Agung Mulyo Widodo

Mr. Agung Mulyo Widodo

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
18 March 2022 in Electronics
Verified
Journal Article
Open access
PDF file
Hsing-Chung ChenHsing-Chung Chen
Hsing-Chung Chen
AWAgung Mulyo Widodo
Agung Mulyo Widodo
AWAndika Wisnujati
Andika Wisnujati
MRMosiur Rahaman
Mosiur Rahaman
Jerry Chun-Wei LinJerry Chun-Wei Lin
Jerry Chun-Wei Lin
CWChien-Erh Weng
Chien-Erh Weng
With limited retrieval of reserves and restricted capability in plant pathology, automation of processes becomes essential. All over the world, farmers are struggling to prevent various harm from bacteria or pathogens such as viruses, fungi, worms, protozoa, and insects. Deep learning is currently widely used across a wide range of applications, including desktop, web, and mobile. In this study, the authors attempt to implement the function of AlexNet modification architecture-based CNN on the Android platform to predict tomato diseases based on leaf image. A dataset with of 18,345 training data and 4,585 testing data was used to create the predictive model. The information is separated into ten labels for tomato leaf diseases, each with 64 × 64 RGB pixels. The best model using the Adam optimizer with a realizing rate of 0.0005, the number of epochs 75, batch size 128, and an uncompromising cross-entropy loss function, has a high model accuracy with an average of 98%, a strictness rate of 0.98, a recall value of 0.99, and an F1-count of 0.98 with a loss of 0.1331, so that the classification results are good and very precise.

10 July 2024 in Aptisi Transactions on Technopreneurship (ATT)
Verified
Journal Article
Open access
PDF file
NANizirwan Anwar
Nizirwan Anwar
AWAgung Mulyo Widodo
Agung Mulyo Widodo
BSBinastya Anggara Sekti
Binastya Anggara Sekti
MUMuhamad Bahrul Ulum
Muhamad Bahrul Ulum
MRMosiur Rahaman
Mosiur Rahaman
HAHani Dewi Ariessanti
Hani Dewi Ariessanti
This research aims to compare the performance of two forensic investigation methods, the National Institute of Justice (NIJ) and the National Institute of Standards and Technology (NIST), specifically for evidence analysis of MicroSD cards. MicroSD cards are frequently used as external storage in various digital devices, making them critical in digital forensic investigations. The study evaluates the effectiveness of these methods using tools such as Access Data FTK Imager and autopsy. The NIJ method enthis comparative passes detailed stages of preparation, collection, examination, analysis, and reporting, while the NIST method includes stages of collection, examination, analysis, and reporting. Results indicate that the NIJ method provides more comprehensive and detailed results, while the NIST method offers a faster investigation process. Additionally, tables and graphs illustrating performance metrics are included to substantiate the findings. This comparative analysis provides valuable insights for technopreneurs in optimizing digital forensic methods for better data integrity and efficiency, ultimately enhancing decision-making processes in technological entrepreneurship. Furthermore, this study aligns with the United Nations' Sustainable Development Goals (SDGs), particularly Goal 9: Industry, Innovation, and Infrastructure, by promoting innovative forensic methods that support the development of resilient infrastructure and foster innovation in the digital age. This study highlights the importance of effective forensic methods in supporting technopreneurial ventures.

28 August 2023 in Journal of World Science
Verified
Journal Article
Open access
PDF file
DDDedy Dwiputra
Dedy Dwiputra
AWAgung Mulyo Widodo
Agung Mulyo Widodo
HAHabibullah Akbar
Habibullah Akbar
GFGerry Firmansyah
Gerry Firmansyah
This study focuses on applying data mining techniques, especially association rules mining using the Apriori and FP-GROWTH algorithms, for market basket analysis on PT. XYZ is a pharmaceutical company in Indonesia. A quantitative methodology uses a dataset of 100,498 transactions originating from 432,356 rows of data covering July to December 2022 in the JABODETABEK area. Apriori and FP-GROWTH algorithms are applied for association rules mining. The results show that FP-GROWTH has the fastest execution time of 84,655 seconds. However, the memory usage for the Apriori algorithm is the lowest at 482.32 MiB, with increments of: 0.21 MiB. For the rules generated, the two algorithms, both Apriori and FP-GROWTH, produce the same number of rules and values of support, confidence, lift, Bi-Support, Bi-Confidence, and Bi-Lift. In conclusion, Apriori is recommended for sales datasets if memory usage and ease of implementation are important. However, if the speed of execution time and a large amount of data are considered, FP-GROWTH is a better choice because the execution time is faster for large amounts of data. However, the choice of algorithm depends on the specific analysis objectives, itemset size, data scale, and computational capabilities. Results from association rules mining provide evidence of product popularity, purchasing patterns, and opportunities for strategic marketing and inventory management. These findings can help PT. XYZ improves business efficiency, understands customer behavior, and increases profitability.

9 October 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Hsing-Chung ChenHsing-Chung Chen
Hsing-Chung Chen
AWAgung Mulyo Widodo
Agung Mulyo Widodo
Jerry Chun-Wei LinJerry Chun-Wei Lin
Jerry Chun-Wei Lin
CWChien-Erh Weng
Chien-Erh Weng
Addressing the challenges of internet-based 5G technology, namely increasing density through micro-cell systems, frequency spectrum, and reducing resource costs, is needed to meet the use of IoT-based 6G technology with the goal of high-speed, high-capacity, and low-latency communication. In this research, we considered the coverage performance and ergodic capacity of the Reconfigurable Intelligent Surface (RIS)-aided cooperative nonorthogonal multiple-access network (NOMA) of an IoT system. This enables the upgrading of 5G- toward 6G-technology-based IoT systems. We developed a closest-form formula of near and far user coverage probabilities as a function of perfect channel statistical information (p-CSI) using only a single-input single-output (SISO) system with a finite number of RIS elements under the Nakagami-m fading channel. We also define ergodic capacity as a simple upper limit by simplifying the use of symbolic functions and it could be used for a sustained period. The simulation findings suggest that RIS-assisted NOMA has a reduced risk of outage than standard NOMA. All of the derived closed-form formulas agree with Monte Carlo simulations, indicating that the distant user’s coverage probability outperforms the nearby user. The bigger the number of RIS parts, however, the greater the chance of coverage. They also disclose the scaling law of the number of phase shifts at the RIS-aided NOMA based on the asymptotic analysis and the upper bound on channel capacity. In both arbitrary and optimum phase shifts, the distant user’s ergodic capacity outperforms the near user.

14 August 2024
Verified
Book Chapter
Closed access
AWAgung Mulyo Widodo
Agung Mulyo Widodo
PPPrincy Pappachan
Princy Pappachan
BSBinastya Anggara Sekti
Binastya Anggara Sekti
NANizirwan Anwar
Nizirwan Anwar
RWRiya Widayanti
Riya Widayanti
RBRitika Bansal
Ritika Bansal
Quantum-resistant cryptography develops cryptographic protocols and algorithms that can withstand attacks from quantum computers. Quantum computers can solve certain mathematical problems much faster than classical computers, making current encryption techniques like RSA and ECC vulnerable to quantum algorithms such as Shor's algorithm. To address this, quantum-resistant cryptography focuses on creating new algorithms based on mathematical problems that are difficult for quantum computers to solve efficiently. Examples include lattice-based, code-based, hash-based, and multivariate polynomial cryptography. The National Institute of Standards and Technology (NIST) is leading efforts to standardize these algorithms to ensure they are compatible with various systems and applications. While these quantum-resistant algorithms offer protection, they may involve higher computational complexity and larger key sizes compared to traditional methods, posing implementation challenges that ongoing research aims to address.

13 May 2025
Verified
Book Chapter
Closed access
NANizirwan Anwar
Nizirwan Anwar
BSBinastya Anggara Sekti
Binastya Anggara Sekti
AWAgung Mulyo Widodo
Agung Mulyo Widodo
NENixon Erzed
Nixon Erzed
HGHendry Gunawan
Hendry Gunawan
NBNugroho Budhisantosa
Nugroho Budhisantosa
Future trends in AI and green computing for security are crucial areas of research and development in the realm of information technology. The integration of artificial intelligence (AI) and machine learning (ML) in cloud computing is a significant trend that is enhancing data security and operational efficiency. AI is envisioned to play a pivotal role in empowering intelligent, adaptive, and autonomous security management in 5G and beyond networks, enabling faster and more accurate decisions. Additionally, AI is at the forefront of triggering digital security innovations to address emerging threats in the post-COVID-19 world. Moreover, the proactive use of AI in predicting and preventing cyberattacks before they occur is a promising approach to enhancing security measures. As AI continues to advance, it is expected to have a transformative influence on military power, strategic competition, and international security. The use of AI as force multipliers for defensive and offensive cyber weapons is anticipated to revolutionize cybersecurity.