This paper presents the development of an IoT camera system aimed at detecting wildlife animals in outdoor settings. To achieve higher detection accuracy, reduce power consumption, and lower costs, we propose a novel approach for surveillance systems. Before the stage of uploading image and video data into a cloud server, we perform spectral analysis on both infrared and audio data collected from the environment. Our approach significantly reduces transmission costs while minimizing power consumption. We conducted a series of experiments, including motion detection and battery endurance tests, to validate our approach. Our system showed stable operation over an extended period of time and promising detection accuracy. The results demonstrate the potential for our approach to revolutionize the field of wildlife monitoring and management.

Changing amount of radiation dose has been a great concern by citizen near the difficult-to-return area after the Fukushima Daiichi nuclear disaster. Rigorous assessment of public safety including inaccessible forest areas at a meter level is one of the keys in the disaster recovery plan. Each measurement point near the ground surface in UAV (Unmanned Aerial Vehicle) sensing are exposed from the effects of radiation emission from various angles in the fields including forest and plain, and thus acquisition of the attenuation characteristics on site is not realistic by simply using the spatial integration of point-kernels. The proposed method in this paper utilizes a double exponential curve for the least-squares fitting. The field test at a resident in the forests near the difficult-to-return area was performed, and we found not only a strong correlation between measured value and estimation result of the proposed method (r = 0.86, p < 0.01) but also the improvement of more than 10% in RMSE (root mean squared error) from results of the existing methods using an exponential decay function. Importantly, the experimental result suggested that the proposed method completely accepts to use the different measurement data, both measurement points near the ground surface and the flight heights during the UAV sensing.

Mental disorder caused by chronic stress is mostly difficult to be aware of by oneself. There are social barriers including lack of perceived need for mental health services even if the potential patients have the desire to receive healthcare support. On the other hand, self-report inventories such as the Beck Depression Inventory (BDI-II) and State-Trait Anxiety Inventory (STAI) can tell the emotional valence as a screening test for depressive and anxiety disorders, which are the key elements in the mental health assessment. However, the results of the self-report inventories themselves are not sufficient tool to persuade the test respondents to clearly understand how the results can be serious and the causal factors can affect the mental state in their recent life-style. On the other hand, Laterality Index at Rest (LIR) has been proposed for evaluation of mental stress level from the analysis of dynamic changes in oxygen concentration in the prefrontal cortex at the restingstate. This study practically applies LIR for the long-term lifelog monitoring. Correlation analysis on LIR, STAI and BDI-II for 19 young subjects was first performed, and then compared with the temporal changes in the lifelog including the sleep time and the amount of physical activity. Importantly, LIR correlates to both STAI and BDI scores in the time series with different cycles.

Changing amount of radiation dose has been a great concern by citizen near the difficult-to-return area in Japan. Rigorous assessment of public safety including inaccessible areas at a meter level is one of the keys to resolution of this concern. Observation approach in this study is the use of quadcopter UAVs (unmanned aerial vehicles) for extensively covering measurement points. However, sometimes measurement points are surrounded by different landcovers including high forest, building and uneven ground, and thus estimation accuracy depends on the geographical feature near the measurement point. This paper presents a landcover-based 3-dimensional inverse distance weighting for visualization of radiation dose in a web service system. The field test at a resident in forests was performed, and we found that the proposed method improves RMSE by 23% with the greater visibility at the roads surrounded by high forests where the average dose was 0.5 μSv/h.

Dimensional situation analytics provides a formal framework to analyze situations from Data Information Knowl-edge Wisdom (DIKW) point of view. To date, the advent of big data driven applications opens up many frontiers in artificial intelligence and computer science, and yet it also raises a series of challenges due to theirs empirical and experimental nature. In particular, to systematically and analytically understand the logical connection through which intelligence and knowledge is derived from data and information deterministically is one of the far-reaching future objectives in computer science. Starting from an earlier result on Dimensional Situation Analytics (DSA), where the initial efforts targeted at the integration of situations and DIKW ontology, this paper brings the prospect of real world applications of DSA into perspective. A good example is UAV path planning for efficient radiation detection and monitoring, which links the pervious result, i.e., the DSA formal framework, with real world experimentation and thereof further explores on the effectiveness and future work for the DSA.

This paper introduces a UAV path planning system to provide path plans for radiation dose mapping near residential area in meter-level resolution. The proposed method first identifies void areas, i.e., the GPS coordinates without sufficient measured points within a search radius, from the observation result of the previous UAV flight. The proposed method employs the flood-fill algorithm for path planning within each chunk of adjacent void areas, and the 2-opt algorithm performs path planning between the chunks of void areas. From the result obtained in our real-world case study of radiation dose mapping near an area affected by the Fukushima Daiichi Nuclear Power Plant disaster, the proposed method significantly reduces flight time compared to the results given from the algorithms of 2-opt only and flood-fill only, respectively. More importantly, one of our findings is that, even if multi-rotor UAV is used, the number of turns during the flight is the major factor of actual flight cost.

This study assesses the Frontal Alpha Asymmetry (FAA) obtained from EEG data at the resting-state and Laterality Index at Rest (LIR) given from NIRS data for detection of depression risk in the early stage. The Comfort Vector model (CVM) is another potential biomarker using the feature value of prefrontal alpha wave fluctuation. In this paper, we discuss the potential biomarkers for assessment of depression risk. From the experimental result by simultaneous NIRS and EEG recordings of healthy subjects, the values of FAA, LIR and CVM associated with BDI score were found. We discuss the potentials of long-term simultaneous NIRS and EEG monitoring.

The three papers in this special section were presented at the 14th International Conference on Smart Homes and Health Telematics (ICOST 2016) that was hosted by Huazhong University of Science and Technology in China. Addresses the emergence of Digital Healthcare where there has been a sharp increase of activities in research, design, development, real-world deployment and evaluation of smart environments, assistive technologies, medical robotics and health telematics systems by employing computing and communication technologies in the health domain. Digital Health can be described as convergence of digital and genomic technologies with health, healthcare, living, and society to enhance the efficiency of healthcare delivery and make medicine prescription and medical treatments more personalized and precise.

In this paper we present a new human-centered requirements elicitation methodology that effectively considers end-user's desire, behavioral and environmental contexts. We follow a methodology that uses a computationally rich definition of situation as a 3-tuple where d denotes human desire, A denotes the action vector, and E denotes the environment context vector. The proposed method of human-centered requirements elicitation is based on the situation -- transition structure which is a directed weighted graph that represents transition from one situation to another. We illustrate the proposed methodology through some case studies with open access data sets. Requirements thus elicited appear to be valid after manual inspection. Future directions along this line of research are then asserted.

Presents a listing of the Symposium organizing committee.

Critical situations such as running into an impasse and failure of decision-making during collaborative work are often hard to recognize by team members themselves. Such critical situations drive the collaborative work into poor continuity. Remote collaboration is even harder to stay active due to communication difficulty in decision-making. This study argues an effective visualization method for monitoring causal factors of conversational situation by multimodal dialogue analysis from turn-taking and mental workload for collaborative working and communication use. Our approach to Follow Awareness visualizes frequency of turn-taking and changing mental workload by the analysis of an EEG (electroencephalogram) based index. Mental workloads of two team members are compared as difference in their changes within a predetermined amount of times for the analysis of follows between the team members. Frequency of turn-taking and changes in mental workload are then displayed by a mobile device during their collaborative work for validation in real-time. Evaluation results from a case study of collaborative work in pair programming presented large difference of changes in mental workload at the point their active communication turned to silence by a small setback.

User problems encountered during the use of a software product are often hard to identify even after the software product is thoroughly-tested and then released. There are inevitably unexpected situations introduced or triggered by transient use patterns, however, these unexpected situations can be hardly eliminated due to various human factors on user interaction. This study of situation-oriented real user monitoring develops an application of concept lattice to represent use patterns from user interaction and perceive potential user problems. Data structure of user problem is modeled based on user problem ontology. Once a user problem is recognized, observation data of the use patterns are the subject for further analysis. In this paper, use patterns in a file upload service are used to demonstrate how the concept lattice is used and discuss about validity of the causal factors found in the concept lattice.

In order for the intelligent assistant systems to provide users with timely and appropriate assistances, most of them focus on what is considered to be the "rational" aspect of the user behaviors. However, since human desire is the fundamental driving force of human behaviors, without including users' desires, the system cannot provide most appropriate responses. We propose a hierarchical desire inference process based on the Bayesian Belief Networks (BBNs), that considers the affective states, behavior contexts and environmental contexts of a user at given points in time to infer the user's desire. The inferred desire of the highest probability from the BBNs is then used in the follow-up decision making.

While software evolution has been studied extensively in software engineering, few of these efforts have involved a systematic exploration of human epistemological attitudes, such as human desire and intention, as the driving force of software service evolution. Our work proposes a theoretical framework to monitor and reason about human intention and its changes, which in turn can be used to determine how software and services should evolve to be individualized and better serve each user. Extending the Situ framework, we explore the service satisfiability problem through sub-world coverage following Kripke semantics, which enjoys wide application in AI and other fields related to human epistemic reasoning.

Evolvability is essential for computer systems to adapt to the dynamic and changing requirements in response to instant or delayed feedback from a service environment that nowadays is becoming more and more context aware; however, current context-aware service-centric models largely lack the capability to continuously explore human intentions that often drive system evolution. To support service requirements analysis of real-world applications for services computing, this paper presents a situation-theoretic approach to human-intention-driven service evolution in context-aware service environments. In this study, we give situation a definition that is rich in semantics and useful for modeling and reasoning human intentions, whereas the definition of intention is based on the observations of situations. A novel computational framework is described that allows us to model and infer human intentions by detecting the desires of an individual as well as capturing the corresponding context values through observations. An inference process based on Hidden Markov Model makes instant definition of individualized services at runtime possible, and significantly, shortens service evolution cycle. We illustrate the possible applications of this framework through a smart home example aimed at supporting independent living of elderly people.

This paper proposes an Input Adjustable Tree Algorithm for the flag problems of evolutionary testing (ET). With the algorithm, the dependencies of input and internal/flag variables can be determined. Based on that, ET guides the search efficiently with the presence of flag variables in the source code.

Changing system requirements, especially for context awareness (CA) systems, often cause modifications in the software systems in order to adapt to dynamic environments. Since the requirements may become temporarily obsolete or contrary to human intentions, the CA systems need to be tuned to resolve the conflict. On the other hand, most CA design methods rely on pre-defined requirements and reasoning engine, thus, fail to address all the possible situations. Consequently, services provided by such a CA system are limited to accommodate some situations and unable to react as expected. Therefore, it is critical for CA systems to capture exceptions at runtime, infer changed human intentions, and adapt to these changes. This study focuses on inference of ever-changing human intentions and monitoring human intentions to handle system evolution. In this paper, we present an inference mechanism of human intentions via the human-machine dimensional inference ontology (HDIO). This ontology gives inference rules based on the BDI logic to deduce human intentions from contexts. Furthermore, the inference exercises of a healthcare system example shows how user intentions relate to system requirements and how they help improve self-adaptability of CA systems.

User intentions to obtain services evolve over time. Since the changes of intention may occur at any time, some system requirements may become temporarily obsolete or contrary to a user intention. However, user intentions often indicate potential, valuable goals for upgrading the system to a new version or engaging new development. Our research tackles requirements analysis issues via feedback from context awareness systems to identify user intentions and capture instant definitions of goal in a robust manner. This paper presents a context-aware goal elicitation process by exploring the aspects of data, information, knowledge and wisdom. Furthermore, captured user intentions and goals are shown in a case study of healthcare system, and issues for the goal elicitation are explored.

In large-scale, real-time systems, the software design process is still highly dependent on the skills of the developers. To enable the efficient, speedy design of reliable software products, we require a means of conveying design decisions from experts to other engineers. Our approach involves the development of the "causality of problem-issue-solution" (CAPIS) model which can be used to represent experts' thought processes. The CAPIS model divides a thought process that includes complexity and diversity into problems, issues, and solutions (PIS), and then describes conceptual models based on the knowledge hierarchy of data, information, knowledge, and wisdom. The PIS ontology is used to describe items in the conceptual models. This paper describes a software design method that is based on this CAPIS model. As an example, we consider the thought processes involved in building reliability into a UML class diagram