In disaster scenarios, effective communication is crucial, yet language barriers often hinder timely and accurate information dissemination, exacerbating vulnerabilities and complicating response efforts. This paper presents a novel, multilingual, voice-based social network specifically designed to address these challenges. The proposed system integrates advanced artificial intelligence (AI) with blockchain technology to enable secure, asynchronous voice communication across multiple languages. The application operates independently of external servers, ensuring reliability even in compromised environments by functioning offline through local networks. Key features include AI-driven real-time translation of voice messages, ensuring seamless cross-linguistic communication, and blockchain-enabled storage for secure, immutable records of all interactions, safeguarding message integrity. Designed for cross-platform use, the system offers consistent performance across devices, from mobile phones to desktops, making it highly adaptable in diverse disaster situations. Evaluation metrics demonstrate high accuracy in speech recognition and translation, low latency, and user satisfaction, validating the system’s effectiveness in enhancing communication during crises. This solution represents a significant advancement in disaster communication, bridging language gaps to support more inclusive and efficient emergency response.

Critical infrastructures, such as water treatment plants (WTPs) and communication networks, are vital to our daily lives, providing essential resources. As these infrastructures increasingly rely on computer systems and internet networks, conducting cybersecurity training on expensive, real-world equipment becomes impractical due to the risk of operational interruptions. To address this challenge, we present a Digital Twin training platform that simulates three key cybersecurity concepts: Input Manipulation, Output Manipulation, and Denial of Service attacks, within the context of WTPs. These concepts are mapped to four critical functions: water level, chlorine level, water temperature, and the microbial water purification process. This paper primarily focuses on the design and development of the VR component of our digital twin platform, as well as the integration process with our hardware testbed. Initial investigations demonstrated significant potential for the experiential learning platform, serving as an effective tool for educating users about cybersecurity issues in mission-critical facilities such as WTPs.

Numerical simulation has become omnipresent in the automotive domain, posing new challenges such as high-dimensional parameter spaces and large as well as incomplete and multi-faceted data. In this design study, we show how interactive visual exploration and analysis of high-dimensional, spectral data from noise simulation can facilitate design improvements in the context of conflicting criteria. Here, we focus on structure-borne noise, i.e., noise from vibrating mechanical parts. Detecting problematic noise sources early in the design and production process is essential for reducing a product's development costs and its time to market. In a close collaboration of visualization and automotive engineering, we designed a new, interactive approach to quickly identify and analyze critical noise sources, also contributing to an improved understanding of the analyzed system. Several carefully designed, interactive linked views enable the exploration of noises, vibrations, and harshness at multiple levels of detail, both in the frequency and spatial domain. This enables swift and smooth changes of perspective; selections in the frequency domain are immediately reflected in the spatial domain, and vice versa. Noise sources are quickly identified and shown in the context of their neighborhood, both in the frequency and spatial domain. We propose a novel drill-down view, especially tailored to noise data analysis. Split boxplots and synchronized 3D geometry views support comparison tasks. With this solution, engineers iterate over design optimizations much faster, while maintaining a good overview at each iteration. We evaluated the new approach in the automotive industry, studying noise simulation data for an internal combustion engine.

Energy consumption of buildings varies significantly across buildings with similar functions and locations. Occupant behavior is one of the most significant sources of uncertainty related to energy consumption in buildings. A deeper understanding of occupant energy behavior can help in designing personalized behavior intervention strategies to save energy and predict energy consumption. This paper uses the Pecan Street dataset to cluster building occupants based on the energy they consume for each appliance in the household, and then developed load profiles for each of the clusters.

The outbreak of COVID-19 has put various restrictions on human lifestyle. At the beginning of the outbreak, almost all public spaces were closed to minimize the spread of this virus. Even as public spaces open up, they have several restrictions. Such restrictions include limited occupancy in common rooms to ensure social distancing and this can lead to increased occupancy costs inside buildings. The strategy of "Design as a cure" has been long used by architects and urban planners to minimize the spread of infectious diseases in urban environments. Re-configuring the space layout and optimizing the heating, ventilation, and air condition (HVAC) operations were some immediate solutions proposed by building designers to minimize the risk of COVID-19 infection in buildings. This paper explores the use of smart re-configurable spaces (SReS) to improve the efficiency of indoor space utilization while maintaining a safe indoor environment. We used an existing smart building design framework to design SReS for a common area/lounge in one of the cadet resident halls at Virginia Tech. User requirements were measured by conducting an interview with the residential coordinator and focus groups among the cadets. The concept of generative design was used in Revit 2021 to design various layouts of the lounge. Towards the end, we create a layout for maximum occupancy and suggest various re-configuration strategies. Future work includes modeling and evaluating the human-building interaction of SReS in virtual reality (VR).

We describe an approach to human posture classification using RGBD camera (Kinect V2 sensor) data. We compared deep learning methods for human posture classification versus classical data classification methods. We conducted a user study where participants assumed various postures, including whole body, upper and lower body, as well as body transition motion. Several classical data classification methods, such as support vector machine, random forest, neural network, and Adaboost, were used for posture classification. Results show that the posture classification accuracy for the classical data classification methods is between 75% an 99%. The accuracy of the classical data classification methods is comparable to the accuracy of the long-short-term-memory (LSTM) deep learning method which is between 86% and 99%. Our findings suggest that the use of the classical data classification methods on the RGBD camera data is likely sufficient for posture classification, at least for certain task scenarios without incurring the overhead of deep learning.

Analysis of unstructured, complex data is a challenging task that requires a combination of various data analysis techniques, including, among others, deep learning, statistical analysis, and interactive methods. A simple use of individual data analysis techniques addresses only a part of the overall data exploration and analysis challenge. The visual exploration process also requires exploration of what-if scenarios, a continuous and iterative process of generating and testing hypotheses. We describe a comprehensive approach to exploration of complex data that combines automatic and interactive data analysis and hypotheses testing techniques. The proposed approach is illustrated on a publicly available spatio-temporal data set, a collection of bird songs recorded over an extended period of time. Convolutional Neural Network is used to identify and classify bird species from the bird songs data. In addition, two new interactive views, integrated within a coordinated multiple views setup, are introduced: the what-if view and the spectrogram view. The proposed approach is used to develop a unified tool for exploration of bird songs data, called Bird Song Explorer.

US and Europe have been experiencing an unprecedented increase in the number of older adults. Increased life expectancy and increasingly aging population present challenges in terms of costs associated with elderly healthcare and wellbeing, as well as decreasing availability of health personnel. Similar trends are occurring in the rest of the world. There is a strong push to promote remote telehealth monitoring centers or virtual care centers (VCCs) as a way to address health care needs, especially for the aging population. Technology advances, such as Internet of Things and Smart Built Environments, support proliferation of smart and secure telehealth care that can be implemented at all levels. Remote patient monitoring, combined with personalized interventions and coaching, serves as the foundation for VCCs. However, there are trade-offs with regard to privacy and changes in the living environment and the overall scalability. We need to explore how technology can be utilized to provide health services while protecting and preserving privacy of all stakeholders. A distributed VCC (DVCC), created from individual VCCs and crossing regional and national borders, can provide effective, continuous service with ability to adjust to unforeseen events and emergencies. We discuss a meta-model-based approach to protect patients’ data while improving the efficiency of the care center personnel, which will allow remote care centers to more easily scale as need to provide round-the-clock monitoring.

Recent advances in wearable devices capable of measuring physiological signals such as Electrodermal Activity (EDA) support affective computing and related applications. We present an algorithm that uses EDA signals to detect highlights of a stimulus. To test the accuracy of our method, two different mediums, a scene from a movie, as our ground truth, and a scene from a video game, for testing the algorithm, were selected. We conducted a user study with 20 participants, analyzed the differences between mediums and validated the accuracy of our method for detecting the highlights of the stimulus using only EDA signals. Our approach uses commonalities among users based on their phasic responses for detecting highlights. The result of the study shows a F1 score of 0.93 and 0.89 for movie and video game respectively. We are in a process of conducting a user study with several sensory devices to explore combined physiological responses using IAPS data set as a stimulus.

Smart Built Environments (SBEs) empowered by the Internet of Things (IoT) dramatically augment the capabilities of traditional built environments by imbuing everyday objects with computational and communication capabilities. SBEs primarily consist of three types of components: architectural elements, embedded technology (smart objects) and enhanced interaction modalities. As smart objects hold the ability to change the state of the environment, inefficient design of smart configurations can lead to potentially harmful conditions affecting the safety and security of the inhabitants. The interaction scenarios and space use pattern of SBEs are also notably different from traditional built environments. But, to the best of our knowledge, there has been limited work on developing a consolidated design framework addressing the three interdependent SBE elements and evaluating the safety and security of the IoT application environment. We propose an SBE design framework based on the traditional architectural design process. The framework combines the technological aspects of SBEs with the traditional architectural design process while leveraging Building Information Modeling (BIM) and participatory design. We describe a Mixed Reality(MR)-based reference framework implementation that is particularly helpful for representing, visualizing and modeling the vast amount of data, digital components and novel SBE interaction scenarios.

We propose a vision and a new paradigm for a Marketplace of Services as an integral part of a Smart Community Infrastructure. The Smart Communities of the (near) future will provide a large number of services to be offered as utilities and sold on a metered basis. These services will be aggregated and synthesized from a hierarchy of resources produced and shared by the community itself. Smart Community members or visitors will purchase as much or as little of these services as they find suitable to their needs and are billed accordingly. The context and condition of the members and the environment play a major role in service offerings and adaptations. Smart Communities have four fundamental characteristics: sustainability, resilience, empathy-driven proactive intelligence, and emergent behavior. These fundamental characteristics are a direct consequence of the underlying platform construction and management of the marketplace and its underlying IoT infrastructure. We illustrate our vision using examples of services that the marketplace may offer. We also highlight some major research challenges that need to be resolved to make our vision reality.

Parking has been a major challenge in big cities for decades. Studies have shown direct correlation between parking and the increase in traffic density, thus leading to higher levels of pollution and longer overall trip time. Conventional solutions mainly depend on area-based semi-automated digital parking assistants. Such solutions fall short of offering an optimized solution that enhances the utilization of the set of city-wide parking garages (global garage space), regardless of the physical location. We propose smartpark, a novel, comprehensive location-independent smart park and transfer service to satisfy users objectives such as timeliness, low cost and convenience, while providing efficient globally-balanced garage-space utilization.smartpark utilizes an IoT network to monitor the availability of parking spots in a city-wide multi-garage system. The system employs a genetic algorithm to find the optimal balance between all users and system’s objectives. Simulation results demonstrate that smartpark services are both effective and efficient.

We often simulate multiple variations of the same model - a simulation ensemble - to better understand intricate physical phenomena. The analysis of complex simulation ensembles represents a grand challenge which is approached by both computational and interactive, visual methods. We describe how modern visual analytics helps to analyze simulation ensemble data. A clever combination of computational and interactive methods supports the simulation expert to gain deeper insight into the data and into the physical phenomenon that is represented by the ensemble. An analysis environment that combines interactive visualization and computational analysis provides unique advantages for the exploration and analysis of complex ensemble data. It helps the domain expert to efficiently cope with analysis tasks, in particular when they are only partially defined. In this work, we describe the basics of interactive visual analysis, several approaches to interactive ensemble steering, and means for results quantification and analysis reproducibility.

We describe our analysis of VAST Challenge 2018 Mini-Challenge 2 data set using a collection of visualization tools. We used the tools for better user interaction and to introduce new views in support of visual analytics. We answer some of the challenge questions and plan further research on data exploration and analysis based on the newly introduced data model, interaction, and views.

Figure 1.Analysis workflow: we combine automatic and interactive approach in order to analyze complex data. Neither approach alone would have been sufficient for the analysis.We describe our analysis of VAST Challenge 2018 Mini-Challenge 1. Our approach combines automatic analysis and interactive exploration. We improve user interaction and introduce new views to support analysis. At the same time, we design a convolutional neural network in order to compute a classifier of bird-singing audio files. The classifier and the interactive exploration tool are used to answer some of the challenge questions. Our analysis suggest that the audio files are most probably not of Pipits and, moreover, if there are Pipits among them, they are represented in minority. This finding indicates a need for further investigation.

The Internet of Things (IoT) systems usually use constrained devices with limited computation and communication resources facilitating the use of lightweight communication protocols. Message Queue Telemetry Transport (MQTT) is a lightweight publish-subscribe-based messaging protocol that works on top of the TCP/IP protocol. We present our progress towards building a simulation tool for evaluating the Quality of Service (QoS) in MQTT-based IoT systems. This tool can facilitate the design of IoT systems that need to meet certain QoS requirements.

Exploratory visual analysis helps scientists and domain experts gain insight into complex data sets. Tangible visual analysis can be used to bring interactive data exploration to non-expert users, such as visitors in science museums (or similar settings). Collaborative possibilities make it attractive for experts users, as well. We present a preliminary work on tangible brushing for visual analysis in a mixed reality environment. Mixed reality devices, such as Microsoft HoloLens, are blurring the barriers between the real and virtual environments. We can take advantage of these new technologies to provide a mixed reality based system for tangible visual analysis. We describe the main idea, the design principles, and the prototype development.

Microblogs, such as Twitter, are a way for users to express their opinions or share pieces of interesting news by posting relatively short messages (corpus) compared with the regular blogs. The volume of corpus updates that users receive daily is overwhelming. Also, as information diffuses from one user to another, some topics become of interest to only small groups of users, thus do not become widely adopted, and could fade away quickly. This paper proposes a framework to enhance user's interaction and experience in social networks. It first introduces a model that provides better subscription to the user through a dynamic personalized recommendation system that provides the user with the most important tweets. This paper also presents TrendFusion, an innovative model used to enhance the suggestions provided by the social media to the users. It analyzes, predicts the localized diffusion of trends in social networks, and recommends the most interesting trends to the user. Our performance evaluation demonstrates the effectiveness of the proposed recommendation system and shows that it improves the precision and recall of identifying important tweets by up to 36% and 80%, respectively. Results also show that TrendFusion accurately predicts places in which a trend will appear, with 98% recall and 80% precision.

IoT-enabled built environments have potential to improve the lives of individuals, groups, and the broader community. Internet of Things (IoT), a collection of networked and interacting embedded devices, provides the necessary infrastructure and enabling technologies to design, develop and deploy smart built environments. We describe an approach to supporting user interaction with IoT-enabled smart built environments. This approach takes advantages of affordances and embodied cognition in a physical space to model user interaction with built spaces. The corresponding implementation leverages standard protocols (MQTT) and IoT-Lite ontology to represent IoT resources, entities and services. A proof-of-concept light-control application demonstrates the approach.