Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Mamdani Fuzzy Expert System for Online Learning to Diagnose Infectious Diseases
Get PDFE-learning and expert systems can be implemented for learning in the health sector. Through the e-learning system, prospective health workers can analyze problems by exploring the material in the system. However, material learning alone is less effective, so case study-based learning using an expert system is needed to strengthen understanding. The research applies an expert system to online learning to diagnose several infectious diseases. The disease diagnosis process uses the backward chaining method and the Mamdani fuzzy inference system. The fuzzy Mamdani inference system determines the intensity of disease severity so that appropriate treatment recommendations can be made. The test findings on 15 test datasets yielded a backward chaining accuracy value of 100%. Three test scenarios were used to establish the test using the Mamdani fuzzy inference method. Scenario 1: Testing with the Center of Gravity defuzzification and Fuzzy Mamdani Min inference system Tests employing the Fuzzy Mamdani Min inference method and center average defuzzification are used in Scenario 2. Scenario 3 involves testing using the Fuzzy Mamdani Product Inference System with Center Average Defuzzification. The average outcome for the intensity of disease severity utilizing the Fuzzy Mamdani Min inference system with Center of Gravity defuzzification was greater than that of the two test scenarios that were suggested, which was 49.43%.
E-learning and expert systems can be implemented for learning in the health sector. Through the e-learning system, prospective health workers can analyze problems by exploring the material in the system. However, material learning alone is less effective, so case study-based learning using an expert system is needed to strengthen understanding. The research applies an expert system to online learning to diagnose several infectious diseases. The disease diagnosis process uses the backward chaining method and the Mamdani fuzzy inference system. The fuzzy Mamdani inference system determines the intensity of disease severity so that appropriate treatment recommendations can be made. The test findings on 15 test datasets yielded a backward chaining accuracy value of 100%. Three test scenarios were used to establish the test using the Mamdani fuzzy inference method. Scenario 1: Testing with the Center of Gravity defuzzification and Fuzzy Mamdani Min inference system Tests employing the Fuzzy Mamdani Min inference method and center average defuzzification are used in Scenario 2. Scenario 3 involves testing using the Fuzzy Mamdani Product Inference System with Center Average Defuzzification. The average outcome for the intensity of disease severity utilizing the Fuzzy Mamdani Min inference system with Center of Gravity defuzzification was greater than that of the two test scenarios that were suggested, which was 49.43%
Optimization Ground Glass Opacities (GGO) Detection Using Multipixel Interpolation Techniques
Get PDFGround Glass Opacities (GGO) are a picture of abnormal lung conditions characterized by white or gray areas. This picture of GGO in the lungs could previously be detected based on the results of medical examinations such as Computerized Tomography (CT scan) and Magnetic Resonance Imaging (MRI) images of patients suffering from Covid-19. However, from the results of the examination, it can be seen that the CT scan and MRI images still have a noise level that is too high, causing difficulties in describing the distribution pattern of the GGO itself. The purpose of this study was to optimize the detection of GGO on MRI images using the Multipixel Interpolation technique. The detection process adopts several stages including image preprocessing, edge detection process, and gradient morphological segmentation. Image preprocessing is done to remove noise and improve the MRI input image. The edge detection process is carried out to detect lung organs automatically using the Canny method which is optimized with the multipixel interpolation technique. The final stage of the research is the segmentation process using a gradient morphology technique to see the spread of GGO in patients with Covid-19 contained in the MRI image. The results of this study present an overview of the GGO pattern with fairly good results. The results of the GGO pattern description will also measure the level of spread to see the severity of pneumonia. Based on the results presented, this research is useful as an alternative solution in the process of diagnosis and treatment of Covid-19 patients.Ground Glass Opacities (GGO) are a picture of abnormal lung conditions characterized by white or gray areas. This picture of GGO in the lungs could previously be detected based on the results of medical examinations such as Computerized Tomography (CT scan) and Magnetic Resonance Imaging (MRI) images of patients suffering from Covid-19. However, from the results of the examination, it can be seen that the CT scan and MRI images still have a noise level that is too high, causing difficulties in describing the distribution pattern of the GGO itself. The purpose of this study was to optimize the detection of GGO on MRI images using the Multipixel Interpolation technique. The detection process adopts several stages including image preprocessing, edge detection process, and gradient morphological segmentation. Image preprocessing is done to remove noise and improve the MRI input image. The edge detection process is carried out to detect lung organs automatically using the Canny method which is optimized with the multipixel interpolation technique. The final stage of the research is the segmentation process using a gradient morphology technique to see the spread of GGO in patients with Covid-19 contained in the MRI image. The results of this study present an overview of the GGO pattern with fairly good results. The results of the GGO pattern description will also measure the level of spread to see the severity of pneumonia. Based on the results presented, this research is useful as an alternative solution in the process of diagnosis and treatment of Covid-19 patients
The Role of Genetics in Domestic Research on Forestry Issues: A Text Mining Analysis
Get PDFAs a megadiverse country, Indonesia has plentiful genetic resources. The interest of domestic researchers in it and its relation to forestry scope is the focus of this paper. The objective is to determine the genetics aspects represented in forestry scholarly articles. Text mining analysis is carried out for the abstract articles, followed by topic modeling and trend analysis. Python libraries were used to conduct this research. Garuda website was the main source of the data collection. Natural language Toolkits (NLTK) were used to retrieve article information from Garuda. Sci-kit learn (SKLearn) of Latent Dirichlet Allocation module was used for topic modeling analysis, and pyLDAVis was used to represent it. SKLearn was also used for trending analysis. After article text retrieval, three topic clusters were found: forest diversity, products, and land use. The topics were scattered in 1966 abstract articles that were found during data retrieval. Article growth showed the quadratic pattern known after regression analysis. The trend showed the rapid growth of topics and scholars' interest, but the number of articles was low compared to the total articles on the Garuda portal.
As a megadiverse country, Indonesia has plentiful genetic resources. The interest of domestic researchers in it and its relation to forestry scope is the focus of this paper. The objective is to determine the genetics aspects represented in forestry scholarly articles. Text mining analysis is carried out for the abstract articles, followed by topic modeling and trend analysis. Python libraries were used to conduct this research. Garuda website was the main source of the data collection. Natural language Toolkits (NLTK) were used to retrieve article information from Garuda. Sci-kit learn (SKLearn) of Latent Dirichlet Allocation module was used for topic modeling analysis, and pyLDAVis was used to represent it. SKLearn was also used for trending analysis. After article text retrieval, three topic clusters were found: forest diversity, products, and land use. The topics were scattered in 1966 abstract articles that were found during data retrieval. Article growth showed the quadratic pattern known after regression analysis. The trend showed the rapid growth of topics and scholars' interest, but the number of articles was low compared to the total articles on the Garuda portal
Optimization Analysis Model Determining PNMP Mandiri Loan Status Based on Pearson Correlation
Get PDFPNPM Mandiri is an organization engaged in financing small and medium enterprises in the community. The problem that always occurs is an error in determining the loan status resulting in bad credit. This study aims to present a classification analysis model for determining loan status at PNPM Mandiri. The classification analysis model was built using the Perceptron algorithm artificial neural network. The analysis model will later be optimized using the Person Correlation (PC) method to measure the accuracy of the variables used. The research dataset is based on historical data from the last 2 years as many as 67 data samples. The analysis variables consist of Business Type (X1), Loan Amount (X2), Collateral (X3), Income (X4), and Expenses (X5). The results of the analysis show that the model built can provide optimal classification results. These results can be seen based on the results of variable measurements using the PC method indicating that variable X2 has no significant relationship. With the results of these measurements, the performance of the artificial neural network presents maximum results in determining loan status. Overall, the results of this study can provide an effective analytical model as well as an alternative solution for determining loan status.
PNPM Mandiri is an organization engaged in financing small and medium enterprises in the community. The problem that always occurs is an error in determining the loan status resulting in bad credit. This study aims to present a classification analysis model for determining loan status at PNPM Mandiri. The classification analysis model was built using the Perceptron algorithm artificial neural network. The analysis model will later be optimized using the Person Correlation (PC) method to measure the accuracy of the variables used. The research dataset is based on historical data from the last 2 years as many as 67 data samples. The analysis variables consist of Business Type (X1), Loan Amount (X2), Collateral (X3), Income (X4), and Expenses (X5). The results of the analysis show that the model built can provide optimal classification results. These results can be seen based on the results of variable measurements using the PC method indicating that variable X2 has no significant relationship. With the results of these measurements, the performance of the artificial neural network presents maximum results in determining loan status. Overall, the results of this study can provide an effective analytical model as well as an alternative solution for determining loan status
Heart Attack Notification and Monitoring System Using Internet of Things
Get PDFPeople are frequently shocked when someone passes away suddenly without any prior symptoms. One of the contributing factors is a heart attack. This condition might occur anywhere and at any time. A sudden heart attack can be highly perilous for a person who is alone, without family members or friends because the family cannot be informed of the victim's condition or their location. Therefore, it is vital to raise awareness of heart attacks. With the support of the Internet of Things, this study aims to develop a wearable device that people may use to monitor their heart health and connect with hospitals to get alerts in case of a heart attack. This system also provides family members with access to a web-based patient monitoring tool. The heart beat is considered as the parameter in developing this system. There are three types of evaluation which are conducted in this study, namely: 1) Sub-system evaluation; 2) Black-box testing; and 3) Integrating system testing. The three evaluation results show that all assembled hardware components are work properly and the system effectively satisfies the objectives of monitoring, buzzer activation, hospital and patient family notification, and so forth, with 1.96% average sensor error, which is still considerably acceptable.
People are frequently shocked when someone passes away suddenly without any prior symptoms. One of the contributing factors is a heart attack. This condition might occur anywhere and at any time. A sudden heart attack can be highly perilous for a person who is alone, without family members or friends because the family cannot be informed of the victim's condition or their location. Therefore, it is vital to raise awareness of heart attacks. With the support of the Internet of Things, this study aims to develop a wearable device that people may use to monitor their heart health and connect with hospitals to get alerts in case of a heart attack. This system also provides family members with access to a web-based patient monitoring tool. The heart beat is considered as the parameter in developing this system. There are three types of evaluation which are conducted in this study, namely: 1) Sub-system evaluation; 2) Black-box testing; and 3) Integrating system testing. The three evaluation results show that all assembled hardware components are work properly and the system effectively satisfies the objectives of monitoring, buzzer activation, hospital and patient family notification, and so forth, with 1.96% average sensor error, which is still considerably acceptable
Optimization Prediction of Big Five Personality in Twitter Users
Get PDFVarious kinds of information can be acquired from social media platforms; one of them is on Twitter. User biographical information and tweets are the essential assets for research that can describe the Big Five Personality, including openness, conscientiousness, extraversion, agreeableness, and neuroticism. Several previous studies have tried the prediction of Big Five Personality. However, the authors found problems in how to optimize the work of the personality prediction system. So, in this study, Big Five Personality predictions were carried out on users of Twitter and improved the performance of the personality prediction system. We implement optimization techniques such as sampling, feature selection, and hyperparameter tuning to enhance the performance. This study also applies linguistic feature extraction, such as LIWC and TF-IDF. By using 287 Twitter users that have permitted their data to be crawled acquired from an online survey using Big Five Inventory (BFI), and applying all optimization techniques, the average accuracy result is 84.22% which is a 74.44% gain over the specified baseline.Various kinds of information can be acquired from social media platforms; one of them is on Twitter. User biographical information and tweets are the essential assets for research that can describe the Big Five Personality, including openness, conscientiousness, extraversion, agreeableness, and neuroticism. Several previous studies have tried the prediction of Big Five Personality. However, the authors found problems in how to optimize the work of the personality prediction system. So, in this study, Big Five Personality predictions were carried out on users of Twitter and improved the performance of the personality prediction system. We implement optimization techniques such as sampling, feature selection, and hyperparameter tuning to enhance the performance. This study also applies linguistic feature extraction, such as LIWC and TF-IDF. By using 287 Twitter users that have permitted their data to be crawled acquired from an online survey using Big Five Inventory (BFI), and applying all optimization techniques, the average accuracy result is 84.22% which is a 74.44% gain over the specified baseline
Perbandingan Model Proses Algoritma Alpha dan Alpha++ Pada Aplikasi E-commerce
Get PDFUtilization of information technology is currently growing rapidly in helping activities especially in storing an event log. The activity which is behavior of the user can be analyzed using process mining. The process mining purpose to extract information from event logs on business processes that working. Discovery technique is used in this research. The purpose of this study is to compare two algorithms applied by creating an e-commerce application that is aware of the processes. E-commerce applications require event logs to read the behavior of visitor activities against the application. This research method starts from understanding the business processes that working, then designing a website by creating the application used. Furthermore, data collection through applications that are promoted through social media. The application will be recorded user activity and formed an event log. The event log that formed then discovered using alpha and alpha++ algorithms by utilizing the ProM Lite 1.2 tools. The evaluation results show that the alpha algorithm has shortcomings, namely length one loop, length two loop and non-free choice. And the alpha++ algorithm fixed this deficiency.
Pemanfaatan teknologi informasi saat ini berkembang sangat pesat dalam membantu aktivitas terutama dalam penyimpanan sebuah event log. Aktivitas tersebut yang merupakan behavior dari user dapat dianalisa menggunakan proses mining. Proses mining bertujuan untuk mengekstrak informasi dari event log pada proses bisnis yang dijalankan. Salah satu teknik proses mining yang digunakan pada penelitian ini yaitu teknik discovery. Tujuan dari penelitian ini adalah membandingkan dua algoritma yang diaplikasikan dengan membuat aplikasi e-commerce yang aware terhadap proses. Aplikasi e-commerce membutuhkan event log untuk membaca perilaku aktivitas pengunjung terhadap aplikasi. Metode penelitian ini dimulai dari pemahaman proses bisnis yang dijalankan, kemudian merancang website dengan membuat aplikasi yang digunakan. Selanjutnya pengumpulan data melalui aplikasi yang dipromosikan melalui media social. Aplikasi akan merekam aktivitas user dan membentuk event log. Event log yang terbentuk kemudian di- discover menggunakan algoritma alpha dan alpha++ dengan memanfaatkan tools ProM Lite 1.2. Hasil evaluasi menunjukan algoritma alpha memiliki kekurangan yaitu length one loop, length two loop dan non-free choice. Dan algoritma alpha++ memperbaiki kekurangan tersebut
Bidirectional Long Short-Term Memory and Word Embedding Feature for Improvement Classification of Cancer Clinical Trial Document
Get PDFIn recent years, the application of deep learning methods has become increasingly popular, especially for big data, because big data has a very large data size and needs to be predicted accurately. One of the big data is the document text data of cancer clinical trials. Clinical trials are studies of human participation in helping people's safety and health. The aim of this paper is to classify cancer clinical texts from a public data set. The proposed algorithms are Bidirectional Long Short Term Memory (BiLSTM) and Word Embedding Features (WE). This study has contributed to a new classification model for documenting clinical trials and increasing the classification performance evaluation. In this study, two experiments work are conducted, namely experimental work BiLSTM without WE, and experimental work BiLSTM using WE. The experimental results for BiLSTM without WE were accuracy = 86.2; precision = 85.5; recall = 87.3; and F-1 score = 86.4. meanwhile the experiment results for BiLSTM using WE stated that the evaluation score showed outstanding performance in text classification, especially in clinical trial texts with accuracy = 92,3; precision = 92.2; recall = 92.9; and F-1 score = 92.5.In recent years, the application of deep learning methods has become increasingly popular, especially for big data, because big data has a very large data size and needs to be predicted accurately. One of the big data is the document text data of cancer clinical trials. Clinical trials are studies of human participation in helping people's safety and health. The aim of this paper is to classify cancer clinical texts from a public data set. The proposed algorithms are Bidirectional Long Short Term Memory (BiLSTM) and Word Embedding Features (WE). This study has contributed to a new classification model for documenting clinical trials and increasing the classification performance evaluation. In this study, two experiments work are conducted, namely experimental work BiLSTM without WE, and experimental work BiLSTM using WE. The experimental results for BiLSTM without WE were accuracy = 86.2; precision = 85.5; recall = 87.3; and F-1 score = 86.4. meanwhile the experiment results for BiLSTM using WE stated that the evaluation score showed outstanding performance in text classification, especially in clinical trial texts with accuracy = 92,3; precision = 92.2; recall = 92.9; and F-1 score = 92.5
Applying Different Resampling Strategies In Random Forest Algorithm To Predict Lumpy Skin Disease
No full textThe spread of Lumpy Skin Disease (LSD) that infects livestock is increasingly widespread in various parts of the world. Early detection of the diseaseβs spread is necessary so that the economic losses caused by LSD are not higher. The use of machine learning algorithms to predict the presence of a disease has been carried out, including in the field of animal health. The study aims to predict the presence of LSD in an area by utilizing the LSD dataset obtained from Mendeley Data. The number of lumpy infected cases is so low that it creates imbalanced data, posing a challenge in training machine learning models. Handling the unbalanced data is performed by sampling technique using the Random Under-sampling technique and Synthetic Minority Oversampling Technique (SMOTE). The Random Forest classification model was trained on sample data to predict cases of lumpy infection. The Random Forest classifier performs very well on both under-sampling and oversampling data. Measurement of performance metrics shows that SMOTE has a superior score of 1-2% compared to the use of Random Undersampling. Furthermore, Re-call rate, which is the metric we want to maximize in identifying lumpy cases, is superior when using SMOTE and has slightly better precision than Random Undersampling. This research only focuses on how to balance unbalanced data classes so that the optimization of the model has not been implemented, which creates opportunities for further research in the future.
The spread of Lumpy Skin Disease (LSD) that infects livestock is increasingly widespread in various parts of the world. Early detection of the diseaseβs spread is necessary so that the economic losses caused by LSD are not higher. The use of machine learning algorithms to predict the presence of a disease has been carried out, including in the field of animal health. The study aims to predict the presence of LSD in an area by utilizing the LSD dataset obtained from Mendeley Data. The number of lumpy infected cases is so low that it creates imbalanced data, posing a challenge in training machine learning models. Handling the unbalanced data is performed by sampling technique using the Random Under-sampling technique and Synthetic Minority Oversampling Technique (SMOTE). The Random Forest classification model was trained on sample data to predict cases of lumpy infection. The Random Forest classifier performs very well on both under-sampling and oversampling data. Measurement of performance metrics shows that SMOTE has a superior score of 1-2% compared to the use of Random Undersampling. Furthermore, Re-call rate, which is the metric we want to maximize in identifying lumpy cases, is superior when using SMOTE and has slightly better precision than Random Undersampling. This research only focuses on how to balance unbalanced data classes so that the optimization of the model has not been implemented, which creates opportunities for further research in the future
QSAR Study on Diacylgycerol Acyltransferase-1 (DGAT-1) Inhibitor as Anti-diabetic using PSO-SVM Methods
No full textDiabetes mellitus is a chronic disease that can occur in anyone. Up until now, there are no specific drugs have been found which can completely cure diabetes. One of the possible steps to treat diabetes mellitus is by inhibiting the growth of the Diacylglycerol Acyltransferase-1 (DGAT-1) enzyme. This study aims to build a QSAR model on DGAT-1 inhibitors as anti-diabetic using Particle Swarm Optimization (PSO) and Support Vector Machine (SVM). Acyl-CoA: DGAT1 is a microsomal enzyme in lipogenesis which is increased in metabolically active cells to meet nutrient requirements. Microsomal enzymes that have an important in the triglyceride-synthesis process of 1,2-diacylglycerol by-catalyzing-acyl-coa-dependent-acylations as anti-diabetics. The dataset used in this study consists of 228 samples containing molecular structures and their inhibitor activities. We reduce the number of features by removing features with a standard deviation less than the threshold value, followed by the PSO algorithm. The best-predicted result is obtained through the implementation of SVM with RBF kernel, with the score of and are 0.75 and 0.67, respectively.Diabetes mellitus is a chronic disease that can occurred to anyone. Up until now, there are no specific drugs that have been found which can completely cure diabetes. One of the possible steps to treat diabetes mellitus is by inhibiting the growth of Diacylglycerol Acyltransferase-1 (DGAT-1) enzyme. This study aims to build a QSAR model on DGAT-1 inhibitors as anti-diabetic using Particle Swarm Optimization (PSO) and Support Vector Machine (SVM). Acyl-CoA: DGAT1 is a mikrosomal enzyme in lipogenesis which is increased in metabolically active cells to meet nutrient requirements. Microsomal-enzymes-that have an-important in the triglyceride-synthesis process-of 1,2-diacylglycerol by-catalyzing-acyl-coa-dependent-acylations as anti-diabetics. The dataset used in this study consists of 228 samples containing molecular structures and their inhibitor activities. We reduce the number of features by removing features with a standard deviation less than the threshold value, followed by the PSO algorithm. The best-predicted result is obtained through the implementation of SVM with RBF kernel, with the score of and are 0.75 and 0.67, respectively.