Garuda - Garba Rujukan Digital

Speech Classification to Recognize Emotion Using Artificial Neural Network Helmiyah, Siti; Riadi, Imam; Umar, Rusydi; Hanif, Abdullah
Khazanah Informatika Vol. 7 No. 1 April 2021
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v7i1.11913

This study seeks to identify human emotions using artificial neural networks. Emotions are difficult to understand and hard to measure quantitatively. Emotions may be reflected in facial expressions and voice tone. Voice contains unique physical properties for every speaker. Everyone has different timbres, pitch, tempo, and rhythm. The geographical living area may affect how someone pronounces words and reveals certain emotions. The identification of human emotions is useful in the field of human-computer interaction. It helps develop the interface of software that is applicable in community service centers, banks, education, and others. This research proceeds in three stages, namely data collection, feature extraction, and classification. We obtain data in the form of audio files from the Berlin Emo-DB database. The files contain human voices that express five sets of emotions: angry, bored, happy, neutral, and sad. Feature extraction applies to all audio files using the method of Mel Frequency Cepstrum Coefficient (MFCC). The classification uses Multi-Layer Perceptron (MLP), which is one of the artificial neural network methods. The MLP classification proceeds in two stages, namely the training and the testing phase. MLP classification results in good emotion recognition. Classification using 100 hidden layer nodes gives an average accuracy of 72.80%, an average precision of 68.64%, an average recall of 69.40%, and an average F1-score of 67.44%.This study seeks to identify human emotions using artificial neural networks. Emotions are difficult to understand and hard to measure quantitatively. Emotions may be reflected in facial expressions and voice tone. Voice contains unique physical properties for every speaker. Everyone has different timbres, pitch, tempo, and rhythm. The geographical living area may affect how someone pronounces words and reveals certain emotions. The identification of human emotions is useful in the field of human-computer interaction. It helps develop the interface of software that is applicable in community service centres, banks, and education and others. This research proceeds in three stages, namely data collection, feature extraction, and classification. We obtain data in the form of audio files from the Berlin Emo-DB database. The files contain human voices that express five sets of emotions: angry, bored, happy, neutral and sad. Feature extraction applies to all audio files using the method of Mel Frequency Cepstrum Coefficient (MFCC). The classification uses Multi-Layer Perceptron (MLP), which is one of the artificial neural network methods. The MLP classification proceeds in two stages, namely the training and the testing phase. MLP classification results in good emotion recognition. Classification using 100 hidden layer nodes gives an average accuracy of 72.80%, an average precision of 68.64%, an average recall of 69.40%, and an average F1-score of 67.44%.

Integration of Double Exponential Smoothing Damped Trend with Metaheuristic Methods to Optimize Forecasting Rupiah Exchange Rate against USD during COVID-19 Pandemic Hakimah, Maftahatul; Kurniawan, Muchamad
Khazanah Informatika Vol. 6 No. 2 October 2020
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v6i2.9887

COVID-19 pandemic has brought great changes to the stability of the Indonesian state. The disease not only has an impact on public health but also has the effect of weakening the economic sector. One indicator is the weakening of the rupiah exchange rate against the USD. When the pandemic emerged, the rupiah exchange rate started to weaken, which may encourage investors to reduce investment in Indonesia. Therefore, it is necessary to predict the rupiah exchange rate during the COVID-19 pandemic for the coming period. This study applies the Double Exponential Smoothing forecasting method by adding a damped trend factor. The calculation of the parameters of the method becomes the research optimization problem. This optimization problem is then solved using metaheuristic methods, namely Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The performance of the forecasting model is measured based on the magnitude of the forecast error. This study shows that the PSO algorithm is better at obtaining the optimal parameters for predicting the rupiah exchange rate in the coming period compared to GA. The integration error rate of Double Exponential Smoothing damped trend with PSO is 0.70%, while the error rate for the same method with GA is 0.72%. Thus, the integrated performance of double exponential smoothing with metaheuristic optimization is a more excellent method in predicting the rupiah exchange rate against the USD during the period of the Coronavirus outbreak. Furthermore, the addition of a trend dampening factor to the DES method also significantly increases the forecast accuracy.

Performance Assessment of University Lecturers: A Data Mining Approach Milkhatun, Milkhatun; Rizal, Alfi Ari Fakhrur; Asthiningsih, Ni Wayan Wiwin; Latipah, Asslia Johar
Khazanah Informatika Vol. 6 No. 2 October 2020
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v6i2.9069

A lecturer with a good performance has a positive impact on the quality of teaching and learning. The said quality Â includes the delivery of teaching materials, learning methods, and ultimately the academic results of students. Performance of lecturers contributes significantly to the quality of research and community service which in turn improves the quality of teaching materials. It is desirable, therefore, to have a method to measure the performance of lecturers in carrying out the Tri Dharma (or the three responsibility) activities, which consist of teaching and learning process, research, and community service activities, including publications at both national and international level. This study seeks to measure the performance of lecturers and cluster them into three categories, namely "satisfactory", "good", and "poor". Data were taken from academic works of nursing study program lecturers in conducting academic activities. Clustering process is carried out using two machine learning approaches, which is K-Means and K-Medoids algorithms. Evaluation of the clustering results suggests that K-Medoids algorithm performs better compared to using K-Means. DBI score for clustering techniques using K-Means is -0.417 while the score for K-Medoids is -0.652. The significant difference in the score shows that K-Medoids algorithm works better in determining the performance of lecturers in carrying out Tri Dharma activities.

Decision Support System for Selection of the Best Member at Junjung Biru Waste Bank Using the Composite Performance Index (CPI) Purwaningtias, Fitri; Ulfa, Maria; Franata, Febi
Khazanah Informatika Vol. 6 No. 2 October 2020
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v6i2.11058

Junjung Biru Waste Bank conducts a selection of the best member biennially. The process is crucial, but it does not have a supporting system, which poses problems emerging from data redundancies and data loss. Among the problem is the difficulty for administrators in summarizing data of members who have transactions. To solve the problem, we devised and implemented a decision support system using the CPI (Composite Performance Index) method. The criteria are the amount of balance and active saving during a six-month interval. The results of this research is a web-based decision support system that produces a ranking order of members, which helps in selecting the best member.

Combining Usability Testing with In-Depth Interview for Online Credit Hour Website Evaluation Sukmasetya, Pristi; Arumi, Endah Ratna; Setiawan, Agus
Khazanah Informatika Vol. 6 No. 2 October 2020
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v6i2.10804

The Online Credits Hour (KRS) application is one of the existing systems at the University of Muhammadiyah Magelang where the academic community, including lecturers, students, and education staff, produces a large amount of student academic data. Evaluation is necessary to find out whether the system runs well. This study is an effort to evaluate the system employing a usability test consisting of five indicators, namely learning ability, memory, efficiency, errors, and satisfaction. The five indicators materialized in the form of questionnaires to online KRS users. The survey involved 118 respondents. The method of study includes validity and reliability tests. The validity test employs a correlation test. The reliability test uses a simple linear regression analysis test and the comparison uses the significance value Alpha equals 0.05. The validity test for all five indicators results in value above 0.05. The reliability test of all the answers in the questionnaire has a Cronbach's Alpha value of 0.93, which suggests that the whole has correspondence. The evaluation results show that the KRS Online application has the highest value in the memorability indicator at 3.97, indicating that the KRS Online application is easily accessible with easy procedures to obtain data. The lowest value is on the error indicator at a level of 3, which means that the KRS Online website shows many errors, such as a broken link or poor navigation.

Analysis of the Causal Relationship of Body Image Factors in Patients with Cancer Vita Ari Fatmawati; Christantie Effendy; Ridho Rahmadi
Khazanah Informatika Vol. 7 No. 2 October 2021
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v7i2.14287

Patients with cancer can potentially experience the negative impacts of treatment. Physical conditions due to illness and therapy can affect the patient's body image. This study aims to find a causal model among body image factors of patients with cancer using the S3C-Latent Method. The measurement of body image of patients with cancer used the BIS questionnaire. One hundred and ninety-nine patients with cancer participated in this study. The results showed the existence of causal relationships between behavior to cognitive factors and duration of illness with reliability scores of 0.8 and 0.6, respectively; from gender to affective factors, illness duration, behavior, and cognitive factors with reliability scores of 0.6, 0.8, 0.65, and 1, respectively. There are also causal relationships from age to affective factors, duration of illness, and cognitive factors with reliability scores of 0.8, 0.7, and 0.9, respectively. The results also showed that affective factors are associated with behavior, cognitive factors, and duration of illness, with reliability scores of 1, 1, and 0.9, respectively. The results showed further the association of cognitive factors and illness duration with a reliability score of 1. We expect that the estimated causal model will serve as a scientific reference for medical experts in developing a better intervention such as treatment.

Classification of Pandavas Figure in Shadow Puppet Images using Convolutional Neural Networks Wiwit Supriyanti; Dimas Aryo Anggoro
Khazanah Informatika Vol. 7 No. 1 April 2021
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v7i1.12484

Indonesia is a nation with various ethnicities and rich cultural backgrounds that span from Sabang to Merauke. One of the cultural products of Indonesian society is shadow puppet. Shadow puppet has been internationally renowned as a masterpiece of cultural art and recognized by UNESCO. The development of Indonesian society is very dependent on technological sophistication and it may shift the existing traditional culture out from the memory of the nation. Practices of modern life and the busy activities of the people exacerbate the condition and may make the society to ignore traditional culture. This study seeks to preserve traditional Indonesian culture by making shadow puppets as the object of classification. We use a deep learning algorithm called convolutional neural network (CNN) to classify 430 puppet images into 4 classes. The proportion of training, validation and test data is 70 by 20 by 10. The experiments show that the most efficient model is obtained with 3 convolution layer. It reaches an accuracy rate of 0.93 and a drop out rate of 0.2

Implementation of the Fisher-Yates Shuffle Algorithm in Exam-Problem Randomization on M-Learning Applications Chandra Kirana; Benny Wijaya; Abdul Holil
Khazanah Informatika Vol. 7 No. 2 October 2021
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v7i2.11761

Many schools are currently using conventional approaches in learning material deliveries and examination methods. Conventional examination processes referred to here are the provision of question sheets in paper form. They have several drawbacks, such as students cheating and a waste of paper printing costs. To overcome these problems, we propose an online examination system. The online system leaves students to work on a different question set from other students. The feature is made possible by applying a randomization algorithm. There are several algorithms for scrambling questions, one of which is the Fisher-Yates Shuffle algorithm. This study aims to ease schools in the implementation of quality exams that may find out the level of student understanding of study materials and reduce the risk of cheating. The research product works on Android smartphones, which may be attractive to students and schools. The product allows schools to hold quality exams and reduce paper costs.

Blood Glucose Prediction Using Convolutional Long Short-Term Memory Algorithms Redy Indrawan; Siti Saadah; Prasti Eko Yunanto
Khazanah Informatika Vol. 7 No. 2 October 2021
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v7i2.14629

Diabetes Mellitus is one of the preeminent causes of death to date. Effective procedures are necessary to prevent diabetes and avoid complications that may cause early death. A common approach is to control patient blood glucose, which necessitates a periodic measurement of blood glucose concentration. This study developed a blood glucose prediction system using a convolutional long short-term memory (Conv-LSTM) algorithm. Conv-LSTM is a variation of LSTM algorithms that are suitable for use in time series problems. Conv-LSTM overcomes the lack in the LSTM algorithm because the latter algorithm cannot access the content of previous memory cells when its output gate has closed. We tested the algorithm and varied the experiment to check the effect of the cross-validation ratio between 70:30 and 80:20. The study indicates that the cross-validation using a ratio of 70:30 data split is more stable compared to one with 80:20 data split. The best result shows a measure of 21.44 in RMSE and 8.73 in MAE. With the application of conv-LSTM using correct parameters and selected data split, our experiment attains accuracy comparable to the regular LSTM.

Speech Classification to Recognize Emotion Using Artificial Neural Network Siti Helmiyah; Imam Riadi; Rusydi Umar; Abdullah Hanif
Khazanah Informatika Vol. 7 No. 1 April 2021
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v7i1.11913

This study seeks to identify human emotions using artificial neural networks. Emotions are difficult to understand and hard to measure quantitatively. Emotions may be reflected in facial expressions and voice tone. Voice contains unique physical properties for every speaker. Everyone has different timbres, pitch, tempo, and rhythm. The geographical living area may affect how someone pronounces words and reveals certain emotions. The identification of human emotions is useful in the field of human-computer interaction. It helps develop the interface of software that is applicable in community service centers, banks, education, and others. This research proceeds in three stages, namely data collection, feature extraction, and classification. We obtain data in the form of audio files from the Berlin Emo-DB database. The files contain human voices that express five sets of emotions: angry, bored, happy, neutral, and sad. Feature extraction applies to all audio files using the method of Mel Frequency Cepstrum Coefficient (MFCC). The classification uses Multi-Layer Perceptron (MLP), which is one of the artificial neural network methods. The MLP classification proceeds in two stages, namely the training and the testing phase. MLP classification results in good emotion recognition. Classification using 100 hidden layer nodes gives an average accuracy of 72.80%, an average precision of 68.64%, an average recall of 69.40%, and an average F1-score of 67.44%.This study seeks to identify human emotions using artificial neural networks. Emotions are difficult to understand and hard to measure quantitatively. Emotions may be reflected in facial expressions and voice tone. Voice contains unique physical properties for every speaker. Everyone has different timbres, pitch, tempo, and rhythm. The geographical living area may affect how someone pronounces words and reveals certain emotions. The identification of human emotions is useful in the field of human-computer interaction. It helps develop the interface of software that is applicable in community service centres, banks, and education and others. This research proceeds in three stages, namely data collection, feature extraction, and classification. We obtain data in the form of audio files from the Berlin Emo-DB database. The files contain human voices that express five sets of emotions: angry, bored, happy, neutral and sad. Feature extraction applies to all audio files using the method of Mel Frequency Cepstrum Coefficient (MFCC). The classification uses Multi-Layer Perceptron (MLP), which is one of the artificial neural network methods. The MLP classification proceeds in two stages, namely the training and the testing phase. MLP classification results in good emotion recognition. Classification using 100 hidden layer nodes gives an average accuracy of 72.80%, an average precision of 68.64%, an average recall of 69.40%, and an average F1-score of 67.44%.

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota surakarta,

Jawa tengah

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name -

Contact Email -

Phone -

Journal Mail Official -

Editorial Address -

Location Kota surakarta, Jawa tengah INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota surakarta,

Jawa tengah

INDONESIA