Article Per Year (5 Year)
p-Index From 2019 - 2024
0.61
P-Index
This Author published in this journals
All Journal Jurnal Edukasi dan Penelitian Informatika (JEPIN) Register: Jurnal Ilmiah Teknologi Sistem Informasi Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Sari, Zamah
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Energy Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Performance Comparisson Human Activity Recognition Using Simple Linear Method Kusuma, Wahyu Andhyka; Sari, Zamah; Minarno, Agus Eko; Wibowo, Hardianto; Akbi, Denar Regata; Jawas, Naser
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 5, No. 1, February 2020
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (731 KB) | DOI: 10.22219/kinetik.v5i1.1025

Abstract

Human activity recognition (HAR) with daily activities have become leading problems in human physical analysis. HAR with wide application in several areas of human physical analysis were increased along with several machine learning methods. This topic such as fall detection, medical rehabilitation or other smart appliance in physical analysis application has increase degree of life. Smart wearable devices with inertial sensor accelerometer and gyroscope were popular sensor for physical analysis. The previous research used this sensor with a various position in the human body part. Activities can classify in three class, static activity (SA), transition activity (TA), and dynamic activity (DA). Activity from complexity in activities can be separated in low and high complexity based on daily activity. Daily activity pattern has the same shape and patterns with gathering sensor. Dataset used in this paper have acquired from 30 volunteers.  Seven basic machine learning algorithm Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, Gradient Boosted and K-Nearest Neighbor. Confusion activities were solved with a simple linear method. The purposed method Logistic Regression achieves 98% accuracy same as SVM with linear kernel, with same result hyperparameter tuning for both methods have the same accuracy. LR and SVC its better used in SA and DA without TA in each recognizing.
Implementasi Chatbot Pembelajaran Bahasa Inggris menggunakan Media Sosial Sarosa, Moechammad; Kusumawardani, Mila; Suyono, Achmad; Sari, Zamah
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 6, No 3 (2020): Volume 6 No 3
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v6i3.43191

Abstract

Bagi sebagian kalangan belajar bahasa Inggris adalah sesuatu yang tidak mudah sehingga perlu pendamping untuk memperbaiki jika terjadi kesalahan. Belajar bahasa Inggris bisa diawali dengan memahami secara benar strukturnya sehingga dapat membantu dan  memberikan rasa percaya ciri saat mempelajari materi-materi selanjutnya seperti reading, listening maupun writing. Penelitian ini bertujuan mengembangkan suatu aplikasi chatbot untuk belajar struktur bahasa Inggris menggunakan media sosial. Pertimbangan utama penggunaan media sosial sebagai sarana pembelajaran yaitu sebagian besar aktifitas masyarakat hingga pelajar di musim pandemic ini menggunakan media sosial atau sarana belajar berbasis online, sehingga dirasa bahwa media sosial bukan sesuatu yang baru bagi khalayak ramai dan menjadi alternatif terbaik yang dapat digunakan sebagai sarana untuk menyampaikan materi struktur bahasa Inggris. Facebook dengan fasilitas chatfuel-nya digunakan untuk mengembangkan chatbot pembelajaran struktur bahasa Inggris dengan memanfaatkan metode Organization Exercise Items (OEI). Dengan menggunakan metode OEI maka chatbot secara otomatis akan memberikan bantuan apabila ada seseorang yang sedang belajar mengalami kesulitan. Aplikasi yang diberi nama ELA-bot atau English Learning Assistant Bot ini telah diimplementasikan pada mahasiswa program studi D3 Bahasa Inggris, Politeknik Negeri Malang. Hasil pengujian menunjukkan bahwa 98% mahasiswa menyatakan chatbot telah membantu dalam proses pembelajaran struktur Bahasa inggris. 
QoS Analysis Of Kinematic Effects For Bluetooth HC-05 And NRF24L01 Communication Modules On WBAN System Faiqurahman, Mahar; Novitasari, Diyan Anggraini; Sari, Zamah
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 4, No 2, May 2019
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v4i2.826

Abstract

Wireless Body Area Network (WBAN) consists of a number of sensor nodes that are attached to the human body, and intended for monitor the human body condition. The WBAN system has several wireless communication modules that are used for sending or exchanging data between sensor nodes and gateway nodes or gateway nodes. There are some factors that are used to decide which communication modules should be implemented on WBAN system, including communication efficiency, distance range, power consumption, and the effect of mobility on QoS. In this study, we analyze the impact of the kinematic movement of sensor nodes on QoS parameter of HC-05 Bluetooth and NRF25L01 communication modules, during sending and receiving process among nodes. We assume that the sensor node and gateway node are attached on the limbs to catch the movement. We use Quality of Service (QoS) parameters such as delay, jitter, and packet loss, to analyze the impact of movement on communication modules. Based on the experimental result, it was found that the average value of delay and jitter for booth communication modules was slightly influenced by the speed of the sensor node movement. During the sensor node movement and data transmission, we found that the NRF24L01 module have a lower delay and jitter value than Bluetooth HC-05 module. The percentage of packet loss tends to be stable at 0% value, even though the speed value becomes higher.
Implementasi Pull Message dengan menggunakan Restful Web Service pada komunikasi Wireless Sensor Hidayatullah, Rakhmad Arif; Sari, Zamah; Faiqurahman, Mahar
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 3, No 2 (2017): July
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v3i2.699

Abstract

 Wireless Sensor Network (WSN) merupakan jaringan dengan skalabilitas yang sangat tinggi, dan memiliki jumlah sensor node yang sangat banyak. Untuk efisiensi biaya, sensor node banyak diterapkan dengan menggunakan Arduino. Arduino merupakan papan rangkaian elektronik open source yang di dalamnya terdapat chip mikrokontroler. Dengan keterbatasan resource yang dimiliki oleh Arduino, efisiensi komputasi yang ada di dalam sensor node harus diperhatikan. Salah satunya berkaitan dengan proses komunikasi dan pengiriman data dari sensor node ke sink node (gateway). Restful web service merupakan salah satu protokol komunikasi yang memanfaatkan HTTP. Protokol ini dikenal memiliki efisiensi yang cukup tinggi, di samping karena interoperabilitasnya untuk digunakan pada berbagai platform. Dalam makalah ini akan diuraikan hasil dari implementasi model pull message dengan menggunakan restful web service, pada komunikasi antara sink node (gateway) dengan sensor node, di dalam infrastruktur WSN. Dalam penelitian yang dilakukan, digunakan mikrokontroler Arduino sebagai sensor node, dan Raspberry Pi sebagai sink node. Selain itu juga diimplementasikan mekanisme thread untuk menangani multi-process yang berjalan di dalam sensor node. Hasil dari pengujian menunjukan bahwa interval sensing, ukuran data, dan jumlah sink node yang melakukan request, tidak begitu berpengaruh terhadap ketersedian free memory heap pada sensor node. Sedangkan ukuran dari data hasil sensing yang dikirim mempunyai pengaruh terhadap request-response time.    Wireless Sensor Network (WSN) infrastructure has very high scalability, which is composed of a large number of the sensor node. For cost efficiency, sensor node broadly deployed using Arduino. Arduino is the open-source electronic circuit board, which has embedded microcontroller chipset. Due to limited resource, the efficiency of computation inside Arduino must be considered during the development of sensor node. One of them is related to communication and data delivery process between the sensor node and sink node. Restful Web Service is one of communication protocol framework which uses HTTP protocol and claimed to be the most efficient Web Service. As well as the other web services, Restful also support high interoperability of communication. In this paper we describe the implementation of pull message mechanism on WSN communication between the sensor node and sink node, using Restful Web Service. We implemented sensor node using Arduino board, and sink node using Raspberry Pi. We also used thread mechanism to handle multi-process that run in the sensor node. The results of the study show that the interval time in sensing, data size, and the number of sink node which makes requests, didn’t give too much influence in the availability of free memory heap in the sensor node. While the size of sensor data that was sent to sink node have an influence on a request-response time.
Co-Authors Agus Eko Minarno Akbi, Denar Regata Hardianto Wibowo Hidayatullah, Rakhmad Arif Kusumawardani, Mila Mahar Faiqurahman Moechammad Sarosa Naser Jawas, Naser Novitasari, Diyan Anggraini Suyono, Achmad Wahyu Andhyka Kusuma