Computer Science

This paper aims to propose a decision tool that helps estimate the risk probability in the petroleum sector in Iraq, which has many benefits for identifying the most important factor. This model was developed by using the relative importance index (RII) method incorporated into fuzzy Logic. An extensive literature review was conducted, and a questionnaire was distributed to the private and government sectors to scan all possible risks in the petroleum sector. As a result, forty–eight risks in the petroleum sector were identified and categorized into four groups: operational risks, financial and administrative risks, economic and political risks, and potential risks. Over 170 questionnaire forms have been distributed to engineers, managers, experts, and technicians, and 153 forms have been adopted for the analysis. The SPSS software was used to execute the statistical analysis concerning statical mean and relative important index. Also, the questionnaire results were analyzed using t...

The University at Buffalo Space Bulls team has designed a prototype planetary rover to compete at NASA’s Johnson Space Center as part of the 2015 RASC-AL Exploration Robo-Ops Competition. In order to provide the necessary remote manipulation capabilities to collect rock samples, a 2 segment arm with 4 degrees of freedom, and an end effector was designed. The arm is driven by linear actuators from Frigelli in order to provide the necessary torque and take full advantage of lever arms. In addition the actuators are lightweight and provide more power, precision, and range of motion than servo motors. 3D printed parts allowed for rapid prototyping before precise laser cut parts were fabricated. This combination of build speed and precision allowed for rapid testing, modification and final integration of the arm with the University at Buffalo Space Bulls team’s prototype rover and control systems.

Interestingly, prevention program development and evaluation an incidence reduction culturally relevant approach that you really wait for now is coming. It's significant to wait for the representative and beneficial books to read. Every book that is provided in better way and utterance will be expected by many peoples. Even you are a good reader or not, feeling to read this book will always appear when you find it. But, when you feel hard to find it as yours, what to do? Borrow to your friends and don't know when to give back it to her or him. It's needed now to own this book by you. It is not as difficult as previously to find a book. The modern technology always is the best way to find something. As here, we are the website that always provides the book that you need. As prevention program development and evaluation an incidence reduction culturally relevant approach, we provide it in the soft file. You may not to print it and get it as papers and pilled one by one. Reading this book in computer device or laptop can be also same. Moreover, you can also read it on your gadget or Smartphone. Now, that's available enough. One that makes this book is strongly read by amounts people is that it gives a different way to utter the meaning of this book for the reader. Easy to read and easy to understand become one part characters that people will consider in choosing a book. So, it is very appropriate to consider prevention program development and evaluation an incidence reduction culturally relevant approach as your reading material. Depending on the needs, this book also features the willingness of many people to make changes. The way is by situating the content and how you understand it. One that should be remembered is that this book is also written by a good writer, good author wit professionalism. So, prevention program development and evaluation an incidence reduction culturally relevant approach is much recommended for you, a person who expects better way to living style.

In this paper a class of sliding-mode based controllers for passive synchronization of a multi-robotic system is proposed. The considered system is composed of a master robot which provides motion commands to the slave robot which performs the actual task. The conventional approach to synchronization of bilateral teleoperators is based on assumption that both robots have the same structure or regression matrix. Such an assumption allows applications of the conventional adaptive control approach for asymptotic tracking. The controller proposed in this paper provides asymptotic synchronization of master and slave robotic systems with different structural configurations. Simulation example with two robots with two revolute joints in horizontal and vertical plane demonstrates the effectiveness of the proposed control strategy.

This paper presents the derivation of the numerical algorithm for optimal control of nonlinear multivariable systems with control and state vectors constraints. The algorithm derivation is based on the backpropagationthrough-time (BPTT) algorithm which is used as a learning algorithm for recurrent neural networks. This approach is not based on Lagrange multiplier techniques and the calculus of variations. The derived algorithm is used for the control of the cooperative work of two robots with two degrees of freedom. The main problem is the determination of the control vectors of robots for the transfer of rigid load from the initial state to the final one in a fixed time while maintaining constant distance between robot hands and avoiding the cross-section of the robot hands.

Currently, fuzzy systems often apply where the number of inputs and outputs is small and events happen relatively slowly. Meanwhile, there are applications such as robot control, videorich multimedia and virtual reality, which can require many more rules of greater complexity operating in milliseconds. It becomes necessary to suggest ways to cope with a vexing problem in fuzzy logic: the exponential growth in rules as the number of variables increases. This problem is solved in the paper by introducing of a new adaptive analytic fuzzy logic control synthesis procedure. For this purpose the following objectives are preferred and reached : (i) an introduction of a new adaptive shape of fuzzy sets and a new adaptive distribution of input fuzzy sets , (ii) a determination of an analytic activation function, instead of using of min-max operators, (iii) a definition of a new analytic function that determines the positions of centres of output fuzzy sets, instead of definition of rule base, and (iv) an introduction of an analytic defuzzification formula. A real capability of the proposed fuzzy logic control synthesis procedures is presented by synthesis of adaptive fuzzy logic control of robot of RRTR-structure. 1 Introduction Fuzzy sets are a generalization of conventional set theory that were introduced by Zadeh in 1965 [1] as a mathematical way to represent vagueness in everyday life. Fuzzy interpretations of data structures are very natural and intuitively plausible way to formulate and solve various problems. The grade of membership or ftizziness has been properly

ELT laser guide star wavefront sensors are planned to handle an expected amount of data to be overwhelmingly large (1600x1600 pixels at 700 fps). According to the calculations involved, the solutions must consider to run on specialized hardware as Graphical Processing Units (GPUs) or Field Programmable Gate Arrays (FPGAs), among others. In the case of a Shack-Hartmann wavefront sensor is finally selected, the wavefront slopes can be computed using centroid or correlation algorithms. Most of the developments are designed using centroid algorithms, but precision ought to be taken in account too, and then correlation algorithms are really competitive. This paper presents an FPGA-based wavefront slope implementation, capable of handling the sensor output stream in a massively parallel approach, using a correlation algorithm previously tested and compared to the centroid algorithm. Time processing results are shown, and they demonstrate the ability of the FPGA integer arithmetic in the resolution of AO problems. The selected architecture is based in today's commercially available FPGAs which have a very limited amount of internal memory. This limits the dimensions used in our implementation, but this also means that there is a lot of margin to move real-time algorithms from the conventional processors to the future FPGAs, obtaining benefits from its flexibility, speed and intrinsically parallel architecture.

Because the Lie Theory solely applies to linear systems, in 1978 Santilli proposed the isotopic lifting of Lie's theory for nonlinear systems, today known as the Lie-Santilli isotheory, via the reconstruction of linearity on the isotopic lifting of spaces and fields. In order to identify the proper mathematical background of the Lie-Santilli isotheory, Kadeisvili introduced in 1992 the notion of isocontinuity; Tsagas and Sourlas proposed in 1995 a for of isotopology defined over conventional fields; Santilli extended it in 1996 its formulation on isofields; and the authors conducted in 2003 a systematic study of the new isotopology. In this paper we outline the foundation of the new isotopology and present various advances. Dedication: This paper is dedicated to the memory of Prof. Gr. Tsagas in admiration of his studies on Lie-Santilli isotheory.

Symmetries are ubiquitous in a wide range of nonlinear systems. Particularly in systems whose dynamics is determined by a Lagrangian or Hamiltonian function. For hybrid systems which possess a continuous-time dynamics determined by a Lagrangian function, with a cyclic variable, the degrees of freedom for the corresponding hybrid Lagrangian system can be reduced by means of a method known as hybrid Routhian reduction. In this paper we study sufficient conditions for the existence of periodic orbits in hybrid Routhian systems which also exhibit a time-reversal symmetry. Likewise, we explore some stability aspects of such orbits through the characterization of the eigenvalues for the corresponding linearized Poincaré map. Finally, we apply the results to find periodic solutions in underactuated hybrid Routhian control systems.

The paper presents a gradient-based algorithm for optimal control of nonlinear multivariable systems with control and state vectors constraints. The algorithm has a backward-intime recurrent structure similar to the backpropagation-throughtime (BPTT) algorithm, which is mostly used as a learning algorithm for dynamic neural networks. Other main features of the algorithm include the use of higher order Adams timediscretization schemes, numerical calculation of Jacobians, and advanced conjugate gradient methods for favorable convergence properties. The algorithm performance is illustrated on an example of off-line vehicle dynamics control optimization based on a realistic high-order vehicle model. The optimized control variables are active rear differential torque transfer and active rear steering road wheel angle, while the optimization tasks are trajectory tracking and roll minimization for a double lane change maneuver.

Identifying negation scopes in a text is an important subtask of information extraction that can benefit other natural language processing tasks, like relation extraction, question answering and sentiment analysis, and serves the task of social media text understanding. The task of negation scope detection can be regarded as a token-level sequence labelling problem. In this paper, we propose different models based on recurrent neural networks (RNNs) and word embedding that can be successfully applied to such tasks without any task-specific feature engineering effort. Our experimental results show that RNNs, without using any hand-crafted features, outperform feature-rich CRF-based model.

Identifying negation scopes in a text is an important subtask of information extraction that can benefit other natural language processing tasks, like relation extraction, question answering and sentiment analysis, and serves the task of social media text understanding. The task of negation scope detection can be regarded as a token-level sequence labelling problem. In this paper, we propose different models based on recurrent neural networks (RNNs) and word embedding that can be successfully applied to such tasks without any task-specific feature engineering effort. Our experimental results show that RNNs, without using any hand-crafted features, outperform feature-rich CRF-based model.

Identifying negation scopes in a text is an important subtask of information extraction that can benefit other natural language processing tasks, like relation extraction, question answering and sentiment analysis, and serves the task of social media text understanding. The task of negation scope detection can be regarded as a token-level sequence labelling problem. In this paper, we propose different models based on recurrent neural networks (RNNs) and word embedding that can be successfully applied to such tasks without any task-specific feature engineering effort. Our experimental results show that RNNs, without using any hand-crafted features, outperform feature-rich CRF-based model.

The purpose of this research is to present knowledge in the field of work of databases that contain semi-structured data, also known as NoSQL, in applications using big data. The characteristics of the main categories of the non-relational databases and some of their typical representatives (MongoDB, Redis) have been reviewed from the point of view of using them for storage and analysis of data in the social networks. The article presents a study, conducted on the already existing research in regards to the implementation of the non-relational databases in the social networks. Some of the perspectives of the future research are outlined as well.

Sleep spindles are a hallmark of NREM sleep. They result from a widespread thalamo-cortical loop and involve synchronous cortical networks that are still poorly understood. We investigated whether brain activity during spindles can be characterized by specific patterns of functional connectivity among cortical generators. For that purpose, we developed a wavelet-based approach aimed at imaging the synchronous oscillatory cortical networks from simultaneous MEG-EEG recordings. First, we detected spindles on the EEG and extracted the corresponding frequency-locked MEG activity under the form of an analytic ridge signal in the time-frequency plane . Secondly, we performed source reconstruction of the ridge signal within the Maximum Entropy on the Mean framework , yielding a robust estimate of the cortical sources producing observed oscillations. Lastly, we quantified functional connectivity among cortical sources using phase-locking values. The main innovations of this methodology are (1) to reveal the dynamic behavior of functional networks resolved in the time-frequency plane and (2) to characterize functional connectivity among MEG sources through phase interactions. We showed, for the first time, that the switch from fast to slow oscillatory mode during sleep spindles is required for the emergence of specific patterns of connectivity. Moreover, we show that earlier synchrony during spindles was associated with mainly intra-hemispheric connectivity whereas later synchrony was associated with global long-range connectivity. We propose that our methodology can be a valuable tool for studying the connectivity underlying neural processes involving sleep spindles, such as memory, plasticity or aging.

Boltzmann machine is a powerful machine learning model with many real-world applications, for example by constructing deep belief networks. Statistical inference on a Boltzmann machine can be carried out by sampling from its posterior distribution. However, uniform sampling from such a model is not trivial due to an extremely multi-modal distribution. Quantum computers have the promise of solving some non-trivial problems in an efficient manner. We explored the application of a D-Wave quantum annealer to generate samples from a restricted Boltzmann machine. The samples are further improved by Markov chains in a hybrid quantum-classical setup. We demonstrated that quantum annealer samples can improve the performance of Gibbs sampling compared to random initialization. The hybrid setup is considerably more efficient than a pure classical sampling. We also investigated the impact of annealing parameters (temperature) to improve the quality of samples. By increasing the amount of classical processing (Gibbs updates) the benefit of quantum annealing vanishes, which may be justified by the limited performance of today's quantum computers compared to classical.

To investigate the fundamental nature of matter and its interactions, particles are accelerated to very high energies and collided inside detectors, producing a multitude of other particles that are scattered in all directions. As charged particles traverse the detector, they leave signals of their passage. The problem of track reconstruction is to recover the original trajectories from these signals. This challenging data analysis task will become even more demanding as the luminosity of future accelerators increases, leading to collision events with a more complex structure. We identify four fundamental routines present in every local tracking method and analyse how they scale in the context of a standard tracking algorithm. We show that for some of these routines we can reach a lower computational complexity with quantum search algorithms. Although the found quantum speedups are mild, this constitutes, to the best of our knowledge, the first rigorous evidence of a quantum advantage for a high-energy physics data processing task.

To investigate the fundamental nature of matter and its interactions, particles are accelerated to very high energies and collided inside detectors, producing a multitude of other particles that are scattered in all directions. As charged particles traverse the detector, they leave signals of their passage. The problem of track reconstruction is to recover the original trajectories from these signals. This challenging data analysis task will become even more demanding as the luminosity of future accelerators increases, leading to collision events with a more complex structure. We identify four fundamental routines present in every local tracking method and analyse how they scale in the context of a standard tracking algorithm. We show that for some of these routines we can reach a lower computational complexity with quantum search algorithms. Although the found quantum speedups are mild, this constitutes, to the best of our knowledge, the first rigorous evidence of a quantum advantage for a high-energy physics data processing task.

Software maintenance and evolutions often result in large cost overruns and delayed delivery of required changes or improvements. As numerous studies have shown, adopting software to meet ever-changing business needs constitutes a major part of the software maintenance cost. The demand to facilitate software maintenance has led to the emergence of different methods for automated knowledge extraction from source code and other artefacts of existing software systems. This paper presents a systematic literature review of peer-reviewed conference and journal articles on this topic. The review has been undertaken to summarise the state-of-the-art in the research field, identify any gaps and explore possible directions for the further research. In this review, 7 digital libraries were searched and 24 papers dealing with the topic were identified and classified according to the four dimensions: extracted business knowledge kind, extraction techniques, kinds of software artefacts used as input sources, and extracted knowledge representation forms. The results of this study indicate that the research field is still immature and requires more comprehensive research. The results also show that there is a minority of methods that rely on widely adopted business knowledge classification schemes and only very few of methods employ standards for knowledge representation. It is believed that this review and classification scheme proposed in the paper would serve as a guide for both researches and practitioners in the further studies.

Software maintenance and evolutions often result in large cost overruns and delayed delivery of required changes or improvements. As numerous studies have shown, adopting software to meet ever-changing business needs constitutes a major part of the software maintenance cost. The demand to facilitate software maintenance has led to the emergence of different methods for automated knowledge extraction from source code and other artefacts of existing software systems. This paper presents a systematic literature review of peer-reviewed conference and journal articles on this topic. The review has been undertaken to summarise the state-of-the-art in the research field, identify any gaps and explore possible directions for the further research. In this review, 7 digital libraries were searched and 24 papers dealing with the topic were identified and classified according to the four dimensions: extracted business knowledge kind, extraction techniques, kinds of software artefacts used as input sources, and extracted knowledge representation forms. The results of this study indicate that the research field is still immature and requires more comprehensive research. The results also show that there is a minority of methods that rely on widely adopted business knowledge classification schemes and only very few of methods employ standards for knowledge representation. It is believed that this review and classification scheme proposed in the paper would serve as a guide for both researches and practitioners in the further studies.

Energy scarcity at homes is becoming a critical issue due to exponential growth of energy consumption by numerous smart home appliances. Renewable energy sources help to reduce the pressure of grid operation, enabling Smart Home Energy Management System (HEMS) using Internet of Things (IoT) devices. In this work, we have developed policies for parsimonious renewable energy management using smart IoT devices. With the help of Exponential Weighted Moving Average (EWMA), an HEMS predicts energy production and consumption. The results of the prediction decides whether to sell or purchase energy following it is in energy surplus or deficit, respectively. Our energy budget management follows max-min fairness algorithm. The performance evaluation of our proposed system shows that significant performance improvement in terms of monetary expense and user utility can be achieved compared to state-of-the-art works.

Decubitus ulcers occur in an estimated 2.5 million Americans each year at an annual cost of $11 billion to the U.S. health system. Current screening and prevention techniques for assessing risk for decubitus ulcer formation and repositioning patients every 1-2 hours are labor-intensive and can be subjective. We propose use of a Bluetooth-enabled fabric-based pressure sensor array as a simple tool to objectively assess and continuously monitor decubitus ulcer risk.

We deal with transmission phenomena across highly conductive interfaces, investigating the limit behavior of solutions for second order transmission problems. In particular, we investigate via finite element method the influence of thermal conductivity on the heat flux flowing into an interface.

one of the important challenges in grid is quality of service (QoS) for all the accepted users or applications, while increasing the utilization of resources through resource sharing. An effective resource management approach must guarantee the QoS and balance the load among grid nodes which are frequently highly dynamic and heterogeneous. Grid resources are commonly varied regarding their software and hardware formations. Collecting and supervision of these resources, and discovering appropriate resources is an important topic. So semantic can be very useful for resource discovery and resource selection. Fuzzy theory is another intelligent approach which shows uncertainty in Phenomena. In this paper, a novel approach, which is using semantic and fuzzy theory, is proposed to discover grid resource in Grid environment. Search expressiveness, efficiency and scalability, precision and also discover more related resources are the characteristics of the proposed framework.

Speaker verification is the process of accepting or rejecting claimed identity in terms of its sound features. A speaker verification system can be used for numerous security systems, including bank account accessing, getting to security points, criminology and etc. When a speaker verification system wants to check the identity of individuals remotely, it confronts problems such as noise effect on speech signal and also identity falsification with speech synthesis. In this system, we have proposed a new speaker verification system based on Multi Model GMM, called SV-MMGMM, in which all speakers are divided into seven different age groups, and then an isolated GMM model for each group is created; instead of one model for all speakers. In order to evaluate, the proposed method has been compared with several speaker verification systems based on Naïve, SVM, Random Forest, Ensemble and basic GMM. Experimental results show that the proposed method has so better efficiency than others.

Large-scale social networks emerged rapidly in recent years. Social networks have become complex networks. The structure of social networks is an important research area and has attracted much scientific interest. Community is an important structure in social networks. In this paper, we propose a community detection algorithm based on influential nodes. First, we introduce how to find influential nodes based on random walk. Then we combine the algorithm with order statistics theory to find community structure. We apply our algorithm in three classical data sets and compare to other algorithms. Our community detection algorithm is proved to be effective in the experiments. Our algorithm also has applications in data mining and recommendations.

Discovering overlapping community structures is a crucial step to understanding the structure and dynamics of many networks. In this paper we develop a symmetric binary matrix factorization model (SBMF) to identify overlapping communities. Our model allows us not only to assign community memberships explicitly to nodes, but also to distinguish outliers from overlapping nodes. In addition, we propose a modified partition density to evaluate the quality of community structures. We use this to determine the most appropriate number of communities. We evaluate our methods using both synthetic benchmarks and real world networks, demonstrating the effectiveness of our approach.

We present a realizability interpretation for classical analysis-an association of a term to every proof so that the terms assigned to existential formulas represent witnesses to the truth of that formula. For classical proofs of Π2 sentences ∀x∃yA(x, y), this provides a recursive type 1 function which computes the function given by f (x) = y iff y is the least number such that A(x, y).

These are times of crisis. Recently, the COVID-19 pandemic and the resurgence of a form of Cold War raised international concerns about Health & Well-Being, Climate & Biodiversity, and Technology & Economy. Articulating bridges between disciplines, between cultures and between knowledges has never been more urgent to accelerate the translation of values and policies into actions. This comprehensive review argues for a radical ecosystemic approach to bridge the Medical & Environmental fields (studies, sectors, and technics) in an integrated management practice of Care, Production & Biodiversity. As bridging implies solving the epistemological gap, the argument emphasizes the need to raise awareness with theoretical hybridizations, fieldwork hypotheses, and working theories. According to Van Rensselaer Potter, who coined the term 'bioethics', awareness means to refocus the Medical & Environmental studies and surveillance processes from a target (e.g., the disease, the pathogen, or the resource) to its context (e.g., adding history, demography and ecology). Thus reframed, concerned researchers, leaders, and citizens should invest their effort in preparing the (contextual) terrain for ever-more organizational resilience. We conclude on the need for actions to shape the Health & Biodiversity determinants, to improve communication systems, data-sharing networks, and responsible innovations, and to foster knowledge translation to envision a better realistic future. "Ecology's uneconomic, but with another kind of logic economy's unecologic" (Potter 1988, p.9)

The concept of searching and localizing vehicles from live traffic videos based on descriptive textual input has yet to be explored in the scholarly literature. Endowing Intelligent Transportation Systems (ITS) with such a capability could help solve crimes on roadways. One major impediment to the advancement of fine-grain vehicle recognition models is the lack of video testbench datasets with annotated ground truth data. Additionally, to the best of our knowledge, no metrics currently exist for evaluating the robustness and performance efficiency of a vehicle recognition model on live videos and even less so for vehicle search and localization models. In this paper, we address these challenges by proposing V-Localize, a novel artificial intelligence framework for vehicle search and continuous localization captured from live traffic videos based on input textual descriptions. An efficient hashgraph algorithm is introduced to compute valid target information from textual input. This work further introduces two novel datasets to advance AI research in these challenging areas. These datasets include (a) the most diverse and large-scale Vehicle Color Recognition (VCoR) dataset with 15 color classes-twice as many as the number of color classes in the largest existing such dataset-to facilitate finer-grain recognition with color information; and (b) a Vehicle Recognition in Video (VRiV) dataset, a first of its kind video testbench dataset for evaluating the performance of vehicle recognition models in live videos rather than still image data. The VRiV dataset will open new avenues for AI researchers to investigate innovative approaches that were previously intractable due to the lack of annotated traffic vehicle recognition video testbench dataset. Finally, to address the gap in the field, five novel metrics are introduced in this paper for adequately accessing the performance of vehicle recognition models in live videos. Ultimately, the proposed metrics could also prove intuitively effective at quantitative model evaluation in other video recognition applications. T One major advantage of the proposed vehicle search and continuous localization framework is that it could be integrated in ITS software solution to aid law enforcement, especially in critical cases such as of amber alerts or hit-and-run incidents.

The advancement of wearable eye-tracking technology enables cognitive researchers to capture vast amounts of eye gaze information while participants are completing specific tasks without restrictions on their movement. However, while eye trackers can overlay a gaze indicator on the scene video, identifying the specific objects being looked at and analyzing the resulting dataset are accomplished mostly by manual annotation. This method is a cost-prohibitive and time-consuming approach that is prone to human error. Such analytic difficulty limits researchers' ability to data mine the information efficiently, ultimately restricting the number of scenarios that can feasibly be conducted within budget. Here, the first fully automated solution for eye-tracking data analysis is presented, which eliminates the need for manual annotation. The proposed software architecture, gaze to object classification (GoC), processes the gaze-overlaid video from commercially available wearable eye trackers, recognizes and classifies the specific object a user is focusing on and calculates the gaze duration time. GoC utilizes an image cross-correlation method to locate the gaze indicator and an image similarity measurement to support faster processing. The presented system has been successfully adopted by cognitive psychologists. GoC's exceptional performance in analyzing a case study spanning over 50 h of mobile eye-tracking is presented. The accuracy and a cost-analysis comparison between GoC and state-of-the-art manual annotation software are provided. GoC has game-changing potential for increasing the ecological validity of using eye-tracking technology in cognitive research.

Edge detection is an important task in image processing, and the quality of further processing is often reflected by the quality of edge detector outputs. Therefore, it is necessary to develop effective edge map quality measures to assist in evaluating the performance of edge detectors. Objective evaluation measures are crucial in automatically determining the optimal edge map for a given image or an application, as well as its parameter values. In this paper, a new reference-based edge measure (RBEM) is introduced to evaluate the performance of edge detector outputs relative to a ground truth. The new measure fuses four component metrics, based on edge pixel presence, edge corner localization, thick edge occurrence, and edge connectivity. Each of these metrics can be used separately or as a standalone measure to evaluate the quality of an edge map in terms of specific characteristics. The effectiveness of the proposed measure is demonstrated for selecting the best edge detector among several edge detectors, as well as for selecting the optimal parameter values, for both synthetic images and natural images. Experimental results show that the presented RBEM outperforms the existing methods according to subjective evaluation mean opinion scores, as it considers more important visual features in its evaluation.

Currently published tone mapping operators (TMO) are often evaluated on a very limited test set of high dynamic range (HDR) images. Thus, the resulting performance index is highly subject to extensive hyperparameter tuning, and many TMOs exhibit sub-optimal performance when tested on a broader spectrum of HDR images. This indicates that there are deficiencies in the generalizable applicability of these techniques. Finally, it is a challenge developing parameter-free tone mapping operators using data-hungry advanced deep learning methods due to the paucity of large scale HDR datasets. In this paper, these issues are addressed through the following contributions: a) a large scale HDR image benchmark dataset (LVZ-HDR dataset) with multiple variations in sceneries and lighting conditions is created to enable performance evaluation of TMOs across a diverse conditions and scenes that will also contribute to facilitate the development of more robust TMOs using state-of-the-art deep learning methods; b) a deep learning-based tone mapping operator (TMO-Net) is presented, which offers an efficient and parameter-free method capable of generalizing effectively across a wider spectrum of HDR content; c) finally, a comparative analysis, and performance benchmarking of 19 state-of-the-art TMOs on the new LVZ-HDR dataset are presented. Standard metrics including the Tone Mapping Quality Index (TMQI), Feature Similarity Index for Tone Mapped images (FSITM), and Natural Image Quality Evaluator (NIQE) are used to qualitatively evaluate the performance index of the benchmarked TMOs. Experimental results demonstrate that the proposed TMO-Net qualitatively and quantitatively outperforms current state-of-the-art TMOs.

This paper proposes a novel framework for enhancing headmounted eye tracking data analysis by utilizing state-of-art computer vision techniques. Recently, the development of mobile eye tracking sensors allowed researchers to explore more comprehensive eye movements in an unobtrusive environment. It opened a door that stationary eye tracking devices could never approach. Literature demonstrates applications of mobile eye tracking technology to fields such as psychology, education and learning, usability, marketing, and medical diagnostics. The eye tracking research community is interested in analyzing the details of what and where a person is looking at using large-scale headmounted eye tracking data. We formulated this problem to be eye tracking video processing, which can be resolved by locating at region-of-interests (ROI) based on fixation location, cropping and zooming in the ROI and enhancing the partial image by superresolution image transformation. Experimental results and evaluation using image quality measurements show the effectiveness, efficiency, and robustness of the proposed prototype system. Furthermore, we discuss and demonstrate potential realtime applications using the proposed framework with emphasis on using an Augmented Reality (AR) headset with eye tracking capabilities.

Images captured in real-world applications in remote sensing, image or video retrieval, and outdoor surveillance suffer degraded quality introduced by poor weather conditions. Conditions such as rain and mist, introduce artifacts that make visual analysis challenging and limit the performance of high-level computer vision methods. For time-critical applications where a rapid response is necessary, it becomes crucial to develop algorithms that automatically remove rain, without diminishing the quality of the image contents. This article aims to develop a novel quaternion multi-stage multiscale neural network with a selfattention module called QSAM-Net to remove rain streaks. The novelty of this algorithm is that it requires significantly fewer parameters by a factor of 3.98, over prior methods, while improving visual quality. This is demonstrated by the extensive evaluation and benchmarking on synthetic and real-world rainy images. This feature of QSAM-Net makes the network suitable for implementation on edge devices and applications requiring near real-time performance. The experiments demonstrate that by improving the visual quality of images. In addition, object detection accuracy and training speed are also improved. Adverse weather conditions (haze, snow, rain, fog) are among the most prevalent reasons for the limited use of automatic video surveillance, crowd counting, accident detection, person re-identification, computational photography, and other computer vision tasks . Consequently, a preprocessing step is necessary to limit the impact of weather conditions on the rest of the image analysis system. In real-world applications mentioned above, image de-raining is highly desirable due to the facts that a) rainy weather often causes poor visibility, contrast reduction, and color modification, b) the removal of rain-streaks typically produces over-smoothed images and leads to lost image details, c) the lack of robust prior-models of both rainstreaks and background, and d) the image rain removal is a highly ill-posed problem . Image de-raining aims to create a sharp, clean image from a rainy image. Therefore, it is essential to develop algorithms that automatically remove these artifacts and not degrade the rest of the image's contents. Current deraining efforts can be grouped into model-based and data-driven approaches. Model-based de-raining algorithms make use of the prior information about rain distribution. They exploit images' sparsity and local similarity properties of the rain by using sparse dictionaries and GMM . Data-driven de-raining methods use deep neural networks trained on end-to-end synthetic and clean/rainy image pairs. Various network architectures were explored, including classical CNNs, recurrent neural networks, and generative adversarial networks . Recently, multiscale multistage methods such as MPRNet, HINet, and Restormer demonstrated high performance on image processing tasks, including rain streak removal . Despite the significant progress, both model-based and data-driven approaches have their drawbacks. Due to the inadequacy of existing models, some methods tend to remove non-rain-related vertical textures and generate underexposed images . This problem is especially apparent in the case of supervised learning. Modern methods use different network architectures, assumptions, and priors but fail when previously unseen conditions occur .

Edge detection has been used extensively as a preprocessing step for many computer vision tasks. Due to its importance in image processing and the highly subjective nature of human evaluation and visual comparison of edge detectors, it is desirable to formulate objective edge map evaluation measures. One would like to use such a measure to make comparisons of results using the same edge detector with different parameters as well as to make comparisons of results using different edge detectors. Reconstruction-based measures have the clear advantage that they effectively incorporate original image data. In this paper, a general model for reconstruction-based measures is established in order to alleviate the shortcomings of the reconstruction-based measures, followed by the formulation of a new non-reference measure for objective edge map evaluation. Experimental results illustrate the effectiveness of the new measure both as a means of selecting optimal edge detector parameters and as a means of determining the relative performance of edge detectors for a given image.

Current state-of-the-art object tracking methods have largely benefited from the public availability of numerous benchmark datasets. However, the focus has been on open-air imagery and much less on underwater visual data. Inherent underwater distortions, such as color loss, poor contrast, and underexposure, caused by attenuation of light, refraction, and scattering, greatly affect the visual quality of underwater data, and as such, existing open-air trackers perform less efficiently on such data. To help bridge this gap, this article proposes a first comprehensive underwater object tracking (UOT100) benchmark dataset to facilitate the development of tracking algorithms well-suited for underwater environments. The proposed dataset consists of 104 underwater video sequences and more than 74 000 annotated frames derived from both natural and artificial underwater videos, with great varieties of distortions. We benchmark the performance of 20 state-of-the-art object tracking algorithms and further introduce a cascaded residual network for underwater image enhancement model to improve tracking accuracy and success rate of trackers. Our experimental results demonstrate the shortcomings of existing tracking algorithms on underwater data and how our generative adversarial network (GAN)-based enhancement model can be used to improve tracking performance. We also evaluate the visual quality of our model's output against existing GAN-based methods using well-accepted quality metrics and demonstrate that our model yields better visual data.

This paper introduces an modelling approach to determining the appropriate width of a time window within which an admission is classified as a readmission. The approach is based on an intuitive idea that patients, who are discharged from hospital, can be broadly considered as consisting of two groups -a group that is at high risk of readmission and a group that is at low risk. Using national data from the London area (UK), we demonstrate its usefulness in the case of chronic obstructive pulmonary diseases (COPD), one of the leading causes of early readmission. Although marked regional differences exist for the optimal width of the time window for COPD patients, our findings are largely inline with figures used by the government, hance provide some support for the use of 28 days as the time window for defining COPD readmissions. The novelty of this modelling approach lies in its ability to estimate an appropriate time window based on evidence objectively derived from operational data. Therefore, it can provide a means of monitoring performance for hospitals, and can potentially contribute to the better management of patient care.

As the UK population ages, it is forecasted that there will be an unsustainable increase in the need for, and therefore in the costs of long-term care. Although several studies have been performed to estimate these costs, they do not take into account the impact of survival patterns on costs. Focussing only on residents already in care (known commitments), we have developed, in association with an English local authority, a framework for estimating the future gross cost incurred by this group, built around a survival model. We apply this framework to forecast the cost over a given period of time, of maintaining a group of individuals in residential and nursing care, funded by the local authority. One of the novelties in the model is that it translates survival inputs and unit fees for care into cost in a manner, which was useful and meaningful to decision makers.