Article Per Year (5 Year)
p-Index From 2020 - 2025
1.835
P-Index
This Author published in this journals
All Journal JST ( Jurnal Sains Terapan ) Jurnal Sistem Teknik Industri Journal of Scientific Insights Jurnal Teknologi dan Sains Modern
Fajar, Nurhikmah
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Engineering Industrial & Manufacturing Engineering Mathematics Public Health Social Sciences Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Need Identification on Android-Based Neighborhood Electric Vehicle Dashboard View Using The Kano Model Fajar, Nurhikmah; Wibisono, Muh Arif; Kusuma, Enas Dhuhri
Jurnal Sistem Teknik Industri Vol. 23 No. 2 (2021): JSTI Volume 23 Number 2 July 2021
Publisher : TALENTA Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jsti.v23i2.6388

Abstract

A customer is someone who repeatedly comes to the same place when he wants to buy an item or get service because he is satisfied with the goods or services. Companies must understand the needs and desires of customers in order to satisfy customer needs. Technology that is currently developing is electric cars, especially the Neighborhood Electric Vehicle (NEV) with the application of smartphones. Conventional dashboards can be replaced with smartphones Android-based. Fulfillment of customer satisfaction with smartphone dashboard products is identified by conducting a customer desires survey and categorized it using the Kano model. The survey was conducted on 14 attributes by producing three categories, such as one dimensional, attractive and indifferent. The Android dashboard is built based on survey results instruments. The use of Arduino nano and ESP32 as controllers that process vehicle instrument data sent using Wi-Fi in real time to Android-based smartphones has a maximum error of 5% for speed data.
Rancang Bangun Keran Wudu Otomatis Fajar, Nurhikmah; Iriawan EP, Nur Azhary
JST (Jurnal Sains Terapan) Vol 9, No 2 (2023): JST (Jurnal Sains Terapan)
Publisher : Pusat Penelitian dan Pengabdian kepada Masyarakat, Politeknik Negeri Balikpapan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32487/jst.v9i2.1716

Abstract

Kebutuhan peralatan otomatis dalam setiap bidang semakin meningkat karena pertimbangan sifat yang praktis dan efisiens termasuk kebutuhan spiritual. Kegiatan spiritual yang dapat menerapkan teknologi yaitu pada proses pengambilan air wudu. Pemanfaatkan arduino dan sensor ultrasonik PING HC-SR04 sebagai pendeteksi jarak benda dapat membuat keran menjadi otomatis sehingga praktis. Prinsip kerja keran otomatis ini apabila solenoid akan aktif saat sensor mendeteksi objek di bawah keran pada jarak 5 hingga 40 cm. Sudut deteksi maksimum adalah 40°.
Transforming the Diabetes Mellitus Diagnosis and Treatment Using Data Technology: Comprehensive Analysis of Deep Learning and Machine Learning Methodologies Anggriani, Dwi; Mustamin, Syaiful Bachri; Sahriani; Atnang, Muhammad; Fatmah, Siti; Mar, Nur Azaliah; Fajar, Nurhikmah
Journal of Scientific Insights Vol. 1 No. 1 (2024): June
Publisher : Science Tech Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69930/jsi.v1i1.71

Abstract

Recent research in health data analysis has transformed our understanding, prediction, and management of diabetes mellitus. This review explores various approaches used in related studies to enhance understanding and management strategies of diabetes through data analysis. Various data analysis methods, including machine learning such as neural networks, Gaussian Process Classification (GPC), and deep learning, have been used to enhance illness management and forecast accuracy. One of the included studies created customised care plans and used data to forecast the likelihood of complications in diabetes.. Another focused on comparative approaches for diabetes diagnosis using artificial intelligence, while others explored disease classification techniques using GPC algorithms. On the other hand, some studies utilized deep learning to identify diverse trajectories of type 2 diabetes from routine medical records, while others developed wide and deep learning models to predict diabetes onset. This review notes that data analysis approaches have significantly advanced accuracy in diagnosis, predictive modeling, and disease management of diabetes. Integrating these technologies allows for more personalized treatment approaches, where patient data can tailor individualized care strategies. Study findings indicate that machine learning and deep learning applications not only enhance prediction accuracy but also unlock new potentials in identifying risk factors, managing complications, and preventing diseases. Thus, this review provides profound insights into how data analysis has shifted paradigms in diabetes management, extending beyond diagnosis and treatment to encompass prevention and long-term management of chronic diseases. These studies lay a robust foundation for further research in developing more sophisticated and effective approaches in health data analysis, ultimately aiming to enhance the overall quality of life for patients with diabetes.
Research Techniques for IoT Use, Wearable Technology, and Smart Sensors in Mental Well-Being: A Literature Review from Several Studies Sahriani; Surahmawanti, Mita; Samsidar; Fatmah, Siti; Mustamin, Syaiful Bachri; Atnang, Muhammad; Fajar, Nurhikmah; Mar, Nur Azaliah
Journal of Scientific Insights Vol. 1 No. 1 (2024): June
Publisher : Science Tech Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69930/jsi.v1i1.72

Abstract

This study reviews the literature on the application of technology to wearables, smart sensors, and the Internet of Things (IoT) in the monitoring and treatment of mental health. Several studies analyzed employ systematic review, experimental, and literature survey approaches to explore various aspects of technology implementation in the context of mental health. The studies adopt a systematic review design without involving specific samples or measurement tools but highlight the application of IoT in mental health monitoring. Meanwhile, other studies conduct systematic reviews encompassing 41 studies utilizing smart devices and wearable technology in mental health monitoring, yet without specifying the software used. Another research proposes an experimental design to test a wearable sensor-based machine learning stress monitoring system. On the other hand, there are literature survey reports on the use of wearable sensors in mental health monitoring without providing details of the reviewed study methodologies. Other studies explore the literature using a scoping review method to gather information on mental health technology, identifying 37 relevant scientific articles. This review emphasizes the need for rigorous methodological approaches to effectively understand and apply technology in mental health monitoring and intervention. Overall, this literature review highlights the importance of developing technology that can enhance mental health monitoring and intervention. The application of IoT, wearable devices, and smart sensors can be a potential solution but requires a multidisciplinary approach and meticulous methodology to optimize their use in clinical practice
A Review on Growth Factors in Digital Start-ups: Digital Marketing, Scaling, Adaptation, Advanced Tech Fatmah, Siti; Samsidar; Atnang, Muhammad; Mustamin, Syaiful Bachri; Sahriani; Mar, Nur Azaliah; Fajar, Nurhikmah
Journal of Scientific Insights Vol. 1 No. 1 (2024): June
Publisher : Science Tech Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69930/jsi.v1i1.73

Abstract

Understanding MRBS (Massive and Rapid Business Scaling) is critical in the context of digital start-ups as it helps maximize the use of limited office space, better manage time, and support effective collaboration. This study aims to explore the concept of MRBS in the context of digital start-ups and identify the factors that drive the phenomenon. The focus of this study is on the significant increase in MRBS driven by recent advances in digitization, despite only about 3% of start-ups ever reaching a market valuation of $1 billion (USD) or more. Using an inductive qualitative research approach through 53 semi-structured interviews with start-up founders, executives, and advisors, this study seeks to fill the gap in previous literature that has not comprehensively explored the drivers of MRBS in the context of digital start-ups. The findings of this study reveal seven core drivers that contribute to the MRBS process, namely access to capital, product innovation, technology adoption, competent team, marketing strategy, networks and partnerships, and scale of operations. In addition, this study also identified several areas of tension that arise in the MRBS process, such as pressure for rapid growth, risk of failure, and challenges in maintaining corporate culture. Other related literature studies also explored the potential impact of extended digital marketing and its influence on the growth of startups. This research develops a macrodynamic framework that describes the drivers of startup growth supported by digital marketing and analyzes the differences in the use of B2B and B2C digital marketing, as well as the impact of new technologies on digital marketing. The results of these two studies are expected to provide researchers and practitioners with valuable insights into the MRBS phenomenon and the potential of digital marketing in supporting startup growth. Thus, this research contributes to understanding how start-ups can achieve large and rapid business scale in today's digital era.
Smart Sensors and Intelligent Analysis: A Literature Review on More Effective Early Warning Systems with IoT and Machine Learning Mustamin, Syaiful Bachri; Atnang , Muhammad; Sahriani , Sahriani; Fajar, Nurhikmah; Sari, Sri Kurnian; Pahlawan , Muammar Reza; Amrullah, Mujahidin
Journal of Scientific Insights Vol. 1 No. 4 (2024): December
Publisher : Science Tech Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69930/jsi.v1i4.182

Abstract

The IoT system described in the article "LoRaWAN-Based IoT System Implementation for Long-Range Outdoor Air Quality Monitoring" monitors air quality in real-time and transmits data through a LoRaWAN network to a public IoT platform. It measures seven key air quality parameters: nitrogen dioxide (NO₂), sulfur dioxide (SO₂), carbon dioxide (CO₂), carbon monoxide (CO), PM2.5, temperature, and humidity. These parameters were chosen for their significant effects on air quality and human health. NO₂ and SO₂ come from fossil fuel combustion and can cause respiratory issues and acid rain. CO₂ contributes to climate change, while CO is toxic and harmful to health. PM2.5 particles can lead to respiratory and cardiovascular problems. The system uses sensors connected to an Arduino microcontroller to collect data, which is transmitted through a LoRa Shield to a LoRaWAN gateway. Data is then sent to The Things Network (TTN), integrated with ThingSpeak, and displayed on a web dashboard. Additionally, it is synchronized with the Virtuino smartphone app for mobile monitoring. The system has been validated by comparing its data to Aeroqual air quality monitors, demonstrating reliable real-time monitoring and transmission of air quality information over the internet.
The Application of Machine Learning and Intelligent Sensors for Real-Time Air Quality Monitoring: A Literature Review Mustamin, Syaiful Bachri; Atnang, Muhammad; Sahriani, Sahriani; Fajar, Nurhikmah; Sari, Sri Kurnian; Pahlawan , Muammar Reza; Amrullah, Mujahidin
Journal of Scientific Insights Vol. 1 No. 3 (2024): October
Publisher : Science Tech Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69930/jsi.v1i3.183

Abstract

Air pollution is a global issue that has major consequences for human health and the environment. Accurate air quality prediction plays an important role in mitigating and preventing the negative impacts of air pollution. The thirteen sources analyzed in this literature study show a growing trend in the use of machine learning for air quality prediction, driven by the limitations of traditional methods and machine learning capabilities in efficiently processing complex data. This literature study examines a variety of commonly used machine learning models, such as Support Vector Regression (SVR), Random Forest, Gradient Boosting, and Long Short-Term Memory (LSTM), and evaluates their performance based on metrics such as RMSE, MAE, and R². The sources also highlight the importance of understanding the factors that affect air quality, including concentrations of various pollutants (PM2.5, PM10, NO2, CO, SO2, and ozone), meteorological data (temperature, humidity, wind speed, air pressure, precipitation, and temperature inversion), traffic data, and spatial-temporal variations. The integration of the Internet of Things (IoT) and machine learning is the main focus in the development of real-time air quality monitoring systems. IoT sensors enable the collection of real-time air quality and meteorological data, which are then processed using machine learning models to generate predictions. This literature study identifies several challenges in air quality prediction, such as data limitations, the complexity of air pollution dynamics, and ethical & privacy considerations. However, machine learning offers great potential to improve the accuracy of air quality predictions and monitoring, thus contributing to a healthier and more sustainable environment.
Inovasi Pembelajaran Mesin untuk Deteksi Malware: Analisis Komprehensif dan Tinjauan Literatur Samsidar; Mustamin, Syaiful Bachri; Atnang, Muhammad; Sahriani; Fajar, Nurhikmah
Jurnal Teknologi dan Sains Modern Vol. 1 No. 1 (2024): Mei-Juni
Publisher : CV. Science Tech Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69930/jtsm.v1i1.58

Abstract

Penelitian tentang deteksi malware menggunakan pembelajaran mesin dan teknik deep learning telah menjadi topik yang menarik dalam beberapa tahun terakhir. Kombinasi fitur statis dan dinamik telah terbukti efektif dalam meningkatkan akurasi deteksi hingga 95%, sementara pendekatan ensemble learning juga menunjukkan peningkatan yang signifikan, mencapai akurasi hingga 97% untuk malware nol-hari. Implikasi temuan ini sangat penting dalam konteks keamanan siber, dengan kemampuan deteksi yang lebih baik dapat membantu melindungi sistem dan infrastruktur kritis dari serangan malware yang semakin canggih. Namun, ada beberapa batasan dalam penelitian ini, termasuk fokus yang terbatas pada tinjauan literatur dan tidak mencakup evaluasi eksperimental langsung. Oleh karena itu, penelitian lanjutan diperlukan untuk menguji metode ini pada dataset yang lebih beragam dan lingkungan operasional yang lebih realistis. Kontribusi dari penelitian ini terletak pada pengembangan solusi deteksi malware yang lebih efektif dan akurat menggunakan pendekatan pembelajaran mesin dan deep learning. Pertanyaan dan arah penelitian baru termasuk investigasi efektivitas metode dalam lingkungan produksi, pengembangan model hibrid yang menggabungkan pembelajaran mesin dengan teknik lain, serta eksplorasi penggunaan pembelajaran mesin untuk deteksi malware pada perangkat Internet of Things (IoT). Penelitian ini juga menyoroti pentingnya mempertimbangkan variabel tambahan seperti kompleksitas malware, metode penyebaran, dan dampak terhadap sistem target dalam penelitian mendatang. Secara keseluruhan, temuan ini mendukung gagasan bahwa pembelajaran mesin dan deep learning memiliki potensi besar dalam mengatasi tantangan deteksi malware yang semakin kompleks dan dinamis, dengan implikasi yang luas dalam meningkatkan keamanan siber.
Studi Literatur Deep Learning dan Machine Learning untuk Analisis dan Prediksi Pasar Saham: Metodologi, Representasi Data, dan Studi Kasus Sari, Eka Purnama; Mustamin, Syaiful Bachri; Atnang, Muhammad; Sahriani; Fajar, Nurhikmah
Jurnal Teknologi dan Sains Modern Vol. 1 No. 1 (2024): Mei-Juni
Publisher : CV. Science Tech Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69930/jtsm.v1i1.59

Abstract

Penelitian ini mengkaji penggunaan model Machine Learning (ML) dan Deep Learning (DL) untuk peramalan harga saham, sebuah topik yang semakin relevan di sektor keuangan. Model ensemble "Random Forest + XG-Boost + LSTM" terbukti memiliki kinerja yang lebih baik dibandingkan model ML dan DL lainnya, menunjukkan bahwa integrasi model dapat meningkatkan akurasi prediksi. Penelitian lain juga menyoroti potensi jaringan deep learning untuk analisis pasar saham, menemukan bahwa jaringan saraf dapat mengekstrak informasi tambahan yang meningkatkan kinerja prediksi, meskipun sangat bergantung pada representasi data yang digunakan. Penggabungan variabel sentimen publik dari media sosial dengan variabel teknis dapat meningkatkan akurasi prediksi, terutama dalam kondisi pasar yang tidak stabil. Berdasarkan tinjauan pustaka komprehensif terhadap lebih dari 150 artikel dan menemukan bahwa algoritma ML, terutama RNN, menunjukkan kinerja unggul dalam prediksi pasar keuangan. Model yang menggunakan sentimen dari media sosial untuk memprediksi pergerakan harga saham, menunjukkan bahwa informasi sentimen dapat memberikan informasi tambahan yang signifikan untuk prediksi. Penelitian-penelitian ini menegaskan pentingnya penggunaan model ML dan DL dalam peramalan harga saham serta manfaat integrasi variabel non-teknis seperti sentimen dari media sosial dengan variabel teknis. Meski demikian, diperlukan penelitian lebih lanjut untuk memperluas cakupan data dan menguji generalisasi model pada berbagai pasar saham global serta periode waktu yang lebih panjang.
Teknologi Terkini dalam Pemantauan Infrastruktur: Tinjauan Literatur tentang Penerapan IoT dalam Pemantauan Kualitas Air dan Deteksi Retak Permukaan Jalan Samsidar; Kiki; Mustamin, Syaiful Bachri; Atnang, Muhammad; Sahriani; Fajar, Nurhikmah
Jurnal Teknologi dan Sains Modern Vol. 1 No. 1 (2024): Mei-Juni
Publisher : CV. Science Tech Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69930/jtsm.v1i1.60

Abstract

Pemantauan kualitas air dan deteksi retak permukaan jalan merupakan dua bidang penting dalam teknologi infrastruktur dan lingkungan. Artikel-artikel yang dipelajari dalam tinjauan ini memberikan wawasan mendalam tentang perkembangan terkini dalam kedua bidang tersebut, dengan fokus utama pada penerapan Internet of Things (IoT) dan teknik pengolahan citra digital. Pembahasan dalam beberapa artikel meliputi tinjauan terhadap sistem pemantauan kualitas air berbasis IoT untuk aplikasi domestik. Tinjauan ini mengidentifikasi tren, teknik, dan tantangan terkini dalam sistem tersebut, memberikan wawasan tentang potensi pemanfaatan teknologi IoT untuk pengembangan sistem pemantauan kualitas air yang lebih efisien dan aman. Implikasi dari temuan ini mencakup meningkatnya pemantauan kualitas air secara real-time untuk menjamin keamanan air minum dan potensi penerapan teknologi IoT dalam skala yang lebih luas seperti kota pintar. Namun, keterbatasan utama adalah ketiadaan studi empiris yang menguatkan temuan literatur. Pada artikel lainnya membahas pengembangan metode deteksi retak pada permukaan jalan menggunakan teknik non-lokal dalam pengolahan citra digital. Temuan ini mengungkapkan bahwa metode denoising dan peningkatan kualitas citra non-lokal dapat meningkatkan akurasi deteksi retak pada permukaan jalan, yang berpotensi digunakan dalam pemantauan kondisi jalan dan perencanaan pemeliharaan infrastruktur. Kontribusi dari penelitian ini adalah pengembangan metode deteksi retak yang lebih akurat, meskipun batasan utamanya adalah kurangnya informasi tentang validasi hasil secara lebih komprehensif.
Co-Authors Amrullah, Mujahidin Anggriani, Dwi Atnang , Muhammad Atnang, Muhammad Eka Purnama Sari, Eka Purnama Kiki Konasara, Zakiyah Muhammad Arif Wibisono, Muhammad Arif Mustamin, Syaiful Bachri Nur Azaliah MAR, Nur Azaliah Nur Azhary Iriawan Eka Putra Nurul Hidayatullah, Nurul Pahlawan , Muammar Reza Ramli, Agus Salim Sahriani Sahriani , Sahriani Sahriani, Sahriani Samsidar Sari, Sri Kurnian Siti Fatmah, Siti Surahmawanti, Mita