Automatic building detection using the Dempster-Shafer algorithm

An approach and strategy for automatic detection of buildings from aerial images using combined image analysis and interpretation techniques is described in this paper. It is undertaken in several steps. A dense DSM is obtained by stereo image matching and then the results of multi-band classification, the DSM, and Normalized Difference Vegetation Index (NDVI) are used to reveal preliminary building interest areas. From these areas, a shape modeling algorithm has been used to precisely delineate their boundaries. The Dempster-Shafer data fusion technique is then applied to detect buildings from the combination of three data sources by a statistically-based classification. A number of test areas, which include buildings of different sizes, shape, and roof color have been investigated. The tests are encouraging and demonstrate that all processes in this system are important for effective building detection.

Multisensorial obstacles detection and classification for ADAS and autonomous driving

A reliable perception of the real world is a key-feature for an autonomous vehicle and the Advanced Driver Assistance Systems (ADAS). Obstacles detection (OD) is one of the main components for the correct reconstruction of the dynamic world. Historical approaches based on stereo vision and other 3D perception technologies (e.g. LIDAR) have been adapted to the ADAS first and autonomous ground vehicles, after, providing excellent results. The obstacles detection is a very broad field and this domain counts a lot of works in the last years. In academic research, it has been clearly established the essential role of these systems to realize active safety systems for accident prevention, reflecting also the innovative systems introduced by industry. These systems need to accurately assess situational criticalities and simultaneously assess awareness of these criticalities by the driver; it requires that the obstacles detection algorithms must be reliable and accurate, providing: a real-time output, a stable and robust representation of the environment and an estimation independent from lighting and weather conditions. Initial systems relied on only one exteroceptive sensor (e.g. radar or laser for ACC and camera for LDW) in addition to proprioceptive sensors such as wheel speed and yaw rate sensors. But, current systems, such as ACC operating at the entire speed range or autonomous braking for collision avoidance, require the use of multiple sensors since individually they can not meet these requirements. It has led the community to move towards the use of a combination of them in order to exploit the benefits of each one. Pedestrians and vehicles detection are ones of the major thrusts in situational criticalities assessment, still remaining an active area of research. ADASs are the most prominent use case of pedestrians and vehicles detection. Vehicles should be equipped with sensing capabilities able to detect and act on objects in dangerous situations, where the driver would not be able to avoid a collision. A full ADAS or autonomous vehicle, with regard to pedestrians and vehicles, would not only include detection but also tracking, orientation, intent analysis, and collision prediction. The system detects obstacles using a probabilistic occupancy grid built from a multi-resolution disparity map. Obstacles classification is based on an AdaBoost SoftCascade trained on Aggregate Channel Features. A final stage of tracking and fusion guarantees stability and robustness to the result.

Probabilistic methods for drug discovery

This thesis introduces a flexible visual data exploration framework which combines advanced projection algorithms from the machine learning domain with visual representation techniques developed in the information visualisation domain to help a user to explore and understand effectively large multi-dimensional datasets. The advantage of such a framework to other techniques currently available to the domain experts is that the user is directly involved in the data mining process and advanced machine learning algorithms are employed for better projection. A hierarchical visualisation model guided by a domain expert allows them to obtain an informed segmentation of the input space. Two other components of this thesis exploit properties of these principled probabilistic projection algorithms to develop a guided mixture of local experts algorithm which provides robust prediction and a model to estimate feature saliency simultaneously with the training of a projection algorithm.Local models are useful since a single global model cannot capture the full variability of a heterogeneous data space such as the chemical space. Probabilistic hierarchical visualisation techniques provide an effective soft segmentation of an input space by a visualisation hierarchy whose leaf nodes represent different regions of the input space. We use this soft segmentation to develop a guided mixture of local experts (GME) algorithm which is appropriate for the heterogeneous datasets found in chemoinformatics problems. Moreover, in this approach the domain experts are more involved in the model development process which is suitable for an intuition and domain knowledge driven task such as drug discovery. We also derive a generative topographic mapping (GTM) based data visualisation approach which estimates feature saliency simultaneously with the training of a visualisation model.

Intelligent Computations for Flood Monitoring

Floods represent the most devastating natural hazards in the world, affecting more people and causing more property damage than any other natural phenomena. One of the important problems associated with flood monitoring is flood extent extraction from satellite imagery, since it is impractical to acquire the flood area through field observations. This paper presents a method to flood extent extraction from synthetic-aperture radar (SAR) images that is based on intelligent computations. In particular, we apply artificial neural networks, self-organizing Kohonen’s maps (SOMs), for SAR image segmentation and classification. We tested our approach to process data from three different satellite sensors: ERS-2/SAR (during flooding on Tisza river, Ukraine and Hungary, 2001), ENVISAT/ASAR WSM (Wide Swath Mode) and RADARSAT-1 (during flooding on Huaihe river, China, 2007). Obtained results showed the efficiency of our approach.

Modelling and linking transformations in EPCIS governing supply chain business processes

Supply chains comprise of complex processes spanning across multiple trading partners. The various operations involved generate large number of events that need to be integrated in order to enable internal and external traceability. Further, provenance of artifacts and agents involved in the supply chain operations is now a key traceability requirement. In this paper we propose a Semantic web/Linked data powered framework for the event based representation and analysis of supply chain activities governed by the EPCIS specification. We specifically show how a new EPCIS event type called "Transformation Event" can be semantically annotated using EEM - The EPCIS Event Model to generate linked data, that can be exploited for internal event based traceability in supply chains involving transformation of products. For integrating provenance with traceability, we propose a mapping from EEM to PROV-O. We exemplify our approach on an abstraction of the production processes that are part of the wine supply chain.

Reducing uncertainties in estimation of wind effects on tall buildings using aerodynamic wind tunnel tests

Tall buildings are wind-sensitive structures and could experience high wind-induced effects. Aerodynamic boundary layer wind tunnel testing has been the most commonly used method for estimating wind effects on tall buildings. Design wind effects on tall buildings are estimated through analytical processing of the data obtained from aerodynamic wind tunnel tests. Even though it is widely agreed that the data obtained from wind tunnel testing is fairly reliable the post-test analytical procedures are still argued to have remarkable uncertainties. This research work attempted to assess the uncertainties occurring at different stages of the post-test analytical procedures in detail and suggest improved techniques for reducing the uncertainties. Results of the study showed that traditionally used simplifying approximations, particularly in the frequency domain approach, could cause significant uncertainties in estimating aerodynamic wind-induced responses. Based on identified shortcomings, a more accurate dual aerodynamic data analysis framework which works in the frequency and time domains was developed. The comprehensive analysis framework allows estimating modal, resultant and peak values of various wind-induced responses of a tall building more accurately. Estimating design wind effects on tall buildings also requires synthesizing the wind tunnel data with local climatological data of the study site. A novel copula based approach was developed for accurately synthesizing aerodynamic and climatological data up on investigating the causes of significant uncertainties in currently used synthesizing techniques. Improvement of the new approach over the existing techniques was also illustrated with a case study on a 50 story building. At last, a practical dynamic optimization approach was suggested for tuning structural properties of tall buildings towards attaining optimum performance against wind loads with less number of design iterations.

Uma plataforma adaptável para localização em ambientes internos

Location systems have become increasingly part of people's lives. For outdoor environments, GPS appears as standard technology, widely disseminated and used. However, people usually spend most of their daily time in indoor environments, such as: hospitals, universities, factories, buildings, etc. In these environments, GPS does not work properly causing an inaccurate positioning. Currently, to perform the location of people or objects in indoor environments no single technology could reproduce for indoors the same result achieved by GPS for outdoors environments. Due to this, it is necessary to consider use of information from multiple sources using diferent technologies. Thus, this work aims to build an Adaptable Platform for Indoor location. Based on this goal, the IndoLoR platform is proposed. This platform aims to allow information reception from diferent sources, data processing, data fusion, data storage and data retrieval for the indoor location context.

Uma plataforma adaptável para localização em ambientes internos

Location systems have become increasingly part of people's lives. For outdoor environments, GPS appears as standard technology, widely disseminated and used. However, people usually spend most of their daily time in indoor environments, such as: hospitals, universities, factories, buildings, etc. In these environments, GPS does not work properly causing an inaccurate positioning. Currently, to perform the location of people or objects in indoor environments no single technology could reproduce for indoors the same result achieved by GPS for outdoors environments. Due to this, it is necessary to consider use of information from multiple sources using diferent technologies. Thus, this work aims to build an Adaptable Platform for Indoor location. Based on this goal, the IndoLoR platform is proposed. This platform aims to allow information reception from diferent sources, data processing, data fusion, data storage and data retrieval for the indoor location context.

Soil organic carbon storage and soil properties for 50 soil profiles in the Lena River Delta including land form description and map

To project the future development of the soil organic carbon (SOC) storage in permafrost environments, the spatial and vertical distribution of key soil properties and their landscape controls needs to be understood. This article reports findings from the Arctic Lena River Delta where we sampled 50 soil pedons. These were classified according to the U.S.D.A. Soil Taxonomy and fall mostly into the Gelisol soil order used for permafrost-affected soils. Soil profiles have been sampled for the active layer (mean depth 58±10 cm) and the upper permafrost to one meter depth. We analyze SOC stocks and key soil properties, i.e. C%, N%, C/N, bulk density, visible ice and water content. These are compared for different landscape groupings of pedons according to geomorphology, soil and land cover and for different vertical depth increments. High vertical resolution plots are used to understand soil development. These show that SOC storage can be highly variable with depth. We recommend the treatment of permafrost-affected soils according to subdivisions into: the surface organic layer, mineral subsoil in the active layer, organic enriched cryoturbated or buried horizons and the mineral subsoil in the permafrost. The major geomorphological units of a subregion of the Lena River Delta were mapped with a land form classification using a data-fusion approach of optical satellite imagery and digital elevation data to upscale SOC storage. Landscape mean SOC storage is estimated to 19.2±2.0 kg C/m**2. Our results show that the geomorphological setting explains more soil variability than soil taxonomy classes or vegetation cover. The soils from the oldest, Pleistocene aged, unit of the delta store the highest amount of SOC per m**2 followed by the Holocene river terrace. The Pleistocene terrace affected by thermal-degradation, the recent floodplain and bare alluvial sediments store considerably less SOC in descending order.

Real-time analytics on large dynamic graphs

In today's fast-paced and interconnected digital world, the data generated by an increasing number of applications is being modeled as dynamic graphs. The graph structure encodes relationships among data items, while the structural changes to the graphs as well as the continuous stream of information produced by the entities in these graphs make them dynamic in nature. Examples include social networks where users post status updates, images, videos, etc.; phone call networks where nodes may send text messages or place phone calls; road traffic networks where the traffic behavior of the road segments changes constantly, and so on. There is a tremendous value in storing, managing, and analyzing such dynamic graphs and deriving meaningful insights in real-time. However, a majority of the work in graph analytics assumes a static setting, and there is a lack of systematic study of the various dynamic scenarios, the complexity they impose on the analysis tasks, and the challenges in building efficient systems that can support such tasks at a large scale. In this dissertation, I design a unified streaming graph data management framework, and develop prototype systems to support increasingly complex tasks on dynamic graphs. In the first part, I focus on the management and querying of distributed graph data. I develop a hybrid replication policy that monitors the read-write frequencies of the nodes to decide dynamically what data to replicate, and whether to do eager or lazy replication in order to minimize network communication and support low-latency querying. In the second part, I study parallel execution of continuous neighborhood-driven aggregates, where each node aggregates the information generated in its neighborhoods. I build my system around the notion of an aggregation overlay graph, a pre-compiled data structure that enables sharing of partial aggregates across different queries, and also allows partial pre-computation of the aggregates to minimize the query latencies and increase throughput. Finally, I extend the framework to support continuous detection and analysis of activity-based subgraphs, where subgraphs could be specified using both graph structure as well as activity conditions on the nodes. The query specification tasks in my system are expressed using a set of active structural primitives, which allows the query evaluator to use a set of novel optimization techniques, thereby achieving high throughput. Overall, in this dissertation, I define and investigate a set of novel tasks on dynamic graphs, design scalable optimization techniques, build prototype systems, and show the effectiveness of the proposed techniques through extensive evaluation using large-scale real and synthetic datasets.

Computational Analysis of Intelligent Agents: Social and Strategic Settings

The central motif of this work is prediction and optimization in presence of multiple interacting intelligent agents. We use the phrase `intelligent agents' to imply in some sense, a `bounded rationality', the exact meaning of which varies depending on the setting. Our agents may not be `rational' in the classical game theoretic sense, in that they don't always optimize a global objective. Rather, they rely on heuristics, as is natural for human agents or even software agents operating in the real-world. Within this broad framework we study the problem of influence maximization in social networks where behavior of agents is myopic, but complication stems from the structure of interaction networks. In this setting, we generalize two well-known models and give new algorithms and hardness results for our models. Then we move on to models where the agents reason strategically but are faced with considerable uncertainty. For such games, we give a new solution concept and analyze a real-world game using out techniques. Finally, the richest model we consider is that of Network Cournot Competition which deals with strategic resource allocation in hypergraphs, where agents reason strategically and their interaction is specified indirectly via player's utility functions. For this model, we give the first equilibrium computability results. In all of the above problems, we assume that payoffs for the agents are known. However, for real-world games, getting the payoffs can be quite challenging. To this end, we also study the inverse problem of inferring payoffs, given game history. We propose and evaluate a data analytic framework and we show that it is fast and performant.

Dendritic Cells for SYN Scan Detection

Artificial immune systems have previously been applied to the problem of intrusion detection. The aim of this research is to develop an intrusion detection system based on the function of Dendritic Cells (DCs). DCs are antigen presenting cells and key to the activation of the human immune system, behaviour which has been abstracted to form the Dendritic Cell Algorithm (DCA). In algorithmic terms, individual DCs perform multi-sensor data fusion, asynchronously correlating the fused data signals with a secondary data stream. Aggregate output of a population of cells is analysed and forms the basis of an anomaly detection system. In this paper the DCA is applied to the detection of outgoing port scans using TCP SYN packets. Results show that detection can be achieved with the DCA, yet some false positives can be encountered when simultaneously scanning and using other network services. Suggestions are made for using adaptive signals to alleviate this uncovered problem.

Probabilistic Evaluation of Three-Dimensional Reconstructions from X-Ray Images Spanning a Limited Angle

An important part of computed tomography is the calculation of a three-dimensional reconstruction of an object from series of X-ray images. Unfortunately, some applications do not provide sufficient X-ray images. Then, the reconstructed objects no longer truly represent the original. Inside of the volumes, the accuracy seems to vary unpredictably. In this paper, we introduce a novel method to evaluate any reconstruction, voxel by voxel. The evaluation is based on a sophisticated probabilistic handling of the measured X-rays, as well as the inclusion of a priori knowledge about the materials that the object receiving the X-ray examination consists of. For each voxel, the proposed method outputs a numerical value that represents the probability of existence of a predefined material at the position of the voxel while doing X-ray. Such a probabilistic quality measure was lacking so far. In our experiment, false reconstructed areas get detected by their low probability. In exact reconstructed areas, a high probability predominates. Receiver Operating Characteristics not only confirm the reliability of our quality measure but also demonstrate that existing methods are less suitable for evaluating a reconstruction.

Reasoning over knowledge-based generation of situations in context spaces to reduce food waste

With the ever-growing amount of connected sensors (IoT), making sense of sensed data becomes even more important. Pervasive computing is a key enabler for sustainable solutions, prominent examples are smart energy systems and decision support systems. A key feature of pervasive systems is situation awareness which allows a system to thoroughly understand its environment. It is based on external interpretation of data and thus relies on expert knowledge. Due to the distinct nature of situations in different domains and applications, the development of situation aware applications remains a complex process. This thesis is concerned with a general framework for situation awareness which simplifies the development of applications. It is based on the Situation Theory Ontology to provide a foundation for situation modelling which allows knowledge reuse. Concepts of the Situation Theory are mapped to the Context Space Theory which is used for situation reasoning. Situation Spaces in the Context Space are automatically generated with the defined knowledge. For the acquisition of sensor data, the IoT standards O-MI/O-DF are integrated into the framework. These allow a peer-to-peer data exchange between data publisher and the proposed framework and thus a platform independent subscription to sensed data. The framework is then applied for a use case to reduce food waste. The use case validates the applicability of the framework and furthermore serves as a showcase for a pervasive system contributing to the sustainability goals. Leading institutions, e.g. the United Nations, stress the need for a more resource efficient society and acknowledge the capability of ICT systems. The use case scenario is based on a smart neighbourhood in which the system recommends the most efficient use of food items through situation awareness to reduce food waste at consumption stage.

The DCA:SOMe comparison: a comparative study between two biologically-inspired algorithms

The dendritic cell algorithm (DCA) is an immune-inspired algorithm, developed for the purpose of anomaly detection. The algorithm performs multi-sensor data fusion and correlation which results in a ‘context aware’ detection system. Previous applications of the DCA have included the detection of potentially malicious port scanning activity, where it has produced high rates of true positives and low rates of false positives. In this work we aim to compare the performance of the DCA and of a self-organizing map (SOM) when applied to the detection of SYN port scans, through experimental analysis. A SOM is an ideal candidate for comparison as it shares similarities with the DCA in terms of the data fusion method employed. It is shown that the results of the two systems are comparable, and both produce false positives for the same processes. This shows that the DCA can produce anomaly detection results to the same standard as an established technique.