Pub Date : 2023-10-02DOI: 10.17977/um018v6i12023p103-113
Akmal Vrisna Alzuhdi, Harits Ar Rosyid, M. Chuttur, Shah Nazir
Assessment of a player's knowledge in game education has been around for some time. Traditional evaluation in and around a gaming session may disrupt the players' immersion. This research uses an optimized Random Forest to construct a non-invasive prediction of a game education player's Memorization via in-game data. Firstly, we obtained the dataset from a 3-month survey to record in-game data of 50 players who play 4-15 game stages of the Chem Fight (a test case game). Next, we generated three variants of datasets via the preprocessing stages: resampling method (SMOTE), normalization (min-max), and a combination of resampling and normalization. Then, we trained and optimized three Random Forest (RF) classifiers to predict the player's Memorization. We chose RF because it can generalize well given the high-dimensional dataset. We used RF as the classifier, subject to optimization using its hyperparameter: n_estimators. We implemented a Grid Search Cross Validation (GSCV) method to identify the best value of n_estimators. We utilized the statistics of GSCV results to reduce the weight of n_estimators by observing the region of interest shown by the graphs of performances of the classifiers. Overall, the classifiers fitted using the BEST n_estimators (i.e., 89, 31, 89, and 196 trees) from GSCV performed well with around 80% accuracy. Moreover, we successfully identified the smaller number of n_estimators (OPTIMAL), at least halved the BEST n_estimators. All classifiers were retrained using the OPTIMAL n_estimators (37, 12, 37, and 41 trees). We found out that the performances of the classifiers were relatively steady at ~80%. This means that we successfully optimized the Random Forest in predicting a player's Memorization when playing the Chem Fight game. An automated technique presented in this paper can monitor student interactions and evaluate their abilities based on in-game data. As such, it can offer objective data about the skills used.
{"title":"Optimizing Random Forest Algorithm to Classify Player's Memorisation via In-game Data","authors":"Akmal Vrisna Alzuhdi, Harits Ar Rosyid, M. Chuttur, Shah Nazir","doi":"10.17977/um018v6i12023p103-113","DOIUrl":"https://doi.org/10.17977/um018v6i12023p103-113","url":null,"abstract":"Assessment of a player's knowledge in game education has been around for some time. Traditional evaluation in and around a gaming session may disrupt the players' immersion. This research uses an optimized Random Forest to construct a non-invasive prediction of a game education player's Memorization via in-game data. Firstly, we obtained the dataset from a 3-month survey to record in-game data of 50 players who play 4-15 game stages of the Chem Fight (a test case game). Next, we generated three variants of datasets via the preprocessing stages: resampling method (SMOTE), normalization (min-max), and a combination of resampling and normalization. Then, we trained and optimized three Random Forest (RF) classifiers to predict the player's Memorization. We chose RF because it can generalize well given the high-dimensional dataset. We used RF as the classifier, subject to optimization using its hyperparameter: n_estimators. We implemented a Grid Search Cross Validation (GSCV) method to identify the best value of n_estimators. We utilized the statistics of GSCV results to reduce the weight of n_estimators by observing the region of interest shown by the graphs of performances of the classifiers. Overall, the classifiers fitted using the BEST n_estimators (i.e., 89, 31, 89, and 196 trees) from GSCV performed well with around 80% accuracy. Moreover, we successfully identified the smaller number of n_estimators (OPTIMAL), at least halved the BEST n_estimators. All classifiers were retrained using the OPTIMAL n_estimators (37, 12, 37, and 41 trees). We found out that the performances of the classifiers were relatively steady at ~80%. This means that we successfully optimized the Random Forest in predicting a player's Memorization when playing the Chem Fight game. An automated technique presented in this paper can monitor student interactions and evaluate their abilities based on in-game data. As such, it can offer objective data about the skills used.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"84 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139324120","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 : 2023-09-24DOI: 10.17977/um018v6i12023p92-102
Atkia Akila Karim, Naushin Nower
With the recent surge in road traffic within major cities, the need for both short and long-term traffic flow forecasting has become paramount for city authorities. Previous research efforts have predominantly focused on short-term traffic flow estimations for specific road segments and paths. However, applications of paramount importance, such as traffic management and schedule routing planning, demand a deep understanding of long-term traffic flow predictions. However, due to the intricate interplay of underlying factors, there exists a scarcity of studies dedicated to long-term traffic prediction. Previous research has also highlighted the challenge of lower accuracy in long-term predictions owing to error propagation within the model. This model effectively combines Graph Convolutional Network (GCN) capacity to extract spatial characteristics from the road network with the stacked GCN aptitude for capturing temporal context. Our developed model is subsequently employed for traffic flow forecasting within urban road networks. We rigorously compare our method against baseline techniques using two real-world datasets. Our approach significantly reduces prediction errors by 40% to 60% compared to other methods. The experimental results underscore our model's ability to uncover spatiotemporal dependencies within traffic data and its superior predictive performance over baseline models using real-world traffic datasets.
{"title":"Long-Term Traffic Prediction Based on Stacked GCN Model","authors":"Atkia Akila Karim, Naushin Nower","doi":"10.17977/um018v6i12023p92-102","DOIUrl":"https://doi.org/10.17977/um018v6i12023p92-102","url":null,"abstract":"With the recent surge in road traffic within major cities, the need for both short and long-term traffic flow forecasting has become paramount for city authorities. Previous research efforts have predominantly focused on short-term traffic flow estimations for specific road segments and paths. However, applications of paramount importance, such as traffic management and schedule routing planning, demand a deep understanding of long-term traffic flow predictions. However, due to the intricate interplay of underlying factors, there exists a scarcity of studies dedicated to long-term traffic prediction. Previous research has also highlighted the challenge of lower accuracy in long-term predictions owing to error propagation within the model. This model effectively combines Graph Convolutional Network (GCN) capacity to extract spatial characteristics from the road network with the stacked GCN aptitude for capturing temporal context. Our developed model is subsequently employed for traffic flow forecasting within urban road networks. We rigorously compare our method against baseline techniques using two real-world datasets. Our approach significantly reduces prediction errors by 40% to 60% compared to other methods. The experimental results underscore our model's ability to uncover spatiotemporal dependencies within traffic data and its superior predictive performance over baseline models using real-world traffic datasets.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"45 3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139336805","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 : 2023-09-22DOI: 10.17977/um018v6i12023p79-91
I. K. W. Sudiatmika, G. Indrawan, S. Sariyasa
The Provincial Government of Bali assumes a crucial role in administering various public service applications to meet the requirements of its community, traditional villages, and regional apparatus. Nevertheless, the escalating magnitude of traffic and uneven distribution of requests have resulted in substantial server burdens, which may jeopardize the operation of applications and heighten the likelihood of downtime. Ensuring efficient load distribution is of utmost importance in tackling these difficulties, and the Round Robin algorithm is often utilized for this purpose. However, the current body of research has not extensively examined the distinct circumstances surrounding on-premise servers in the Bali Provincial Government. The primary objective of this study is to address the significant gap in knowledge by conducting a comprehensive evaluation of the Round Robin algorithm's effectiveness in load-balancing on-premise servers inside the Bali Provincial Government. The primary objective of our study is to assess the appropriateness of the algorithm within the given context, with the ultimate goal of providing practical and implementable suggestions. The observations above can optimize system efficiency and minimize periods of inactivity, thereby enhancing the provision of vital public services across Bali. This study provides essential insights for enhancing server infrastructure and load-balancing strategies through empirical evaluation and comprehensive analysis. Its findings are valuable for the Bali Provincial Government and serve as a reference for other organizations facing challenges managing server loads. This study signifies a notable advancement in establishing reliable and practical public service applications within Bali.
{"title":"Round-Robin Algorithm in Load Balancing for National Data Centers","authors":"I. K. W. Sudiatmika, G. Indrawan, S. Sariyasa","doi":"10.17977/um018v6i12023p79-91","DOIUrl":"https://doi.org/10.17977/um018v6i12023p79-91","url":null,"abstract":"The Provincial Government of Bali assumes a crucial role in administering various public service applications to meet the requirements of its community, traditional villages, and regional apparatus. Nevertheless, the escalating magnitude of traffic and uneven distribution of requests have resulted in substantial server burdens, which may jeopardize the operation of applications and heighten the likelihood of downtime. Ensuring efficient load distribution is of utmost importance in tackling these difficulties, and the Round Robin algorithm is often utilized for this purpose. However, the current body of research has not extensively examined the distinct circumstances surrounding on-premise servers in the Bali Provincial Government. The primary objective of this study is to address the significant gap in knowledge by conducting a comprehensive evaluation of the Round Robin algorithm's effectiveness in load-balancing on-premise servers inside the Bali Provincial Government. The primary objective of our study is to assess the appropriateness of the algorithm within the given context, with the ultimate goal of providing practical and implementable suggestions. The observations above can optimize system efficiency and minimize periods of inactivity, thereby enhancing the provision of vital public services across Bali. This study provides essential insights for enhancing server infrastructure and load-balancing strategies through empirical evaluation and comprehensive analysis. Its findings are valuable for the Bali Provincial Government and serve as a reference for other organizations facing challenges managing server loads. This study signifies a notable advancement in establishing reliable and practical public service applications within Bali.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"135 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139337490","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 research conducted in this study was driven by the East Java provincial government's requirement to assess the transaction levels of the Student Business Group (KUS) in the SMA Double Track program. These transaction levels are a basis for allocating supplementary financial aid to each business group. The system's primary objective is to assist the provincial government of East Java in making well-informed choices pertaining to the distribution of supplementary capital to the KUS. The classification technique employed in this study is the multilayer perceptron. However, the K-Means Clustering method is utilised to generate target data due to the limited availability during the classification process, which involves dividing the transaction level attributes into three distinct groups: (0) low transactions, (1) medium transactions, and (2) high transactions. The clustering process encompasses three distinct features: (1) income, (2) spending, and (3) profit. These three traits will be utilized as input data throughout the categorization procedure. The classification procedure employing the Multilayer Perceptron technique involved processing a dataset including 1383 data points. The training data constituted 80% of the dataset, while the remaining 20% was allocated for testing. In order to evaluate the efficacy of the constructed model, the training error was assessed using K-Fold cross-validation, yielding an average accuracy score of 0.92. In the present study, the categorization technique yielded an accuracy of 0.96. This model aims to classify scenarios when the dataset lacks prior target data.
东爪哇省政府要求评估 SMA 双轨项目中学生企业集团（KUS）的交易水平，本研究正是在此要求下开展的。这些交易水平是向每个企业集团分配补充财政援助的依据。该系统的主要目的是协助东爪哇省政府在向 KUS 分配补充资金时做出明智的选择。本研究采用的分类技术是多层感知器。然而，在分类过程中，由于可用性有限，因此使用 K-Means 聚类法生成目标数据，该方法涉及将交易级属性分为三个不同的组别：（0）低交易、（1）中交易和（2）高交易。聚类过程包括三个不同的特征：(1) 收入、(2) 支出和 (3) 利润。这三个特征将在整个分类过程中用作输入数据。采用多层感知器技术的分类程序需要处理包括 1383 个数据点的数据集。训练数据占数据集的 80%，其余 20% 用于测试。为了评估所建模型的有效性，使用 K-Fold 交叉验证法对训练误差进行了评估，得出的平均准确率为 0.92。在本研究中，分类技术的准确率为 0.96。该模型旨在对缺乏先验目标数据的数据集进行场景分类。
{"title":"K-Means Clustering and Multilayer Perceptron for Categorizing Student Business Groups","authors":"Miftahul Walid, Norfiah Lailatin Nispi Sahbaniya, Hozairi Hozairi, Fajar Baskoro, Arya Yudhi Wijaya","doi":"10.17977/um018v6i12023p69-78","DOIUrl":"https://doi.org/10.17977/um018v6i12023p69-78","url":null,"abstract":"The research conducted in this study was driven by the East Java provincial government's requirement to assess the transaction levels of the Student Business Group (KUS) in the SMA Double Track program. These transaction levels are a basis for allocating supplementary financial aid to each business group. The system's primary objective is to assist the provincial government of East Java in making well-informed choices pertaining to the distribution of supplementary capital to the KUS. The classification technique employed in this study is the multilayer perceptron. However, the K-Means Clustering method is utilised to generate target data due to the limited availability during the classification process, which involves dividing the transaction level attributes into three distinct groups: (0) low transactions, (1) medium transactions, and (2) high transactions. The clustering process encompasses three distinct features: (1) income, (2) spending, and (3) profit. These three traits will be utilized as input data throughout the categorization procedure. The classification procedure employing the Multilayer Perceptron technique involved processing a dataset including 1383 data points. The training data constituted 80% of the dataset, while the remaining 20% was allocated for testing. In order to evaluate the efficacy of the constructed model, the training error was assessed using K-Fold cross-validation, yielding an average accuracy score of 0.92. In the present study, the categorization technique yielded an accuracy of 0.96. This model aims to classify scenarios when the dataset lacks prior target data.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139339252","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}
Automatic summarization is reducing a text document with a computer program to create a summary that retains the essential parts of the original document. Automatic summarization is necessary to deal with information overload, and the amount of data is increasing. A summary is needed to get the contents of the article briefly. A summary is an effective way to present extended information in a concise form of the main contents of an article, and the aim is to tell the reader the essence of a central idea. The simple concept of a summary is to take an essential part of the entire contents of the article. Which then presents it back in summary form. The steps in this research will start with the user selecting or searching for text documents that will be summarized with keywords in the abstract as a query. The proposed approach performs text preprocessing for documents: sentence breaking, case folding, word tokenizing, filtering, and stemming. The results of the preprocessed text are weighted by term frequency-inverse document frequency (tf-idf), then weighted for query relevance using the vector space model and sentence similarity using cosine similarity. The next stage is maximum marginal relevance for sentence extraction. The proposed approach provides comprehensive summarization compared with another approach. The test results are compared with manual summaries, which produce an average precision of 88%, recall of 61%, and f-measure of 70%.
{"title":"Maximum Marginal Relevance and Vector Space Model for Summarizing Students' Final Project Abstracts","authors":"Gunawan Gunawan, Fitria Fitria, Esther Irawati Setiawan, Kimiya Fujisawa","doi":"10.17977/um018v6i12023p57-68","DOIUrl":"https://doi.org/10.17977/um018v6i12023p57-68","url":null,"abstract":"Automatic summarization is reducing a text document with a computer program to create a summary that retains the essential parts of the original document. Automatic summarization is necessary to deal with information overload, and the amount of data is increasing. A summary is needed to get the contents of the article briefly. A summary is an effective way to present extended information in a concise form of the main contents of an article, and the aim is to tell the reader the essence of a central idea. The simple concept of a summary is to take an essential part of the entire contents of the article. Which then presents it back in summary form. The steps in this research will start with the user selecting or searching for text documents that will be summarized with keywords in the abstract as a query. The proposed approach performs text preprocessing for documents: sentence breaking, case folding, word tokenizing, filtering, and stemming. The results of the preprocessed text are weighted by term frequency-inverse document frequency (tf-idf), then weighted for query relevance using the vector space model and sentence similarity using cosine similarity. The next stage is maximum marginal relevance for sentence extraction. The proposed approach provides comprehensive summarization compared with another approach. The test results are compared with manual summaries, which produce an average precision of 88%, recall of 61%, and f-measure of 70%.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139352161","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 : 2023-07-18DOI: 10.17977/um018v6i12023p41-56
Arik Kurniawati, E. M. Yuniarno, Y. Suprapto
Javanese gamelan, a traditional Indonesian musical style, has several song structures called gendhing. Gendhing (songs) are written in conventional notation and require gamelan musicians to recognize patterns in the structure of each song. Usually, previous research on gendhing focuses on artistic and ethnomusicological perspectives, but this study is to explore the correlation between gendhing as traditional music in Indonesia and deep learning technology that replaces the task of gamelan composers. This research proposes CNN-LSTM to generate notation of ricikan struktural instruments as an accompaniment to Javanese gamelan music compositions based on balungan notation, rhythm, song structure, and gatra information. This proposed method (CNN-LSTM) is compared with LSTM and CNN. The musical data in this study is represented using numerical notation for the main melody in balungan notation. The experimental results showed that the CNN-LSTM model showed better performance compared to the LSTM and CNN models, with accuracy values of 91.9%, 91.5%, and 91.2% for CNN-LSTM, LSTM, and CNN, respectively. And the value of note distance for the Sampak song structure is 4 for the CNN-LSTM model, 8 for the LSTM model, and 12 for the CNN model. The smaller the note distance, the closer it is to the original notation provided by the gamelan composer. This study provides relevance for novice gamelan musicians who are interested in learning karawitan, especially in understanding ricikan struktural music notation and gamelan art in composing musical compositions of a song.
{"title":"Deep Learning for Multi-Structured Javanese Gamelan Note Generator","authors":"Arik Kurniawati, E. M. Yuniarno, Y. Suprapto","doi":"10.17977/um018v6i12023p41-56","DOIUrl":"https://doi.org/10.17977/um018v6i12023p41-56","url":null,"abstract":"Javanese gamelan, a traditional Indonesian musical style, has several song structures called gendhing. Gendhing (songs) are written in conventional notation and require gamelan musicians to recognize patterns in the structure of each song. Usually, previous research on gendhing focuses on artistic and ethnomusicological perspectives, but this study is to explore the correlation between gendhing as traditional music in Indonesia and deep learning technology that replaces the task of gamelan composers. This research proposes CNN-LSTM to generate notation of ricikan struktural instruments as an accompaniment to Javanese gamelan music compositions based on balungan notation, rhythm, song structure, and gatra information. This proposed method (CNN-LSTM) is compared with LSTM and CNN. The musical data in this study is represented using numerical notation for the main melody in balungan notation. The experimental results showed that the CNN-LSTM model showed better performance compared to the LSTM and CNN models, with accuracy values of 91.9%, 91.5%, and 91.2% for CNN-LSTM, LSTM, and CNN, respectively. And the value of note distance for the Sampak song structure is 4 for the CNN-LSTM model, 8 for the LSTM model, and 12 for the CNN model. The smaller the note distance, the closer it is to the original notation provided by the gamelan composer. This study provides relevance for novice gamelan musicians who are interested in learning karawitan, especially in understanding ricikan struktural music notation and gamelan art in composing musical compositions of a song.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"95 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139358216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-25DOI: 10.17977/um018v6i12023p24-40
Issah Iddrisu, Peter Appiahene, Obed Appiah, Inusah Fuseini
During the course of this research, binary classification and the Knowledge Discovery Process (KDP) were used. The experimental and analytical capabilities of Rapid Miner's 9.10.010 instructional environment are supported by five different classifiers. Included in the analysis were 2334 entries, 17 characteristics, and one class variable containing the students' average score for the semester. There were twenty experiments carried out. During the studies, 10-fold cross-validation and ratio split validation, together with bootstrap sampling, were used. It was determined whether or not to use the Random Forest (RF), Rule Induction (RI), Naive Bayes (NB), Logistic Regression (LR), or Deep Learning (DL) methods. RF outperformed the other four methods in all six selection measures, with an accuracy of 93.96%. According to the RF classifier model, the level of education that a child's parents have is a major factor in that child's academic performance before entering higher education.
{"title":"Exploring the Impact of Students Demographic Attributes on Performance Prediction through Binary Classification in the KDP Model","authors":"Issah Iddrisu, Peter Appiahene, Obed Appiah, Inusah Fuseini","doi":"10.17977/um018v6i12023p24-40","DOIUrl":"https://doi.org/10.17977/um018v6i12023p24-40","url":null,"abstract":"During the course of this research, binary classification and the Knowledge Discovery Process (KDP) were used. The experimental and analytical capabilities of Rapid Miner's 9.10.010 instructional environment are supported by five different classifiers. Included in the analysis were 2334 entries, 17 characteristics, and one class variable containing the students' average score for the semester. There were twenty experiments carried out. During the studies, 10-fold cross-validation and ratio split validation, together with bootstrap sampling, were used. It was determined whether or not to use the Random Forest (RF), Rule Induction (RI), Naive Bayes (NB), Logistic Regression (LR), or Deep Learning (DL) methods. RF outperformed the other four methods in all six selection measures, with an accuracy of 93.96%. According to the RF classifier model, the level of education that a child's parents have is a major factor in that child's academic performance before entering higher education.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139368590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-06DOI: 10.17977/um018v6i12023p15-23
S. Wibawanto, K. Kirana, Hani Ramadhan
In the early stages of learning resistors, introducing color-based values is needed. Moreover, some combinations require a resistor trip analysis to identify. Unfortunately, a resistor body color is considered a local solution, which often confuses resistor coloration. Ant Colony Optimization (ACO) is a heuristic algorithm that can recognize problems with traveling a group of ants. ACO is proposed to select commercial matrix values to be computed without preventing local solutions. In this study, each explores the matrix based on pheromones and heuristic information to generate local solutions. Global solutions are selected based on their high degree of similarity with other local solutions. The first stage of testing focuses on exploring variations of parameter values. Applying the best parameters resulted in 85% accuracy and 43 seconds for 20 resistor images. This method is expected to prevent local solutions without wasteful computation of the matrix.
{"title":"Ant Colony Optimization for Resistor Color Code Detection","authors":"S. Wibawanto, K. Kirana, Hani Ramadhan","doi":"10.17977/um018v6i12023p15-23","DOIUrl":"https://doi.org/10.17977/um018v6i12023p15-23","url":null,"abstract":"In the early stages of learning resistors, introducing color-based values is needed. Moreover, some combinations require a resistor trip analysis to identify. Unfortunately, a resistor body color is considered a local solution, which often confuses resistor coloration. Ant Colony Optimization (ACO) is a heuristic algorithm that can recognize problems with traveling a group of ants. ACO is proposed to select commercial matrix values to be computed without preventing local solutions. In this study, each explores the matrix based on pheromones and heuristic information to generate local solutions. Global solutions are selected based on their high degree of similarity with other local solutions. The first stage of testing focuses on exploring variations of parameter values. Applying the best parameters resulted in 85% accuracy and 43 seconds for 20 resistor images. This method is expected to prevent local solutions without wasteful computation of the matrix.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139370739","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 : 2022-06-07DOI: 10.17977/um018v5i12022p78-86
L. Latumakulita, Sandy Laurentius Lumintang, Deiby Tineke Salakia, S. R. Sentinuwo, A. Sambul, N. Islam
The human facial expression identification system is essential in developing human interaction and technology. The development of Artificial Intelligence for monitoring human emotions can be helpful in the workplace. Commonly, there are six basic human expressions, namely anger, disgust, fear, happiness, sadness, and surprise, that the system can identify. This study aims to create a facial expression identification system based on basic human expressions using the Convolutional Neural Network (CNN) with a 16-layer VGG architecture. Two thousand one hundred thirty-seven facial expression images were selected from the FER2013, JAFFE, and MUG datasets. By implementing image augmentation and setting up the network parameters to Epoch of 100, the learning rate of 0,0001, and applying in the 5Fold Cross Validation, this system shows performance with an average accuracy of 84%. Results show that the model is suitable for identifying the basic facial expressions of humans.
{"title":"Human Facial Expressions Identification using Convolutional Neural Network with VGG16 Architecture","authors":"L. Latumakulita, Sandy Laurentius Lumintang, Deiby Tineke Salakia, S. R. Sentinuwo, A. Sambul, N. Islam","doi":"10.17977/um018v5i12022p78-86","DOIUrl":"https://doi.org/10.17977/um018v5i12022p78-86","url":null,"abstract":"The human facial expression identification system is essential in developing human interaction and technology. The development of Artificial Intelligence for monitoring human emotions can be helpful in the workplace. Commonly, there are six basic human expressions, namely anger, disgust, fear, happiness, sadness, and surprise, that the system can identify. This study aims to create a facial expression identification system based on basic human expressions using the Convolutional Neural Network (CNN) with a 16-layer VGG architecture. Two thousand one hundred thirty-seven facial expression images were selected from the FER2013, JAFFE, and MUG datasets. By implementing image augmentation and setting up the network parameters to Epoch of 100, the learning rate of 0,0001, and applying in the 5Fold Cross Validation, this system shows performance with an average accuracy of 84%. Results show that the model is suitable for identifying the basic facial expressions of humans.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49406322","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 : 2022-06-07DOI: 10.17977/um018v5i12022p67-77
R. Suhana, W. Mahmudy, Agung Setia Budi
The existence of fish species diversity in coastal ecosystems which include mangrove forests, seagrass beds and coral reefs is one of the benchmarks in determining health in coastal ecosystems. It is certain that we must maintain, preserve and care for so that conservation efforts need to be carried out in water areas. Many experts at the Indonesian Fisheries and Marine Research and Development Agency often classify fish images manually, of course it will take a long time, therefore with today's developments they can use the latest technology. One of the reliable techniques in terms of image classification is Convolutional Neural Network (CNN). As time goes by, of course, many people want fast learning and solving new problems faster and better, so transfer learning appears, which adopts part of CNN, the name is modified convolution layer. Observing the needs of experts in the field of marine conservation, the researchers decided to solve this problem by using transfer learning modifications. The transfer learning used is an architectural model from the pre-trained Mobilenet V2, which is known for its light computing process and can be applied to our gadgets and other embedded tools. The research image data used is 49.281 data of various sizes and there are 18 types of fish, in the pre-processing data there is a resize of the image to a size of 224x224 pixels. testing with the modified transfer learning architectural model obtained an accuracy score of 99.54%, this model is quite reliable in classifying fish images.
{"title":"Fish Image Classification Using Adaptive Learning Rate In Transfer Learning Method","authors":"R. Suhana, W. Mahmudy, Agung Setia Budi","doi":"10.17977/um018v5i12022p67-77","DOIUrl":"https://doi.org/10.17977/um018v5i12022p67-77","url":null,"abstract":"The existence of fish species diversity in coastal ecosystems which include mangrove forests, seagrass beds and coral reefs is one of the benchmarks in determining health in coastal ecosystems. It is certain that we must maintain, preserve and care for so that conservation efforts need to be carried out in water areas. Many experts at the Indonesian Fisheries and Marine Research and Development Agency often classify fish images manually, of course it will take a long time, therefore with today's developments they can use the latest technology. One of the reliable techniques in terms of image classification is Convolutional Neural Network (CNN). As time goes by, of course, many people want fast learning and solving new problems faster and better, so transfer learning appears, which adopts part of CNN, the name is modified convolution layer. Observing the needs of experts in the field of marine conservation, the researchers decided to solve this problem by using transfer learning modifications. The transfer learning used is an architectural model from the pre-trained Mobilenet V2, which is known for its light computing process and can be applied to our gadgets and other embedded tools. The research image data used is 49.281 data of various sizes and there are 18 types of fish, in the pre-processing data there is a resize of the image to a size of 224x224 pixels. testing with the modified transfer learning architectural model obtained an accuracy score of 99.54%, this model is quite reliable in classifying fish images.","PeriodicalId":52868,"journal":{"name":"Knowledge Engineering and Data Science","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46307625","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：