Journal of Computer Science and Informatics Engineering (J-Cosine) <p>J-COSINE (Journal of Computer Science and Informatics Engineering) merupakan jurnal dibidang Ilmu Komputer dan Teknik Informatika yang dipublikasi oleh Program Studi Teknik Infroamtika Fakultas Teknik Universitas Mataran dengan <em><strong>online ISSN 2541-0806</strong></em> dan <em><strong>print ISSN &nbsp;2540-8895.&nbsp;</strong></em>J-Cosine juga merupakan&nbsp;&nbsp;<em>blind</em>&nbsp;&nbsp;dan&nbsp;<em>peer-review jurnal</em> yang proses reviewenya dilakukan oleh sekurang-kurangnya &nbsp;2 orang reviewer yang ditujuk oleh&nbsp;associate editor.&nbsp;Jumlah terbitaan dari J-Cosine sebanyak 2 kali dalam setahun.</p> <p>Tujuan&nbsp;&nbsp;utama dari&nbsp;J-Cosine adalah untuk mempublikasikan paper hasil penelitian, inovasi aplikasi, studi perbandingan &nbsp;yang&nbsp;berkualitas baik&nbsp;dan&nbsp;mengikuti&nbsp;perkembangan dan tren teknologi baru dibidang&nbsp;Ilmu Komputer dan Teknik Informatika. Paper yang dipublikasikan pada J-Cosine dapat ditulis dalam bahasa Indonesia atau bahasa Inggris.</p> Informatics Engineering Dept., Faculty of Engineering, University of Mataram en-US Journal of Computer Science and Informatics Engineering (J-Cosine) 2540-8895 Meningkatkan Kinerja Protokol Routing Aomdv Dalam Memilih Node Tetangga Berdasarkan Bandwidth, Round Trip Time, Dan Packet Loss Ratio Untuk Menemukan Rute Terbaik <p>Mobile ad hoc network or in short MANET is a group of node that exchange the information from source node to destination node on wireless network. The main problem in MANET is on the network structure that change continously that is cause by node mobility that made route disconnected. If route disconnect there will be another route discovery processes that will take much time. AOMDV (Ad hoc On-demand Multipath Distance Vector) routing protocol works by doing broadcast Route Request Packet (RREQ) from source node to neighbor node (intermediate node) and then it will continously until it arrives to destination node. AOMDV didnt choose the best neighbor node while broadcast RREQ packet so the route constructed have high possibility to disconnected and must re-broadcast until it find stable route and it will be a long time and not effective. To solve this problem it proposed to add a modification with AOMDV routing protocol with calculation of bandwidth, round trip time, and packet loss ratio to choose neighbor node to find the best route. Routing protocol performance will tested using test parameter throughput, delay, and packet delivery ratio to choose the best neighbor node. Based on test result, the proposed modification can improve the preformance of AOMDV routing protocol. After modification, average throughput has improved 43.26 %, Packet Delivery Ratio (PDR) improved 3.15 % and average end-to-end delay reduce 31.26%.</p> I Putu Gede Krisna Parwata Andy Hidayat Jatmika Ariyan Zubaidi Copyright (c) 2022 I Putu Gede Krisna Parwata, Andy Hidayat Jatmika, Ariyan Zubaidi 2022-12-21 2022-12-21 6 2 91 98 10.29303/jcosine.v6i2.433 Performance Comparison of Deep Learning Algorithm for Speech Emotion Recognition <p><strong>One of the problems in Speech emotion recognition is related to time series data, while the feedforward process in neural networks is unidirectional where the results from one layer are directly channeled to the next layer. This kind of feedforward process cannot store past data. Thus, if Deep Neural Network (DNN) is used for Speech emotion recognition, some problems arise, such as the speech rate of the speaker. DNN cannot analyze the existing acoustic patterns and so cannot map different levels of speech rate. Another method that can take input at once while retaining relevant data in the previous process is the Recurrent Neural Network (RNN). This paper presents the characteristics of the RNN method consisting of LSTM and GRU techniques for Speech emotion recognition using the Berlin EMODB dataset. The dataset is divided into 80% for training and 20% for testing. The feature extraction methods used are Zero crossing Rate (ZCR), Mel Frequency Cepstral Coefficients (MFCC), Root Mean Square Energy (RMSE), Mel Spectrogram, and Chroma. This study compares the CNN, LSTM, and GRU algorithms. The classification results show that the CNN algorithm gets better results, namely 79.13%. Meanwhile, LSTM and GRU only got an accuracy of 55.76% and 55.14%, respectively</strong></p> I Gusti Bagus Arya Pradnja Paramitha Hendra Budi Kusnawan Muji Ernawati Copyright (c) 2022 I Gusti Bagus Arya Pradnja Paramitha, Hendra Budi Kusnawan, Muji Ernawati 2022-12-21 2022-12-21 6 2 99 106 10.29303/jcosine.v6i2.443 WebGIS-Based Subak Rice Field Irrigation Monitoring Information System <p>Subak is a traditional organization owned by the Balinese people to manage rice field irrigation. In the process of irrigating the fields, subak administrators and farmers check the condition of the irrigation in the fields by directly coming to the location to check the condition of the water level in the fields, so it is time consuming and less efficient. The creation of a geographic information system is intended so that subak administrators and farmers know the water level of the fields and regulate irrigation without going to the fields. The geographic information system is built using the Laravel framework equipped with a map. The map was created with the Google Maps API with the aim of displaying the location of rice fields. The result of this research is a geographic information system that can monitor the height of rice fields and display data on a map. The information system can also receive sensor data and send configuration data to Antares. In black box testing, the information system has been running according to the functions and scenarios given. Based on the results of the System Usability Scale test, the application obtained a score of 76,125 which indicates the application is classified as good and can be accepted by the user.</p> I Gusti Agung Anom Semara Putra Ni Made Ary Esta Dewi Wirastuti Komang Oka Saputra Copyright (c) 2022 I Gusti Agung Anom Semara Putra, Ni Made Ary Esta Dewi Wirastuti, Komang Oka Saputra 2022-12-21 2022-12-21 6 2 133 141 10.29303/jcosine.v6i2.450 SOA Implementation Design for Prototyping Coaching Information System of Pondok Pesantrena Alam Sayang Ibu (PAMSI) <p>The presence of service-oriented computing, through the Service Oriented Architecture (SOA), and the implementation of information technology through website applications provide opportunities for more appropriate system utilization for an organization by providing options for implementing functionalities in a modular manner, according to the needs of the organization following the evolution of service growth, without the need for large Information Technology infrastructure investments. In order to develop an Coaching Information System for Pondok Pesantren Alam Sayang Ibu (PAMSI) with a service functionality basis, it is necessary to define a prototype model of Coaching Information System with an SOA approach through understanding the process of coaching activities and must be relevant to the needs of each party involved. This study aims to create a SOA implementation design that can be used as a guideline to be used as the main foundation in the creation of a PAMSI Coaching Information System and can be used as a reference for the development of other Information Systems at PAMSI.</p> Noor Alamsyah Royana Afwani Sri Endang Anjarwani Moh. Ali Albar Ahmad Zafrullah Mardiansyah Copyright (c) 2022 Noor Alamsyah 2022-12-21 2022-12-21 6 2 159 166 10.29303/jcosine.v6i2.470 Android-Based Subak Rice Field Irrigation Monitoring Application <p><em>Subak is a group of farmers in Bali to manage rice fields irrigation. Farmers come directly to the rice fields which need time to monitor their fields irrigation so that it’s less efficient. Based on this, an Android-based subak irrigation monitoring application was designed using the flutter framework with subak culture system for monitoring farmers fields irrigation and using supporting application namely Android Studio. The result of this research is an Android application that can display the location of the rice fields that registered, successfully sends a high water request, successfully sends a request for registration of subak fields, and successfully reports damages in case of damages to the fields and also successfully retrieves data on the condition of rice fields whose data is taken from the Antares database. The Black-box testing and System usability scale (SUS) used in the Android application has been successfully run according to the given scenario and functions and also suitable for use by users because the result of SUS are above the average value that is 72.875</em>.</p> Ni Made Ary Esta Dewi Wirastuti Zaky Zamani Noor Komang Oka Saputra Copyright (c) 2022 Ni Made Ary Esta Dewi Wirastuti, Zaky Zamani Noor, Komang Oka Saputra 2022-12-21 2022-12-21 6 2 123 132 10.29303/jcosine.v6i2.449 Analysis and Prediction of GPA Based on UTBK scores Using Linear Regression Algorithm <p class="Abstract"><span lang="EN-US">Education is an important element that needs special attention, because education is an important element for the progress of a nation. Not only formal education starting from elementary school to high school, it can now be said that higher education has a central role in developing the capabilities of the Indonesian people. One way to get into state universities is with Ujian Tertulis Berbasis Komputer (UTBK). UTBK is set to be the main requirement to take part in the Seleksi Bersama Masuk Perguruan Tinggi Negeri (SBMPTN). Students' abilities cannot necessarily be measured by the UTBK scores. Student achievement when entering tertiary institutions is determined by an assessment of the GPA (Cumulative Achievement Index). In this study the authors tried to find a relationship between the UTBK scores and student GPAs using the linear regression method. The results showed that the correlation between the UTBK and GPA scores was 0.670157 and the mean squared error was 0.0546.</span></p> Ilham Firman Ashari Meida Cahyo Untoro Sophia Nouriska Muhammad A.M Hikar Syahrial Makruf Alkarhi Copyright (c) 2022 Ilham Firman Ashari 2022-12-21 2022-12-21 6 2 107 114 10.29303/jcosine.v6i2.444 Performance Comparison of Edge Detection Method for Extracting Images of Lutjanus spp. Contour <p>Lutjanus spp. is one of the 72 genera of fish species which includes to the Lutjanidae family around the world. The Lutjanus spp. is healthy for consumption and suitable for fishing tourism. The production volume increased by 6.21% between 2001 and 2011 to produce over 118608 tons. However, about 10 species are experiencing population decline. This is because the data of captured fisheries production is still limited, making it challenging to identify the species resulting in overfishing of certain species. The process of identifying the species is based on morphometric characteristics using edge detection. This method involves a pattern identification technique by detecting outlines at the boundaries of objects in the image. In this research, several edge detection algorithms were conducted following many steps to clarify contour extraction of Lutjanus spp. (L. argentimaculatus, L. bohar, L. carponatatus, L. fulviflamma, and L. sebae). The steps included image preprocessing, shape extraction with edge detection algorithms involving the Sobel, Canny, and Laplacian operations, and visual evaluation. The results showed that the three algorithms could be used to extract the contours of Lutjanus spp. The Laplacian algorithm produced the best performance because it could extract the contours with a success rate of 89.88% without noise or broken contours.</p> Ishak Ariawan Novi Sofia Fitriasari Ayang Armelita Rosalia Willdan Aprizal Arifin Lukman Nabila Tufailah Afrizal Dzikrillah Copyright (c) 2022 Ishak Ariawan 2022-12-21 2022-12-21 6 2 115 122 10.29303/jcosine.v6i2.445 Potential Methods For Calculating Clock Skew <p>Some studies such as Aoki measure clock skew by filtering outliers by selecting the minimum offset that is collected using linear regression to calculate the slope of the accumulated minimum offset. Huang who uses the QPM (Quick Piecewise Minimum) algorithm to calculate the skew of the minimum offset at the beginning and end of the collected offsets and Moon's research that uses the LPA (Linear Programming Algorithm) algorithm which determines the clock skew of the line gradient that is below the offset. In addition, there are several methods that have the potential to be used in measuring clock skew including ant colony, bee colony, particle swarm, and also genetic algorithm. From these several methods, one method that has potential as a method that can be used for measuring clock skew will be selected. The method that can be used is particle swarm optimization because it is considered more efficient and flexible and easy to implement with few parameters used.</p> I Gede Agus Aditya Putra Aditya Komang Oka Saputra Ni Made Ary Esta Dewi Wirastuti Copyright (c) 2022 I Gede Agus Aditya Putra Aditya, Komang Oka Saputra, Ni Made Ary Esta Dewi Wirastuti 2022-12-21 2022-12-21 6 2 142 149 10.29303/jcosine.v6i2.459 Improving Convolutional Neural Network with Recurrent Model and Generative Adversarial Networks for Imbalance Classification of Wearable ECG Signal Quality Assessment <p>Signal quality assessment is important procedure to assess if a signal can be preprocessed into next step or not. In this study, we proposed an improving of convolutional neural network with recurrent model and generative adversarial network. The experiment shows that enhancing convolutional neural network by using recurrent model or data augmentation via GAN for wearable ECG signal quality assessment is feasible to try. Adding recurrent model to CNN increase its performance by approximately 3% margin in un-augmented dataset. Generating fake samples from “unacceptable” class can enhance CNN performance up to 2% margin. Combination of recurrent model and GAN still not yet matched found. However, It doesn’t mean that the combination is impossible to do.</p> M. Anwar Ma'sum Copyright (c) 2022 M. Anwar Ma'sum 2022-12-21 2022-12-21 6 2 150 158 10.29303/jcosine.v6i2.460 Term Weighting Based Indexing Class and Indexing Short Document for Indonesian Thesis Title Classification <p>Document classification nowadays is an easy thing to do because there are the latest methods to get maximum results. Document classification using the term weighting TF-IDF-ICF method has been widely studied. Documents used in this research generally use large documents. If the term weighting TF-IDF method is used in a short text document such as the Thesis Title, the document will not get a perfect score from the classification results. Because in the IDF will calculate the weight of words that always appear to be few, ICF will calculate the weight of words that often appear in the class to be few. While the word should have great weight to be the core of a short text document. Therefore, this study aims to conduct research on word weighting based on class indexation and short document indexation, namely TF-IDF-ICF-IDSF. This study uses a classification comparison Naïve Bayes and SVM. The dataset used is Thesis Title of Informatics Education student at Trunojoyo Madura University. The test results show that the classification results using the TF-IDF-ICF-IDSF term weighting method outperform other term weighting, namely getting 91% Precision, 93% Recall, 86% F1-Score, and 84% Accuracy on SVM.</p> Ana Tsalitsatun Ni'mah Fahmi Syuhada Copyright (c) 2022 Ana Tsalitsatun Ni'mah, Fahmi Syuhada 2022-12-21 2022-12-21 6 2 167 175 10.29303/jcosine.v6i2.471