Andrey Ferriyan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Andrey Ferriyan has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Achmad Husni Thamrin
Keio University
2 shared publications - Andi Nurkholis
UPN Veteran Yogyakarta
2 shared publications - Heru Cahya Rustamaji
Universitas Pembangunan Nasional Veteran Yogyakarta
2 shared publications - Jun Murai
Keio University, Tokyo 108-8345, Japan
2 shared publications - Keiji Takeda
Faculty of Environment and Information Studies, Keio University, Kanagawa 252-0882, Japan
2 shared publications - Panut Mulyono
Universitas Gadjah Mada
2 shared publications
Latest Publications
- Open Access
- 28 February 2026
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 12 (1) , 247-266
Non-destructive classification of sugarcane milling feasibility using deep learning: A comparative study of VGG19 and ResNet50
Assessing sugarcane quality is crucial for ensuring both economic value and processing efficiency in sugar production. Conventional approaches, such as refractometer-based Brix measurements, are destructive, labor-intensive, and unsuitable for large-scale or rapid field evaluations. This study proposes a non-destructive deep learning framework for classifying sugarcane internodes into two quality categories (< 16 °Bx and ≥16 °Bx) to address existing limitations. Two convolutional neural network architectures, VGG19 and ResNet50, were evaluated utilizing a defined transfer learning and data augmentation methodology. Because of its residual connections, which enable deeper and more stable feature learning, ResNet50 consistently outperformed VGG19, achieving the highest accuracy of 78.85% on the Luar2_Putih dataset. This comparative finding demonstrates that modern residual-based networks provide superior robustness for subtle visual classification tasks in agricultural imaging, while also validating the stability of the proposed two-phase training framework. The study advances AI-driven non-destructive quality assessment by offering a scalable, field-deployable solution that supports sustainable, efficient sugarcane processing in line with the UN Sustainable Development Goals (SDG 2, 9, and 12).
- 28 February 2026
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 12 (1) , 247-266
Open AccessNon-destructive classification of sugarcane milling feasibility using deep learning: A comparative study of VGG19 and ResNet50
Assessing sugarcane quality is crucial for ensuring both economic value and processing efficiency in sugar production. Conventional approaches, such as refractometer-based Brix measurements, are destructive, labor-intensive, and unsuitable for large-scale or rapid field evaluations. This study proposes a non-destructive deep learning framework for classifying sugarcane internodes into two quality categories (< 16 °Bx and ≥16 °Bx) to address existing limitations. Two convolutional neural network architectures, VGG19 and ResNet50, were evaluated utilizing a defined transfer learning and data augmentation methodology. Because of its residual connections, which enable deeper and more stable feature learning, ResNet50 consistently outperformed VGG19, achieving the highest accuracy of 78.85% on the Luar2_Putih dataset. This comparative finding demonstrates that modern residual-based networks provide superior robustness for subtle visual classification tasks in agricultural imaging, while also validating the stability of the proposed two-phase training framework. The study advances AI-driven non-destructive quality assessment by offering a scalable, field-deployable solution that supports sustainable, efficient sugarcane processing in line with the UN Sustainable Development Goals (SDG 2, 9, and 12).
- 30 December 2025
- Published by Universitas Pembangunan Nasional Veteran Yogyakarta in OPSI
- Vol. 18 (2) , 448-462
Feature-based classification of sugarcane quality using the K-nearest neighbor algorithm
The rapid advancement of artificial intelligence has enabled practical, data-driven approaches to agricultural quality assessment. However, many existing methods rely on complex sensor systems that are costly and difficult to deploy in the field. This study proposes a lightweight and interpretable K-Nearest Neighbor (KNN) model for non-destructive evaluation of sugarcane milling feasibility using five easily measurable physical attributes: relative distance ratio, internode length, mean diameter, circumference, and weight per centimeter. Samples with Brix less than 16 are categorized as not feasible for milling, while Brix equal to or greater than 16 are classified as possible. A dataset of 1,889 Bululawang samples collected in Malang, East Java, Indonesia, was evaluated across twenty-two scenarios that varied the train-test split, normalization method, distance metric, and neighborhood size. The optimal configuration, consisting of an 80:20 split, Standard normalization, the Minkowski distance metric, and k=75, achieved an accuracy of 78%. The findings confirm that physical measurements can serve as effective predictors of sugarcane quality and support data-driven inspection and sustainable resource utilization in line with SDGs 2, 9, and 12.
- 30 December 2025
- Published by Universitas Pembangunan Nasional Veteran Yogyakarta in OPSI
- Vol. 18 (2) , 448-462
Feature-based classification of sugarcane quality using the K-nearest neighbor algorithm
The rapid advancement of artificial intelligence has enabled practical, data-driven approaches to agricultural quality assessment. However, many existing methods rely on complex sensor systems that are costly and difficult to deploy in the field. This study proposes a lightweight and interpretable K-Nearest Neighbor (KNN) model for non-destructive evaluation of sugarcane milling feasibility using five easily measurable physical attributes: relative distance ratio, internode length, mean diameter, circumference, and weight per centimeter. Samples with Brix less than 16 are categorized as not feasible for milling, while Brix equal to or greater than 16 are classified as possible. A dataset of 1,889 Bululawang samples collected in Malang, East Java, Indonesia, was evaluated across twenty-two scenarios that varied the train-test split, normalization method, distance metric, and neighborhood size. The optimal configuration, consisting of an 80:20 split, Standard normalization, the Minkowski distance metric, and k=75, achieved an accuracy of 78%. The findings confirm that physical measurements can serve as effective predictors of sugarcane quality and support data-driven inspection and sustainable resource utilization in line with SDGs 2, 9, and 12.
- Open Access
- 7 October 2025
- Published by LP2M Universitas Islam Negeri (UIN) Syarif Hidayatullah Jakarta in Applied Information System and Management (AISM)
- Vol. 8 (2) , 297-304
Cocoa Land Suitability Analysis Using ID3 Spatial Algorithm
Cocoa production in Indonesia encounters ongoing challenges due to declining plantation areas and suboptimal land utilization. This study applies the ID3 Spatial algorithm to evaluate land suitability for cocoa cultivation in Bogor Regency, West Java Province. The methodology integrates nine basic land characteristics, including elevation, drainage, relief, base saturation, cation exchange capacity, soil texture, soil pH, and mineral soil depth, derived from field surveys conducted by BBSDLP. Two classification models were developed and tested using spatial data preprocessing techniques. Model M1 was the baseline approach without constraints, while Model M2 incorporated a minimum planted area threshold of ≥1 ha. The results show notable performance differences between models. Model M2 achieved a reasonable accuracy of 87.27% compared to Model M1’s 29.09%, with relief identified as the root node due to its higher gain value and reduced entropy. Classification results indicate that Bogor Regency’s cocoa cultivation potential comprises 16,443 ha of S2 (moderately suitable) land and 231,018 ha of S3 (marginally suitable) land. The generated land suitability map may provide stakeholders with helpful guidance for identifying potential cultivation areas. The result suggests that artificial intelligence integration, specifically the ID3 spatial algorithm, could improve land suitability evaluation processes, potentially supporting more informed agricultural development decisions.
- 7 October 2025
- Published by LP2M Universitas Islam Negeri (UIN) Syarif Hidayatullah Jakarta in Applied Information System and Management (AISM)
- Vol. 8 (2) , 297-304
Open AccessCocoa Land Suitability Analysis Using ID3 Spatial Algorithm
Cocoa production in Indonesia encounters ongoing challenges due to declining plantation areas and suboptimal land utilization. This study applies the ID3 Spatial algorithm to evaluate land suitability for cocoa cultivation in Bogor Regency, West Java Province. The methodology integrates nine basic land characteristics, including elevation, drainage, relief, base saturation, cation exchange capacity, soil texture, soil pH, and mineral soil depth, derived from field surveys conducted by BBSDLP. Two classification models were developed and tested using spatial data preprocessing techniques. Model M1 was the baseline approach without constraints, while Model M2 incorporated a minimum planted area threshold of ≥1 ha. The results show notable performance differences between models. Model M2 achieved a reasonable accuracy of 87.27% compared to Model M1’s 29.09%, with relief identified as the root node due to its higher gain value and reduced entropy. Classification results indicate that Bogor Regency’s cocoa cultivation potential comprises 16,443 ha of S2 (moderately suitable) land and 231,018 ha of S3 (marginally suitable) land. The generated land suitability map may provide stakeholders with helpful guidance for identifying potential cultivation areas. The result suggests that artificial intelligence integration, specifically the ID3 spatial algorithm, could improve land suitability evaluation processes, potentially supporting more informed agricultural development decisions.
- Open Access
- 31 May 2025
- Published by LP2M Universitas Islam Negeri (UIN) Syarif Hidayatullah Jakarta in Applied Information System and Management (AISM)
- Vol. 8 (1) , 29-36
Sentiment Analysis of COVID-19 Booster Vaccines on Twitter Using Multi-Class Support Vector Machine
The Indonesian government's implementation of a booster vaccination program as part of its COVID-19 response has generated diverse public reactions, particularly on social media platforms like Twitter. This study aims to analyze public sentiment regarding booster vaccines by examining Twitter data to understand the prevailing discourse and attitudes toward this policy. The research employs sentiment analysis, a text mining and processing technique, to classify tweets into positive, neutral, and negative categories. The study utilizes the Support Vector Machine (SVM) algorithm, evaluating its performance through a multi-class parameter assessment. Two multi-class strategies, One-against-one (OAO) and One-against-rest (OAR) are combined with various kernels (Sigmoid, Polynomial, and RBF) to identify the most accurate model for sentiment classification. The results show that the OAO method with the RBF kernel achieves the highest accuracy of 96%, outperforming other combinations like OAO with Polynomial (95.2%) and Sigmoid (93.7%) kernels. Similarly, the RBF kernel performs best with 95.5% accuracy in the OAR approach. Using the optimal model, sentiment analysis classifies 49 tweets as positive, 927 as neutral, and 24 as negative, revealing a predominantly neutral public sentiment with limited positive and negative opinions. In conclusion, this study demonstrates the effectiveness of SVM, particularly the OAO method with the RBF kernel, for sentiment analysis of social media data. The findings provide insights into public perceptions of the booster vaccine program, offering policymakers a data-driven basis for designing targeted communication strategies to address concerns and enhance public acceptance.
- 31 May 2025
- Published by LP2M Universitas Islam Negeri (UIN) Syarif Hidayatullah Jakarta in Applied Information System and Management (AISM)
- Vol. 8 (1) , 29-36
Open AccessSentiment Analysis of COVID-19 Booster Vaccines on Twitter Using Multi-Class Support Vector Machine
The Indonesian government's implementation of a booster vaccination program as part of its COVID-19 response has generated diverse public reactions, particularly on social media platforms like Twitter. This study aims to analyze public sentiment regarding booster vaccines by examining Twitter data to understand the prevailing discourse and attitudes toward this policy. The research employs sentiment analysis, a text mining and processing technique, to classify tweets into positive, neutral, and negative categories. The study utilizes the Support Vector Machine (SVM) algorithm, evaluating its performance through a multi-class parameter assessment. Two multi-class strategies, One-against-one (OAO) and One-against-rest (OAR) are combined with various kernels (Sigmoid, Polynomial, and RBF) to identify the most accurate model for sentiment classification. The results show that the OAO method with the RBF kernel achieves the highest accuracy of 96%, outperforming other combinations like OAO with Polynomial (95.2%) and Sigmoid (93.7%) kernels. Similarly, the RBF kernel performs best with 95.5% accuracy in the OAR approach. Using the optimal model, sentiment analysis classifies 49 tweets as positive, 927 as neutral, and 24 as negative, revealing a predominantly neutral public sentiment with limited positive and negative opinions. In conclusion, this study demonstrates the effectiveness of SVM, particularly the OAO method with the RBF kernel, for sentiment analysis of social media data. The findings provide insights into public perceptions of the booster vaccine program, offering policymakers a data-driven basis for designing targeted communication strategies to address concerns and enhance public acceptance.
- Open Access
- 23 February 2022
- Published by MDPI AG in Electronics
- Vol. 11 (5) , 679
Encrypted Malicious Traffic Detection Based on Word2Vec
Network-based intrusion detections become more difficult as Internet traffic is mostly encrypted. This paper introduces a method to detect encrypted malicious traffic based on the Transport Layer Security handshake and payload features without waiting for the traffic session to finish while preserving privacy. Our method, called TLS2Vec, creates words from the extracted features and uses Long Short-Term Memory (LSTM) for inference. We evaluated our method using traffic from three malicious applications and a benign application that we obtained from two publicly available datasets. Our results showed that TLS2Vec is promising as a tool to detect such malicious traffic.
- 23 February 2022
- Published by MDPI AG in Electronics
- Vol. 11 (5) , 679
Open AccessEncrypted Malicious Traffic Detection Based on Word2Vec
Network-based intrusion detections become more difficult as Internet traffic is mostly encrypted. This paper introduces a method to detect encrypted malicious traffic based on the Transport Layer Security handshake and payload features without waiting for the traffic session to finish while preserving privacy. Our method, called TLS2Vec, creates words from the extracted features and uses Long Short-Term Memory (LSTM) for inference. We evaluated our method using traffic from three malicious applications and a benign application that we obtained from two publicly available datasets. Our results showed that TLS2Vec is promising as a tool to detect such malicious traffic.
- Open Access
- 26 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (17) , 7868
Generating Network Intrusion Detection Dataset Based on Real and Encrypted Synthetic Attack Traffic
The lack of publicly available up-to-date datasets contributes to the difficulty in evaluating intrusion detection systems. This paper introduces HIKARI-2021, a dataset that contains encrypted synthetic attacks and benign traffic. This dataset conforms to two requirements: the content requirements, which focus on the produced dataset, and the process requirements, which focus on how the dataset is built. We compile these requirements to enable future dataset developments and we make the HIKARI-2021 dataset, along with the procedures to build it, available for the public.
- 26 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (17) , 7868
Open AccessGenerating Network Intrusion Detection Dataset Based on Real and Encrypted Synthetic Attack Traffic
The lack of publicly available up-to-date datasets contributes to the difficulty in evaluating intrusion detection systems. This paper introduces HIKARI-2021, a dataset that contains encrypted synthetic attacks and benign traffic. This dataset conforms to two requirements: the content requirements, which focus on the produced dataset, and the process requirements, which focus on how the dataset is built. We compile these requirements to enable future dataset developments and we make the HIKARI-2021 dataset, along with the procedures to build it, available for the public.