Fusion of Environmental Sensors for Occupancy Detection in a Real Construction Site.

Internet-of-Things systems are increasingly being installed in buildings to transform them into smart ones and to assist in the transition to a greener future. A common feature of smart buildings, whether commercial or residential, is environmental sensing that provides information about temperature, dust, and the general air quality of indoor spaces, assisting in achieving energy efficiency. Environmental sensors though, especially when combined, can also be used to detect occupancy in a space and to increase security and safety. The most popular methods for the combination of environmental sensor measurements are concatenation and neural networks that can conduct fusion in different levels. This work presents an evaluation of the performance of multiple late fusion methods in detecting occupancy from environmental sensors installed in a building during its construction and provides a comparison of the late fusion approaches with early fusion followed by ensemble classifiers. A novel weighted fusion method, suitable for imbalanced samples, is also tested. The data collected from the environmental sensors are provided as a public dataset.

Multi-Sensors for Human Activity Recognition.

Human activity recognition (HAR) has made significant progress in recent years, with growing applications in various domains, and the emergence of wearable and ambient sensors has provided new opportunities in the field [...].

Assessing Virtual Reality Spaces for Elders Using Image-Based Sentiment Analysis and Stress Level Detection.

Seniors, in order to be able to fight loneliness, need to communicate with other people and be engaged in activities to keep their minds active to increase their social capital. There is an intensified interest in the development of social virtual reality environments, either by commerce or by academia, to address the problem of social isolation of older people. Due to the vulnerability of the social group involved in this field of research, the need for the application of evaluation methods regarding the proposed VR environments becomes even more important. The range of techniques that can be exploited in this field is constantly expanding, with visual sentiment analysis being a characteristic example. In this study, we introduce the use of image-based sentiment analysis and behavioural analysis as a technique to assess a social VR space for elders and present some promising preliminary results.

Graph Theoretical Analysis of EEG Functional Connectivity Patterns and Fusion with Physiological Signals for Emotion Recognition.

Emotion recognition is a key attribute for realizing advances in human-computer interaction, especially when using non-intrusive physiological sensors, such as electroencephalograph (EEG) and electrocardiograph. Although functional connectivity of EEG has been utilized for emotion recognition, the graph theory analysis of EEG connectivity patterns has not been adequately explored. The exploitation of brain network characteristics could provide valuable information regarding emotions, while the combination of EEG and peripheral physiological signals can reveal correlation patterns of human internal state. In this work, a graph theoretical analysis of EEG functional connectivity patterns along with fusion between EEG and peripheral physiological signals for emotion recognition has been proposed. After extracting functional connectivity from EEG signals, both global and local graph theory features are extracted. Those features are concatenated with statistical features from peripheral physiological signals and fed to different classifiers and a Convolutional Neural Network (CNN) for emotion recognition. The average accuracy on the DEAP dataset using CNN was 55.62% and 57.38% for subject-independent valence and arousal classification, respectively, and 83.94% and 83.87% for subject-dependent classification. Those scores went up to 75.44% and 78.77% for subject-independent classification and 88.27% and 90.84% for subject-dependent classification using a feature selection algorithm, exceeding the current state-of-the-art results.

A Review of Multisensor Data Fusion Solutions in Smart Manufacturing: Systems and Trends.

Manufacturing companies increasingly become "smarter" as a result of the Industry 4.0 revolution. Multiple sensors are used for industrial monitoring of machines and workers in order to detect events and consequently improve the manufacturing processes, lower the respective costs, and increase safety. Multisensor systems produce big amounts of heterogeneous data. Data fusion techniques address the issue of multimodality by combining data from different sources and improving the results of monitoring systems. The current paper presents a detailed review of state-of-the-art data fusion solutions, on data storage and indexing from various types of sensors, feature engineering, and multimodal data integration. The review aims to serve as a guide for the early stages of an analytic pipeline of manufacturing prognosis. The reviewed literature showed that in fusion and in preprocessing, the methods chosen to be applied in this sector are beyond the state-of-the-art. Existing weaknesses and gaps that lead to future research goals were also identified.

Smart integration of sensors, computer vision and knowledge representation for intelligent monitoring and verbal human-computer interaction.

The details presented in this article revolve around a sophisticated monitoring framework equipped with knowledge representation and computer vision capabilities, that aims to provide innovative solutions and support services in the healthcare sector, with a focus on clinical and non-clinical rehabilitation and care environments for people with mobility problems. In contemporary pervasive systems most modern virtual agents have specific reactions when interacting with humans and usually lack extended dialogue and cognitive competences. The presented tool aims to provide natural human-computer multi-modal interaction via exploitation of state-of-the-art technologies in computer vision, speech recognition and synthesis, knowledge representation, sensor data analysis, and by leveraging prior clinical knowledge and patient history through an intelligent, ontology-driven, dialogue manager with reasoning capabilities, which can also access a web search and retrieval engine module. The framework's main contribution lies in its versatility to combine different technologies, while its inherent capability to monitor patient behaviour allows doctors and caregivers to spend less time collecting patient-related information and focus on healthcare. Moreover, by capitalising on voice, sensor and camera data, it may bolster patients' confidence levels and encourage them to naturally interact with the virtual agent, drastically improving their moral during a recuperation process.

Combining RSSI and Accelerometer Features for Room-Level Localization.

The continuing advancements in technology have resulted in an explosion in the use of interconnected devices and sensors. Internet-of-Things (IoT) systems are used to provide remote solutions in different domains, like healthcare and security. A common service offered by IoT systems is the estimation of a person's position in indoor spaces, which is quite often achieved with the exploitation of the Received Signal Strength Indication (RSSI). Localization tasks with the goal to locate the room are actually classification problems. Motivated by a current project, where there is the need to locate a missing child in crowded spaces, we intend to test the added value of using an accelerometer along with RSSI for room-level localization and assess the performance of ensemble learning methods. We present here the results of this preliminary approach of the early and late fusion of RSSI and accelerometer features in room-level localization. We further test the performance of the feature extraction from RSSI values. The classification algorithms and the fusion methods used to predict the room were evaluated using different protocols applied to a public dataset. The experimental results revealed better performance of the RSSI extracted features, while the accelerometer's individual performance was poor and subsequently affected the fusion results.

Study of gene expressions' correlation structures in subgroups of Chronic Lymphocytic Leukemia Patients.

In chronic lymphocytic leukemia (CLL) the interaction of leukemic cells with the microenvironment ultimately affects patient outcome. CLL cases can be divided in two subgroups with different clinical course based on the mutational status of the immunoglobulin heavy variable (IGHV) genes: mutated CLL (M-CLL) and unmutated CLL (U-CLL). Since in CLL, the differentiated relation of genes between the two subgroups is of greater importance than the individual gene behavior, this paper investigates the differences between the groups' gene interactions, by comparing their correlation structures. Fisher's test and Zou's confidence intervals are employed to detect differences of correlation coefficients. Afterwards, networks created by the genes participating in most differences are estimated with the use of structural equation models (SEM). The analysis is enhanced with graph modeling in order to visualize the between group differences in the gene structures of the two subgroups. The applied methodology revealed stronger correlations between genes in U-CLL patients, a finding in line with related biomedical literature. Using SEM for multigroup analysis, different gene structures between the two groups of patients were confirmed. The study of correlation structures can facilitate the detection of differential gene expression profiles in CLL subgroups, with potential applications in other diseases. Comparison of correlations can be very useful in understanding the complex internal structural differences which signify the variations of a disease.

Not all IGHV3-21 chronic lymphocytic leukemias are equal: prognostic considerations.

An unresolved issue in chronic lymphocytic leukemia (CLL) is whether IGHV3-21 gene usage, in general, or the expression of stereotyped B-cell receptor immunoglobulin defining subset #2 (IGHV3-21/IGLV3-21), in particular, determines outcome for IGHV3-21-utilizing cases. We reappraised this issue in 8593 CLL patients of whom 437 (5%) used the IGHV3-21 gene with 254/437 (58%) classified as subset #2. Within subset #2, immunoglobulin heavy variable (IGHV)-mutated cases predominated, whereas non-subset #2/IGHV3-21 was enriched for IGHV-unmutated cases (P = .002). Subset #2 exhibited significantly shorter time-to-first-treatment (TTFT) compared with non-subset #2/IGHV3-21 (22 vs 60 months, P = .001). No such difference was observed between non-subset #2/IGHV3-21 vs the remaining CLL with similar IGHV mutational status. In conclusion, IGHV3-21 CLL should not be axiomatically considered a homogeneous entity with adverse prognosis, given that only subset #2 emerges as uniformly aggressive, contrasting non-subset #2/IGVH3-21 patients whose prognosis depends on IGHV mutational status as the remaining CLL.

Clinical effect of stereotyped B-cell receptor immunoglobulins in chronic lymphocytic leukaemia: a retrospective multicentre study.

BACKGROUND: About 30% of cases of chronic lymphocytic leukaemia (CLL) carry quasi-identical B-cell receptor immunoglobulins and can be assigned to distinct stereotyped subsets. Although preliminary evidence suggests that B-cell receptor immunoglobulin stereotypy is relevant from a clinical viewpoint, this aspect has never been explored in a systematic manner or in a cohort of adequate size that would enable clinical conclusions to be drawn. METHODS: For this retrospective, multicentre study, we analysed 8593 patients with CLL for whom immunogenetic data were available. These patients were followed up in 15 academic institutions throughout Europe (in Czech Republic, Denmark, France, Greece, Italy, Netherlands, Sweden, and the UK) and the USA, and data were collected between June 1, 2012, and June 7, 2013. We retrospectively assessed the clinical implications of CLL B-cell receptor immunoglobulin stereotypy, with a particular focus on 14 major stereotyped subsets comprising cases expressing unmutated (U-CLL) or mutated (M-CLL) immunoglobulin heavy chain variable genes. The primary outcome of our analysis was time to first treatment, defined as the time between diagnosis and date of first treatment. FINDINGS: 2878 patients were assigned to a stereotyped subset, of which 1122 patients belonged to one of 14 major subsets. Stereotyped subsets showed significant differences in terms of age, sex, disease burden at diagnosis, CD38 expression, and cytogenetic aberrations of prognostic significance. Patients within a specific subset generally followed the same clinical course, whereas patients in different stereotyped subsets-despite having the same immunoglobulin heavy variable gene and displaying similar immunoglobulin mutational status-showed substantially different times to first treatment. By integrating B-cell receptor immunoglobulin stereotypy (for subsets 1, 2, and 4) into the well established Döhner cytogenetic prognostic model, we showed these, which collectively account for around 7% of all cases of CLL and represent both U-CLL and M-CLL, constituted separate clinical entities, ranging from very indolent (subset 4) to aggressive disease (subsets 1 and 2). INTERPRETATION: The molecular classification of chronic lymphocytic leukaemia based on B-cell receptor immunoglobulin stereotypy improves the Döhner hierarchical model and refines prognostication beyond immunoglobulin mutational status, with potential implications for clinical decision making, especially within prospective clinical trials. FUNDING: European Union; General Secretariat for Research and Technology of Greece; AIRC; Italian Ministry of Health; AIRC Regional Project with Fondazione CARIPARO and CARIVERONA; Regione Veneto on Chronic Lymphocytic Leukemia; Nordic Cancer Union; Swedish Cancer Society; Swedish Research Council; and National Cancer Institute (NIH).