Merlinda Wibowo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Merlinda Wibowo has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Agi Prasetiadi
Program Studi Teknik Informatika, Fakultas Informatika, Institut Teknologi Telkom Purwokerto, Indonesia
2 shared publicationsAbimanyu Manusakerti
Institut Teknologi Telkom Purwokerto, Purwokerto
1 shared publication- Eva Rahma Indriyani
Institut Teknologi Telkom Purwokerto, Banyumas
1 shared publication - Fadhilah Gusti Safinatunnajah
Program Studi Teknik Informatika, Fakultas Informatika, Institut Teknologi Telkom Purwokerto, Indonesia
1 shared publication Muh. Rizieq Fazlulrahman Djafar
Institut Teknologi Telkom Purwokerto, Purwokerto
1 shared publicationNicolaus Euclides Wahyu Nugroho
Institut Teknologi Telkom Purwokerto, Purwokerto
1 shared publication
Latest Publications
- Open Access
- 28 January 2023
- Published by Universitas Budi Darma in JURNAL MEDIA INFORMATIKA BUDIDARMA
- Vol. 7 (1) , 153-159
Perbandingan Metode Klasifikasi Untuk Deteksi Stress Pada Mahasiswa di Perguruan Tinggi
The outbreak of the COVID-19 pandemic is increasingly affecting the high level of stress in humans. Stress due to this pandemic has also occurred, especially for students. This stress is caused by students spending too much time studying online. Using student data can act as a tool to identify student stress by processing it through various machine-learning methods. This method can extract information and find patterns and information from the data. Classification techniques are used as data groupings based on mapping data into sample data. This study used several classification methods: Naïve Bayes, Decision Tree, Support Vector Machine (SVM), Neural Network, Random Tree, Random Forest, and K Nearest Neighbor (KNN). These methods were successfully compared to determine which is the best for detecting stress precisely and accurately based on the classification performance results of each method. Random Tree and Decision tree were chosen as the best methods for the results of this performance comparison with an 80:20 split reaching up to 100%.
- 28 January 2023
- Published by Universitas Budi Darma in JURNAL MEDIA INFORMATIKA BUDIDARMA
- Vol. 7 (1) , 153-159
Open AccessPerbandingan Metode Klasifikasi Untuk Deteksi Stress Pada Mahasiswa di Perguruan Tinggi
The outbreak of the COVID-19 pandemic is increasingly affecting the high level of stress in humans. Stress due to this pandemic has also occurred, especially for students. This stress is caused by students spending too much time studying online. Using student data can act as a tool to identify student stress by processing it through various machine-learning methods. This method can extract information and find patterns and information from the data. Classification techniques are used as data groupings based on mapping data into sample data. This study used several classification methods: Naïve Bayes, Decision Tree, Support Vector Machine (SVM), Neural Network, Random Tree, Random Forest, and K Nearest Neighbor (KNN). These methods were successfully compared to determine which is the best for detecting stress precisely and accurately based on the classification performance results of each method. Random Tree and Decision tree were chosen as the best methods for the results of this performance comparison with an 80:20 split reaching up to 100%.
- Open Access
- 30 December 2022
- Published by Forum Kerjasama Pendidikan Tinggi (FKPT) in Building of Informatics, Technology and Science (BITS)
- Vol. 4 (3)
Pendekatan Algoritma Tree dalam Prediksi Populasi pada Smart Poultry
Intelligent systems for monitoring poultry in kennels are experiencing an increasing trend in several studies. Monitoring poultry is very important in the cage so that you can find out the chickens' condition and environment in the cage. Conditions that can be monitored include the weight of the chickens, whether or not there is enough water in a day, CO2 levels in the cages, air temperature, and humidity in the cages. Several studies have been conducted studies on monitoring poultry cages using IoT-based sensors. However, people have yet to predict the poultry population for tomorrow. So this study aims to predict the number of poultry populations in kennels based on related parameters. The prediction method used in this research is a decision tree and Support Vector Machine (SVM) to see which prediction method is better. The results evaluation techniques used in this study are Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R2. The experimental results show that using the decision tree method, and the results are MSE 61987.202, RMSE 248.972, MAE 85.086, and R2 0.969. Overall the results of the decision tree method are superior to SVM.
- 30 December 2022
- Published by Forum Kerjasama Pendidikan Tinggi (FKPT) in Building of Informatics, Technology and Science (BITS)
- Vol. 4 (3)
Open AccessPendekatan Algoritma Tree dalam Prediksi Populasi pada Smart Poultry
Intelligent systems for monitoring poultry in kennels are experiencing an increasing trend in several studies. Monitoring poultry is very important in the cage so that you can find out the chickens' condition and environment in the cage. Conditions that can be monitored include the weight of the chickens, whether or not there is enough water in a day, CO2 levels in the cages, air temperature, and humidity in the cages. Several studies have been conducted studies on monitoring poultry cages using IoT-based sensors. However, people have yet to predict the poultry population for tomorrow. So this study aims to predict the number of poultry populations in kennels based on related parameters. The prediction method used in this research is a decision tree and Support Vector Machine (SVM) to see which prediction method is better. The results evaluation techniques used in this study are Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R2. The experimental results show that using the decision tree method, and the results are MSE 61987.202, RMSE 248.972, MAE 85.086, and R2 0.969. Overall the results of the decision tree method are superior to SVM.
- Open Access
- 25 October 2022
- Published by Universitas Budi Darma in JURNAL MEDIA INFORMATIKA BUDIDARMA
- Vol. 6 (4) , 2140-2147
Rancangan dan Evaluasi Usability Pada Aplikasi Website Media Pembelajaran Cyberbullying Menggunakan Metode Gamifikasi
Cyberbullying is bullying act carried out on social media to cause harm the victim. The potential for cyberbullying is very high among teenagers. This is due to high frequency of using social media, increasing cases of cyberbullying, and the lack of education about cyberbullying. Cyberbullying education has been carried out using digital literacy educational activities using digital literacy only focus on introducing and preventing cyberbullying in the form of seminars or lectures. However, using this method has many shortcomings, for example someone easily forgets the material presented and gives less space to develop creativity. Interactive education is needed to increase motivation to learn about cyberbullying. The gamification method is very suitable to be applied in learning because the gamification method involves game elements such as points, leaderboards, badges, challenges, and achievements. In addition to using the gamification methods, visual media such as images and animation video is also suitable for learning. This research utilizes gamification-based learning and visual media to deliver the material as a prototype application for cyberbullying learning sites. This research aims to provide education and increase motivation to learn about more interactively cyberbullying. This research involved 42 respondents with a range of ages between 12-21 years. This research will use System Usability Scale (SUS) to evaluate the prototype's usability. The usability score from the prototype in this research is 77.8, meaning the prototype is acceptable to use.
- 25 October 2022
- Published by Universitas Budi Darma in JURNAL MEDIA INFORMATIKA BUDIDARMA
- Vol. 6 (4) , 2140-2147
Open AccessRancangan dan Evaluasi Usability Pada Aplikasi Website Media Pembelajaran Cyberbullying Menggunakan Metode Gamifikasi
Cyberbullying is bullying act carried out on social media to cause harm the victim. The potential for cyberbullying is very high among teenagers. This is due to high frequency of using social media, increasing cases of cyberbullying, and the lack of education about cyberbullying. Cyberbullying education has been carried out using digital literacy educational activities using digital literacy only focus on introducing and preventing cyberbullying in the form of seminars or lectures. However, using this method has many shortcomings, for example someone easily forgets the material presented and gives less space to develop creativity. Interactive education is needed to increase motivation to learn about cyberbullying. The gamification method is very suitable to be applied in learning because the gamification method involves game elements such as points, leaderboards, badges, challenges, and achievements. In addition to using the gamification methods, visual media such as images and animation video is also suitable for learning. This research utilizes gamification-based learning and visual media to deliver the material as a prototype application for cyberbullying learning sites. This research aims to provide education and increase motivation to learn about more interactively cyberbullying. This research involved 42 respondents with a range of ages between 12-21 years. This research will use System Usability Scale (SUS) to evaluate the prototype's usability. The usability score from the prototype in this research is 77.8, meaning the prototype is acceptable to use.
- Open Access
- 24 October 2022
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 3 (5) , 1363-1372
IDENTIFICATION OF MENTAL ILNESS FROM PATIENT DISEASES USING KNN AND LEVENSHTEIN DISTANCE ALGORITHM
According to WHO, in 2017, the estimated number of people with mental disorders worldwide was around 450 million people, including schizophrenia. Globally, for the condition of Southeast Asia alone, the number of people affected by mental disorders is 13.5%. Meanwhile, 13.4% of cases in Indonesia are affected by mental illness. The Association of Mental Medicine Specialists (PDSKJ) during October 2020 noted that 5661 people who did self-examination through the PDSKJ website came from 31 provinces and found that 32% of the population had psychological problems and 68% had no psychological issues. Seeing that the level of mental illness in Indonesia is increasing, it is necessary to have a system to help the community with early prevention and treatment. With the growth of technology at its peak, Machine Learning technology can overcome the problem which is part of artificial intelligence. Furthermore, machine learning has an important role in improving the quality of health services because it is able to provide a medical diagnosis to predict disease. Therefore, the authors conducted a study to create a system to identify mental illness using the TF-IDF method. This method calculates the word weighting from a collection of complaints that the user gives. Then, these complaints will be classified using the KNN algorithm classification method and the Levenshtein Distance method to find the distance between the word inputted by the user and the word in the database and then calculate the number of differences between the two strings in the form of a matrix. The accuracy result of this machine learning classification is 0.928 or 93%, and will be visualized through web-based software using the Flask framework.
- 24 October 2022
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 3 (5) , 1363-1372
Open AccessIDENTIFICATION OF MENTAL ILNESS FROM PATIENT DISEASES USING KNN AND LEVENSHTEIN DISTANCE ALGORITHM
According to WHO, in 2017, the estimated number of people with mental disorders worldwide was around 450 million people, including schizophrenia. Globally, for the condition of Southeast Asia alone, the number of people affected by mental disorders is 13.5%. Meanwhile, 13.4% of cases in Indonesia are affected by mental illness. The Association of Mental Medicine Specialists (PDSKJ) during October 2020 noted that 5661 people who did self-examination through the PDSKJ website came from 31 provinces and found that 32% of the population had psychological problems and 68% had no psychological issues. Seeing that the level of mental illness in Indonesia is increasing, it is necessary to have a system to help the community with early prevention and treatment. With the growth of technology at its peak, Machine Learning technology can overcome the problem which is part of artificial intelligence. Furthermore, machine learning has an important role in improving the quality of health services because it is able to provide a medical diagnosis to predict disease. Therefore, the authors conducted a study to create a system to identify mental illness using the TF-IDF method. This method calculates the word weighting from a collection of complaints that the user gives. Then, these complaints will be classified using the KNN algorithm classification method and the Levenshtein Distance method to find the distance between the word inputted by the user and the word in the database and then calculate the number of differences between the two strings in the form of a matrix. The accuracy result of this machine learning classification is 0.928 or 93%, and will be visualized through web-based software using the Flask framework.
- Open Access
- 24 October 2022
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 3 (5) , 1349-1353
CLASSIFICATION OF CAT SOUNDS USING CONVOLUTIONAL NEURAL NETWORK (CNN) AND LONG SHORT-TERM MEMORY (LSTM) METHODS
Cats become pets who are very close to humans, and they convey messages by producing identical sounds. Therefore, analysis of pet voices is important for a better relationship between cats and human. Animal communication through sound, especially in cats, depends on the situation or context in which the sound is made such as in a state of danger. Based on these problems, a classification method is needed to classify the similarity of characteristics in the resulting sound pattern. The classification methods used are Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) which can remember information for a long time and are used for a long time period. This study aimed to determine feelings or moods based on the sound produced into 4 categories: The Purr, The Meow, The Mating Call, and The Howl. The result of this study is that the best architectural model is to use 4 CNN convolution layers measuring 8-8-8-8 and 2 LSTM layers measuring 8-8. The precision value in this architecture is 0.68, the recall value is 1.00, the accurary value is 0.5625 and the f1-score value is 0.77. The small value of the confusion matrix is caused by the lack of dataset duration in the training process, resulting in underfitting.
- 24 October 2022
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 3 (5) , 1349-1353
Open AccessCLASSIFICATION OF CAT SOUNDS USING CONVOLUTIONAL NEURAL NETWORK (CNN) AND LONG SHORT-TERM MEMORY (LSTM) METHODS
Cats become pets who are very close to humans, and they convey messages by producing identical sounds. Therefore, analysis of pet voices is important for a better relationship between cats and human. Animal communication through sound, especially in cats, depends on the situation or context in which the sound is made such as in a state of danger. Based on these problems, a classification method is needed to classify the similarity of characteristics in the resulting sound pattern. The classification methods used are Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) which can remember information for a long time and are used for a long time period. This study aimed to determine feelings or moods based on the sound produced into 4 categories: The Purr, The Meow, The Mating Call, and The Howl. The result of this study is that the best architectural model is to use 4 CNN convolution layers measuring 8-8-8-8 and 2 LSTM layers measuring 8-8. The precision value in this architecture is 0.68, the recall value is 1.00, the accurary value is 0.5625 and the f1-score value is 0.77. The small value of the confusion matrix is caused by the lack of dataset duration in the training process, resulting in underfitting.
- Open Access
- 25 July 2022
- Published by Universitas Budi Darma in JURNAL MEDIA INFORMATIKA BUDIDARMA
- Vol. 6 (3) , 1545-1553
Perbandingan Metode Naïve Bayes dan Support Vector Machine Untuk Analisis Sentimen Terhadap Vaksin Astrazeneca di Twitter
The implementation of Covid-19 vaccination in Indonesia turned out to have various pro and contra opinions from the public. The discovery of disinformation and misinformation about vaccines spread through social media content affects a person's absorption of information so which leads to vaccine delays. When in fact, vaccination is one of the biggest and most effective contributions to preventing the Covid-19 pandemic. Astrazeneca is one of the vaccines provided by the Indonesian government. This vaccine used to be controversial amongst the public regarding its halalness and the safety of the vaccine because of the issue of the said vaccine containing swine trypsin. Nowadays Twitter has become a place for users to express their concerns and opinion regarding the Covid-19 vaccine. Data obtained from Twitter will be useful if it is analyzed, one of which is sentiment analysis. In this study, data collection was carried out using the snscrape library with a total of 3105 tweets obtained from the period May to June 31, 2021. The dataset that has been collected is then preprocessed to optimize the data. After passing the preprocessing stage, the data was labeled as tweet class using a lexicon-based dictionary which resulted in 1275 tweets with positive opinin labels and 1830 tweets labeled as negative opinion. The aim of this study is to examines the performance of Naïve Bayes and Support Vector Machine with adding the weighting method TF-IDF (Term Frequency – Inverse Document Frequency). The evaluation results show that the Support Vector Machine has a greater accuracy, precision, recall and f1-score of 87.27%, 90.41%, 77,34% and 83.37% compared to Naïve Bayes which has an accuracy, precision, recall and f1- of 76.81%, 72.40%, 70.70% and 71.52%.
- 25 July 2022
- Published by Universitas Budi Darma in JURNAL MEDIA INFORMATIKA BUDIDARMA
- Vol. 6 (3) , 1545-1553
Open AccessPerbandingan Metode Naïve Bayes dan Support Vector Machine Untuk Analisis Sentimen Terhadap Vaksin Astrazeneca di Twitter
The implementation of Covid-19 vaccination in Indonesia turned out to have various pro and contra opinions from the public. The discovery of disinformation and misinformation about vaccines spread through social media content affects a person's absorption of information so which leads to vaccine delays. When in fact, vaccination is one of the biggest and most effective contributions to preventing the Covid-19 pandemic. Astrazeneca is one of the vaccines provided by the Indonesian government. This vaccine used to be controversial amongst the public regarding its halalness and the safety of the vaccine because of the issue of the said vaccine containing swine trypsin. Nowadays Twitter has become a place for users to express their concerns and opinion regarding the Covid-19 vaccine. Data obtained from Twitter will be useful if it is analyzed, one of which is sentiment analysis. In this study, data collection was carried out using the snscrape library with a total of 3105 tweets obtained from the period May to June 31, 2021. The dataset that has been collected is then preprocessed to optimize the data. After passing the preprocessing stage, the data was labeled as tweet class using a lexicon-based dictionary which resulted in 1275 tweets with positive opinin labels and 1830 tweets labeled as negative opinion. The aim of this study is to examines the performance of Naïve Bayes and Support Vector Machine with adding the weighting method TF-IDF (Term Frequency – Inverse Document Frequency). The evaluation results show that the Support Vector Machine has a greater accuracy, precision, recall and f1-score of 87.27%, 90.41%, 77,34% and 83.37% compared to Naïve Bayes which has an accuracy, precision, recall and f1- of 76.81%, 72.40%, 70.70% and 71.52%.
- Open Access
- 31 July 2021
- Published by Universitas Budi Darma in JURNAL MEDIA INFORMATIKA BUDIDARMA
- Vol. 5 (3) , 913-921
Perbandingan Metode Klasifikasi Data Mining Untuk Rekomendasi Tanaman Pangan
Determination of the right food crops needs to be done to improve the community's economy in the agricultural sector. The use of traditional cropping patterns needs to be changed by utilizing information technology. The utilization of data from local governments can be used to assist in providing recommendations for types of food crops by processing them with several data mining methods. This method can extract information to find patterns and knowledge from the data. The classification method approach is used as a grouping of data based on data attachment to sample data. This study uses several classification methods, namely Naïve Bayes, Decision Tree, Support Vector Machine (SVM), Neural Network, Random Tree, Random Forest, dan K Nearest Neighbor (KNN). These methods were successfully compared to find out which method is the best to help recommend appropriate and accurate food crops based on the results of the classification performance of each method. Random Tree was chosen as the best method for the results of this performance comparison using discretization and normalization methods at the pre-processing stage of the data. It can be seen based on the results of the Accuracy, Precision, Recall, and F1-Score values on the use of discretization of 98%, respectively. Meanwhile, normalization showed that the results of the Accuracy, Precision, Recall, and F1-Score values are 99%, respectively.
- 31 July 2021
- Published by Universitas Budi Darma in JURNAL MEDIA INFORMATIKA BUDIDARMA
- Vol. 5 (3) , 913-921
Open AccessPerbandingan Metode Klasifikasi Data Mining Untuk Rekomendasi Tanaman Pangan
Determination of the right food crops needs to be done to improve the community's economy in the agricultural sector. The use of traditional cropping patterns needs to be changed by utilizing information technology. The utilization of data from local governments can be used to assist in providing recommendations for types of food crops by processing them with several data mining methods. This method can extract information to find patterns and knowledge from the data. The classification method approach is used as a grouping of data based on data attachment to sample data. This study uses several classification methods, namely Naïve Bayes, Decision Tree, Support Vector Machine (SVM), Neural Network, Random Tree, Random Forest, dan K Nearest Neighbor (KNN). These methods were successfully compared to find out which method is the best to help recommend appropriate and accurate food crops based on the results of the classification performance of each method. Random Tree was chosen as the best method for the results of this performance comparison using discretization and normalization methods at the pre-processing stage of the data. It can be seen based on the results of the Accuracy, Precision, Recall, and F1-Score values on the use of discretization of 98%, respectively. Meanwhile, normalization showed that the results of the Accuracy, Precision, Recall, and F1-Score values are 99%, respectively.