Garuda - Garba Rujukan Digital

Pengenalan Pola Depresi Berbasis Suara Menggunakan Ekstraksi Fitur Mel-Frequency Cepstral Coefficients Saputro, Wahju Tjahjo; Fadlil, Abdul; Murinto, Murinto
Jurnal PROCESSOR Vol 20 No 2 (2025): Jurnal Processor
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/processor.2025.20.2.2513

The identification of depression patterns from human voices is important because depression can interfere with activities, reduce interest in learning, and hinder socialisation. Depression is a significant problem today because there has been a global increase in the number of people suffering from it. The factors contributing to depression are numerous and complex, and can affect all groups, from children to the elderly. The purpose of this study was to identify depression patterns based on voice feature extraction. The feature extraction method used is Mel-Frequency Cepstral Coefficients (MFCC). The MFCC method is capable of extracting features that closely resemble the human auditory system. The dataset used is the EATD-Corpus, which contains 162 recordings of students from Tongji University in China. The results of the study show that depression and healthy patterns can be distinguished using MFCC parameters, namely 25 measurements per frame, 10 frame intervals, an alpha value of 0.97 as the pre-emphasis coefficient, a maximum of 40 Mel filterbank coefficients, and 12 cepstral coefficients. Classification thresholds can be obtained for two classes: healthy with thresholds < 53.00 and depressed ≥ 53.00 using the Self-Rating Depression Scale.

Pemberdayaan Kelompok Guru Sekolah Dasar Dalam Upaya Mengembangkan Kemampuan Numerasi Siswa Melalui NICE (Nusantara Interactive E-Comic Berbasis Android) Saputro, Wahju Tjahjo; Ratnaningsih, Arum; Wibowo, Teguh; Purwoko, Riawan Yudi; Purwaningrum, Jayanti Putri
KOMUNITA: Jurnal Pengabdian dan Pemberdayaan Masyarakat Vol 4 No 4 (2025): November
Publisher : PELITA NUSA TENGGARA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60004/komunita.v4i4.250

Kemampuan numerasi merupakan bagian penting dari literasi dasar yang harus dimiliki siswa untuk menghadapi berbagai permasalahan kehidupan nyata. Namun, hasil asesmen nasional dan studi internasional seperti PISA menunjukkan bahwa kemampuan numerasi siswa Indonesia masih tergolong rendah. Salah satu faktor penyebabnya adalah pendekatan pembelajaran yang belum kontekstual dan minim penggunaan media yang relevan dengan kehidupan siswa. Kegiatan pengabdian ini bertujuan untuk memberdayakan kelompok guru sekolah dasar dalam mengembangkan pembelajaran numerasi berbasis konteks budaya lokal melalui media NICE (Nusantara Interactive E-Comic Berbasis Android). Kegiatan dilaksanakan di SDN Sindurjan, Kecamatan Purworejo, Kabupaten Purworejo, selama enam bulan, dengan melibatkan 11 guru sebagai peserta. Metode pelaksanaan terdiri dari empat tahapan utama: observasi dan identifikasi kebutuhan, pelatihan penggunaan media NICE, pendampingan implementasi di kelas, serta evaluasi terhadap hasil pembelajaran. Hasil kegiatan menunjukkan peningkatan kompetensi guru dalam menyusun dan menerapkan pembelajaran numerasi kontekstual berbasis media digital dan etnomatematika. Siswa menunjukkan ketertarikan lebih tinggi terhadap materi numerasi, serta keterlibatan aktif dalam proses pembelajaran. Pemberdayaan guru melalui pendekatan praktik langsung (learning by doing), penggunaan media berbasis budaya, dan pendampingan berkelanjutan terbukti efektif dalam meningkatkan kualitas proses dan hasil pembelajaran. Media NICE juga mendorong kolaborasi antar guru melalui komunitas belajar yang terbentuk selama kegiatan. Program ini menunjukkan bahwa pembelajaran numerasi yang menyenangkan, kontekstual, dan relevan sangat mungkin diwujudkan melalui inovasi berbasis teknologi dan lokalitas.

INOVASI PENGHITUNGAN KENDARAAN PADA MANAJEMEN PARKIR DENGAN SENSOR INFRARED BERBASIS IOT Hanifatus Sa’diyah Widihasaniputri; Wahju Tjahjo Saputro; Hamid Muhammad Jumasa
TEKNIMEDIA: Teknologi Informasi dan Multimedia Vol. 6 No. 2 (2025): Desember 2025
Publisher : Badan Penelitian dan Pengabdian Masyarakat (BP2M) STMIK Syaikh Zainuddin NW Anjani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46764/teknimedia.v6i2.280

Traffic and parking management are still major issues in urban areas. The average driver spends 7.8 minutes to find a parking space, and 30% of traffic congestion is caused by finding a parking space.This research focuses on designing a system that adopts infrared sensors and IoT to detect the number of vehicles in a smart parking system.The method used is the prototype method. The process starts with activating the device to monitor vehicles entering and leaving the parking area. Next, the detected vehicles will be checked, if the vehicle enters then the system automatically reduces the number of available parking slots. Conversely, if the vehicle exits, the system adds one slot to the number of available parking slots. the results of component testing carried out, found that all components, including infrared sensors, PIR sensors, LCDs, servo motors, and Arduino Uno R3 microcontrollers, have functioned properly. This is supported by the average system response delay test which only reaches 1.50 seconds and is included in the responsive category for smart parking systems

Kompresi Adaptif untuk Streaming Multimedia Multi-Platform: A Review Ekawati, Nia; Tresnawati, Shandy; Hanief, Shofwan; Saputro, Wahju Tjahjo
INTEK : Jurnal Informatika dan Teknologi Informasi Vol. 8 No. 2 (2025)
Publisher : Program Studi Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37729/intek.v8i2.7167

The current digital era is characterized by cross-platform multimedia consumption, which has become the backbone of information and entertainment, with video content dominating more than 82% of total global internet traffic. The main challenge of adaptive compression for multi-platform multimedia streaming lies in device heterogeneity, network conditions, and the need for Quality of Experience (QoE), as adaptive compression adjusts the bitrate, resolution, and encoding level in real-time. The aim of this research is to explore these issues through a literature review study to identify the scope, taxonomy, gaps, and proposed future research directions. The method used is a literature review covering 51 publications (interval 2019-2025) to examine conceptual aspects, system taxonomy (System Architecture Layer, Adaptation Strategy, Compression Technique, and Artificial Intelligence Model), and to identify research gaps. The review results show that streaming efficiency depends on adaptive compression mechanisms, with a research paradigm shifting from rule-based adaptation toward intelligent adaptive compression. Despite these developments, significant unaddressed gaps remain, particularly concerning synchronization across platforms based on different codecs, low-latency real-time AI compression, robust network adaptation solutions for 5G/B5G, and cross-dimensional integration within a single framework. Future research directions are proposed in platform-specific synchronization models, multi-constraint compression, adaptive AI for slicing, and energy optimization through Federated Learning.

Improving Performance Convolutional Neural Networks Using Modified Pooling Function Achmad Lukman; Wahju Tjahjo Saputro; Erni Seniwati
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3763

The Visual Geometry Group-16 (VGG16) network architecture, as part of the development of convolutional neural networks, has been popular among researchers in solving classification tasks, so in this paper, we investigated the number of layers to find better performance. In addition, we also proposed two pooling function techniques inspired by existing research on mixed pooling functions, namely Qmax and Qavg. The purpose of the research was to see the advantages of our method; we conducted several test scenarios, including comparing several modified network configurations based on VGG16 as a baseline and involving our pooling technique and existing pooling functions. Then, the results of the first scenario, we selected a network that can adapt well to our pooling technique, whichwas then carried out several tests involving the Cifar10, Cifar100, TinyImageNet, and Street View House Numbers (SVHN) datasets as benchmarks. In addition, we were also involved in several existing methods. The experiment results showed that Net-E has the highest performance, with 93.90% accuracy for Cifar10, 71.17% for Cifar100, and 52.84% for TinyImageNet. Still, the accuracy was low when the SVHN dataset was used. In addition, in comparison tests with several optimization algorithms using the Qavg pooling function, it can be seen that the best accuracy results lie in the SGD optimization algorithm, with 89.76% for Cifar10 and 89.06% for Cifar100.

Sentiment Analysis of the Skyscanner Application on Google Play Store with a Comparison of Naive Bayes and Support Vector Machines Laely Triana; Wahju Tjahjo Saputro; Dewi Chirzah
Journal of Computer Science, Information Technology and Telecommunication Engineering Vol 7, No 1 (2026)
Publisher : Universitas Muhammadiyah Sumatera Utara, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30596/jcositte.v7i1.29212

The digital world is growing rapidly and has a significant impact on the tourism sector. Therefore, technology must adapt to developments to meet human needs. Travel booking services such as Skyscanner allow users to book flights, accommodation, and transportation online through the app. With the large number of Skyscanner user reviews on the Google Play Store. The majority of data reviews use Indonesian languanges; sentiment analysis is needed to determine user sentiment towards the app. This study aims to analyze user sentiment towards the Skyscanner app using collected user comment review data. The data is then classified into two sentiment classes: positive and negative. The classification results using a comparison of two algorithms, Naive Bayes and Support Vector Machine, SVM produced a higher accuracy of 89.74%. Naive Bayes achieves lower accuracy 82.08% than SVM. This concludes that the SVM algorithm is more effective in producing optimal classification accuracy than its comparison algorithm, Naive Bayes.

Optimizing Business Process To Government Using Business Process Improvement (BPI) and Bizagi Modeler (Case Study: PT. XYZ) Pangga Cahyo Dwiyono; Murhadi Murhadi; Wahju Tjahjo Saputro; Miftahul Huda; Matthew Nepomuceno
Justek : Jurnal Sains dan Teknologi Vol 9, No 1 (2026): March
Publisher : Unversitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/justek.v9i1.37752

Business to Government (B2G) processes frequently suffer from inefficiencies caused by manual workflows and limited system integration. This study aims to enhance B2G business process performance at PT XYZ by applying the Business Process Improvement (BPI) approach using Business Process Model and Notation (BPMN) implemented through Bizagi Modeler. The research methodology involves analysing the existing process, designing an optimized process model, and conducting performance simulations based on processing time, operational costs, data accuracy, delay risk, and institutional satisfaction. The results indicate significant improvements, including a 41.7% reduction in processing time, a 26.7% decrease in operational costs, a 90% increase in data accuracy, a 40.9% reduction in delay risk, and an 85% improvement in institutional satisfaction. These findings demonstrate that the integration of BPI and BPMN effectively improves the efficiency and quality of B2G business processes in government procurement.

Utilization of ChatGPT and Artificial Intelligence in Educational Transformation: Trends, Challenges, and Effects on the Learning Process Bintang Fauzan Rayadika; Wahju Tjahjo Saputro; Dewi Chirzah; Zohaib Hassan Sain; Abdul Said Bin Ambotang
Justek : Jurnal Sains dan Teknologi Vol 9, No 1 (2026): March
Publisher : Unversitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/justek.v9i1.37606

This study aims to identify and analyse the relationship between the level of student dependence on Artificial Intelligence (AI) applications, particularly ChatGPT, and its impact on their critical thinking skills, in line with educational transformation issues in the digital era. This quantitative research employed a convenience non-probability sampling approach, involving 112 student respondents in Indonesia. Data were analysed using reliability tests, normality tests, and the Paired Sample T-test. The findings indicate a high level of ChatGPT usage (Mean Score, M = 4.12), confirming students' enthusiasm for utilizing the tool for learning effectiveness and time efficiency. However, the statistical test revealed a significant difference between the level of ChatGPT usage and students' critical thinking ability (Sig. (2-tailed) = 0.009 < 0.05). This difference suggests that excessive reliance on the tool has the potential to impede the development of social and collaboration skills, and may significantly reduce students' learning independence and critical thinking ability. The study concludes that educational institutions must promptly formulate wise policies to guide students in optimally utilizing AI as a learning assistant, not as a substitute for the thinking process to ensure a balanced and sustainable educational transformation.

INOVASI PENGHITUNGAN KENDARAAN PADA MANAJEMEN PARKIR DENGAN SENSOR INFRARED BERBASIS IOT Hanifatus Sa’diyah Widihasaniputri; Wahju Tjahjo Saputro; Hamid Muhammad Jumasa
TEKNIMEDIA: Teknologi Informasi dan Multimedia Vol. 6 No. 2 (2025): Desember 2025
Publisher : Badan Penelitian dan Pengabdian Masyarakat (BP2M) STMIK Syaikh Zainuddin NW Anjani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46764/teknimedia.v6i2.280

Traffic and parking management are still major issues in urban areas. The average driver spends 7.8 minutes to find a parking space, and 30% of traffic congestion is caused by finding a parking space.This research focuses on designing a system that adopts infrared sensors and IoT to detect the number of vehicles in a smart parking system.The method used is the prototype method. The process starts with activating the device to monitor vehicles entering and leaving the parking area. Next, the detected vehicles will be checked, if the vehicle enters then the system automatically reduces the number of available parking slots. Conversely, if the vehicle exits, the system adds one slot to the number of available parking slots. the results of component testing carried out, found that all components, including infrared sensors, PIR sensors, LCDs, servo motors, and Arduino Uno R3 microcontrollers, have functioned properly. This is supported by the average system response delay test which only reaches 1.50 seconds and is included in the responsive category for smart parking systems

Pengembangan Smart Lighting Berbasis ESP32 dan Blynk untuk Mendukung Smart Village Wahju Tjahjo Saputro; Hamid Muhammad Jumasa; Murhadi
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 2 (2026): Mei 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i2.205

Efficient public lighting infrastructure plays a crucial role in supporting the development of smart villages. However, conventional street lighting systems are often energy-intensive and difficult to monitor and control remotely. This study aims to develop an Internet of Things (IoT)-based smart lighting system using the ESP32 WROOM microcontroller and the Blynk platform. The system was developed following the ADDIE framework, which consists of Analysis, Design, Development, Implementation, and Evaluation stages. The hardware components include an ESP32 WROOM DevKitC v4, a PZEM-004T v3 power monitoring module, a 2-channel optocoupler relay, and a smartphone. The software environment comprises Arduino IDE, Fritzing, EasyEDA, and Blynk as the user interface. Experimental results demonstrate that the proposed system can effectively monitor and control public lighting in real time through a smartphone from any location. The system exhibited fast response times, stable operation, and the potential to reduce electricity consumption by 23.33%. These findings indicate that the proposed solution effectively supports modern and energy-efficient smart village infrastructure while providing a low-cost, reliable, and easily deployable smart lighting model.

Title

Found 40 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 40 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 40 Documents
Search