Benjamin Chanakot

Benjamin Chanakot

Auto-generated profile, based on publicly available information

Benjamin Chanakot

Rajamangala University of Technology Srivijaya

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
16 December 2023
Verified
Conference Paper
Open access
Nattapong KaewboonmaNattapong Kaewboonma
Nattapong Kaewboonma
PLPURIWAT LERTKRAI
PURIWAT LERTKRAI
BCBenjamin Chanakot
Benjamin Chanakot
JLJutaporn Lertkrai
Jutaporn Lertkrai
This research investigated the utilization of deep learning methodologies for the precise classification of Thai rubber leaf diseases using leaf images. The study employed a diverse set of convolutional neural network (CNN) models, including VGG16, ResNet50, EfficientNet, and YOLOv8, to accomplish this task. Data augmentation techniques were employed to address overfitting, thereby enhancing the robustness of the models. The dataset, meticulously curated and labeled by domain experts, comprised 734 high-quality rubber leaf images categorized into three distinct classes: new diseases, powdery mildew disease, and healthy leaves. The findings revealed that YOLOv8n-cls emerged as the optimal choice, demonstrating exceptional efficiency with a diminutive model size (5.5 MB) and a parsimonious parameter count (1.44 million). This model exhibited remarkable accuracy (98.68%) and an impressive F1-score of 0.98, establishing its proficiency in delivering precise and reliable predictions. Furthermore, a comparative analysis of YOLOv8 pretrained classify models underscored YoloV8s as the most favorable option, characterized by the lowest validation loss. These results highlighted the potential of deep learning methodologies in the field of agricultural disease detection, offering a cost-effective and efficient solution for rubber plantation owners and farmers. This research contributed valuable insights into the application of advanced technology to address critical challenges in the agricultural sector, particularly in the context of plant disease detection and classification.

1 February 2023 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
BCBenjamin Chanakot
Benjamin Chanakot
CSCharun Sanrach
Charun Sanrach
This research aimed to measure the effectiveness of Thai news headlines classification using an artificial neural network (ANN). The headlines consisted of i) political news, ii) sports news, iii) economic news, and iv) crime news, 1,200 headlines in total. The distribution of headlines was measured by using chi-square, information gain, and term frequency inverse class frequency (TFICF). Threshold default value was set in relation to terms of headlines before cross-validation was employed to categorize the data to examine the efficiency of the model using a neural network algorithm in classifying the headlines. The investigation of the news headline classification efficiency revealed that the 15-fold data division using TFICF was the most accurate in classifying headlines, with the accuracy rate of 99.60% and F-measure rate of 99.05%. Moreover, it was found that when more news headlines were provided as the learning data, the news headline classification became more accurate. Likewise, appropriate threshold value determination facilitated the selection of appropriate features in the headlines and resulted in more effective and accurate classification. Hence, it can be concluded that headline classification will be more accurate if the appropriate amount of learning data exists, and appropriate threshold value was set.

1 February 2023 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
KPKornkanok Phoksawat
Kornkanok Phoksawat
EPEakkarat Phoksawat
Eakkarat Phoksawat
BCBenjamin Chanakot
Benjamin Chanakot
This research aimed to create suitable forecasting models with long-short term memory (LSTM) from time series data, the price of rubber smoked sheets (RSS3) using 2,631 data from the Rubber Authority of Thailand for the past 10 years. The data was divided into two sets: first series 2,105 data points were used to create the LSTM prediction model; second series 526 data points were used to estimate forecasting performance using the root mean square error (RMSE), the mean absolute percentage error (MAPE), and accuracy rate of the model. The results showed that the most suitable forecasting model for time series data, with a total of 9 LSTM layers comprised of 3 primary LSTMs. Each LSTM layer has the number of neurons 100, 150, and 200 to obtain an optimal neural network of the LSTM technique. The number of epochs and iteration was 30, 40, and 50. Dropout layers between each LSTM layer have a probability of 30%. The results of the test to measure the performance of the time series forecasting data showed that the 9-layer model with the LSTM model architecture of LSTM 3 layers gave the best forecast, with RMSE of 2.4121, MAPE of 0.0413 and 95.88% accuracy rate.

1 February 2024 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
BCBenjamin Chanakot
Benjamin Chanakot
CSCharun Sanrach
Charun Sanrach
The objective of this study is to create a Thai-language chatbot analyzing mosquito-borne diseases using Jaccard similarity with an aim to develop an artificial intelligence (AI)-based chatbot used to analyze Aedes-borne diseases through natural language processing. The analysis occurred when the symptoms provided by users on the chatbot were assessed to select relevant words as text attributes using the term frequency-inverse document frequency (TF-IDF) before the Jaccard similarity was used to measure the similarity of the information on the mosquito-borne disease database. The Line Messaging API was applied to facilitate communication between users and the chatbot through the Line application. The chatbot applied PHP 7.2.34 and MySQL 5.7.32 for database management, with Apache 2.2.29 serving as the bot server. The performance evaluation of the chatbot revealed that the chatbot accurately understood user intentions with an intent accuracy of 85.00%. Likewise, the usability of the chatbot was assessed using the system usability scale (SUS), and it received a score of 89.75, indicating a high level of user-friendliness. Furthermore, it has been found that appropriate tokenization enables accurate feature selection. This leads to improved accuracy in measuring Jaccard similarity. Consequently, the chatbot is capable of providing precise responses that align with the user's intent.

1 January 2025 in International Journal of Computer Theory and Engineering
Verified
Journal Article
Open access
PDF file
PLPURIWAT LERTKRAI
PURIWAT LERTKRAI
BCBenjamin Chanakot
Benjamin Chanakot
Nattapong KaewboonmaNattapong Kaewboonma
Nattapong Kaewboonma
This research presents an approach for real-time detection of rubber leaf diseases using the YOLOv8 deep learning model, integrated with the LINE messaging platform. The system enables users to submit rubber leaf images via LINE, where they are processed by an Artificial Intelligence (AI)—powered backend hosted on Heroku, utilizing Docker and Flask for scalability and efficiency. The YOLOv8 model was trained on a dataset comprising three classes: Healthy, New Disease, and Powdery Mildew. It achieved an overall mAP50 of 57.9% and an mAP50-95 of 42.8%, demonstrating strong performance in detecting healthy leaves (mAP50: 98.3%) but lower accuracy in identifying Powdery Mildew (mAP50: 22.4%), likely due to significant class imbalance. User testing involved 50 beta testers who submitted 500 images through the chatbot, yielding a detection accuracy of 72.4%, a misclassification rate of 5.4%, and an average response time of 2.5 seconds. Key performance metrics included a macro-average precision of 78.2%, recall of 73.0%, and an F1 score of 75.5%. User feedback highlighted satisfaction with the system’s ease of use and response speed, though improvements were suggested in handling misclassifications and providing treatment recommendations. These results indicate that the system offers a robust and scalable solution for rubber leaf disease detection, with potential for further optimization.