A5037717724- Context-Aware Activity Recognition Systems
- Emotion and Mood Recognition
- COVID-19 diagnosis using AI
- Human Mobility and Location-Based Analysis
- IoT and Edge/Fog Computing
- Digital Mental Health Interventions
- Color perception and design
- Innovative Human-Technology Interaction
- Mobile Health and mHealth Applications
- Artificial Intelligence in Healthcare
- AI in cancer detection
- Human Pose and Action Recognition
- Nutritional Studies and Diet
- Technology Use by Older Adults
- Video Surveillance and Tracking Methods
- Face and Expression Recognition
- Data-Driven Disease Surveillance
- Radiomics and Machine Learning in Medical Imaging
- Speech and Audio Processing
- Time Series Analysis and Forecasting
- Advanced Steganography and Watermarking Techniques
- Machine Learning and Data Classification
- Gait Recognition and Analysis
- COVID-19 Digital Contact Tracing
- Imbalanced Data Classification Techniques
Hanwha Solutions (South Korea)
2023
Kyung Hee University
2013-2022
There is sufficient evidence proving the impact that negative lifestyle choices have on people’s health and wellness. Changing unhealthy behaviours requires raising self-awareness also providing healthcare experts with a thorough continuous description of user’s conduct. Several monitoring techniques been proposed in past to track users’ behaviour; however, these approaches are either subjective prone misreporting, such as questionnaires, or only focus specific component context, activity...
The most significant barrier to success in human activity recognition is extracting and selecting the right features. In traditional methods, features are chosen by humans, which requires user have expert knowledge or do a large amount of empirical study. Newly developed deep learning technology can automatically extract select Among various convolutional neural networks (CNNs) advantages local dependency scale invariance suitable for temporal data such as accelerometer (ACC) signals. this...
Recently, social media have been used by researchers to detect depressive symptoms in individuals using linguistic data from users’ posts. In this study, we propose a framework identify information as significant predictor of depression. Using the proposed framework, develop an application called Socially Mediated Patient Portal (SMPP), which detects depression-related markers Facebook users applying data-driven approach with machine learning classification techniques. We examined set 4350...
The user experience (UX) is an emerging field in research and design, the development of UX evaluation methods presents a challenge for both researchers practitioners. Different have been developed to extract accurate data. Among methods, mixed-method approach triangulation has gained importance. It provides more precise information about while interacting with product. However, this requires skilled developers integrate multiple devices, synchronize them, analyze data, ultimately produce...
Multimodal emotion recognition has gained much traction in the field of affective computing, human-computer interaction (HCI), artificial intelligence (AI), and user experience (UX). There is growing demand to automate analysis towards HCI, AI, UX evaluation applications for providing services. Emotions are increasingly being used, obtained through videos, audio, text or physiological signals. This led process emotions from multiple modalities, usually combined ensemble-based systems with...
Activity recognition for the purposes of recognizing a user's intentions using multimodal sensors is becoming widely researched topic largely based on prevalence smartphone. Previous studies have reported difficulty in life-logs by only smartphone due to challenges with activity modeling and real-time recognition. In addition, difficult absence an established framework which enables use different sources sensor data. this paper, we propose smartphone-based Hierarchical Recognition Framework...
Data-driven knowledge acquisition is one of the key research fields in data mining. Dealing with large amounts has received a lot attention field recently, and number methodologies have been proposed to extract insights from an automated or semi-automated manner. However, these generally target specific aspect mining process, such as acquisition, preprocessing, classification. comprehensive method crucial support end-to-end engineering process. In this paper, we introduce system that covers...
Cloud computing has revolutionized healthcare in today’s world as it can be seamlessly integrated into a mobile application and sensor devices. The sensory data is then transferred from these devices to the public private clouds. In this paper, hybrid distributed environment built which capable of collecting phone store cloud. We developed an activity recognition transfer cloud for further processing. Big technology Hadoop MapReduce employed analyze create user timeline user’s activities....
Personalized emotion recognition provides an individual training model for each target user in order to mitigate the accuracy problem when using general models collected from multiple users. Existing personalized speech research has a cold-start that requires large amount of emotionally-balanced data samples creating model. Such is difficult apply real environments due difficulty collecting numerous with label samples. Therefore, we propose Robust Emotion Recognition Framework Adaptive Data...
Activity recognition through smartphones has been proposed for a variety of applications. The orientation the smartphone significant effect on accuracy; thus, researchers generally propose using features invariant to or displacement achieve this goal. However, those reduce capability system differentiate among some specific commuting activities (e.g., bus and subway) that normally involve similar postures. In work, we recognize by analyzing vibrations vehicle in which user is traveling. We...
Feature selection is considered to be one of the most critical methods for choosing appropriate features from a larger set items. This task requires two basic steps: ranking and filtering. Of these, former necessitates all features, while latter involves filtering out irrelevant based on some threshold value. In this regard, several feature with well-documented capabilities limitations have already been proposed. Similarly, also nontrivial, as it designation an optimal cutoff value so...
The monitoring of human lifestyles has gained much attention in the recent years. This work presents a novel approach to combine multiple context-awareness technologies for automatic analysis people's conduct comprehensive and holistic manner. Activity recognition, emotion location detection, social techniques are integrated with ontological mechanisms as part framework identify behavior. Key architectural components, methods evidences described this paper illustrate interest proposed approach.
The emerging research on automatic identification of user's contexts from the cross-domain environment in ubiquitous and pervasive computing systems has proved to be successful. Monitoring diversified behaviors can help controlling lifestyle associated chronic diseases using context-aware applications. However, availability heterogeneous provides a challenging opportunity for their fusion obtain abstract information further analysis. This work demonstrates extension our previous single...
Abstract Coronavirus disease 2019 (COVID-19) is a novel harmful respiratory that has rapidly spread worldwide. At the end of 2019, COVID-19 emerged as previously unknown in Wuhan, Hubei Province, China. The world health organization (WHO) declared coronavirus outbreak pandemic second week March 2020. Simultaneous deep learning detection and classification based on full resolution digital X-ray images key to efficiently assisting patients by enabling physicians reach fast accurate diagnosis...
Introduction High adherence to oral anticoagulants is essential for stroke prevention in patients with atrial fibrillation (AF). We developed a smartphone application (app) that pushes alarms taking medication and measuring blood pressure (BP) heart rate (HR) at certain times of the day. In addition drug alarms, habit one’s BP HR may reinforce by improving self-awareness disease. This pilot study aims test feasibility efficacy app-based intervention AF. Methods analysis A total 10 university...
Smartphones are contributing to the improvement of healthcare information and services with help mHealth apps. Commercially available apps have drawn prominent public attention by providing improved medication adherence efficient results, but some studies exist support their use. Usability has become main factor for success or adoption smartphone since it helps organize consistency users achieve goal in an easy way. This study aims investigate usability evaluation process applications a...
The novel coronavirus 2019 (COVID-19) becomes recently a global pandemic as declared by the World Health Organization (WHO) in March 2020. COVID-19 rapidly spread and attacked people more than 200 countries worldwide. use of artificial intelligence (AI) techniques has become urgent to prevent exacerbation astounding this pernicious disease. This paper presents rapid deep learning computer-aided Diagnosis (CAD) framework for simultaneously detecting diagnosing against different respiratory...