Jurnal Sistem Komputer - JSK (Department of Computer System Engineering, Diponegoro University, Indonesia)
Not a member yet
108 research outputs found
Sort by
APLIKASI BUKU DIGITAL ATRAKTIF UNTUK MENDUKUNG PEMBELAJARAN BERBASIS FUN LEARNING MANAGEMENT DENGAN PENDEKATAN USER CENTERED DESIGN (STUDI KASUS : MATAKULIAH ALGORITMA)
Full text linkAlgoritma merupakan kunci bagi mahasiswa untuk menyelesaikan permasalahan komputasi secara efektif dan efisien. Matakuliah algoritma biasanya diberikan pada semester awal dimana mahasiswa dalam tahap adaptasi dan belum memiliki dasar pemrograman sama sekali. Penelitian ini bertujuan untuk mengembangkan perangkat lunak bantu pembelajaran algoritma dengan mengadopsi konsep buku digital atraktif yang dapat menyajikan gambar, teks, audio, video dan animasi. Metode pengembangan aplikasi menggunakan pendekatan user centered design. Hasil penelitian menunjukkan penilaian ahli materi berdasarkan aspek pembelajaran dan isi materi memberikan skor rata-rata nilai sebesar 4,46 (sangat baik). Penilaian ahli media yang meliputi aspek teks/bahasa, warna, gambar/ilustrasi dan interaktifitas menunjukkan skor rata-rata nilai sebesar 4,43 (sangat baik). Penilaian mahasiswa yang meliputi aspek teks/bahasa, gambar/ilustrasi,materi dan fun learning menunjukkan skor rata-rata nilai sebesar 4,19 (Baik). Berdasarkan hasil pengujian tersebut menunjukkan aplikasi buku digital algoritma layak untuk dikembangkan dan digunakan pada pembelajaran algoritma
FUZZY LOGIC DAN LEXICAL CHAINS UNTUK PERINGKASAN TEKS OTOMATIS
Full text linkAutomatic text summarization (ATS) is a process that was required to produce a summary of a text that contains information with help from a computer. This system is needed to determine the subject matter of a document so that readers can quickly understand. ATS systems need to process the documents resulting in important sentences from the document. In this study, lexical chains were used to generate optimal value for the candidate most powerful word in each sentence. The document is extracted to produce features such as sentence length, the weight of the sentence, the position of the sentence, and the similarity between sentences. The value of the strongest chain will be combined with fuzzy parameters. These features Fuzzy logic predicted the results of a summary of the values of the parameters to be grouped based on the value of linguistic important and unimportant. Furthermore, the final value of the fuzzy will determine the final outcome text summary of the document that was input by the user lexical chains. Testing conducted by manual sentence summary results sourced from respondents and a summary of the results of the ATS system recall, precision and F-measure. Based on the results of research that include the step of determining the problem, the analysis to implementation and testing that has been done before, it can be concluded that the results of the implementation of the method of lexical chains with fuzzy logic for automatic text summarization achieve fairly good
Perancangan Sistem Informasi Rekam Medis Hasil Deteksi Kaki Datar Berbasis Web
Full text linkFootprint analysis for foot type classification using FPA methods produces the output of footprint images and various calculated parameters that have been performed. These data need to be stored and processed in order to be reused when needed. Manual data storage is very slow and error-prone, also it makes storing and processing the data difficult. This study aims to design a medical record information system that can store and manage patient data and detection results of flat foot disease. System development methodology used is Extreme Programming method consisting of requirement analysis, design, implementation, and testing. From this research produced a medical record information system that can assist in storage and data processing of the result of flat foot detection. Based on the test results with black box method can be concluded that the produced information system has worked well and meet every function required
DESAIN MONITOR DAN KONTROL JARAK JAUH PROTOTIPE RUANG CERDAS MENGGUNAKAN PAPAN INTEL GALILEO SEBAGAI IMPLEMENTASI INTERNET OF THINGS
Full text linkThe proper way of using room facility often neglected by its user. Human negligence is the main factor of this problem. Internet of Things (IoT) is one of automation technology that used Internet as the control mechanism. This research consist of monitoring and control design of the smart room that able to control the door and the lamp of the room in short and long distance so that the facilities is used efficiently. The design built is the control design for smart room consists of TMP36 as temperature sensor, touch sensor, solenoid door lock, keypad, BH1750FVI as ambient light sensor, lamp, LED as an indicator, Intel Galileo board and Blynk application. Control mechanism can be done directly to the prototype or in a long distance by using smartphone. The result shows that the smart room control design can be implemented well
Towards Digital Intervention: Overview Of Dyscalculia In Indonesia
Full text linkDyscalculia is a learning disability. It affects the arithmetic ability of student, and usually can’t be separated from mathematical learning difficulty. It is usually occurred in early stage of learning, and unless an intervention (traditional or digital) is given, the disability will persist until adulthood. This paper will present an overview of current condition of dyscalculia in Indonesia. Researches in traditional and digital intervention and the role of computer-assisted instruction are also discussed
PENGEMBANGAN LEARNING CHARACTERISTIC RULE PADA ALGORITMA DATA MINING ATTRIBUTE ORIENTED INDUCTION
Full text linkThis paper shows the improvement of current characteristic rule learning in Attribute Oriented Induction (AOI) data mining technique. The proposed algorithm was applied with improvement upon current algorithm with 3 steps where the first step is elimination for checking condition if there is no higher level concept in concept hierarchy for attribute. The second step is elimination of attribute removal if fulfill for checking condition if there is no higher level concept. The third step is elimination of attributes in input dataset which no higher level concept in concept hierarchy. The development of these data mining algorithm applied Knowledge Data Discovery (KDD) methodology which consist 7 steps. Current and proposed AOI characteristic rule learning were implemented with server programming such as PHP Hypertext Preprocessor (PHP) and using 4 input datasets such as adult, breast cancer, census and IPUMS from University of California, Irvine (UCI) machine learning repository. The experiments showed that proposed AOI characteristic rule are better than current AOI characteristic rule, where experiments upon adult, breast cancer, census, IPUMS datasets have average 11, 3.8, 7.2, 7.2 respectively times better performance. The experiments were carried on AMD A10-7300(1.90 GHz) processor with 8.00 GB RA
PENDEKATAN MODEL ANALITIS UNTUK BROADCAST PADA JARINGAN VANET
Full text linkThe broadcast storm problem in VANETs can be addressed by the use of single-hop and/or two-hop information in VANET’s broadcast decision. Most studies had been obtained from experiment and only few of them were from analytical analysis. This study attempts to approach analytically the one-hop information based broadcast. A combination of multiple broadcast schemes can also be analytically derived from the individual analysis. However, one must take a great care of using both speed and vehicular density at once, as analytically, the speed is linearly related to the vehicular density
PERANCANGAN APLIKASI PENCARIAN LAYANAN KESEHATAN BERBASIS HTML 5 GEOLOCATION
Full text linkKesehatan merupakan kebutuhan primer bagi manusia dan layanan kesehatan masyarakat merupakan suatu elemen penting dalam kehidupan. Di suatu daerah, umumnya terdapat berbagai jenis layanan kesehatan, sehingga informasi tentang jenis, lokasi dan jam operasional suatu layanan kesehatan sangat penting bagi masyarakat. Dalam penelitian ini dirancang sebuah system informasi layanan kesehatan di kota Salatiga menggunakan HTML 5 berbasis Geolocation. Jarak layanan kesehatan dengan lokasi pengguna dihitung menggunakan metode Haversine dan Euclidian. Hasil eksperiment menunjukkan bahwa akurasi jarak yang dihasilkan menggunakan metode Haversine lebih baik daripada menggunakan merode Euclidian, akan tetapi waktu yang diperlukan lebih lama daripada metode euclidia
