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 Rancang Bangun Smart Meter System untuk Penggunaan Air pada Rumah Tangga Berbasis Internet of Things <p>Water is one of the mineral resources which is a source of basic human needs and has many uses including drinking, bathing, washing and so on. In urban areas, clean water services are generally provided by the government through the PDAM (Regional Water Company). In the use of water, sometimes the user is not able to control the use of water which causes an enlarged water bill as in one of the houses in Pancor, East Lombok Regency. In this area, monitoring is still carried out conventionally by checking the water meter used. Monitoring systems are now widely used as an alternative way to monitor one of them in monitoring water use. In this study, a system (Smart Meter System) that can be used to control and monitor water usage in the household for more efficient water use is designed. By using WeMos as a microcontroller, Water Flow Sensor and MQTT (Message Queuing Telemetry Transport) protocol as data communication, remote control and monitoring of water use in households can be done in real-time.</p> Ramdani Ramdani I Gede Putu Wirarama Wedashwara W Ariyan Zubaidi Copyright (c) 2020 Ramdani Ramdani, I Gede Putu Wirarama Wedashwara W, Ariyan Zubaidi 2020-12-31 2020-12-31 4 2 149 160 10.29303/jcosine.v4i2.300 Implementasi Fuzzy Logic pada Penjadwalan Pengairan Irigasi (Studi Kasus : BPSDA Serayu Citanduy) <p>Abstract - Irrigation system is an activity to get water to facilitate agricultural activities. The activity is to drain and provide water regularly to the land and then use it for land needs. This irrigation system has been implemented by BPSDA Serayu Citanduy, Central Java by using river water. Intelligent control system using Sugeno fuzzy algorithm in this study can determine the proper scheduling. The stages in the Sugeno fuzzy method are to form Fuzzy sets and then implement the implication function, the next process is Defuzzification. An intelligent control system prototype for scheduling soil irrigation using LoRa as a telemetry medium. Sugeno fuzzy algorithm application is to measure the discharge in river water and then compare it with the area of agricultural land. In this study using 50 hectares of land area and 38.18 L/sec water discharge resulted in 74 minutes.</p> Krisna Ardhi Tama Maman Abdurohman Rahmat Yasirandi Copyright (c) 2020 Krisna Ardhi Tama, Maman Abdurohman, Rahmat Yasirandi 2020-12-31 2020-12-31 4 2 161 167 10.29303/jcosine.v4i2.320 Analisa Kepuasan Mahasiswa Terhadap Kegiatan Belajar Mengajar Di Program Studi Teknik Informatika Universitas Mataram Menggunakan Metode Importance Performance Analysis <p><strong>This study discusses "Student Satisfaction Analysis on Teaching and Learning Activities in Informatics Engineering Program University of Mataram Using Importance Performance Analysis Method". Students are required to fill out a teaching and learning questionnaire from all courses. The questionnaire consisted of questions relating to teaching and learning activities. Students give perceptual value and expectation value on every questionnaire question. Then the relationship between perceptual value and expectation value is analyzed using Importance Performance Analysis method. From the analysis results can be known which variables should be prioritized for improvement and which variables are excessive and does not require priority.</strong></p> Diaz Guntur Febrian Nadiyasari Agitha Copyright (c) 2020 Diaz Guntur Febrian, Nadiyasari Agitha 2020-12-31 2020-12-31 4 2 92 99 10.29303/jcosine.v4i2.85 Rancang Bangun Service Oriented Architecture (SOA) Pada SMKN 1 Selong <p class="Abstract" style="text-indent: 0cm;"><em><span lang="EN-US">In an organization, the development of a system cannot be done as a whole but is done in stages, This is caused by organizational needs that are always changing from time to time. Also, in an organization, there is a lot of data or information that is done together, where one data can be used by several fields and one data can also be used for many functions. Similar to SMK 1 Selong, the same data or information can be used by several midwives and can be used for many functions. To overcome these problems in this study carried out the design and construction of Service Oriented Architecture (SOA). SOA is software development with a service approach. In SOA the data needed for the development of a system is defined from the start to facilitate the development of a continuous system and can facilitate if there is a change in data because SOA provides the ease of integration of several different systems. In this research the SOA analysis and design process at SMK 1 Selong has been carried out and 9 services are obtained: student service, employee service, service teacher, service value, financial service, curriculum service, library service, service facilities and infrastructure, and service administrator. These services are implemented using web service technology with a codeigniter framework</span></em></p> Qori' Rahmawati Pertiwi Royana Afwani Sri Endang Anjarwani Copyright (c) 2020 Qori' Rahmawati Pertiwi, Royana Afwani, Sri Endang Anjarwani 2020-12-31 2020-12-31 4 2 119 128 10.29303/jcosine.v4i2.282 Implementasi Modifikasi Kompresi Run-Length Encoding pada Steganografi <p><strong>RLE is one of the methods to compress data, however it has disadvantages that the compressed data may become twice larger as the original size. Therefore, in this research RLE will be modified to solve the problem. In the experiment we tested 3 file format i.e. JPG, PNG and BMP. The testing on JPG and PNG shows that conventional RLE method is not able to compress all images because it obtained negative compression ratio with an average compression ratio about -97.4%, Meanwhile the compression with RLE modification shows that the all image successfully compress with an average compression ratio about 0.31%. The testing on BMP shows the conventional RLE method successfully compress 5 files out of 11 tested images with average compression ratio about -25.4%, Meanwhile the compression with modified RLE successfully compress all tested images with average compression ratio about 22.4 %.</strong></p> Suwardiman Suwardiman Fitri Bimantoro Copyright (c) 2020 Suwardiman Suwardiman, Fitri Bimantoro 2020-12-31 2020-12-31 4 2 100 109 10.29303/jcosine.v4i2.109 Pengenalan Pola Wajah Menggunakan Metode Block-Eigenface pada Raspberry Pi <p><strong>Rapid technological development has created a human face recognition system. The use of this facial recognition system spread to various fields. One of them is the security field that uses this system for authentication which is usually applied to Internet of Things based systems. The Raspberry Pi microprocessor is used as a place to implement a face recognition system to fulfil the IoT requirements. This facial recognition system measures qualitatively the characteristics of the human face, such as the shape of the face, eyes, nose, and mouth. There are many methods for measuring facial characteristics. One of them is the Block-Eigenface method which is a derivative of the Eigenface method. This method is a development method that applies <em>blocking</em> to the original method. Two datasets were used in this study, the first was a dataset from the results of data collection with 100 images of 10 classes (dataset Informatics), and the second dataset was commonly used was the ORL dataset with 400 images of 40 classes. The blocking done has an effect on the accuracy and computational time of the original method. In the Informatics dataset the Eigenface method got 84% ??results with a classification time of 0.003 seconds, the Block-Eigenface method got an accuracy of 98% with a classification time of 0.094 seconds. The ORL dataset provided an average accuracy of 55.42% with an average classification time of 0.014 seconds on the Eigenface method and 82.22% with an average classification time of 0.019 seconds on Block-Eigenface.</strong></p> <p><strong><em>Key words</em>: Face Recognition, Raspberry Pi, Eigenface, Block<em>-</em>Eigenface, Internet of Things.</strong></p> Arbhi Anggara I Wayan Agus Arimbawa Copyright (c) 2020 Arbhi Anggara, I Wayan Agus Arimbawa 2020-12-31 2020-12-31 4 2 110 118 10.29303/jcosine.v4i2.267 Sistem Pakar Diagnosa Penyakit Kulit pada Manusia dengan Metode Dempster Shafer <p>Skin is the broadest organ in the human body that covers the entire surface of the body and acts as a support for human life. Because of its outermost location, the skin is often attacked by various diseases. This research aims to build an expert system to diagnose 10 types of skin diseases caused by viruses, fungi, bacteria, and parasites based on the knowledge of 3 experts using the Dempster Shafer method to obtain conclusions of skin diseases. Each symptom of skin disease has a value of belief that is used to calculate conclusions in the Dempster Shafer method. Expert system applications that are built can run Android-based smartphones. Testing techniques used in this research are black-box testing, theoretical calculations, system accuracy and MOS (Mean Opinion Score). Comparison of the calculation on the system has been appropriate based on the theoretical calculations. System accuracy testing in 30 sample cases resulted in an accuracy of 90%, but if it was seen as a subsection of expert diagnosis, it resulted in a system accuracy of 92.22%.&nbsp; MOS testing on 30 respondents results in a MOS value of 4.24 from a scale of 5 which shows that the system is proper to use and categorized into a good system.</p> Anita Rosana MZ I Gede Pasek Suta Wijaya Fitri Bimantoro Copyright (c) 2020 Anita Rosana MZ, I Gede Pasek Suta Wijaya, Fitri Bimantoro 2020-12-31 2020-12-31 4 2 129 138 10.29303/jcosine.v4i2.285 Sistem Pakar Diagnosa Awal Penyakit Mata dengan Metode Bayesian Network <p>Almost every human activity needs an eye to support these activities, therefore it will have a bad effect if the eyes experience interference. Disorders that can be experienced in the eye can occur from minor disorders to disorders that cause loss of vision and even death. Based on the results of the Rapid Assessment Assessment of Avoidable Blindness (RAAB), the blindness rate in districts/cities in NTB was 4%. This is not only due to medical-related problems but also due to social problems related to knowledge from the community, facilities, and resources. To make it easier for the public to make an initial diagnosis of eye disease, one thing that can be done is to use an expert system. Various methods can be implemented for expert systems, one of which is the Bayesian Network method. Based on the results of accuracy testing that has been done, this application provides an accuracy rate of 84.99%. Whereas, if the system diagnosis results are a subset of expert diagnostic results, the accuracy rate is 89.99% and based on the results of the use made by the general public, this application has been running well and has provided clear information related to the diagnosis of eye disease.</p> Novanita Laylatul Husna Fitri Bimantoro Copyright (c) 2020 Novanita Laylatul Husna, Fitri Bimantoro 2020-12-31 2020-12-31 4 2 139 148 10.29303/jcosine.v4i2.287 Pengenalan Plat Kendaraan Bermotor Menggunakan Metode Gradien Karakter dan BPNN (Backpropagation Neural Network) <p><em>License plates are a unique feature to identify a vehicle in the combination between letters and numbers. Feature extraction needed to identify each letter and number in a digital image. There are several methods in feature extraction, one of them uses a gradient feature extraction. In this research, an application program to identify the license plate is a character gradient method and backpropagation neural network (BNN). First, the digital image is cropped to get a license plate then segmented to generate each character. The next step is the extraction feature using Character gradient to get a particular feature from each character. Backpropagation neural networks are used as data classification. This research consist of two types of testing: performance analysis based on hidden layers and feature quantity in training datasets and license plate data. From the result, we can conclude that the quantity of features affects the system performance. The highest performance rate in the first scenario test is feature 48 with 60 hidden layers, and in the second scenario, the highest is feature 108 with 60 hidden layers. The lowest performance rate is shown in feature 12 with 20 hidden layers.</em></p> <p><strong><em>Keywords</em></strong><strong><em>: </em></strong><em>License plate, character gradient method, backpropagation neural network, feature, hidden layer.</em></p> Muhammad Ridwan Ali Ario Yudo Husodo Copyright (c) 2020 Muhammad Ridwan Ali, Ario Yudo Husodo 2020-12-31 2020-12-31 4 2 169 178 10.29303/jcosine.v4i2.328 Implementasi Long Short-Term Memory untuk Identifikasi Berita Hoax Berbahasa Inggris pada Media Sosial <p>Hoax or fake news spreads very fast on social media. The news can influence readers and be a poison of the mind. Problems like this must be resolved in a strategic way to identify the news that is read that is disseminated on social media. Some of the methods proposed to predict hoax are to use Support Vector Classifier, Logistic Regression, and MultinomialNaiveBayes. In this study, the researchers applied Long Short-Term Memory to identify hoax. System performance is measured based on the value of precision, recall, accuracy, and F-Measure. Based on the results of experiments conducted on the hoax data obtained the average value of precision, recall, accuracy, and F-Measure respectively 0.94, 0.96, 0.95, and 0.95. Based on the experimental results it was found that the proposed Long Short-Term Memory has better performance compared to the state-of-the-art methods method.</p> Jasman Pardede Raka Gemi Ibrahim Copyright (c) 2020 Jasman Pardede, Raka Gemi Ibrahim 2020-12-31 2020-12-31 4 2 179 187 10.29303/jcosine.v4i2.361