- Digital Imaging for Blood Diseases
- Thermography and Photoacoustic Techniques
- Photoacoustic and Ultrasonic Imaging
- COVID-19 diagnosis using AI
- Ultrasonics and Acoustic Wave Propagation
- Mosquito-borne diseases and control
- Surface Roughness and Optical Measurements
- Industrial Vision Systems and Defect Detection
- Advanced Sensor and Energy Harvesting Materials
- Advanced Measurement and Metrology Techniques
- Electrospun Nanofibers in Biomedical Applications
- AI in cancer detection
- Optical Imaging and Spectroscopy Techniques
- Silk-based biomaterials and applications
- Non-Destructive Testing Techniques
- Spectroscopy Techniques in Biomedical and Chemical Research
- Characterization and Applications of Magnetic Nanoparticles
- Smart Agriculture and AI
- Adhesion, Friction, and Surface Interactions
- Viral Infections and Vectors
- Bird parasitology and diseases
- Nanocomposite Films for Food Packaging
- Robotic Path Planning Algorithms
- Digital Media Forensic Detection
- Additive Manufacturing and 3D Printing Technologies
King Mongkut's Institute of Technology Ladkrabang
2016-2025
Bangkok University
2020
Faculty (United Kingdom)
2020
Engineering (Italy)
2020
University of Manchester
1967-2006
Institute of Science and Technology
2003
Anaplasmosis, which is caused by Anaplasma spp. and transmitted tick bites, one of the most serious livestock animal diseases worldwide, causing significant economic losses as well public health issues. marginale, a gram-negative intracellular obligate bacterium, can cause disease in cattle other ruminants. Because insufficient quality slides, microscopic diagnostic procedure time-consuming challenging to diagnose. Intra- inter-rater variation frequently imposed on technicians who are...
Abstract Microscopic observation of mosquito species, which is the basis morphological identification, a time-consuming and challenging process, particularly owing to different skills experience public health personnel. We present deep learning models based on well-known you-only-look-once (YOLO) algorithm. This model can be used simultaneously classify localize images identify species gender field-caught mosquitoes. The results indicated that concatenated two YOLO v3 exhibited optimal...
Thin films of silk fibroin were prepared by solvent evaporation from calcium chloride/ethanol aqueous solution. The influence alcohol treatments on thermal, mechanical and optical properties silk-fibroin-based film is presented. To understand the conformal structure alcohol-treated film, IR spectral decomposition method employed. especially transparency, haze fluorescence emission systematically investigated together with to effect fibril such as beta-sheet influencing properties. Monohydric...
Object detection is a new artificial intelligence approach to morphological recognition and labeling parasitic pathogens. Due the lack of equipment trained personnel, innovation for searching various products in stool examination will enable patients remote areas undeveloped countries access diagnostic services. Because object developing that has been tested its effectiveness detecting intestinal objects such as protozoan cysts helminthic eggs, it suitable use rural where many factors...
Mosquito-borne diseases such as dengue fever and malaria are the top 10 leading causes of death in low-income countries. Control measure for mosquito population plays an essential role fight against disease. Currently, several intervention strategies; chemical-, biological-, mechanical- environmental methods remain under development need further improvement their effectiveness. Although, a conventional entomological surveillance, required microscope taxonomic key identification by...
Abstract The infection of an avian malaria parasite ( Plasmodium gallinaceum ) in domestic chickens presents a major threat to the poultry industry because it causes economic loss both quality and quantity meat egg production. Computer-aided diagnosis has been developed automatically identify infections classify blood stage development. In this study, four types deep convolutional neural networks, namely Darknet, Darknet19, Darknet19-448 Densenet201 are used P. stages. We randomly collected...
ABSTRACT This study develops and evaluates a deep learning based visual servoing (DLBVS) control system for guiding industrial robots during aircraft refueling, aiming to enhance operational efficiency precision. The employs monocular camera mounted on the robot's end effector capture images of target objects—the refueling nozzle bottom loading adapter—eliminating need prior calibration simplifying real‐world implementation. Using learning, identifies feature points these objects estimate...
Trypanosomiasis, a significant health concern in South America, Asia, and Southeast requires active surveys to effectively control the disease. To address this, we have developed hybrid model that combines deep metric learning (DML) image retrieval. This is proficient at identifying Trypanosoma species microscopic images of thin-blood film examinations. Utilizing ResNet50 backbone neural network, trained-model has demonstrated outstanding performance, achieving an accuracy exceeding 99.71 %...
This research focuses on the development of environmentally friendly textile-based shielding composites, from micro-sized and nanosized Bi2O3 particles, against ionizing radiation. Polyester fabric dyne-coated with either micro- or nano-Bi2O3 particles shields some X-rays but effectiveness is poor. With only ∼58% uptake dyeing polyester fabric, insufficient amount leaded to low density resulting in 30% X-ray at 80 kVp. Cotton coated nano-Bi2O3/poly(vinyl alcohol) (PVA) other hand,...
In this paper, we present the method based on asynchronous deep reinforcement learning adapted for mobile robot navigation with supervised auxiliary tasks. We apply hybrid Asynchronous Advantage Actor-Critic (A3C) algorithm CPU/GPU TensorFlow. The is simulated as tasks OpenAI-Gym-Gazebo-based environment collaboration ROS Multimaster. include depth predictions and position estimation. shows capability to learn navigate only input from raw RGB-image also perform recognition of place map. show...
Abstract This study explores the modification of silk fibroin films for hydrophilic coating applications using various sugar alcohols. Films, prepared via solvent casting, incorporated glycerol, sorbitol, and maltitol, revealing distinctive transparency UV absorption characteristics based on alcohol chemical structures. X-ray diffraction confirmed a I to II transition influenced by Glycerol proved most effective in enhancing β-sheet structure. The also elucidated conformational shift towards...
ABSTRACT With an aim to develop anti‐electrostatic discharge materials based on biodegradable polymers, poly(vinyl alcohol) films composited with two different conductive fillers (carbon black and aluminium) at various contents (20−60%wt), were manufactured using solvent‐casting technique. The mechanical properties of such the investigated through tensile stress‐strain tests. Wettability morphology composite performed by water contact angle measurement SEM, respectively. Young's modulus can...
The enhancement of signals from Rayleigh wave interaction at solid surface features is described, for the case when arise laser-ultrasound/electromagnetic-acoustic transducer (EMAT) detection system. Transient acoustic waves were detected by an in-plane EMAT receiver. B-scan images slot or edge interactions revealed increased signal amplitude these a factor ∼1.59. An explanation based on sensor with wave.
Tracheal collapse is a chronic and progressively worsening disease; the severity of clinical symptoms experienced by affected individuals depends on degree airway collapse. Cutting-edge automated tools are necessary to modernize disease screening using radiographs across various veterinary settings, such as animal clinics hospitals. This primarily due inherent challenges associated with interpreting uncertainties among veterinarians. In this study, an artificial intelligence model was...
Abstract DNA double-strand breaks (DSBs) are the most lethal form of damage to cells from irradiation. γ-H2AX (phosphorylated H2AX histone variant) has become one reliable and sensitive biomarkers DSBs. However, foci assay still limitations in time consumed for manual scoring possible variability between scorers. This study proposed a novel automated method using deep convolutional neural network based on You-Only-Look-Once (YOLO) algorithm quantify peripheral blood samples. FociRad,...