Search

The purpose of this study is to develop an e-LKPD using a Live Worksheets with GeoGebra-assisted for geometric transformations, especially translation. The translation sub-topic was chosen because many students still need help finding translation concept. The type of research carried out in development research to produce e-LKPD using the ADDIE method consists of stages Analysis, Design, Development, Implementation, and Evaluation. The test subjects in this study were 15 students with high, medium, and low math ability categories. Subjects are divided into three categories to determine students' understanding of the e-LKPD so that they are able to achieve learning mastery. Students from junior high school (SMP Negeri 39 Surabaya) were selected as subjects because they had never used GeoGebra-assisted e-LKPD. The data collection instruments in the study consisted of validation sheets, learning outcomes tests (THB) and student response questionnaires. The results of this study indicate that the validation results with an average score of 3.73, which means that the e-LKPD on translation is included in the very valid criteria and is feasible to use. The analysis of the use of e-LKPD shows that the average student response is 3.39, which means e-LKPD is positive and practical. Based on the test scores for learning outcomes, 14 of the 15 research subjects scored pass the KKM, so using e-LKPD can help students learn about translation materials. Thus the translational e-LKPD using a GeoGebra-assisted Live Worksheets are valid, practical and effective. Keywords: e-LKPD, Geometry Transformation, Translation, Geogebra, Live Worksheets.

Pembelajaran daring merupakan salah satu bentuk pemanfaatan teknologi dalam pembelajaran. Pembelajaran daring memanfaatkan internet untuk memudahkan penyampaian materi oleh guru dan memberikan ruang lebih untuk siswa dalam belajar. Penggunaan sumber belajar yang relatif mudah untuk diakses dan terdapat berbagai media pembelajaran yang menarik dan inovatif merupakan kelebihan dari pembelajaran daring. Dalam pembelajaran daring, sumber belajar dan media pembelajaran dapat diintegrasikan dalam satu tempat yang dikenal dengan Learning Management System (LMS). Terdapat berbagai macam LMS yang tersedia, salah satu contoh LMS tersebut adalah Google Classroom. Penelitian ini bertujuan untuk mendeskripsikan penerapan pembelajaran daring pada mata pelajaran matematika materi barisan dan deret ditinjau dari hasil belajar siswa. Penelitian ini merupakan penelitian deskriptif dengan pendekatan kuantitatif yang dilaksanakan di kelas XI B SMA Plus Ar Rahmat Bojonegoro yang terdiri dari 25 siswa. Instrumen penelitian yang digunakan terdiri atas LMS, angket pengelolaan pembelajaran, angket respon siswa, RPP, LKPD, dan ujian yang berupa tes untuk mengukur tingkat pemahaman siswa terkait materi yang diajarkan. LMS yang digunakan dalam penelitian ini adalah Google Classroom dengan alamat situs https://classroom.google.com/c/NTUwNTkyNTU5NDEy?cjc=ywcuuqp. LMS divalidasi oleh ahli media dan mendapatkan kriteria sangat baik dengan persentase 87,5%. Hasil pada penelitian ini menunjukkan kemampuan pengelolaan pembelajaran masuk pada kriteria sangat baik dengan persentase 89,5%. Respon siswa terhadap pembelajaran daring masuk pada kriteria baik dengan persentase 73,94%. Hasil belajar siswa dengan jumlah siswa sebanyak 25 siswa dinyatakan tuntas dengan persentase ketuntasan belajar 84%. Kata Kunci: pembelajaran daring, Learning Management System, barisan dan deret.

The ongoing digitalizing education makes the use of technology is necessary to develop the learning media. Therefore, this research describes the development process of android-based learning media with the ADDIE model and find out the validity and practicality of it. The material is operations of integers because it’s a prerequisite for many other mathematics material. The research subjects were nine 7th-grade students in SMPN 5 Jombang since they had never been given the kind of math learning media based on Android in that school. They were consist of three categories of low, medium, and high mathematical ability to determine whether all types of students can understand the presence of media to achieve their learning mastery. The data analyzed using qualitative descriptive and quantitative data analysis techniques. The result of this research and development are : 1) The Android-based learning media called Math Moist; 2) The learning media is very valid based on the results of media and material validation with a validity percentage of 83.541%; 3) The media is very practical based on the student's response questionnaire scores, with a percentage of practicality is 88.7301%; 4) Based on the result of learning outcomes test, 8 of the 9 research subjects have completed learning after using media. Keywords: development, media, android-based, ADDIE, integer.

Penelitian ini bertujuan untuk mendeskripsikan literasi matematis siswa reflektif, impulsif dalam menyelesaikan masalah kontekstual berorientasi PISA menggunakan indikator merumuskan, menerapkan dan menafsirkan. Namun, hasil asesmen PISA berdasarkan data yang diperoleh dari OECD, peringkat nilai PISA Indonesia tahun 2018 menduduki lima terbawah. Hasil kajian literatur yang diperoleh menyatakan faktor yang menghambat berkembangnya literasi matematis siswa di Indonesia adalah kurangnya mengenal masalah non-rutin. Oleh karena itu siswa diperkenalkan pada masalah non rutin yang mengacu pada PISA melalui AKM. Penelitian pendekatan kualitatif ini, menggunakan instrumen matching familiar figure test untuk memperoleh data gaya kognitif, tes kemampuan matematika, tes literasi matematis dan wawancara yang telah divalidasi oleh tiga dosen pendidikan matematika. Dua siswa yang memiliki kemampuan matematika setara, memilliki gaya kognitif berbeda dan komunikasi yang baik menjadi subjek penelitian, data diperoleh dari matching familiar figure test dan tes kemampuan matematika. Subjek dari setiap gaya kognitif diberikan tes literasi matematis serta dilaksanakan wawancara untuk menggali informasi mengenai literasi matematis siswa. Hasil temuan penelitian menunjukkan bahwa siswa reflektif dapat memberikan jawaban dan penjelasan yang jelas mengenai pekerjaan yang diselesaikan, cenderung teliti, serta mengamati setiap komponen penting masalah dengan cermat, memenuhi semua indikator literasi matematis. Siswa impulsif memberikan jawaban dan penjelasan secara garis besar dari pekerjaan yang diselesaikan, cenderung tergesa-gesa dan kurang teliti, cenderung membaca cepat dan meninggalkan beberapa komponen penting dalam penyelesaian masalah, tidak dapat memenuhi indikator mengenali struktur matematika, memanipulasi bilangan dan persamaan aljabar.

In order to create a joyful learning environment, especially during a pandemic that requires learning to be carried out online, an innovation is needed such as the use of interactive learning media for mutual learning which can be accessed online. Electronic modules with Augmented Reality are packaged in the form of learning media that can be used independently everytime and everywhere. This study aims to develop an electronic module with android-based Augmented Reality named "AR LIMAS" as a media to improve students' abilities on pyramid geometry problem. The selection of pyramid material in the electronic module was based on several previous studies regarding the misconceptions experienced by students on pyramid. The development of this electronic module used the ADDIE research method by taking into account the scores ​​of validity, practicality, and effectiveness for the creation of good learning media. This electronic module was tested on 3 students of VII grade who have low, medium, and high mathematical ability. The categorization of students' mathematical ability was based on the final examination scores in the previous semester. Based on the assessment of experts, this electronic module was declared to have a good category with a validity percentage of 86.59%. Then the results of the questionnaire using the electronic module obtained a practicality percentage value of 98.35% with a very good category. The results of pretest with an average score of 15 increased in posttest with an average score of 82.5, so the module was considered effective in improving students' understanding on pyramid. Keywords: electronic module, android, augmented reality, pyramid, development.

Jantung adalah organ yang mempunyai peranan penting dalam kelangsungan hidup manusia karena fungsinya untuk mendistribusikan darah dari paru-paru ke seluruh bagian tubuh, yang dimana darah tersebut mengandung banyak sekali oksigen sehingga dapat membantu proses metabolisme di dalam tubuh manusia. Maka dari itu, organ jantung perlu dilindungi, dirawat, dan dijaga kondisinya untuk mencegah kerusakan pada jantung yang mengakibatkan penyakit gagal jantung. Begitu banyak orang yang meninggal karena penyakit gagal jantung, sehingga harus ada penelitian yang terbarukan untuk memprediksi penyakit gagal jantung tersebut. Peranan Artificial Intelligence (AI) dalam mendeteksi gagal jantung pada penelitian ini bertujuan untuk membandingkan prediksi akurasi dari tiga metode yang dipakai oleh peneliti, yaitu metode Support Vector Machine (SVM), K-Nearest Neighbors (KNN), dan Random Forest (RF). Dataset diambil dari laman UCI Machine Learning dengan judul Heart Failure Clinical Records Dataset. Akurasi paling tinggi yang dapat dihasilkan adalah menggunakan metode SVM dan RF dimana menghasilkan akurasi yang bernilai sama, yaitu 97% dengan rincian metode SVM menggunakan parameter C = 1, gamma = 0.01, kernel = linear dan dalam total waktu running program selama 2.82 detik sedangkan metode RF menggunakan parameter n_estimators = 30, random_state = 0, dan dalam total waktu running program selama 7.29 detik. Lalu untuk metode KNN menghasilkan akurasi yang bernilai 93%, dengan menggunakan parameter n_neighbors = 20 dan dalam total waktu running program selama 0.60 detik. Pada penelitian ini, peneliti juga membuat program Prediksi Gagal Jantung dengan Graphical User Interface (GUI) menggunakan ketiga metode yang telah diuji akurasinya.

The easiness of accessing video on various platforms can negatively impact if not done wisely, especially for children. Parental supervision is needed so that movies platforms avoid inappropriate displays such as violence. Violent scenes in movies can trigger children to commit acts of violence, which is not desired. Unfortunately, it is not easy to supervise them fully. This study proposed a method for automatic detection of violent scenes in movies. Automatic violence detection assists the parents and censorship institutions in detecting violence easily. This study uses Gated Recurrent Units (GRU) algorithm and wavelet as feature extraction to detect violent scenes. This paper shows comparative studies on the variation of the mother wavelet. The experimental results show that GRU is robust and deliver the best performance accuracy of 0.96 while combining with mother wavelet Symlet and Coiflets8. The combination of GRU with wavelet Coiflets8 shows better results than the predecessor.

The research goal is to produce a mathematics educational game called "Maze Math" as an android-based learning supplement on direct proportions and inverse proportion material as a valid, practical, and effective learning media. The development model in this study is the ADDIE model which includes Analysis, Design, Development, Implementation, and Evaluation. The instrument of validity are media and material expert validation questionnaire, practical instrument is a questionnaire of the use of educational games, and effectiveness instrument consist of a pretest and posttest. The educational game “Maze Math” was tested on 12 students of MTsN 1 Gresik with high, medium, and low math competency. This educational game has valid criteria because the results from the media expert and material expert validation questionnaire show percentage value of 82.71% (81%-90%). Maze Math is practical because the results from the practicality questionnaire filled out by students obtained 85.256% (85%-100%). The results of this study are also effective because the average N-gain categorized as high with a value of 0.740278 (> 0.7).

Pandemi corona telah mengubah proses pembelajaran dari yang semula tatap muka secara langsung (offline) menjadi pembelajaran secara daring (online). Pembelajaran daring ini menyebabkan kesulitan dalam pemantauan perilaku siswa oleh guru karena berkurangnya interaksi secara langsung. Lebih dari itu, siswa seringkali merasa terisolasi sehingga jika dibiarkan, situasi ini akan menyebabkan kegagalan dalam prestasi belajarnya. Permasalahan ini mendorong banyak dilakukannya penelitian tentang pemodelan yang berkaitan dengan perilaku siswa. Namun, para peneliti sebelumnya tidak banyak yang fokus pada peningkatan kinerja model atau sistem yang dibangun, padahal kinerja model ini sangat berpengaruh terhadap kualitas hasil pemetaan perilaku siswa. Untuk itu, makalah ini berfokus pada peningkatan kinerja pengklasteran perilaku siswa ketika berinteraksi dengan sistem e-Learning. Peningkatan kinerja dilakukan dengan reduksi dimensi pada data siswa dengan Principal Component Analysis (PCA). Selanjutnya, dua teknik inisialisasi titik pusat klaster dieksplorasi untuk mendapatkan hasil yang optimal, yaitu: random dan K-means++. Untuk pengukuran kualitas klaster, makalah ini menggunakan silhouette index. Hasil pengujian menunjukkan bahwa klaster dengan kualitas tertinggi dicapai oleh penerapan PCA dengan tujuh komponen dan banyaknya klaster tiga sampai empat untuk semua teknik inisialisasi titik pusat. Klaster yang berkualitas ini dapat membantu guru dalam memonitor perilaku siswa pada pembelajaran secara daring.

Perkembangan teknologi informasi dan komunikasi (TIK) saat ini semakin pesat, salah satunya smartphone berbasis Android dimana telah banyak digunakan siswa dalam pembelajaran. Untuk memaksimalkan penggunaan smartphone berbasis Android dalam pembelajaran, dapat memanfaatkannya menjadi media pembelajaran. Salah satu inovasi pembelajaran yang memanfaatkan smartphone yaitu pengembangan media pembelajaran mobile learning berbasis Android pada materi Pola Bilangan. Tujuan dari penelitian ini yaitu mendeskripsikan proses pengembangan media pembelajaran mobile learning berbasis Android pada materi Pola Bilangan dengan model ADDIE untuk menghasilkan media pembelajaran yang berkualitas baik berdasarkan kriteria kevalidan, kepraktisan, dan keefektifan. Subjek uji coba penelitian ini berjumlah 9 siswa kelas VII MTsN 2 Tulungagung dengan kemampuan matematika tinggi, sedang, dan rendah. Penelitian ini menggunakan instrumen pengumpulan data meliputi lembar validasi media pembelajaran, angket respon pengguna, dan tes hasil belajar. Hasil dari penelitian ini didapatkan bahwa media pembelajaran yang telah dikembangkan berkualitas baik. Media pembelajaran memenuhi kriteria valid diperoleh dari rata-rata nilai validasi oleh validator pakar materi dan validator pakar media berturut-turut adalah 3,47 dan 3,60 dari nilai maksimal 4. Media pembelajaran memenuhi kriteria praktis berdasarkan hasil respon pengguna dalam menggunakan mobile learning menunjukkan kategori sangat baik dengan persentase sebesar 92,75%. Media pembelajaran memenuhi kriteria efektif berdasarkan tes hasil belajar menunjukkan sebanyak 88,89% subjek ujicoba mendapat nilai 75 (KKM). Kata Kunci : media pembelajaran, mobile learning , pengembangan, pola bilangan.

The development of technology that get more advance, such as Android-based smartphones, often makes students prefer to play games than to study. One way to overcome is by utilizing Android-based smartphone as a learning media. This research develop an Android-based learning media on Financial Mathematic that the result reviewed in terms of validity, practically, and effectiveness. The instruments in this research were media validity sheet, material validity sheet, student questionnaire, observation sheet, and the students’ scoresheet. The trial for the learning media were conducted limited to 15 eight graders of SMP Negeri 1 Wonoayu.Based on the research, the average value of total validity was 3,59 (media expert) and 3,58 (material expert) of 4, so that it could be categorized as a valid Android-based learning media. It was practical because the percentage value of student questionnaire was 83,25% and the average value of the observation sheet was 90,67%. Based on the student’s scoresheet, 86,67% student’s score ≥76 (Standar Minimum Score) so that conclud the Android-based learning media was effective.Keywords: development, Android game, learning media, Financial Mathematic

The corona pandemic has changed the learning method from conventional to a more flexible one, such as through the internet. Consequently, students may have less direct interaction with teachers. This condition has made it difficult for teachers to monitor the students' behavior. This research works on this problem by focussing on the clustering of students' behavior using the DBSCAN, which is a density-based algorithm. Noises generated in this process can be considered students who do the uncommon behavior when taking the e-Learning system. Further, we evaluate the resulted clusters using the silhouette index to find their quality. The experimental result shows that the DBSCAN can differentiate clusters containing noises. By taking the silhouette index, the Manhattan distance parameter is superior to that of Euclidean.

Violence detection research is still quite a challenge for researchers and a considerable amount of effort. Before the video can be processed for classification, feature extraction is an important process to obtain important information. Determination of feature extraction and classification algorithms is an important factor for accurate classification results. This study uses deep transfer learning for feature extraction and combining it with the Support Vector Machine (SVM) classifier. The deep transfer learning algorithm in this study is a pre-trained model of Visual Geometry Group Network-16 (VGGNet-16). The video data was extracted using VGGNet-16 and then classified using SVM. Tests were carried out with 5-fold cross-validation with a variety of linear kernel, RBF, and Polynomial functions. The results were also compared with the Principal Component Analysis (PCA) feature extraction algorithm combining with SVM also. The results showed that the combination of deep transfer learning with SVM linear kernel functions resulted in higher accuracy compared to RBF and Polynomial kernel functions, and also compared to PCA combined with SVM.

Pemanfaatan Teknologi Informasi dan Komunikasi (TIK) dalam bidang pendidikan diantaranya adalah untuk pembuatan media pembelajaran. Namun pada umumnya yang digunakan adalah media pembelajaran presentasi yang bersifat satu arah. Agar pembelajaran menarik diperlukan media pembelajaran interaktif yang bersifat dua arah sehingga guru dapat mengetahui umpan balik dari apa yang dipelajari peserta didiknya. Pascasarjana Universitas Negeri Surabaya, khususnya Tim Pengabdian Kepada Masyarakat (PKM), berusaha merintis kerjasama dengan Dinas Pendidikan Kabupaten Lombok Timur. Rintisan kerjasama tersebut dilakukan dengan mengadakan kegiatan PKM dengan sasaran guru-guru sekolah menengah seperti Sekolah Menengah Pertama (SMP), Sekolah Menengah Atas (SMA), atau Sekolah Menengah Kejuruan (SMK) dalam pembuatan media pembelajaran interaktif bagi guru-guru di Kabupaten Lombok Timur.Kegiatan pelatihan berjalan lancar dan peserta merasakan manfaat pelatihan pembuatan media pembelajaran interaktif karena selama ini hanya bersifat satu arah. Namun karena pelatihan ini baru pertama kali dikenal peserta maka waktu yang disediakan masih terasa kurang. Tetapi hal ini dapat diatasi dengan melalukan konsultasi secara online. Peserta pelatihan adalah para Kepala Sekolah sehingga diharapkan dapat menyampaikannya pada guru-guru di sekolahnya.

The development of Information and Communication Technology (ICT) affects in almost every single part of human life, includes education. Using ICT is not a new issues in the classroom or in education research field. Even there are many of product outcomes in research field which could bring to classroom to encourage student's motivation to study, the products need to be tested before released world wide. We have developed a Role-Playing Game (RPG) named “Hello Counselor” to support students' self-study about simultaneous linear equation in word problems which need to be tested in simple limited trial. The aim of this study was to test the validity, practicality, and effectiveness of the developed RPG game to support student self-study. Data were collected from validity observation sheet, response questioner sheet, and game level completeness. The result of the research shows that “Hello Counselor” is qualified as the prototype which could support student self-study about simultaneous linear equation for senior high school students because it is satisfied with three categories: valid, practical, and effective. The RPG game is stated as valid from experts with percentage score 76.98% and said minor revision. The practicality percentage score from response questioner sheet is 76.71%. The last category, the game is labeled as effective with percentage score from game level completeness of subjects is 78.57%.

Penelitian ini bertujuan untuk mengembangkan bahan ajar pada mata kuliah Dasar-Dasar Matematika di Program Studi Matematika, Universitas Negeri Surabaya.Model yang digunakan untuk pengembangan bahan ajar pada penelitian ini adalah model pengembangan ADDIE yang terdiri 5 tahap, yaitu tahap Analisis (Analysis), Perancangan (Design), Pengembangan (Development), Implementasi (Implementation), dan Evaluasi (Evaluation). Sementara, metode yang digunakan untuk menganalisis data adalah metode ceklist pada setiap langkah pada Instructional Design Process Step/Action Checklist, jika tidak maka harus ada langkah alternatif yang dilakukan atau ada alasan yang relevan yang tidak mempengaruhi proses pengembangan. Perkuliahan Dasar-Dasar Matematika menggunakan bahan ajar blended learning telah disusun berdasarkan model pengembangan ADDIE. Setiap langkah pada Instructional Design Process Step/Action Checklist telah dilaksanakan dan telah menghasilkan bahan ajar berbasis blended learning. Penelitian ini diawali dengan pembuatan story line yang merupakan panduan dalam pengembangan bahan ajar. Dari hasil analisis angket respon mahasiswa, diperoleh lebih dari 75% mahasiswa memberikan respon positif tidak hanya pada bentuk perkuliahan yang menggabungkan antara perkuliahan online dan offline melalui blended learning tetapi juga tentang ketergunaan materi yang disampaikan secaran online melalui Vi-learn Unesa.Kata kunci: bahan ajar, blended learning, ADDIEThis study aims to develop teaching materials in the Basic Mathematics course in the Mathematics Study Program, Surabaya State University. The model used for the development of teaching materials in this study is the ADDIE development model consisting of 5 stages, namely the Analysis, Design (Design), Development (Development), Implementation (Implementation), and Evaluation (Evaluation). Meanwhile, the method used to analyze data is the checklist method at each step in the Instructional Design Process Step / Action Checklist, if not then there must be an alternative step taken or there is a relevant reason that does not affect the development process. Lectures on Basic Mathematics using blended learning teaching materials have been prepared based on the ADDIE development model. Every step in the Instructional Design Process Step / Action Checklist has beencarried out and has produced teaching materials based on blended learning. This research begins with the creation of a story line which is a guide in the development of teaching materials. From the analysis of student questionnaire responses, it was obtained that more than 75% of students gave positive responses not only to the form of lectures that combined online and offline lectures through blended learning but also about the use of material delivered online through Vi-learn Unesa.Keywords: ADDIE, blended learning, teaching materials

The combination of traditional learning where teacher and students are in the same classroom and e-learning using technology is known as blended learning. This paper outlines the process of designing blended learning on Differential Calculus. The Successive Approximation Model (SAM) is used as the instructional design upon the course. In the preparation phase, the information gathering is starting to ensure an agreement between the learner’s need and learning solution. Afterward, the design and prototype of a blended course was implemented for Mathematics Education students on Mathematics Department Universitas Negeri Surabaya. Along with iterative development phase, the evaluation is conducted in order to make the course move to Alpha (a complete version of the instructional design blended learning) then evolve into Beta (a better version after Alpha revised) and then the Gold as finale version is reached.

In this disruptive era, the need of independence and innovation in learning strategy are required. Blended learning strategy offers face-to-face learning and self-study that combined both online and offline. In other words, it is a combination of traditional learning in a classroom and e-learning via disruptive technology device. There are several courses were encouraged to provide e-learning and face-to-face in delivering material in Mathematics Department of Universitas Negeri Surabaya such as Computer Application, Basic Mathematics, Contextual Mathematics, Visual Programming, and Discrete Mathematics. At the end of the semester, we gave the final exam followed by giving questionnaire about students’ opinion regarding the blended learning strategy. Positive responses on the application of blended learning were showed by students. Furthermore, the learning result of each courses are above 75. By this condition, blended learning is considered as a way to support students’ learning in the disruptive era.

This study aims to describe the learning outcomes and students’ responses after joining in the Foundation of Mathematics courses using virtual learning. The research subjects were Mathematics students who programed the Foundation of Mathematics which consisted of 31 people. The method of data collection was carried out by test methods and questionnaires. This learning was said to be successful if the learning outcomes of students at least 70% get A. A-, B+, or B grades or at least 70% the scores obtained by students was more than or equal to 70, and students’ responses after joining in Foundation of Mathematics courses using virtual learning is positive category (the percentage of students positive responses was more than 70%). Based on the results of data analysis it can be stated that 90.03% of the final grades of students joining in the Foundation of Mathematics courses are B, B+, A- or A, and the percentage of positive responses of students after joining in Foundation of Mathematics courses was 80.0%. Thus it can be concluded that Foundation of Mathematics courses using virtual learning has been successful.

Gamelan is an ensemble music originated from Indonesia. Gamelan have been made manually but had 7 tonnes for Pelog scale or 5 tonnes for Slendro scale. It is need to classify gamelan tones for digital musical processing for various objectives like learning, teaching, or composing. Fractal analysis can be used to classify physical phenomena like musical tones signal. One of fractal method was Higuchi that is suitable in computing fractal dimension for time series data as musical signals. In this paper, we propose the Higuchi fractal dimension to distinguish gamelan signal tones. Our experiment show that Demung Pelog tones can be classified properly until 82.85%. This result encourages to classify gamelan tones not only for other instruments but also for Slendro scale.

Plant recognition based on digital leaf image has received as particular attention in computer vision and intelligence system, due its important implication in automatic plant identification. Plant species have the unique leaf characteristics such as the shape, texture, margin, and colour, which different each other. This study presents a novel method for automation plant recognition using Generalized Relevance Learning Vector Quantization (GRLVQ). GRLVQ is a competitive based learning algorithm which is integrating features extraction and classification phases. The experimental result shows that GRLVQ has better performance than the predecessor algorithm.

Animal tracker is an important phase in animal behavior analysis. It leads to understanding how, when, and why the animal use the environmental resources, how, where, and when they interact with each other, with other species, and with their environment. Understanding the animal behavior is providing the link to population distribution which is essential for predicting the human-caused environmental change and guidance for conservation strategies. Tracking and detecting the animal is time and cost consuming. Machine Learning can relieve this burden by detecting animal automatically. Complex-Valued Neural Network is a method of Machine Learning that is challenging and interesting to be explored. This study applied of Complex-Valued Neural Network (CVNN) for animal tracking, especially in detecting the animal species. The experiment results present that CVNN is robust to recognition the animal automatically.

Gamelan is a set of musical instruments from Indonesia and played together as an orchestra. In gamelan playing, one of instruments will act as a conductor so the sound of this instrument must be separated from the others.