No description available.

No description available.

No description available.

The study of information extraction and knowledge exploration in the urban environment is gaining popularity. Ubiquitous sensors and a plethora of statistical reports provide an immense amount of heterogeneous urban data, such as traffic data, crime activity statistics, social media messages, and street imagery. The development of methods for heterogeneous urban data-based event identification and impacts analysis for a variety of event topics and assumptions is the subject of this dissertation. A graph convolutional neural network for crime prediction, a multitask learning system for traffic incident prediction with spatiotemporal feature learning, social media-based transportation event detection, and a graph convolutional network-based cyberbullying detection algorithm are the four methods proposed. Additionally, based on the sensitivity of these urban sensor data, a comprehensive discussion on ethical issues of urban computing is presented. This work makes the following contributions in urban perception predictions: 1) Create a preference learning system for inferring crime rankings from street view images using a bidirectional convolutional neural network (bCNN). 2) Propose a graph convolutional networkbased solution to the current urban crime perception problem; 3) Develop street view image retrieval algorithms to demonstrate real city perception. This work also makes the following contributions in traffic incident effect analysis: 1) developing a novel machine learning system for predicting traffic incident duration using temporal features; 2) modeling traffic speed similarity among road segments using spatial connectivity in feature space; and 3) proposing a sparse feature learning method for identifying groups of temporal features at a higher level. In transportation-related incidents detection, this work makes the following contributions: 1) creating a real-time social media-based traffic incident detection platform; 2) proposing a query expansion algorithm for traffic-related tweets; and 3) developing a text summarization tool for redundant traffic-related tweets. Cyberbullying detection from social media platforms is one of the major focus of this work: 1) Developing an online Dynamic Query Expansion process using concatenated keyword search. 2) Formulating a graph structure of tweet embeddings and implementing a Graph Convolutional Network for fine-grained cyberbullying classification. 3) Curating a balanced multiclass cyberbullying dataset from DQE, and making it publicly available. Additionally, this work seeks to identify ethical vulnerabilities from three primary research directions of urban computing: urban safety analysis, urban transportation analysis, and social media analysis for urban events. Visions for future improvements in the perspective of ethics are addressed. / Doctor of Philosophy / The ubiquitously deployed urban sensors such as traffic speed meters, street-view cameras, and even smartphones in everybody's pockets are generating terabytes of data every hour. How do we refine the valuable intelligence out of such explosions of urban data and information became one of the profitable questions in the field of data mining and urban computing. In this dissertation, four innovative applications are proposed to solve real-world problems with big data of the urban sensors. In addition, the foreseeable ethical vulnerabilities in the research fields of urban computing and event predictions are addressed. The first work explores the connection between urban perception and crime inferences. StreetNet is proposed to learn crime rankings from street view images. This work presents the design of a street view images retrieval algorithm to improve the representation of urban perception. A data-driven, spatiotemporal algorithm is proposed to find unbiased label mappings between the street view images and the crime ranking records. The second work proposes a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework. Such functionality provided by this model is helpful for the transportation operators and first responders to judge the influences of traffic incidents. In the third work, a social media-based traffic status monitoring system is established. The system is initiated by a transportation-related keyword generation process. A state-of-the-art tweets summarization algorithm is designed to eliminate the redundant tweets information. In addition, we show that the proposed tweets query expansion algorithm outperforms the previous methods. The fourth work aims to investigate the viability of an automatic multiclass cyberbullying detection model that is able to classify whether a cyberbully is targeting a victim's age, ethnicity, gender, religion, or other quality. This work represents a step forward for establishing an active anti-cyberbullying presence in social media and a step forward towards a future without cyberbullying. Finally, a discussion of the ethical issues in the urban computing community is addressed. This work seeks to identify ethical vulnerabilities from three primary research directions of urban computing: urban safety analysis, urban transportation analysis, and social media analysis for urban events. Visions for future improvements in the perspective of ethics are pointed out.

Accelerometers deployed within smart structures produce a wealth of vibration data that can be analyzed to infer information about the types of acceleration events that are occurring within the structure. In the case of monitored smart buildings, some of these acceleration events are linked to occupant behavior, such as walking, operating machinery, closing doors, etc. The identification and classification of such events has many potential applications within a smart structure or city. Understanding occupant patterns could be beneficial for operations, retail, or HVAC management, as it could be used to monitor occupancy flow with a relatively sparse sensor network. It may also have detrimental implications in terms of cybersecurity, where such information could be mined for malicious practices if unauthorized access to the data was obtained. This work presents methods for the detection and classification of vibration events in an experimental smart building, Goodwin Hall at Virginia Tech. Goodwin Hall's 200+ accelerometer network is used to gather acceleration data, from which vibration events are automatically detected and clustered. The presence of a vibration event is detected from a raw acceleration signal with an adaptive RMS threshold method. A feature vector is then created for each extracted event as areas under regions of the FFT of the event's acceleration signal. The feature vectors are then mapped into a low-dimensional space using principal component analysis, where they are clustered with various unsupervised algorithms. These processes have shown to be successful when gathering vibration events from a single-sensor setup, but pose challenges when expanded to a multi-sensor network. Because of this, expanded applications such as a semi-supervised classifier for events detected anywhere in the building are currently still under development. This semi-supervised process, combined with the known location of each sensor would allow inferences to be drawn about the frequency of different activity types in regions of the building not captured in the labeled data. Future work intends to address these multi-sensor challenges with adjustments to the algorithm process. / Master of Science / All objects experience vibrations when they are disturbed by some force. In the case of this work, the object is complex, a classroom building, but the principle still stands. When the building is disturbed by a force it will vibrate, even if the force is small, such as a person walking down a hallway or closing a door. The vibrations caused by these 'events' are unique to the type of event, that is, footstep vibrations will be different from door vibrations. These vibrations are observed with accelerometers, and the corresponding signal is used to determine what type of event caused the vibration. First, an event is automatically detected within the signal and separated from it. Second, characteristics unique to the signal are identified, a process known as 'feature extraction.' Finally, those features are used to distinguish the event from others and to identify what had caused it based on previous experimental data. The ability to detect these events and classify them introduces many interesting applications, including any that would stem from occupant detection, including improved security or operations, retail, or HVAC management. The methods here may also be applicable to other applications, such as monitoring bridges and machinery, or for developing cutting-edge smartphone applications with the accelerometer that is built in.

This thesis presents a solver to handle constrained-state-space ODEs. This solver locates the points where any of the states go outside of the constraining set, and then, transfers the control from the continuous time ODE to the function governing the behavior of the system on the boundaries of the constrained set. The main contribution of this solver is found simulating complex right-hand-sided ODEs for long periods of time. / Master of Science

Earth observation satellites (EOS) such as Landsat provide image datasets that can be immensely useful in numerous application domains. One way of analyzing satellite images for land use and land cover change (LULCC) is time series analysis (TSA). Several algorithms for time series analysis have been proposed by various groups in remote sensing; more algorithms (that can be adapted) are available in the general time series literature. However, in spite of an abundance of algorithms, the choice of algorithm to be used for analyzing an image stack is presently an open question. A concurrent issue is the prohibitive size of Landsat datasets, currently of the order of petabytes and growing. This makes them computationally unwieldy --- both in storage and processing. An EOS image stack typically consists of multiple images of a fixed area on the Earth's surface (same latitudes and longitudes) taken at different time points. Experiments on multicore servers indicate that carrying out meaningful time series analysis on one such interannual, multitemporal stack with existing state of the art codes can take several days. This work proposes using multiple algorithms to analyze a given image stack in a polyalgorithmic framework. A polyalgorithm combines several basic algorithms, each meant to solve the same problem, producing a strategy that unites the strengths and circumvents the weaknesses of constituent algorithms. The foundation of the proposed TSA based polyalgorithm is laid using three algorithms (LandTrendR, EWMACD, and BFAST). These algorithms are precisely described mathematically, and chosen to be fundamentally distinct from each other in design and in the phenomena they capture. Analysis of results representing success, failure, and parameter sensitivity for each algorithm is presented. Scalability issues, important for real simulations, are also discussed, along with scalable implementations, and speedup results. For a given pixel, Hausdorff distance is used to compare the distance between the change times (breakpoints) obtained from two different algorithms. Timesync validation data, a dataset that is based on human interpretation of Landsat time series in concert with historical aerial photography, is used for validation. The polyalgorithm yields more accurate results than EWMACD and LandTrendR alone, but counterintuitively not better than BFAST alone. This nascent work will be directly useful in land use and land cover change studies, of interest to terrestrial science research, especially regarding anthropogenic impacts on the environment, and in much broader applications such as health monitoring and urban transportation. / M. S.

Event Detection is a process of identifying terrain flatness from which localized events such as potholes in the terrain surface can be found and is an important tool in pavement health monitoring and vehicle performance inspection. Repeated detection of terrain surfaces over an extended period of time can be used by highway engineers for long term road health monitoring. An accurate terrain map can allow maintenance personnel for identifying deterioration in road surface for immediate correction. Additionally, knowledge of the events in terrain surface can be used to predict the performance the vehicles would experience while traveling over it. Event detection is composed of two processes: event edging and stitching edges to events. Edge detection is a process of identifying significant localized changes in the terrain surface. Many edge detection methods have been designed capable of capturing edges in terrain surfaces. Gradient searches are frequently used in image processing to recover useful information from images. The issue with using a gradient search method is that it returns deterministic values resulting in edges which are less precise. In order to predict the precision of the terrain surface, the individual nodal probability densities must be quantified and finally combined for the precision of terrain surface. A Comparative Nodal Uncertainty Method is developed in this work to detect edges based on the probability distribution of the nodal heights within some local neighborhood. Edge stitching is developed to group edges to events in a correct sequence from which an event can be determined finally. / Master of Science

This dissertation thesis describes the area of multimedia semantics which is a research area that brings together research streams that until recently run separately. The aim of the work is to provide an insight to all areas from this wide discipline and give an outlook on current problems especially to the semantic gab phenomena. Number of findings and outcomes in this work comes from international project K-Space, in which the author took part for three years. The extensive theoretical introduction into problematic is followed by a list state-of-the-art application from this area and overview of KIZI activities and involvements in the European project. The contribution of the work is a research on textual resources complementary to video and experiments with automatic detection of sporting events based on pre-classified examples and trained model. The practical contribution is also a demo web application that shows all the resources together and allows non-linear browsing of events.

This work focuses on a cognitive science inspired solution to an event detection problem in a video domain. The thesis raises the question whether video sequences that are taken in highway tunnels can be used to create meaningful data in terms of symbolic representation, and whether these symbolic representations can be used as sequences to be parsed by attribute grammars into abnormal and normal events. The main motivation of the research was to develop a novel algorithm that parses sequences of primitive events created by the image processing algorithms. The domain of the research is video detection and the special application purpose is for highway tunnels, which are critical places for abnormality detection. The method used is attribute grammars to parse the sequences. The symbolic sequences are created from a cascade of image processing algorithms such as / background subtracting, shadow reduction and object tracking. The system parses the sequences and creates alarms if a car stops, moves backwards, changes lanes, or if a person walks into the road or is in the vicinity when a car is moving along the road. These critical situations are detected using Earley&rsquo / s parser, and the system achieves real-time performance while processing the video input. This approach substantially lowers the number of false alarms created by the lower level image processing algorithms by preserving the number of detected events at a maximum. The system also achieves a high compression rate from primitive events while keeping the lost information at minimum. The output of the algorithm is measured against SVM and observed to be performing better in terms of detection and false alarm performance.