Explanipedia

Combining curriculum learning and weakly supervised attention for enhanced thyroid nodule assessment in ultrasound imaging Open

Chadaporn Keatmanee, Dittapong Songsaeng, Songphon Klabwong, Yoichi Nakaguro, Alisa Kunapinun , et al. · 2025

These findings suggest that automated thyroid nodule assessment, supported by curriculum learning, has the potential to complement radiologists in clinical practice, enhancing diagnostic accuracy and aiding in more reliable malignancy dete…

AI-Powered Evaluation of Dementia Severity Based on Clinical Data and Visual Scoring Systems (MTA,ERICA, GCA) from MRI Open

Lin Naing, Alisa Kunapinun, Matthew N. Dailey, Rungsiri Patanasantichai, Sittaya Buathong , et al. · 2025

Dementia, particularly Alzheimer's disease (AD), is a growing concern in aging populations, with mild cognitive impairment (MCI) frequently progressing to AD. Current diagnostic methods rely on clinical assessments and MRI-based visual sco…

Improving Noisy Face Embeddings Using Time Series Transformers and Adaptive Triplet Loss Open

Jednipat Moonrinta, Matthew N. Dailey, Mongkol Ekpanyapong · 2025

Face recognition accuracy is now at the point that it is comparable to human performance, largely driven by improvements in face embedding models. However, face embedding models rely on high-quality images, making them vulnerable to variat…

Deep handwritten diagram segmentation Open

Buntita Pravalpruk, Matthew N. Dailey · 2024

Handwriting is a natural way to communicate and exchange ideas, but converting handwritten diagrams to application‐specific digital formats requires skill and time. Automatic handwritten document conversion can save time, but diagrams and …

Diagnostic performance of artificial intelligence in interpreting thyroid nodules on ultrasound images: a multicenter retrospective study Open

Pawitchaya Namsena, Dittapong Songsaeng, Chadaporn Keatmanee, Songphon Klabwong, Alisa Kunapinun , et al. · 2024

The findings advocate for the integration of AI into clinical settings to enhance the diagnostic accuracy of radiologists in assessing thyroid nodules. The AI system, designed as a supportive tool rather than a replacement, promises to rev…

Explainable Automated TI-RADS Evaluation of Thyroid Nodules Open

Alisa Kunapinun, Dittapong Songsaeng, Sittaya Buathong, Matthew N. Dailey, Chadaporn Keatmanee , et al. · 2023

A thyroid nodule, a common abnormal growth within the thyroid gland, is often identified through ultrasound imaging of the neck. These growths may be solid- or fluid-filled, and their treatment is influenced by factors such as size and loc…

Video analytic system for activity profiling, fall detection, and unstable motion detection Open

Aniqua Nusrat Zereen, Anubinda Gurung, Amir Rajak, Jednipat Moonrinta, Matthew N. Dailey , et al. · 2023

Real time detection of falls and unstable movement by elderly people is vital to their quality of life and safety. We present an edge processing device integrated with a cloud computation framework that can be used for activity profiling a…

Deep Handwritten Diagram Segmentation Open

Buntita Pravalpruk, Matthew N. Dailey · 2023

Handwriting has been a natural way to communicate since ancient times.Humans often prefer to write and draw to facilitate rapid exchange ofideas. When handwritten diagrams need to be converted to application-specific digital formats for la…

Addressing Chemical and Thermomechanical Instabilities in Metal Halide Perovskites Across Length Scales Open

Adam D. Printz, Yanan Li, Patrick J. Lohr, Anton A. Samoylov, Matthew N. Dailey · 2022

The chemical and thermomechanical instabilities of metal halide perovskites represent barriers to long operational lifetimes of perovskite-based devices. There is no single magic bullet to address these instabilities, and so multiple compl…

Improving the Thermomechanical Stability of High Efficiency Perovskite Solar Cells via Polymeric Nanofiber Reinforcement Open

Anton A. Samoylov, Nick Swenson, Chi Thành Nguyên, Antonio Murrieta, Juliana Baltram , et al. · 2022

We show that the mechanical stability of perovskite thin films can be increased by an order of magnitude by nanocompositing with polymeric nanofibers using a scalable method. We discuss the increase in fracture resistance energy, Gc, in th…

Diagnostic Performance of Artificial Intelligence for Interpreting Thyroid Cancer in Ultrasound images Open

Piyanuch Arunrukthavon, Dittapong Songsaeng, Chadaporn Keatmanee, Songphon Klabwong, Mongkol Ekpanyapong , et al. · 2022

Thyroid ultrasonography is mainly used for the detection and characterization of thyroid nodules. However, there is some limitation since the diagnostic performance remains highly subjective and depends on radiologist experiences. Therefor…

Detection of River Plastic Using UAV Sensor Data and Deep Learning Open

Nisha Maharjan, Hiroyuki Miyazaki, Bipun Man Pati, Matthew N. Dailey, Sangam Shrestha , et al. · 2022

Plastic pollution is a critical global issue. Increases in plastic consumption have triggered increased production, which in turn has led to increased plastic disposal. In situ observation of plastic litter is tedious and cumbersome, espec…

ReIL: A Framework for Reinforced Intervention-based Imitation Learning Open

Rom Parnichkun, Matthew N. Dailey, Atsushi Yamashita · 2022

Compared to traditional imitation learning methods such as DAgger and DART, intervention-based imitation offers a more convenient and sample efficient data collection process to users. In this paper, we introduce Reinforced Intervention-ba…

Deep Handwritten Diagram Segmentation Open

Buntita Pravalpruk, Matthew N. Dailey · 2022

Cost-Effective and Low Power IoT-Based Paper Supply Monitoring System: An Application Modeling Approach Open

S. D. Arunya P. Senadeera, Su Kyi, Thanapol Sirisung, Watsamon Pongsupan, Attaphongse Taparugssanagorn , et al. · 2021

IoT designers face the dual complexity of obtaining good application-level performance and user satisfaction under constraints on computing and power resources. We introduce a new IoT device for paper roll supply management in bathrooms an…

Vehicle Trajectory Estimation Based on Fusion of Visual Motion Features and Deep Learning Open

Lianen Qu, Matthew N. Dailey · 2021

Driver situation awareness is critical for safety. In this paper, we propose a fast, accurate method for obtaining real-time situation awareness using a single type of sensor: monocular cameras. The system tracks the host vehicle’s traject…

Ontology-Based Framework for Cooperative Learning of 3D Object Recognition Open

Parkpoom Chaisiriprasert, Karn Yongsiriwit, Matthew N. Dailey, Chutiporn Anutariya · 2021

Advanced service robots are not, as of yet, widely adopted, partly due to the effectiveness of robots’ object recognition capabilities, the issue of object heterogeneity, a lack of knowledge sharing, and the difficulty of knowledge managem…

Evaluation of artificial intelligence models for flood and drought forecasting in arid and tropical regions Open

Kasuni E. Adikari, Sangam Shrestha, Dhanika T. Ratnayake, Aakanchya Budhathoki, S. Mohanasundaram , et al. · 2021

Identification of Road Traffic Injury Risk Prone Area Using Environmental Factors by Machine Learning Classification in Nonthaburi, Thailand Open

Morakot Worachairungreung, Sarawut Ninsawat, Apichon Witayangkurn, Matthew N. Dailey · 2021

Road traffic injuries are a major cause of morbidity and mortality worldwide and currently rank ninth globally among the leading causes of disease burden regarding disability-adjusted life years lost. Nonthaburi and Pathum Thani are parts …

Design and Implementation of a Highly Scalable, Low-Cost Distributed Traffic Violation Enforcement System in Phuket, Thailand Open

Somphop Limsoonthrakul, Matthew N. Dailey, Ramesh Marikhu, Vasan Timtong, Aphinya Chairat , et al. · 2021

The number of global road traffic accidents is rising every year and remains undesirably high. One of the main reasons for this trend is that, in many countries, road users violate road safety regulations and traffic laws. Despite improvem…

Multimodal Sentiment Analysis on Video Streams using Lightweight Deep Neural Networks Open

Atitaya Yakaew, Matthew N. Dailey, Teeradaj Racharak · 2021

Conference information Open

Fumiyuki Adachi, Ron Addie, Yasumichi AIYAMA, Kaspar Althoefer, Ruochen An , et al. · 2020

Recent robot technology (RT) has made remarkable progress in both manufacturing and service sectors.Because of this RT advanced technology, there are growing demands to make robots work more friendly and flexible coordinated with human for…

Vec2Instance: Parameterization for Deep Instance Segmentation Open

N. Lakmal Deshapriya, Matthew N. Dailey, Manzul Kumar Hazarika, Hiroyuki Miyazaki · 2020

Current advances in deep learning is leading to human-level accuracy in computer vision tasks such as object classification, localization, semantic segmentation, and instance segmentation. In this paper, we describe a new deep convolutiona…

WIP: Engaging Pre-college Students in Hypothesis Generation Using a Citizen Scientist Network of Air Quality Sensors Open

James W. Moore, Matthew N. Dailey, Zachary Wilhelm, Kerry E. Kelly, Pascal Goffin , et al. · 2020

Environmental Engineering and a BS in Chemical Engineering, and she just completed 8 years of service on Utah's Air Quality Board.Her research focuses on air quality and the evaluation of emerging energy technologies including consideratio…

Testing Deep Neural Networks for Classification Tasks Through Adversarial Perturbations on Test Datasets Open

Rajasekhar Ponakala, Matthew N. Dailey · 2019

Deep learning models often provide high accuracy on test datasets. However, sometimes, changes in the real-world distribution of the data in production may result in incorrect functioning. Such problems have motivated research in the safet…

Tablet Fish Tank Virtual Reality: a Usability Study Open

Sirisilp Kongsilp, Mintra Ruensuk, Matthew N. Dailey, Takashi Komuro · 2017

In this paper, we describe the development a tablet FTVR prototype that incorporates both motion parallax and stereo cues with the use of easy-to-find hardware. We also present findings of a usability study based on the prototype.

Exploring Land Use and Land Cover of Geotagged Social-Sensing Images Using Naive Bayes Classifier Open

Asamaporn Sitthi, Masahiko Nagai, Matthew N. Dailey, Sarawut Ninsawat · 2016

Online social media crowdsourced photos contain a vast amount of visual information about the physical properties and characteristics of the earth’s surface. Flickr is an important online social media platform for users seeking this inform…

EMPIRICAL STUDY OF CAR LICENSE PLATES RECOGNITION Open

Nasa Zata Dina, Matthew N. Dailey · 2015

The number of vehicles on the road has increased drastically in recent years. The license plate is an identity card for a vehicle. It can map to the owner and further information about vehicle. License plate information is useful to help t…

Volumetric 3D Reconstruction and Parametric Shape Modeling from RGB-D Sequences Open

Yoichi Nakaguro, Waqar S. Qureshi, Matthew N. Dailey, Mongkol Ekpanyapong, Pished Bunnun , et al. · 2015

Matthew N. Dailey YOU? Author Swipe