Driver distraction is a leading factor in car crashes. With goal to reduce traffic accidents and improve transportation safety, this study proposes driver detection system which identifies various types of distractions through camera observing the driver. An assisted driving testbed developed for purpose creating realistic experiences validating algorithms. The authors collected dataset consists images drivers both normal distracted postures. Four deep convolutional neural networks including...

The ubiquitous use of cameras in a home environment raises privacy concerns, which is one the major barriers to deployment smart systems for elderly and disabled care. Social robots are equipped with that can witness embarrassing situations their owners, such as nakedness during morning bath. In this paper, our proposed solution let robot detect privacy-sensitive moments then turn away avoid observing person. We method based on Convolutional Neural Networks (CNN) daily living scenario....

Social robots are coming to our homes and have already been used help humans in a number of ways geriatric care. This article aims develop framework that enables social conduct regular clinical screening interviews care, such as cognitive evaluation, falls' risk pain rating. We robot with essential features enable interviews, including conversational interface, face tracking, an interaction handler, attention management, skills, cloud service management. Besides, general interview management...

The continued increase of senior population worldwide is causing challenges to existing healthcare and support systems in terms infrastructure trained professionals. Recently, smart home environments are being utilized for ubiquitous health monitoring, allowing patients stay at the comfort their homes. In this paper we presented a Cloud-Based Smart Home Environment (CoSHE) healthcare. Our system collects physiological signals through non-invasive wearable sensors provides contextual...

Monitoring daily activities is essential for home service robots to take care of the older adults who live alone in their homes. In this article, we proposed a sound-based human activity monitoring (SoHAM) framework by recognizing sound events environment. First, method context-aware event recognition (CoSER) developed, which uses contextual information disambiguate events. The locational context estimated fusing data from distributed passive infrared (PIR) sensors deployed home. A two-level...

Distracted driving is one of the main contributors to traffic accidents. This paper proposes a deep learning approach detecting multiple distracted behaviors. In order obtain more accurate detection results, synchronized image recognition system based on two cameras designed, by which body movements and face driver are monitored respectively. The images captured from driver's areas fed Convolutional Neural Networks (CNNs) simultaneously ensure performance classification. data collection...

Memory loss is a part of normative aging. Many older adults commonly forget to take prescribed medication, which can have an adverse effect on health. Therefore, it important provide with medication reminder service. There are several mobile apps and devices capable reminding but their user interfaces operations usually unfriendly seniors. Considering the above demands shortcomings, we proposed conversation-based management system (CMMS). The CMMS uses companion robot cloud create reminders...

Negative affects such as anger, fear, nervousness, depression, etc., may increase human's susceptibility to illness. In this letter, we propose a negative emotion management system that is able recognize emotions through ECG signal and perform regulation robot assistant, which has potential for reducing health risks. A smart shirt developed collect the from human body. The assistant ability engage in verbal conversations with humans. Recurrence Quantitative Analysis (RQA) used extract...

This paper proposes and implements an open framework of active auditory learning for a home service robot to serve the elderly living alone at home. The was developed realize various perception capabilities while enabling remote human operator involve in sound event recognition process care. is able estimate source position collaborate with protecting privacy elderly. Our experimental results validated proposed evaluated human–robot collaboration recognition.

This paper aims to develop a robotic platform which conducts cognitive orientation assessments for the elderly people. The robot asks questions based on time, space and memory recall, analyzes voice response from user. With help of natural language processing package SyntaxNet, evaluates answers given by user generates score detailed report session conducted. is used evaluate progression impairment caregivers or physicians. whole system was developed implemented our ASCC Companion Robot....

Water is a highly abundant nutrient in the human body and monitoring of its regulation essential to keep hydrated. A number critical health conditions including swelling brain short/long term memory loss are associated with poor or excessive drinking habits. This can be prevented use real time hydration system. In this paper we presented AutoHydrate, wearable system which continuously monitors activities daily fluid requirements user through automatic detection activities. The built using...

This paper proposes and implements an auditory perception platform for a home service robot that serves the elderly living alone at home. A layered architecture proposed was developed to realize various capabilities while enabling remote caregiver involve in sound event recognition process. We successfully implemented software this realizes services developing high level applications. The is able estimate source position recognize human speech room with multiple sources, as well collaborate...

Sound event recognition without the context is challenging for both humans and robots due to diversity of sound events. Contextual information allows them disambiguate events, example, in a home environment. This paper proposes implements context-aware service robot that monitors elderly living alone at home. The location events estimated by fusing distributed PIR (Passive Infrared) Sensors. A two-level dynamic Bayesian network (DBN) used model intra-temporal inter-temporal constraints among...

This paper proposes and implements a framework for human-robot collaboration in Mobile Visual Sensor Network (MVSN). A collaborative architecture the proposed human-integrated MVSN was developed to allow human operator robots collaborate perform surveillance tasks. We successfully implemented so user can control deployment of mobile sensors through his head movement. also explored using computer vision techniques navigation on robot nodes conduct active target detection. The nodes,...

Individuals with autism spectrum disorder (ASD) often face barriers in accessing opportunities across a range of educational, employment, and social contexts. One these is the development effective communication skills sufficient for navigating demands everyday environments. Fortunately, researchers have established evidence-based practices (EBP) teaching critical to individuals ASD [1]. EBP that has received great deal attention over last few decades technology-aided instruction...

This article introduces methods for applying Deep Learning in identifying aspects from written commentaries on Shopee e-commerce sites. The used datasets are two sets of Vietnamese consumers' comments about purchased products domains. Words and sentences will be performed as vectors, or characteristic matrices through language models such one-hot, fastText, PhoBERT. We then Convolutional Neural Network (CNN) the Fully Connected (Multilayer perceptron - MLP) to learn which mentioned comments....