Donny Maulana

Mr. Donny Maulana

Directorate of Information Technology, Pelita Bangsa University, Bekasi, Jawa Barat, Indonesia
+1
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 January 2026 in Computers
Verified
Journal Article
Open access
PDF file
Donny MaulanaDonny Maulana
Donny Maulana
RRR Kanesaraj Ramasamy
R Kanesaraj Ramasamy
Real-time visual inference on resource-constrained hardware remains a core challenge for edge computing and embedded artificial intelligence systems. Recent deep learning architectures, particularly Vision Transformers (ViTs) and Detection Transformers (DETRs), achieve high detection accuracy but impose substantial computational and memory demands that limit their deployment on low-power edge platforms such as NVIDIA Jetson and Raspberry Pi devices. This paper presents a systematic review of model compression and optimization strategies—specifically quantization, pruning, and knowledge distillation—applied to lightweight object detection architectures for edge deployment. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, peer-reviewed studies were analyzed from Scopus, IEEE Xplore, and ScienceDirect to examine the evolution of efficient detectors from convolutional neural networks to transformer-based models. The synthesis highlights a growing focus on real-time transformer variants, including Real-Time DETR (RT-DETR) and low-bit quantized approaches such as Q-DETR, alongside optimized YOLO-based architectures. While quantization enables substantial theoretical acceleration (e.g., up to 16× operation reduction), aggressive low-bit precision introduces accuracy degradation, particularly in transformer attention mechanisms, highlighting a critical efficiency-accuracy tradeoff. The review further shows that Quantization-Aware Training (QAT) consistently outperforms Post-Training Quantization (PTQ) in preserving performance under low-precision constraints. Finally, this review identifies critical open research challenges, emphasizing the efficiency–accuracy tradeoff and the high computational demands imposed by Transformer architectures. Future directions are proposed, including hardware-aware optimization, robustness to imbalanced datasets, and multimodal sensing integration, to ensure reliable real-time inference in practical agricultural edge computing environments.

30 November 2023 in Journal of Applied Intelligent System
Verified
Journal Article
Open access
PDF file
AAAlfin Abdurrafi
Alfin Abdurrafi
Donny MaulanaDonny Maulana
Donny Maulana
NKNanang Tedi Kurniadi
Nanang Tedi Kurniadi
The use of IoT sensors in technology is a fascinating research subject due to the possibility of real-time monitoring of water usage and temperature effects. Developing tools and systems that make observations of water usage through Max6675 sensors can optimize data collection and processing through remote monitoring. Utilizing the IoT technique, the ESP8266 WeMOS D1 R2 microcontroller and the Max6675 temperature sensor are utilized to regulate the water pump via a relay. This approach enhances water sustainability for plant assumptions based on the predetermined temperature. The device activates the water pump when the temperature surpasses the standard level at the observation site. The outcome indicated that this device operates accordingly with a 100% success rate. The device was determined to function effectively by activating the water pump based on temperature. Additionally, it can provide real-time monitoring data and process sensor data for analysis.

31 July 2023 in Journal of Applied Intelligent System
Verified
Journal Article
Open access
PDF file
MAMajid Aminurdin
Majid Aminurdin
Donny MaulanaDonny Maulana
Donny Maulana
TWTri Ngudi Wiyatno
Tri Ngudi Wiyatno
Nowadays, there are many online travel agencies (OTAs) in Indonesia that provide various options for their customers. Before choosing which OTA to use, customers usually check each platform to ensure that they offer the best service. Traveloka is the most preferred OTA app by 67.5% of respondents. Google Play Store reviews show that users are still confused with information such as pricing and proper payment. Some features do not work properly when making hotel reservations. User Experience Questionnaire is used to quickly measure the user experience level of the product. Attractiveness, perspiculty, efficiency, accuracy, stimulation, and novelty were the six UEQ scales used. A random sample of one hundred app users was selected. The results showed that each scale was overall excellent. The criteria of attractiveness 2.485 ? 1.750, perspiculty 2.290 ? 1.900, efficiency 2.448 ? 1.780, dependability 2.338 ? 1.650, stimulation 2.393 ? 1.550, and novelty 2.293 ? 1.400. This research achieves the objectives or features of the application in terms of design, systems, and services. the result is that the Traveloka application can improve perspiculty with existing functions, so that the hotel booking process becomes easier to understand, easy to learn, simple, and clear.

1 December 2023 in International Journal Software Engineering and Computer Science (IJSECS)
Verified
Journal Article
Open access
PDF file
HYHamdi Yansyah
Hamdi Yansyah
SFSifa Fauziah
Sifa Fauziah
Donny MaulanaDonny Maulana
Donny Maulana
Spare parts encompass various items that are offered, owned, utilized, or consumed to fulfill consumer desires and requirements. This research implements the K-Nearest Neighbor algorithm on a test dataset consisting of 100 data objects, resulting in a novel classification perspective. The study includes a comprehensive model evaluation process involving Cross Validation on both training and testing datasets, comprising 1000 records with 36 critical and 64 non-critical outcomes. Performance assessment and testing utilizing the RapidMiner Studio application yield optimal results under various modeled scenarios. The accuracy of this algorithm model stands at 98.00%, with a standard deviation of +/- 4.00%.

1 January 2023 in AIP Conference Proceedings
Verified
Conference Paper
Open access
PDF file
AMAmali
Amali
Donny MaulanaDonny Maulana
Donny Maulana
EWEdy Widodo
Edy Widodo
ANAgung Nugroho
Agung Nugroho
With the development of Internet of things (IoT) technology, as well as a well-integrated solar energy source that can be operated, monitored, controlled remotely as a technology that continues to be developed. The design of an IoT- based solar energy system for PLTS at the Assyifa Islamic Boarding School Laboratory in Subang Regency as an active contribution to dealing with air pollution as well as renewable energy solutions and handling air pollution as well as solutions for the current depletion of fossil energy sources. The system is planned with solar panels, inverter and electric current controller, which has built-in WiFi connectivity. Solar panels and other devices provide the necessary operating power, sensor controllers mounted on solar panels, irradiant, power distribution panels as well as electricity production and loads that are monitored at the research site points. The PV Syst 7.2.8 design simulator is used to compare the use of 4 combination options from 2 brands of Solar Panels and 2 brands of Inverters for the capacity of PLTS On-Grid 2025Wp. Utilization of building roofs or vacant land for solar power generation is an effective and efficient solution. This study is to compare 4 combination models and see the feasibility of the performance and economic value, calculate the average return on investment under 10 years which produces electrical energy of 4.23kwh/kwp/day and refers to the warranty period for the solar panels themselves. Indonesia is located on the equator and has the availability of sunlight throughout the year.

4 April 2024 in Jurnal Teknik Informatika (Jutif)
Verified
Journal Article
Open access
PDF file
SDSteven Ryan Darmawan
Steven Ryan Darmawan
MFMuhamad Fatchan
Muhamad Fatchan
Donny MaulanaDonny Maulana
Donny Maulana
The potential difference between the popularity of presidential candidates on social media and in the general public poses a serious challenge in predicting the outcome of the 2024 presidential election. Technical constraints in collecting, cleaning and analyzing dynamic and large-scale social media data can threaten the accuracy and validity of predictions. To overcome this problem, careful steps and in-depth understanding are needed. Therefore, this study aims to predict the winner of the 2024 presidential election from the popularity of presidential candidates Anies Baswedan, Ganjar Pranowo, and Prabowo Subianto on Twitter. The K-Nearest Neighbor (K-NN) method with the Both Metric approach (Euclidean and Chebyshev) was used to analyze 51,192 tweet data through the Knowledge Discovery in Database (KDD) stage using Orange software. The evaluation results show almost the same performance, with AUC values of 0.725 for Euclidean and 0.720 for Chebyshev. The CA result was 55.6% for Euclidean and 55.4% for Chebyshev. Although F1, precision, and recall were almost the same, overall, the Euclidean metric was better. The prediction shows Prabowo Subianto as the most popular candidate on Twitter. Nonetheless, these results need to be interpreted with caution and strengthened with further analysis and additional data to get a more comprehensive conclusion. This research shows that K-NN with both metrics can provide predictions above 50%, reliable enough to be able to predict the most popular candidates on Twitter.