One of the main purposes for which people use Twitter is to share emotions with others. Users can easily post a message as short text when they experience such pleasure or sadness. Such tweet serves acquire empathy from followers, and possibly influence others' emotions. In this study, we analyze emotional behaviors user relationships based on data using two dictionaries words. Emotion scores are calculated via keyword matching. Moreover, design three experiments different settings:...

We are living in a cyber-physical-social environment with variety of lifestyles and values.Living support has become important such diverse society.Owing to the ability collect large amount personal data or life logs environment, it is now possible for us provide based on analysis.Moreover, analyzing can facilitate deep understanding an individual.In this study, we focus provision cyber-enabled well-being oriented daily individual analysis.Three categories identified from individual's...

With the rapid development of information and communication technology, a vast amount personal health data is generated, stored, utilized in healthcare related services. However, there are many issues remained to be solved, such as interoperability, security, privacy concerns. On other hand, blockchain, decentralized peer-to-peer digital ledger, has attracted lot attention recent years promising technology protect data. By adopting individuals can take advantage for better healthcare. In...

With the rapid development of sensors and IoT technology, personal health data can be collected stored by various wearable devices utilized for healthcare. To share use sensitive securely efficiently, a variety solutions based on blockchain have been proposed developed. However, there are still many issues to solved, such as how let individuals control manage their own data, make all accesses strictly auditable. In this paper, we present new model Individual-Initiated Auditable Access...

Pulse diagnosis is one of the diagnostic methods in traditional Chinese medicine (TCM). Such diagnoses are made subjectively by a TCM doctor, who requires expert knowledge. If pulse could be automated, it would beneficial for health management. In our previous study, we showed that might related to personal data, such as step count and sleep score. this propose new approach classifying based on combination features from data. characteristics extracted electronically recorded shapes, data...

As an SNS, Twitter is popular because users can post their emotions as a short message easily. Emotional tweets may influence user relationships. In our previous study, we found that positive construct mutual relationships in Twitter. Keyword matching with emotional word dictionaries was used to detect users. The problem of keyword the limitation number. To solve this problem, use machine learning, specifically Naive Bayes Classification, classify tweets. We analyze whether there difference...

Nowadays, it has become convenient to record data related an individual using a wearable device. However, is difficult utilize the according individual, especially anomaly detection. Anomaly detection very important for healthcare, e.g., early detecting of illness. In our previous study, we proposed approach specifying latent factors Structural Equation Modeling (SEM). this paper, propose improved taking account personal status based on factors. To estimate states, adopt Hidden Markov Model...

Underlying latent factors may cause a person to feel unwell. As the influence of increases, will become sick. It is difficult directly measure on risk degrees. However, early symptoms disease affect vital signs such as body temperature and blood pressure, which be result factors. Deep learning often used predict onset owing its high accuracy. reliability this method limited because characteristics black-box model. In study, we propose new approach detect health abnormality. We regard degree...

The lockdown caused by the COVID-19 epidemic has led to using smartphones and decreasing physical activity in world. It is known that increased screen time decreased have bad effects on mental health. However, few studies investigate influence of amount exercise. By analyzing influence, exercise promotion services can be improved. Therefore, this study, we challenge clarify relationship between time. Using a machine learning method, verify importance We collect data smartphone time, tablet...

Personal data is related to an individual, generated by or metadata about individual. To analyze personal comprehensively, it needed consider different types and sources of data. Moreover, should be considered not only explicit attributes but also latent factors. In this study, specify factors, we use Structural Equation Modeling (SEM) with a domain model for analysis. The represents the relationship between factors measures that are possible obtained wearable device. We construct activeness...

COVID-19 has resulted in a public health global crisis. The pandemic control necessitates epidemic models that capture the trends and impacts on infectious individuals. Many exciting can implement this but they lack practical interpretability. This study combines epidemiological network theories proposes framework with causal interpretability response to issue. consists of an extended model interconnected networks dynamic structure major human mobility. networked analysis focuses stochastic...

In recent years, it is very popular to use Twitter as an interaction tool and for information transmission sharing well. It more difficult us understand the flow on than usual dialogue conversation. But will become easier catch if we can focus priority words of Tweets. As know, word Tweets be measured by betweenness centrality based co-occurrence network. However, unknown whether same what users think or not, which has not yet been well studied. this study, design experiment compare...

On Twitter, a user can create multiple accounts and tweet to express emotions or talk about something in the accounts. Tweets reflect user's topics of interest, however, similarity emotion topic across his her is not clear. In this study, we analyze emotional topical tendencies for one's reveal relationship We use Japanese analysis tool named ML-Ask classify estimate tendency. Furthermore, Latent Dirichlet Allocation (LDA) extract Then, investigate accounts, terms respectively. our...