Assisting Personalized Healthcare of Elderly People: Developing a Rule-Based Virtual Caregiver System Using Mobile Chatbot.

To assist personalized healthcare of elderly people, our interest is to develop a virtual caregiver system that retrieves the expression of mental and physical health states through human-computer interaction in the form of dialogue. The purpose of this paper is to implement and evaluate a virtual caregiver system using mobile chatbot. Unlike the conventional health monitoring approach, our key idea is to integrate a rule-based virtual caregiver system (called "Mind Monitoring" service) with the physical, mental, and social questionnaires into the mobile chat application. The elderly person receives one question from the mobile chatbot per day, and answers it by pushing the optional button or using a speech recognition technique. Furthermore, a novel method is implemented to quantify the answers, generate visual graphs, and send the corresponding summaries or advice to the specific elder. In the experimental evaluation, we applied it to eight elderly subjects and 19 younger subjects within 14 months. As main results, its effects were significantly improved by the proposed method, including the above 80% in the response rate, the accurate reflection of their real lives from the responses, and high usefulness of the feedback messages with software quality requirements and evaluation. We also conducted interviews with subjects for health analysis and improvement.

Toward Capturing Scientific Evidence in Elderly Care: Efficient Extraction of Changing Facial Feature Points.

To capture scientific evidence in elderly care, a user-defined facial expression sensing service was proposed in our previous study. Since the time-series data of feature values have been growing at a high rate as the measurement time increases, it may be difficult to find points of interest, especially for detecting changes from the elderly facial expression, such as many elderly people can only be shown in a micro facial expression due to facial wrinkles and aging. The purpose of this paper is to implement a method to efficiently find points of interest (PoI) from the facial feature time-series data of the elderly. In the proposed method, the concept of changing point detection into the analysis of feature values is incorporated by us, to automatically detect big fluctuations or changes in the trend in feature values and detect the moment when the subject's facial expression changed significantly. Our key idea is to introduce the novel concept of composite feature value to achieve higher accuracy and apply change-point detection to it as well as to single feature values. Furthermore, the PoI finding results from the facial feature time-series data of young volunteers and the elderly are analyzed and evaluated. By the experiments, it is found that the proposed method is able to capture the moment of large facial movements even for people with micro facial expressions and obtain information that can be used as a clue to investigate their response to care.

Nonintrusive Fine-Grained Home Care Monitoring: Characterizing Quality of In-Home Postural Changes Using Bone-Based Human Sensing.

In contrast to the physical activities of able-bodied people at home, most people who require long-term specific care (e.g., bedridden patients and patients who have difficulty walking) usually show more low-intensity slow physical activities with postural changes. Although the existing devices can detect data such as heart rate and the number of steps, they have been increasing the physical burden relying on long-term wearing. The purpose of this paper is to realize a noninvasive fine-grained home care monitoring system that is sustainable for people requiring special care. In the proposed method, we present a novel technique that integrates inexpensive camera devices and bone-based human sensing technologies to characterize the quality of in-home postural changes. We realize a local process in feature data acquisition once per second, which extends from a computer browser to Raspberry Pi. Our key idea is to regard the changes of the bounding box output by standalone pose estimation models in the shape and distance as the quality of the pose conversion, body movement, and positional changes. Furthermore, we use multiple servers to realize distributed processing that uploads data to implement home monitoring as a web service. Based on the experimental results, we conveyed our findings and advice to the subject that include where the daily living habits and the irregularity of home care timings needed improvement.

Toward Flexible and Efficient Home Context Sensing: Capability Evaluation and Verification of Image-Based Cognitive APIs.

Cognitive Application Program Interface (API) is an API of emerging artificial intelligence (AI)-based cloud services, which extracts various contextual information from non-numerical multimedia data including image and audio. Our interest is to apply image-based cognitive APIs to implement flexible and efficient context sensing services in a smart home. In the existing approach with machine learning by us, with the complexity of recognition object and the number of the defined contexts increases by users, it still requires directly manually labeling a moderate scale of data for training and continually try to calling multiple cognitive APIs for feature extraction. In this paper, we propose a novel method that uses a small scale of labeled data to evaluate the capability of cognitive APIs in advance, before training features of the APIs with machine learning, for the flexible and efficient home context sensing. In the proposed method, we exploit document similarity measures and the concepts (i.e., internal cohesion and external isolation) integrate into clustering results, to see how the capability of different cognitive APIs for recognizing each context. By selecting the cognitive APIs that relatively adapt to the defined contexts and data based on the evaluation results, we have achieved the flexible integration and efficient process of cognitive APIs for home context sensing.

Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts.

To implement fine-grained context recognition that is accurate and affordable for general households, we present a novel technique that integrates multiple image-based cognitive APIs and light-weight machine learning. Our key idea is to regard every image as a document by exploiting "tags" derived by multiple APIs. The aim of this paper is to compare API-based models' performance and improve the recognition accuracy by preserving the affordability for general households. We present a novel method for further improving the recognition accuracy based on multiple cognitive APIs and four modules, fork integration, majority voting, score voting, and range voting.

Detecting service chains and feature interactions in sensor-driven home network services.

Sensor-driven services often cause chain reactions, since one service may generate an environmental impact that automatically triggers another service. We first propose a framework that can formalize and detect such service chains based on ECA (event, condition, action) rules. Although the service chain can be a major source of feature interactions, not all service chains lead to harmful interactions. Therefore, we then propose a method that identifies feature interactions within the service chains. Specifically, we characterize the degree of deviation of every service chain by evaluating the gap between expected and actual service states. An experimental evaluation demonstrates that the proposed method successfully detects 11 service chains and 6 feature interactions within 7 practical sensor-driven services.

PCR detection of bacterial genes provides evidence of death by drowning.

We have developed a sensitive and specific PCR method for detecting plankton DNA in cases of death by drowning. However, this PCR method could not be used for cases of drowning in water containing no plankton. Bacteria species are normally localized in the throat and trachea and they may invade into blood through the respiratory tract in people who have drowned as well as species localized in water. The aim of this study was to establish a novel and expedient PCR method for detecting bacterial genes in samples from drowning cases. We designed primer pairs for Streptococcus salivarius (SL1) and Streptococcus sanguinis (SN1), which are common species in the throat, and for Aeromonas hydrophila (AH1), which has been found in various water samples. With SL1, SN1, and AH1, we detected 10, 0.1, and 1 pg of target DNA, respectively. Among 19 drowned cases within 3 days postmortem, SL-DNA was detected in all of the blood samples from hearts with SL1 and AH-DNA was detected in several samples with AH1. In a case of drowning in a bathtub, use of the conventional acid digestion method for diatom analyses and the PCR method for identifying plankton DNA revealed no plankton, but our PCR method for detecting bacterial DNA showed a positive result for SL-DNA in a blood sample from the heart. In conclusion, our novel PCR method is highly specific and sensitive for detecting bacterial DNA and is useful for cases of death by drowning in water containing no plankton.