<title>Inference for data fusion</title>

Data Fusion for ITS: Techniques and Research Needs

The detection, classification and counting of the object (vehicle) and persons (pedestrians) in the visual event are the crucial tasks of event analysis. Two object classification systems are reported here: (i) the Fast Region-proposal Convolutional Neural Network with hyper-parameter optimization and (ii) "You Only Look Once" (YOLO). The YOLO object detection method shows improvement in the accuracy of categorizing the vehicles and persons in the video input. High-performance Video Transmission (HpVT) protocol, visual IoT device is applied for grabbing the smooth video streams in real-time. Person (pedestrian)and six classes of vehicle types in a relevant environment are detected. These types are Motorbikes, Bicycle, Bus, Truck, Van and Saloon. New object dataset collected and organized person and vehicle images from several internet websites as 5000 images. The feature extraction and segmentation are performed from the images obtained by video streaming camera. The proposed object detection, classification and counting system will provide to the application of smart tracking, smart trip planning, smart surveillance, smart tourism and pedestrian safety monitoring.

Event Abstract Back to Event Logarithmic Hybrid Optical Neural Network-type systems: towards digital-optical cognitive models of robust object recognition Ioannis Kypraios1* 1 Oxford University, Centre for Innovation & Enterprise, APEM Computing Lab, United Kingdom Abstract - By combining the complex logarithmic r-theta mapping of a space-variant imaging sensor [1, 2] with the hybrid digital-optical neural network filter together with a window unit multiple objects of the same class or of different classes can robustly be recognized. The resulted logarithmic r-theta mapping for hybrid digital-optical neural network system or briefly referred to as logarithmic hybrid optical neural network system is shown to exhibit with a single pass over the input data simultaneously in-plane rotation, out-of-plane rotation, scale, log r-θ map translation and shift invariance, and good clutter tolerance by recognizing correctly the different objects within the cluttered scenes. Here, we study the biologically-inspired knowledge learning and knowledge representation [3] achieved by the logarithmic hybrid optical neural network-type of object recognition systems (see Fig. 1 and Fig. 2). We investigate the effects that altering the knowledge representation can have on the problem’s learned knowledge and the problem solving process, in overall. Further, we study the logarithmic unconstrained-, logarithmic constrained-, and logarithmic modified-hybrid optical neural network systems architectures’ designs [4, 5]. We show how the logarithmic unconstrained-hybrid optical neural network object recognition system applies an unconstrained representation of the problem’s knowledge to maximize the search of solutions, how the logarithmic constrained-hybrid optical neural network object recognition system uses a constrained representation of the problem’s knowledge to guide the search towards certain solutions over others in the multidimensional search space, and how the logarithmic modified-hybrid optical neural network object recognition system uses memory-like masks to recall certain solutions over others in the multidimensional search space. Fig. 1. (a) Simplified human retina and visual cortex model used for description purposes only; (b) A digital-optical computational model for the cognitive interaction between the retina and the human visual cortex with the general logarithmic hybrid optical neural network architercture. Fig. 2. Biologically-inspired knowledge learning and knowledge representation with the logarithmic hybrid optical neural network-type of object recognition systems. Figure 1 Figure 2 References [1] C. F. R. Weiman, “Video compression via log-polar mapping”, Real-Time Image Processing II, SPIE Symposium on OE/Aerospace Sensing, Vol. 1295, 266-277 (1990) [2] C. G. Ho et al., “Sensor geometry and sampling methods for space-variant image processing”, Pattern Analysis and Applications, Vol. 5, 369-384 (2002) [3] I. Lee, and B. Portier, "An empirical study of knowledge representation and learning within conceptual spaces for intelligent agents", 6th IEEE/ACIS International Conference Computer and Information Science, 463-468, Melbourne, Australia (2007) [4] I. Kypraios et al., “Fully invariant complex Logarithmic r- map for the Hybrid Optical Neural Network filter for object recognition within cluttered scenes”, 50th Anniversary International Symposium ELMAR 2008, IEEE Region 8/IEEE Croatia Section/EURASIP, Zadar-Croatia, Vol. 1, 141-146 (2008) [5] I. Kypraios et al., “Logarithmic r-θ mapping for hybrid optical neural network filter for object recogntion within cluttered scenes”, Recent Advances in Multimedia Signal Processing and Communications, SCI231, Springer-Verlag Berlin Heidelberg, 91-120 (2009) Keywords: digital-optical, cognitive, object recognition, Robust and Adaptive Systems, Knowledge representation, learning and memory Conference: Neuroinformatics 2013, Stockholm, Sweden, 27 Aug - 29 Aug, 2013. Presentation Type: Poster Topic: Neuromorphic engineering Citation: Kypraios I (2013). Logarithmic Hybrid Optical Neural Network-type systems: towards digital-optical cognitive models of robust object recognition. Front. Neuroinform. Conference Abstract: Neuroinformatics 2013. doi: 10.3389/conf.fninf.2013.09.00066 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 09 Apr 2013; Published Online: 11 Jul 2013. * Correspondence: Dr. Ioannis Kypraios, Oxford University, Centre for Innovation & Enterprise, APEM Computing Lab, Begbroke, Oxfordshire, OX5 1PF, United Kingdom, ioanniskyp@yahoo.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Ioannis Kypraios Google Ioannis Kypraios Google Scholar Ioannis Kypraios PubMed Ioannis Kypraios Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

The quality of extracted features is the key issue to text mining due to the large number of terms, phrases, and noise. Most existing text mining methods are based on term-based approaches which extract terms from a training set for describing relevant information. However, the quality of the extracted terms in text documents may be not high because of lot of noise in text. For many years, some researchers make use of various phrases that have more semantics than single words to improve the relevance, but many experiments do not support the effective use of phrases since they have low frequency of occurrence, and include many redundant and noise phrases. In this paper, we propose a novel pattern discovery approach for text mining. This approach first discovers closed sequential patterns in text documents for identifying the most informative contents of the documents and then utilise the identified contents to extract useful features for text mining. We develop a novel fusion method based on Dempster-Shafer's evidential reasoning which allows to combine the pieces of document to discover the knowledge (features). To evaluate the proposed approach, we adopt the feature extraction method for information filtering (IF). The experimental results conducted on Reuters Corpus Volume 1 and TREC topics confirm that the proposed approach could achieve excellent performance.

A sensor fusion scheme for mobile robot environment recognition that incorporates range data and contour data is proposed. An ultrasonic sensor provides coarse spatial description but guarantees open space (with no obstacle) within a sonic cone with relatively high belief. A laser structured light system provides a detailed contour description of the environment but is prone to light noise and is easily affected by surface reflectivity. We present a sensor fusion scheme that can compensate the disadvantages of both sensors. Line models from the laser structured light system play a key role in environment description. The overall fusion process is composed of two stages: noise elimination and belief updates. Dempster-Shafer's evidential reasoning is applied at each stage. Open space estimation from sonar range measurements brings elimination of noisy lines from the laser sensor. Comparing actual sonar data to the simulated sonar data enables data of two disparate sensors to be fused in the unified feature space. Experimental results demonstrate the effectiveness of the proposed method.

By integrating Fuzzy Kohonen Clustering Network (FKCN) with Fuzzy Dempster-Shafer Evidential Reasoning Theory (FDSERT), a new multi-source data fusion of Remote Sensing information algorithm is proposed in this paper. The new algorithm can be applied in classification of remote sensing image through FKCN learning and FDSERT fusing. Experimental results comparing with the FKCN algorithm indicates that the classification algorithm of multi-source data fusion of Remote Sensing is superior to that of FKCN algorithm. And the algorithm can obviously improve classification accuracy. At the same time, the algorithm can makes the best of expert knowledge. Therefore the algorithm is an effective classification algorithm of Remote Sensing image.

Having profound implications for autonomous systems, intelligent surveillance, and human-computer interaction, object detection and classification of images are one of the principal challenges in computer vision. Using the vast benchmark datasets of PASCAL VOC and ImageNet, this study introduces a deep learning system for object recognition and classification. The model employs a hybrid structure combining Vision Transformers (ViT) and ResNet-50 for extracting global context and spatial features. On the more diversified and complex PASCAL VOC dataset, the pre-trained weights of ImageNet are transferred for the purpose of generalization and speed of convergence. By thorough testing on PASCAL VOC 2007 and 2012 datasets, the model outperformed baseline models like Faster R-CNN and YOLOv5 by 2.7% and 1.9%, respectively, in terms of mean Average Precision (mAP) at 83.4% on VOC 2007 and 82.1% on VOC 2012. With 78.9% top-1 classification accuracy, ImageNet-based training significantly improved the system discriminative ability for 1,000 object categories. Greater robustness to occlusion and class imbalance were achieved with increased data augmentation, optimized focus loss, and improved attention modules.

This paper concentrates an efficient event detection approa ch exploiting data fusion technology for the heterogeneous wireless sensor networks. In this type of wireless sensor networks, each sensor is equipped with multiple sensing units. Particularly, in this paper, we study on the data fusion approach based on the type of complementary heterogeneous wireless sensor networks, and the fire disaster detection is utilized as an example of event det ection. The proposed event detection model is constructed of data fusion level and information fusion level. In the data fusion level , resource data are collected from the sensors which are both in the sensing field out of the sensing field. In the information fusion level , the event can be detected by computing the data fusion probabilities. For the fire disaster detection process, data collected from temperature sensors and humidity sensors are combined, and then all the measurements are supposed independent on normal random variables. Afterwards, the data fusion process is implemented utilizing genetic algorithm, by which the population is evolved through a predetermined number of consults. Therefore, for each generation of answers, a new set of artificial creatures can be calculated. Furthermore, the answers can be solved by fragments of the most suitable individuals. Finally, experiments are conducted on a series of simulations using the OMNeT++ tool. Compared with other methods, the proposed data fusion based event detection algorithm can effectively find the event through detecting the notify sta te and alert state, and performs better than other two methods both in the fusion quality and fusion efficiency.

Bayesian inference and Dempster–Shafer evidential reasoning and their application to traffic management

Розглянуто основні датчики координатної інформації літака цивільної авіації, що застосовуються для вирішення задачі позиціонування у просторі, а саме супутникову та інерціальну системи; алгоритми зональної навігації у обчислювальній системі літаководіння, що функціонують за сигналами наземних далекомірних (DME) та кутомірних (VOR) радіомаяків. Проаналізовано математичні підходи до об’єднання даних на різних рівнях обробки, зокрема розглянуто поєднання координатної інформації за методом максимальної достовірності. Вперше представлено структурну схему поєднання координат літака, отриманих за результатами попарного та множинного принципів позиціонування на основі даних наземних радіомаяків. Досліджено використання ймовірнісного підходу для поєднання координатної інформації літака у випадку, коли розподіли похибок вимірювання мають Гаусівський вигляд.

Requirement assessment and prioritization are the crucial requirement engineering processes in the software development domain. However, software developers face challenges with various types and categories of requirements due to generality, time, and cost. However, Various techniques are proposed for requirement prioritization, such as hierarchical analytic process (AHP), MOSCOW, cumulative voting (CV), bubble sort, and binary search tree (BST). These techniques are still unreliable for prioritizing a considerable number of requirements which takes a long time. Therefore, there is a crucial need for a reliable and consistent approach that helps deal with functional and non-functional requirements assessment and prioritization, such as the Evidential Reasoning (ER) approach. The study findings showed how the requirements assessment and prioritization process improved according to their weights, evaluation grades, and belief degrees. In addition to the decision matrices that lead to high-quality decisions.KeywordsRequirement prioritizationArchitecture assessmentEvidential Reasoning (ER)Multi-criteria decision making (MCDM)

The problem of sensor integration and data fusion is addressed. We consider the problem of combining information from diversified sources in a coherent fashion. We assume that at the fusion, the information from various sensors may be available in different forms. For example, data from infrared (IR) sensors may be combined with range radar (RR) data, and further combined with visual images. In each case, the data and information from the different sensors are presented in a different format which may not be directly compatible for all sensors. Furthermore, the available information may be in the form of attributes and not dynamical measurements. A theory for sensor integration and data fusion that accommodates diversified sources of information is presented. Data (or, more generically, information) fusion may proceed at different levels, like the level of dynamics, the level of attributes, and the level of evidence. All different levels are considered and several practical examples of real world data fusion problems are discussed.

The field of computer vision is characterized by computationally intensive algorithms and techniques with strict real‐time requirements. Field programmable gate arrays (FPGAs) are based on a concurrent paradigm which allows the design of efficient hardware architectures and has positioned FPGAs as an ideal device for implementing compute‐intensive applications. For this reason, FPGA technology has had a great impact in areas such as computer vision, where one of the main objectives for researchers working in this field is to create efficient automatic object recognition systems. Therefore, the need to provide undergraduates with the necessary skills to design FPGA‐based object recognition systems is evident. With this aim in mind, it is essential that specialization courses related to the design of these systems include the required resources for the student to apply the theoretical knowledge in solving practical problems. In this article, we present a development tool designed to help students, teachers, and researchers during the design‐modeling‐implementation process of object recognition systems based on FPGAs. The proposed tool operates under a modular approach as this facilitates the working on any of the phases of a recognition system and it is considered as a hybrid because the other phases can be developed using a software language. An empirical evaluation involving undergraduates enrolled in a Computer Engineering program was conducted to create a hardware architecture for the DAISY descriptor that uses the homogeneous features of objects immersed in images to produce an efficient representation. By considering similar descriptors such as Scale‐Invariant Feature Transform (SIFT) and Histogram of Oriented Gradients (HOG), DAISY is computed by convolving orientation maps instead of using weighted sums of gradient norms, which offers the same kind of invariance at a lower computational cost for the dense case. The results obtained during such an evaluation indicated that students consider this FPGA‐based tool to be an alternative to receiving practical training on designing systems for solving problems related to the area of object recognition.

Retrospective evaluation of serial FDG-PET/CT scans in head and neck squamous cell cancer (HNSCC) patient's follow-up after primary radiochemotherapy (RCTx), to assess the diagnostic accuracy of an experienced observer vs. an objective classification compared to standard clinical follow-up examinations. Sixty-nine patients with locally advanced HNSCC were included, who received curative RCTx. Follow-up included serial FDG-PET/CT at the following time intervals t1: ≤ 270 d, t2: 271-540 d, t3: > 540 d after curative RCTx. The likelihood to detect local recurrences, nodal and distant metastases were compared between (i) experienced observer, (ii) an objective classification system by Zundel et al. 25, and (iii) routine clinical follow-up examinations. Twenty-two local recurrences, 7 nodal and 17 distant metastases were recorded during the follow-up. The diagnostic accuracy for local recurrence of the experienced observer vs. objective classification was 78 % vs. 77 % for t1, 83 % vs. 79 % for t2 and 100 % vs. 84 % for t3.The classification (ii) and the conventional follow-up (iii) resulted in a relatively high amount of equivocal findings reducing the diagnostic accuracy. Evaluation of FDG-PET/CT by an experienced observer in follow-up of HNSCC patients after curative RCTx resulted in the highest diagnostic accuracy in comparison to an objective classification and to routine clinical examination.HNSCC is a malignant tumor with a high likelihood of recurrence, especially in the first two years after curative RCTx. Early detection of recurrence is of high clinical importance, since there are several effective second line therapies that may have curative potential in some patients.

The power and versatility of multimodal interfaces results in an increased complexity of the code to be developed. To address this problem of software development, multimodal interfaces therefore make necessary the definition of software development tools that satisfy specific requirements such as the fusion of data from different interaction modalities and the management of multiple processes including support for synchronization and race conditions between distinct interaction modalities. This chapter is a reflection on current software design methods and tools for multimodal interfaces. First we present the PAC-Amodeus software architectural model as a generic conceptual solution for addressing the challenges of data fusion and concurrent processing of data of multimodal interfaces. We then focus on software tools for developing multimodal interfaces. The existing tools dedicated to multimodal interfaces are currently few and limited in scope. Either they address a specific technical problem including the fusion mechanism, the composition of several devices and mutual disambiguation, or they are dedicated to specific interaction modalities such as gesture recognition, speech recognition or the combined usage of speech and gesture. Two platforms, ICARE and OpenInterface are more general and are able to handle various interaction modalities. We describe in detail these two platforms and illustrate them by considering developed multimodal interfaces.