopping users. Nearly half of the participants (45%) buy online products frequently, at least one transaction per day. The outcome indicates that our proposed method improves 47% of user perception and interaction compared to the conventional e-commerce application with its static texts and images. Our proposed method is rudimentary yet effective and can be easily implemented in any digital field.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80664824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-17DOI: 10.32890/jict2022.21.3.4
Jia Heng Ong, P. Ong, Kiow Lee Woon
Over the years, numerous studies have been conducted on the integration of computer vision and machine learning in plant disease detection. However, these conventional machine learning methods often require the contour segmentation of the infected region from the entire leaf region and the manual extraction of different discriminative features before the classification models can be developed. In this study, deep learning models, specifically, the AlexNet convolutional neural network (CNN) and the combination of AlexNet and support vector machine (AlexNet-SVM), which overcome the limitation of handcrafting of feature representation were implemented for oil palm leaf disease identification. The images of healthy and infected leaf samples were collected, resized, and renamed before the model training. These images were directly used to fit the classification models, without the need for segmentation and feature extraction as in models, without the need for segmentation and feature extraction as in the conventional machine learning methods. The optimal architecture of AlexNet CNN and AlexNet-SVM models were then determined and subsequently applied for the oil palm leaf disease identification.Comparative studies showed that the overall performance of the AlexNet CNN model outperformed AlexNet-SVM-based classifier.
{"title":"IMAGE-BASED OIL PALM LEAVES DISEASE DETECTION USING CONVOLUTIONAL NEURAL NETWORK","authors":"Jia Heng Ong, P. Ong, Kiow Lee Woon","doi":"10.32890/jict2022.21.3.4","DOIUrl":"https://doi.org/10.32890/jict2022.21.3.4","url":null,"abstract":"Over the years, numerous studies have been conducted on the integration of computer vision and machine learning in plant disease detection. However, these conventional machine learning methods often require the contour segmentation of the infected region from the entire leaf region and the manual extraction of different discriminative features before the classification models can be developed. In this study, deep learning models, specifically, the AlexNet convolutional neural network (CNN) and the combination of AlexNet and support vector machine (AlexNet-SVM), which overcome the limitation of handcrafting of feature representation were implemented for oil palm leaf disease identification. The images of healthy and infected leaf samples were collected, resized, and renamed before the model training. These images were directly used to fit the classification models, without the need for segmentation and feature extraction as in models, without the need for segmentation and feature extraction as in the conventional machine learning methods. The optimal architecture of AlexNet CNN and AlexNet-SVM models were then determined and subsequently applied for the oil palm leaf disease identification.Comparative studies showed that the overall performance of the AlexNet CNN model outperformed AlexNet-SVM-based classifier.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90681580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-07DOI: 10.32890/jict2022.21.2.2
Abdurrakhman Prasetyadi, Budi Nugroho, A. Tohari
Cluster methods such as k-means have been widely used to group areas with a relatively equal number of disasters to determine areas prone to natural disasters. Nevertheless, it is dificult to obtain a homogeneous clustering result of the k-means method because this method is sensitive to a random selection of the centers of the cluster. This paper presents the result of a study that aimed to apply a proposed hybrid approach of the combined k-means algorithm and hierarchy to the clustering process of anticipation level datasets of natural disaster mitigation in Indonesia. This study also added keyword and disaster-type ields to provide additional information for a better clustering process. The clustering process produced three clusters for the anticipation level of natural disaster mitigation. Based on the validation from experts, 67 districts/cities (82.7%) fell into Cluster 1 (low anticipation), nine districts/cities (11.1%) were classiied into Cluster 2 (medium), and the remaining ive districts/cities (6.2%) were categorized in Cluster 3 (high anticipation). From the analysis of the calculation of the silhouette coeficient, the hybrid algorithm provided relatively homogeneous clustering results. Furthermore, applying the hybrid algorithm to the keyword segment and the type of disaster produced a homogeneous clustering as indicated by the calculated purity coeficient and the total purity values. Therefore, the proposed hybrid algorithm can provide relatively homogeneous clustering results in natural disaster mitigation.
{"title":"A Hybrid K-Means Hierarchical Algorithm for Natural Disaster Mitigation Clustering","authors":"Abdurrakhman Prasetyadi, Budi Nugroho, A. Tohari","doi":"10.32890/jict2022.21.2.2","DOIUrl":"https://doi.org/10.32890/jict2022.21.2.2","url":null,"abstract":"Cluster methods such as k-means have been widely used to group areas with a relatively equal number of disasters to determine areas prone to natural disasters. Nevertheless, it is dificult to obtain a homogeneous clustering result of the k-means method because this method is sensitive to a random selection of the centers of the cluster. This paper presents the result of a study that aimed to apply a proposed hybrid approach of the combined k-means algorithm and hierarchy to the clustering process of anticipation level datasets of natural disaster mitigation in Indonesia. This study also added keyword and disaster-type ields to provide additional information for a better clustering process. The clustering process produced three clusters for the anticipation level of natural disaster mitigation. Based on the validation from experts, 67 districts/cities (82.7%) fell into Cluster 1 (low anticipation), nine districts/cities (11.1%) were classiied into Cluster 2 (medium), and the remaining ive districts/cities (6.2%) were categorized in Cluster 3 (high anticipation). From the analysis of the calculation of the silhouette coeficient, the hybrid algorithm provided relatively homogeneous clustering results. Furthermore, applying the hybrid algorithm to the keyword segment and the type of disaster produced a homogeneous clustering as indicated by the calculated purity coeficient and the total purity values. Therefore, the proposed hybrid algorithm can provide relatively homogeneous clustering results in natural disaster mitigation.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89740030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-07DOI: 10.32890/jict2022.21.2.5
Rifo Ahmad Genadi, M. L. Khodra
In aspect-based sentiment analysis, tasks are diverse and consist of aspect term extraction, aspect categorization, opinion term extraction, sentiment polarity classification, and relation extractions of aspect and opinion terms. These tasks are generally carried out sequentially using more than one model. However, this approach is inefficient and likely to reduce the model’s performance due to cumulative errors in previous processes. The co-extraction approach with Dual crOss-sharEd RNN (DOER) and span-based multitask acquired better performance than the pipelined approaches in English review data. Therefore, this research focuses on adapting the co-extraction approach where the extraction of aspect terms, opinion terms, and sentiment polarity are conducted simultaneously from review texts. The co-extraction approach was adapted by modifying the original frameworks to perform unhandled subtask to get the opinion triplet. Furthermore, the output layer on these frameworks was modified and trained using a collection of Indonesian-language hotel reviews. The adaptation was conducted by testing the output layer topology for aspect and opinion term extraction as well as variations in the type of recurrent neural network cells and model hyperparameters used, and then analysing the results to obtain a conclusion. The two proposed frameworks were able to carry out opinion triplet extraction and achieve decent performance. The DOER framework achieves better performance than the baselines on aspect and opinion term extraction tasks.
{"title":"Opinion Triplet Extraction for Aspect-Based Sentiment Analysis Using Co-Extraction Approach","authors":"Rifo Ahmad Genadi, M. L. Khodra","doi":"10.32890/jict2022.21.2.5","DOIUrl":"https://doi.org/10.32890/jict2022.21.2.5","url":null,"abstract":"In aspect-based sentiment analysis, tasks are diverse and consist of aspect term extraction, aspect categorization, opinion term extraction, sentiment polarity classification, and relation extractions of aspect and opinion terms. These tasks are generally carried out sequentially using more than one model. However, this approach is inefficient and likely to reduce the model’s performance due to cumulative errors in previous processes. The co-extraction approach with Dual crOss-sharEd RNN (DOER) and span-based multitask acquired better performance than the pipelined approaches in English review data. Therefore, this research focuses on adapting the co-extraction approach where the extraction of aspect terms, opinion terms, and sentiment polarity are conducted simultaneously from review texts. The co-extraction approach was adapted by modifying the original frameworks to perform unhandled subtask to get the opinion triplet. Furthermore, the output layer on these frameworks was modified and trained using a collection of Indonesian-language hotel reviews. The adaptation was conducted by testing the output layer topology for aspect and opinion term extraction as well as variations in the type of recurrent neural network cells and model hyperparameters used, and then analysing the results to obtain a conclusion. The two proposed frameworks were able to carry out opinion triplet extraction and achieve decent performance. The DOER framework achieves better performance than the baselines on aspect and opinion term extraction tasks.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79985343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-07DOI: 10.32890/jict2022.21.2.1
Noor Ain Syazwani Mohd Ghani, A. K. Jumaat
One of the most important steps in image processing and computer vision for image analysis is segmentation, which can be classified into global and selective segmentations. Global segmentation models can segment whole objects in an image. Unfortunately, these models are unable to segment a specific object that is required for extraction. To overcome this limitation, the selective segmentation model, which is capable of extracting a particular object or region in an image, must be prioritised. Recent selective segmentation models have shown to be effective in segmenting greyscale images. Nevertheless, if the input is vector-valued or identified as a colour image, the models simply ignore the colour information by converting that image into a greyscale format. Colour plays an important role in the interpretation of object boundaries within an image as it helps to provide a more detailed explanation of the scene’s objects. Therefore, in this research, a model for selective segmentation of vector-valued images is proposed by combining concepts from existing models. The finite difference method was used to solve the resulting Euler-Lagrange (EL) partial differential equation of the proposed model. The accuracy of the proposed model’s segmentation output was then assessed using visual observation as well as by using two similarity indices, namely the Jaccard (JSC) and Dice (DSC) similarity coefficients. Experimental results demonstrated that the proposed model is capable of successfully segmenting a specific object in vector-valued images. Future research on this area can be further extended in three-dimensional modelling.
{"title":"Selective Segmentation Model for Vector-Valued Images","authors":"Noor Ain Syazwani Mohd Ghani, A. K. Jumaat","doi":"10.32890/jict2022.21.2.1","DOIUrl":"https://doi.org/10.32890/jict2022.21.2.1","url":null,"abstract":"One of the most important steps in image processing and computer vision for image analysis is segmentation, which can be classified into global and selective segmentations. Global segmentation models can segment whole objects in an image. Unfortunately, these models are unable to segment a specific object that is required for extraction. To overcome this limitation, the selective segmentation model, which is capable of extracting a particular object or region in an image, must be prioritised. Recent selective segmentation models have shown to be effective in segmenting greyscale images. Nevertheless, if the input is vector-valued or identified as a colour image, the models simply ignore the colour information by converting that image into a greyscale format. Colour plays an important role in the interpretation of object boundaries within an image as it helps to provide a more detailed explanation of the scene’s objects. Therefore, in this research, a model for selective segmentation of vector-valued images is proposed by combining concepts from existing models. The finite difference method was used to solve the resulting Euler-Lagrange (EL) partial differential equation of the proposed model. The accuracy of the proposed model’s segmentation output was then assessed using visual observation as well as by using two similarity indices, namely the Jaccard (JSC) and Dice (DSC) similarity coefficients. Experimental results demonstrated that the proposed model is capable of successfully segmenting a specific object in vector-valued images. Future research on this area can be further extended in three-dimensional modelling.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73053482","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：