Jakkree Srinonchat

Dr. Jakkree Srinonchat

Rajamangala University of Technology Thanyaburi (RMUTT)
orcid

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

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

Representative Publications

View All Publications
8 September 2021 in Sensors
Verified
Journal Article
Open access
PDF file
SPSomchai Pohtongkam
Somchai Pohtongkam
JSJakkree Srinonchat
Jakkree Srinonchat
A tactile sensor array is a crucial component for applying physical sensors to a humanoid robot. This work focused on developing a palm-size tactile sensor array (56.0 mm × 56.0 mm) to apply object recognition for the humanoid robot hand. This sensor was based on a PCB technology operating with the piezoresistive principle. A conductive polymer composites sheet was used as a sensing element and the matrix array of this sensor was 16 × 16 pixels. The sensitivity of this sensor was evaluated and the sensor was installed on the robot hand. The tactile images, with resolution enhancement using bicubic interpolation obtained from 20 classes, were used to train and test 19 different DCNNs. InceptionResNetV2 provided superior performance with 91.82% accuracy. However, using the multimodal learning method that included InceptionResNetV2 and XceptionNet, the highest recognition rate of 92.73% was achieved. Moreover, this recognition rate improved when the object exploration was applied to demonstrate.

27 February 2023 in IEEE Access
Verified
Journal Article
Open access
SPSomchai Pohtongkam
Somchai Pohtongkam
JSJakkree Srinonchat
Jakkree Srinonchat
With the development of human-like robotic technologies, robots have been advanced to sense and recognize objects, which is one branch of artificial intelligence to mimic human reactions. Although high-performance computer technologies are used, the ability of object recognition by touch is still low due to the lack of proper sensors. Therefore, this research studied the object learning and recognition system through robot touches by developing an artificial sensory system acting as an electronic skin with tactile sensors. The Tactile Sensor is developed in this research, consisting of 15 Tactile Sensor Arrays and the palm’s touchpoints. Furthermore, recognition analysis was developed on Bag of Word (BoW) and Convolution Neural Network (CNN) algorithms. With the BoW technique, using Support Vector Machine (SVM) as a classifier with Moment Analysis Descriptor (MA) provided the highest accuracy, showing more than 80.15% accuracy from five grasping of an object. With the CNN approach, InceptionNetV3 provided the highest accuracy of 98.28% from only one capture of an object.

18 September 2021 in Agriculture
Verified
Journal Article
Open access
PDF file
CSChaiyan Sirikun
Chaiyan Sirikun
Grianggai SamseemoungGrianggai Samseemoung
Grianggai Samseemoung
Peeyush SoniPeeyush Soni
Peeyush Soni
JLJaturong Langkapin
Jaturong Langkapin
JSJakkree Srinonchat
Jakkree Srinonchat
Rice grain yield was estimated from a locally made Thai combine harvester using a specially developed sensing and monitoring system. The yield monitoring and sensing system, mounted on the rice combine harvester, collected and logged grain mass flow rate and moisture content, as well as pertinent information related to field, position and navigation. The developed system comprised a yield meter, GNSS receiver and a computer installed with customized software, which, when assembled on a local rice combine, mapped real-time rice yield along with grain moisture content. The performance of the developed system was evaluated at three neighboring (identically managed) rice fields. ArcGIS® software was used to create grain yield map with geographical information of the fields. The average grain yield values recorded were 3.63, 3.84 and 3.60 t ha−1, and grain moisture contents (w.b.) were 22.42%, 23.50% and 24.71% from the three fields, respectively. Overall average grain yield was 3.84 t ha−1 (CV = 63.68%) with 578.10 and 7761.58 kg ha−1 as the minimum and maximum values, respectively. The coefficients of variation in grain yield of the three fields were 57.44%, 63.68% and 60.41%, respectively. The system performance was evaluated at four different cutter bar heights (0.18, 0.25, 0.35 and 0.40 m) during the test. As expected, the tallest cutter bar height (0.40 m) offered the least error of 12.50% in yield estimation. The results confirmed that the developed grain yield sensor could be successfully used with the local rice combine harvester; hence, offers and ‘up-gradation’ potential in Thai agricultural mechanization.

7 July 2025 in IEEE Access
Verified
Journal Article
Open access
APAnuruk Prommakhot
Anuruk Prommakhot
JOJakkrit Onshaunhit
Jakkrit Onshaunhit
WOWichian Ooppakaew
Wichian Ooppakaew
Grianggai SamseemoungGrianggai Samseemoung
Grianggai Samseemoung
JSJakkree Srinonchat
Jakkree Srinonchat
Plant diseases have important consequences for livelihoods and economies, both on local and global scales, whereby the spread of plant pathogens can lead to high levels of damage to agricultural productivity. In this regard, deep learning (DL) has evolved as a promising remedy. Nevertheless, the level of diversity of plant species still presents a constant challenge to effective plant disease classification. This research proposed a two-stream convolution operator combining bidirectional long short-term memory (BiLSTM) for effective feature mapping and learning. Moreover, a transformer network (TransNet) is constructed based on sequential learning techniques (SLT) of long short-term memory (LSTM), bidirectional LSTM (BiLSTM), sequence-to-sequence, and gated recurrent unit to highlight important plant disease features. The network is trained on the PlantVillage dataset, which includes 38 species of plant diseases. The experimental results indicate that the proposed model achieves scores of 97.88%, 97.93%, and 97.62% for Accuracy, Precision, and Recall, respectively, along with a low training loss of 0.0696 and a minimal training time of 83.17 minutes. The proposed approach represents a significant improvement over these previous models and demonstrates the potential for the efficiency and accuracy of plant disease classification to be further improved, contributing to the realization of modern technology in the agricultural industry.

6 June 2024 in IEEE Transactions on Human-Machine Systems
Verified
Journal Article
Closed access
CCChana Chansri
Chana Chansri
JSJakkree Srinonchat
Jakkree Srinonchat
The current sensor systems using the human–computer interface to develop a hand gesture recognition system remain challenging. This research presents the development of hand gesture recognition with 16-DoF glove sensors combined with a convolution neural network. The flex sensors are attached to 16 pivot joints of the human hand on the glove so that each knuckle flex can be measured while holding the object. The 16-DoF point sensors collecting circuit and adjustable buffer circuit were developed in this research to work with the Arduino Nano microcontroller to record each sensor's signal. This article investigates the time-series data of the flex sensor signal into 2-D colored images, concatenating the signals into one bigger image with a Gramian angular field and then recognition through a deep convolutional neural network (DCNN). The 16-DoF glove sensors were proposed for testing with three experiments using 8 models of DCNN recognition. These were conducted on 20 hand gesture recognition, 12 hand sign recognition, and object manipulation according to shape. The experimental results indicated that the best performance for the hand grasp experiment is 99.49% with Resnet 101, the hand sign experiment is 100% with Alexnet, and the object attribute experiment is 99.77% with InceptionNet V3.

19 April 2024 in IEEE Access
Verified
Journal Article
Open access
APAnuruk Prommakhot
Anuruk Prommakhot
JSJakkree Srinonchat
Jakkree Srinonchat
Deep learning approaches have shown exceptional efficacy in challenges related to the categorization of images. Nevertheless, the practical use of these methods in classifying fungi faces difficulties due to the distinctive features of fungal morphology and the scarcity of annotated training data. Hence, this study introduces an innovative and inclusive methodology that utilizes the spatial transformer network technique to analyze fungi thoroughly feature alterations. The fungal characteristics are then subjected to processing by integrating four networks. The combined convolutional neural networks are enhanced with adaptive layers, convolutional operations, kernel sizes, dropblock mechanisms, and residual blocks. These components collaborate harmoniously via the concatenate function in the feature mapping process. In that order, the experimental findings demonstrate notable training accuracies, namely 91.89%, 98.24%, 98.49%, and 98.92%. Furthermore, the classification of fungi showcases remarkable precision, achieving high accuracies of 98.91%, 82.50%, 94.11%, 100.0%, and 87.43% for Absidia, Aspergillus, Fusarium, Penicillium, and Rhizopus, respectively. Additionally, the recall performance stood at 100.0%, 87.61%, 96.78%, 100.0%, and 88.45% for Absidia, Aspergillus, Fusarium, Penicillium, and Rhizopus, respectively. The findings of this study suggest that the suggested deep learning approach has considerable promise in developing a reliable system for identifying fungus species.