Search

Detecting plagiarism in academic papers is crucial for maintaining academic integrity, preserving the originality of published work, and safeguarding intellectual property. While existing applications excel at text plagiarism detection, they fall short when it comes to image plagiarism. This paper introduces a novel algorithm, named "VIBRANT-WALK," designed to detect image plagiarism in academic manuscripts. The challenge of identifying plagiarized images is formidable, requiring a unique approach. Traditional Computer Vision algorithms, proficient in image similarity tasks, face limitations in determining whether an image has been previously used in an article. To address this, the proposed algorithm leverages a repository of all published article pages, focusing on absolute identicality rather than image similarity. The algorithm comprises two stages. In the first stage, a "Vibrancy Matrix" is created through image preprocessing, aiding in contour determination. The second stage involves pixel-by-pixel comparison with images from published manuscripts. To enhance efficiency, the algorithm initiates comparisons from the pixel with the highest score in the Vibrancy Matrix, followed by pixel comparisons through random walks, significantly reducing complexity. To conduct the study, a custom dataset was compiled from 69 research articles, capturing snapshots of each page and figure. Overall, we present 485 unique test cases where we can test the accuracy and efficiency of the algorithm. The lack of publicly available datasets necessitated this approach. The proposed algorithm outperformed the existing models and algorithms in this field by achieving an overall accuracy of 94.8% on the collated dataset, identifying 460 instances of plagiarism out of the 485 test cases. The algorithm also demonstrated a 100% accuracy rate in avoiding false positives. [ABSTRACT FROM AUTHOR]

This article explores the application of DNA computing in recyclable waste paper sorting. The primary challenge in paper recycling is to obtain raw materials with the highest purity. In recycling, waste papers are segregated according to their various grades, and these are subjected to different recycling processes. Highly sorted paper streams facilitate high quality end products, while saving on processing chemicals and energy. In the industry, different sensors are used in paper sorting systems, namely, ultrasonic, lignin, gloss, stiffness, infra-red, mid-infra red, and color sensors. Different mechanical and optical paper sorting systems have been developed based on the different sensors. However, due to inadequate throughput and some major drawbacks related to mechanical paper sorting systems, the popularity of optical paper sorting systems has increased. The automated paper sorting systems offer significant advantages over the manual systems in terms of human fatigue, throughput, speed, and accuracy. This research has two objectives: (1) to use a web camera as an image sensor for the vision system in lieu of different sensors; and (2) to develop a new DNA computing algorithm based on the theme of template matching techniques for segregating recyclable waste papers according to paper grades. Using the concepts of replication and massive parallelism operations, the DNA computing algorithm can efficiently reduce the computational time of the template matching method. This is the main strength of the DNA computing algorithm in actual inspections. The algorithm is implemented by using a silicon-based computer to verify the success rate in paper grade identification. [ABSTRACT FROM AUTHOR]

One important reason for the use of field categorization in bibliometrics is the necessity to make citation impact of papers published in different scientific fields comparable with each other. Raw citations are normalized by using field-categorization schemes to achieve comparable citation scores. There are different approaches to field categorization available. They can be broadly classified as intellectual and algorithmic approaches. A paper-based algorithmically constructed classification system (ACCS) was proposed which is based on citation relations. Using a few ACCS field-specific clusters, we investigate the discriminatory power of the ACCS. The micro study focusses on the topic ‘overall water splitting’ and related topics. The first part of the study investigates intellectually whether the ACCS is able to identify papers on overall water splitting reliably and validly. Next, we compare the ACCS with (1) a paper-based intellectual (INSPEC) classification and (2) a journal-based intellectual classification (Web of Science, WoS, subject categories). In the last part of our case study, we compare the average number of citations in selected ACCS clusters (on overall water splitting and related topics) with the average citation count of publications in WoS subject categories related to these clusters. The results of this micro study question the discriminatory power of the ACCS. We recommend larger follow-up studies on broad datasets. [ABSTRACT FROM AUTHOR]

Abstract: A method for the comparison of paper structure using light transmission images and frequency analysis was developed. The resolution of the light transmission images and the algorithm for the feature extraction were greatly improved to enhance the visibility of peaks in the 2D power spectrum that results from frequency analysis. A comparison method based on correlation measures how well the spectra match as a function of the orientation of the paper, yielding an objective and quantitative measure of similarity between 0 and 1. A technical validation was carried out with 25 different papers showing the potential of this method with common copy papers. Finally, the method was applied in a case. [Copyright &y& Elsevier]

Abstract: Recommendation algorithms have been researched extensively to help people deal with abundance of information. In recent years, the incorporation of multiple relevance criteria has attracted increased interest. Such multi-criteria recommendation approaches are researched as a paradigm for building intelligent systems that can be tailored to multiple interest indicators of end-users – such as combinations of implicit and explicit interest indicators in the form of ratings or ratings on multiple relevance dimensions. Nevertheless, evaluation of these recommendation techniques in the context of real-life applications still remains rather limited. Previous studies dealing with the evaluation of recommender systems have outlined that the performance of such algorithms is often dependent on the dataset – and indicate the importance of carrying out careful testing and parameterization. Especially when looking at large scale datasets, it becomes very difficult to deploy evaluation methods that may help in assessing the effect that different system components have to the overall design. In this paper, we study how layered evaluation can be applied for the case of a multi-criteria recommendation service that we plan to deploy for paper recommendation using the Mendeley dataset. The paper introduces layered evaluation and suggests two experiments that may help assess the components of the envisaged system separately. [Copyright &y& Elsevier]

Abstract: A new approach of paper defect recognition is proposed. To implement this method, computer is used to acquire paper image and the subtraction algorithm is used to determine if the image contains defect at first. For the image with paper defect, wavelet packet decomposition is applied to extracting the feature vector of the defect. A BP neural network is designed for recognizing the defect type according to the feature vector. This approach provides a unified detection algorithm for different types of paper defects. The experiment data prove this method is valid and can be applied in modern paper defect inspection system. [Copyright &y& Elsevier]

Abstract: Combining previous image mosaicing algorithms, this paper puts forward a kind of damaged text restore image processing algorithm. The algorithm can restore the shredder pieces tape. A series of tapes which are obtained by scanner are treated through image processing such as binary, segmentation, denoising and enhancement and so on, Then we can get the ideal original text image from some leaflet tapes image. Experimental results show that such algorithm has certain effectiveness. [Copyright &y& Elsevier]

Internet of Things (IoT) powered by high level synthesis (HLS) provides huge opportunity of progress in the area of hardware design. However, the present era of hardware design involves globalization which poses security threat to the design integrators that rely on third party intellectual property (IP) cores for increasing design productivity at reduced design time. This paper presents for the first time in the literature, a low cost optimized hardware Trojan secured HLS approach for hardware (or application specific core) designs that is based on single or nested loop control data flow graphs (CDFG) applications. The paper presents multiple novel vendor allocation schemes (each with its own attribute of delay and area) as security constraint that yield Trojan secured schedules at behavioral level. Demonstration of the proposed approach on a nested loop case study asserts our proposed theory. Results on standard benchmarks indicate significant reduction in final solution cost compared to a similar approach. [ABSTRACT FROM AUTHOR]

This paper introduces a new approach for improving the performance and versatility of Layered Manufacturing (LM), which is an emerging technology that makes it possible to build physical prototypes of 3D parts directly from their computer models using a “3D printer” attached to a personal computer.Current LM processes work by viewing the computer model as a single, monolithic unit. By contrast, the approach proposed here decomposes the model into a small number of pieces, by intersecting it with a suitably chosen plane, builds each piece separately using LM, and then glues the pieces together to obtain the physical prototype. This approach allows large models to be built quickly in parallel. Furthermore, it is very efficient in its use of so-called support structures that are generated by the LM process.This paper presents the first provably correct and efficient geometric algorithms to decompose polyhedral models so that the support requirements (support volume and area of contact) are minimized. Algorithms based on the plane-sweep paradigm are first given for convex polyhedra. These algorithms run in O(nlogn) time for n-vertex convex polyhedra and work by generating expressions for the support volume and contact-area as a function of the height of the sweep plane, and optimizing them during the sweep. These algorithms are then generalized to non-convex polyhedra, which are considerably more difficult due to the complex structure of the supports. It is shown that, surprisingly, non-convex polyhedra can be handled by first identifying certain critical facets using a technique called cylindrical decomposition, and then applying the algorithm for convex polyhedra to these critical facets. The resulting algorithms run in O(n2logn) time. Also given is a method for controlling the size of the decomposition, so that the number of pieces generated is within a user-specified limit. Experimental results show that the proposed approach can achieve significant reduction in support requirements in both the convex and the non-convex case. [Copyright &y& Elsevier]

[Display omitted] • Two colorimetric paper-based sensors for creatinine determination are developed. • Signal readout is achieved with a smartphone with a self-written application. • App relies on computer-vision to enable automatic detection of the zone of interest. • The utility of the platform to determine creatinine in undiluted urine is proved. Creatinine is a clinically significant analyte used to diagnose kidney condition. However, the literature still lacks in creatinine sensors fulfilling point-of-care testing requirements. In this paper, we have developed colorimetric paper-based creatinine sensors adhering to point-of-care testing principles. The signal readout is accomplished with a smartphone modified with 3D-printed elements and processed with a self-written application compromising computer vision algorithm for automatic detection of the colored zone. Two colorimetric methods – routinely used Jaffé method and an alternative one with 3,5-dinitrobenzoic acid were both tested and compared. Hue channel intensity from HSV color space and green channel from RGB color space was used as the analytical signal in Jaffé and 3,5-dinitrobenzoate method, respectively. For both kinds of sensors the linear range of the response covered the range significant for urinary analysis, with precision, expressed as RSD, below 5%. Limit of quantification for Jaffé method was 1.05 mmol·L−1 whereas it was 0.82 mmol·L−1 for 3,5-dinitrobenzoate method. The utility of the developed sensors to selectively quantify creatinine in undiluted urine was proved using artificial urine samples and the obtained recoveries were in the range from 70 to 129 %. [ABSTRACT FROM AUTHOR]

The large deformation of soft rock tunnel is an important problem to be solved urgently with the development of engineering technology. In order to improve the application effect of prestressed anchor cable adaptive active support system, this paper puts forward an optimization method based on adaptive genetic algorithm, reviews the research status of prestressed anchor support in soft rock tunnel, and analyzes and evaluates the existing methods. This paper introduces the construction process of AGA model, establishes the problem description model and genetic optimization algorithm selection model, and constructs the adaptive active support model of prestressed anchor cable. The model adopts an optimization algorithm with a total of 100 iterations. The Simple Genetic Algorithm and Parallel Genetic Algorithm are selected to evaluate the anchoring force, the control effect of surrounding rock displacement, the erosion of supporting structure and the construction time by comparative test. The test results show that AGA has a good effect on the anchoring force, the minimum anchoring force is 457 kN, and the displacement of surrounding rock is controlled within 1.21-1.59mm, which has a good influence on the quality of supporting structure and the construction completion time. Finally, the application of AGA model in parameter optimization of prestressed anchor cable in soft rock tunnel is summarized, and the future research direction is put forward. [ABSTRACT FROM AUTHOR]

Objective image quality assessment involves the use of mathematical models to quantitatively describe image quality. FR-IQA (Full-Reference Image Quality Assessment) methods using reference images are also often used to evaluate image processing and computer vision algorithms. Quality indices often use gradient operators to express relevant visual information, such as edges. Fractional calculus has been applied in the last two decades in various fields such as signal processing, image processing, and pattern recognition. Fractional derivatives are generalizations of integer-order derivatives and can be computed using various operators such as the Riemann-Liouville, Caputo-Fabrizio, and Grünwald-Letnikov operators. In this paper, we propose a modification of the FSIMc image quality index by including fractional derivatives to extract and enhance edges. A study of the usefulness of fractional derivative in the FSIMc model was conducted by assessing Pearson, Spearman and Kendall correlations with MOS scores for images from the TID2013 and KADID-10k databases. Comparison of FD_FSIMc with the classic FSIMc shows an increase of several percent in the correlation coefficients for the modified index. The results obtained are superior to those other known approaches to FR-IQA that use fractional derivatives. The results encourage the use of fractional calculus. [ABSTRACT FROM AUTHOR]

Machine learning (ML) provides algorithms to create computer programs based on data without explicitly programming them. In business process management (BPM), ML applications are used to analyse and improve processes efficiently. Three frequent examples of using ML are providing decision support through predictions, discovering accurate process models, and improving resource allocation. This paper organises the body of knowledge on ML in BPM. We extract BPM tasks from different literature streams, summarise them under the phases of a process's lifecycle, explain how ML helps perform these tasks and identify technical commonalities in ML implementations across tasks. This study is the first exhaustive review of how ML has been used in BPM. We hope that it can open the door for a new era of cumulative research by helping researchers to identify relevant preliminary work and then combine and further develop existing approaches in a focused fashion. Our paper helps managers and consultants to find ML applications that are relevant in the current project phase of a BPM initiative, like redesigning a business process. We also offer – as a synthesis of our review – a research agenda that spreads ten avenues for future research, including applying novel ML concepts like federated learning, addressing less regarded BPM lifecycle phases like process identification, and delivering ML applications with a focus on end-users. • We describe BPM lifecycle phases and define BPM tasks in view of ML applications. • We present an overview of ML applications in the field of BPM. • We provide a technical summary of ML applications of each BPM lifecycle phase. • We derived ten findings from our literature review. • We set up an agenda with ten future research directions for advancing research on ML applications in BPM. [ABSTRACT FROM AUTHOR]

This paper presents a novel Adaptive Mutation Quantum-inspired Squirrel Search Algorithm (AM-QSSA). Firstly, based on the population mutation, a location-update of quantum state correlative and attractor method is proposed. By introducing a random process to modify the sliding factor of the local attractor, the inevitable lack of diversity in the population renewal method is solved. The premature convergence problem of adaptive mutation rate improvement algorithm based on squirrel position update mode is introduced. Meanwhile, the paper decomposes the location update process of the SSA, and improves it with quantum-behavior. Furthermore, it proposes a novel quantum-inspired squirrels search algorithm. This method finds the complementary effect between quantum behavior and squirrel search algorithm, and solves the problem of premature convergence probability of SSA. In addition, it improves population diversity, and achieves the balance between global and local search. The efficiency of the proposed AM-QSSA is evaluated using exploitation analysis, exploration analysis, success rate analysis, convergence rate analysis on classical benchmark functions as well as Congress on Evolutionary Computation (CEC) 2017 test functions. For further study, AM-QSSA optimizes an image registration problem for an extensive study to check its applicability. The results reveal that AM-QSSA is more efficient and stable than SSA. And it is comparable to the most advanced optimization algorithms. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a detailed description of a vision system developed to detect and locate the non-uniformities that appear on the web offset printing machine. Specifically, the system is capable of monitoring the high-speed web offset printing in a real-time environment and alerting the operator of any events (e.g., structural faults, color variations, missing characters, ink splashes, streaks, etc.) that disrupt the uniformities in the web offset printing. Such events are thought to affect crucial printing properties, resulting in non-uniformities in printing and impacting its quality and printability. This paper describes the vision system in terms of its hardware modules, as well as the image processing algorithms that it utilizes to scan the color images and locate areas of defect from the printing web. Basically, the system utilizes high-speed image scanning algorithms to detect edges and boundaries using linear and non-linear filters of dynamic size, threshold and transformation for further analysis. In addition to being tested in a laboratory environment, a prototype of this system was constructed and deployed to a web printing system, where its performance was evaluated under realistic conditions. The system was installed on a Flexo gravure-print-press machine for testing, and it was found that the vision system was able to successfully monitor and detect non-uniformities. [Copyright &y& Elsevier]

Folding planar sheets to make 3D shapes from is an ancient practice with many new applications, ranging from personal fabrication of customized items to design of surgical instruments for minimally invasive surgery in self-folding machines. Given a polyhedral mesh, unfolding is an operation of cutting and flattening the mesh. The flattened polyhedral nets are then cut out of planar materials and folded back to 3D. Unfolding a polyhedral mesh into planar nets usually require segmentation. Either used as a preprocessing step to simplify the mesh and provide semantics or as the result of unfolding to avoid overlapping, the segmentation and the unfolding operations are decoupled. Consequently, segmented components may not be unfoldable and unfolded nets usually provide no semantic meaning and make folding difficult. In this paper, we propose a strategy that tightly couples unfolding and segmentation. We show that the proposed method produces unfoldable segmentation that resembles carefully designed paper craft. The key idea that enables this capability is an algorithm that learns from failed unfoldings. [ABSTRACT FROM AUTHOR]

Missions to small celestial bodies rely heavily on optical feature tracking for characterization of and relative navigation around the target body. While deep learning has led to great advancements in feature detection and description, training and validating data-driven models for space applications is challenging due to the limited availability of large-scale, annotated datasets. This paper introduces AstroVision, a large-scale dataset comprised of 115,970 densely annotated, real images of 16 different small bodies captured during past and ongoing missions. We leverage AstroVision to develop a set of standardized benchmarks and conduct an exhaustive evaluation of both handcrafted and data-driven feature detection and description methods. Next, we employ AstroVision for end-to-end training of a state-of-the-art, deep feature detection and description network and demonstrate improved performance on multiple benchmarks. The full benchmarking pipeline and the dataset will be made publicly available to facilitate the advancement of computer vision algorithms for space applications. • Missions to small bodies rely heavily on humans for optical feature tracking. • Deep Learning has led to great advancements in feature detection and description. • We present AstroVision, a first-of-a-kind dataset for vision-based tasks near small bodies. • We conduct an extensive evaluation of feature detection and description methods. • We demonstrate increased performance by training a deep feature network on our data. [ABSTRACT FROM AUTHOR]

As computer vision algorithms increase in capability, their applications in clinical systems will become more pervasive. These applications include: diagnostics, such as colonoscopy and bronchoscopy; guiding biopsies, minimally invasive interventions, and surgery; automating instrument motion; and providing image guidance using pre-operative scans. Many of these applications depend on the specific visual nature of medical scenes and require designing algorithms to perform in this environment. In this review, we provide an update to the field of camera-based tracking and scene mapping in surgery and diagnostics in medical computer vision. We begin with describing our review process, which results in a final list of 515 papers that we cover. We then give a high-level summary of the state of the art and provide relevant background for those who need tracking and mapping for their clinical applications. After which, we review datasets provided in the field and the clinical needs that motivate their design. Then, we delve into the algorithmic side, and summarize recent developments. This summary should be especially useful for algorithm designers and to those looking to understand the capability of off-the-shelf methods. We maintain focus on algorithms for deformable environments while also reviewing the essential building blocks in rigid tracking and mapping since there is a large amount of crossover in methods. With the field summarized, we discuss the current state of the tracking and mapping methods along with needs for future algorithms, needs for quantification, and the viability of clinical applications. We then provide some research directions and questions. We conclude that new methods need to be designed or combined to support clinical applications in deformable environments, and more focus needs to be put into collecting datasets for training and evaluation. [Display omitted] • We refresh tracking and mapping in medical computer vision, reviewing 515 papers. • We summarize limitations and future directions to enable growth in this field. • Machine learning is increasing in impact for tracking and mapping. • Having more publicly available datasets and robust models is essential. • Modern computer vision methods are frequently adapted to the specifics of medical scenes. [ABSTRACT FROM AUTHOR]

A graph G is k -vertex-critical if G has chromatic number k but every proper induced subgraph of G has chromatic number less than k. The study of k -vertex-critical graphs for graph classes is an important topic in algorithmic graph theory because if the number of such graphs that are in a given hereditary graph class is finite, then there is a polynomial-time algorithm to decide if a graph in the class is (k − 1) -colorable. In this paper, we prove that for every fixed integer k ≥ 1 , there are only finitely many k -vertex-critical (P 5 , gem)-free graphs and (P 5 , P 3 + P 2 ¯) -free graphs. To prove the results we use a known structure theorem for (P 5 ,gem)-free graphs combined with properties of k -vertex-critical graphs. Moreover, we characterize all k -vertex-critical (P 5 , gem)-free graphs and (P 5 , P 3 + P 2 ¯) -free graphs for k ∈ { 4 , 5 } using a computer generation algorithm. [ABSTRACT FROM AUTHOR]

Machine learning algorithms especially deep neural networks have seen tremendous growth in their real-world deployment. While these algorithms have to yield high performances for the task at hand, it is of equal importance that they are robust against the different kinds of singularities or adversarial anomalies. Researchers have generally addressed singularity detection independently for each anomaly, however, for the algorithms to be effective in the real world, the singularity detection algorithm must be able to handle a wide variety of attacks whether trained individually on them or not seen at the time of training. With this objective, in this paper, we propose a unique end-to-end transformation domain network to detect a variety of well-known attacks. The proposed architecture utilizes a combination of two different wavelet transformations to simultaneously learn low-level and high-level image features in a deep stacked layer fashion. The proposed method is generalized to handle a broad set of singularities of several computer vision algorithms whether operating in the object recognition domain or biometrics recognition. We showcase the results on a wide range of singularity points including (i) adversarial perturbations which are learned using deep learning networks, (ii) physical presentation attacks on face recognition which aim to produce fake data for the sensor for acquisition, and identification, (iii) synthetic images, and (iv) digital retouching of the images. Even with a zero-day or open-world attack setting, the results of the proposed algorithm show improvement over state-of-the-art results. The proposed architecture is agnostic to parameters, computationally efficient to provide a sustainable detector to resource-constrained institutions, provides robustness to attacks, and supports green computing. • A novel parameter-agnostic architecture is proposed to defend anomalies. • The proposed algorithm can handle adversaries in seen, unseen, and open-set settings. • The proposed algorithm is domain agnostic i.e., can handle vision and face datasets. • Our unified algorithm surpasses the SOTA works developed to handle specific attacks. • Bring a computationally feasible algorithm, it can be deployed on mobile devices. [ABSTRACT FROM AUTHOR]

With the rise and development of computer networks, network security has become a major issue, and intrusion detection has emerged as a crucial aspect of network security. However, traditional intrusion detection methods suffer from issues like slow detection rates and low accuracy. This necessitates the exploration and development of optimized algorithms for improving intrusion detection efficiency and accuracy. Recently, the multi-objective differential evolution algorithm has shown promising results in the field of intrusion detection. This paper explored the application of the multi-objective differential evolution algorithm in computer network intrusion detection systems. The experimental results on the KDDCUP'99 dataset demonstrated that the algorithm delivers high levels of precision and recall, outperforming other intrusion detection methods. Therefore, combining the multi-objective differential evolution algorithm with traditional intrusion detection methods can lead to significant improvements in intrusion detection efficiency and accuracy. Further optimization of this algorithm can be required to meet complex intrusion detection requirements. The multi-objective differential evolution algorithm presents exciting prospects, which can help enhance the efficiency and accuracy of intrusion detection, and provide strong technical support for ensuring network security and preventing cyber-attacks. [ABSTRACT FROM AUTHOR]

With the rapid development of computer technology. Many scholars pay close attention to computer graphics algorithms, which makes computer graphics widely used in various fields and enters a new revolutionary era. The purpose of this paper is to study the evaluation of computer graphics algorithm demonstration systems. Combining theory with practice, on the basis of careful analysis of the principle of graphics algorithm, a new idea of synchronization of graphics production process and a specific algorithm for realizing graphics are proposed, and most graphics in computer graphics are visualized. It breaks the limitation that only two-dimensional graphic simulation effects can be realized, and increases the interactive user control system. The algorithm complexity is significantly reduced, the graphics creation speed is increased, and the simulation effect is more realistic. After the introduction of this visual teaching demonstration system, these abstract principles can be explained intuitively, which can significantly improve the teaching quality. [ABSTRACT FROM AUTHOR]

Usually a complete computer network system has the following components: source of signals, signal host, cryptographic regime, attack, and interceptor. It is more vulnerable to attacks during the operation of the system, so the security of the system becomes more important. In this paper, by constructing a dual BP neural network combinatorial model and applying it to the computer data communication large integer decomposition encryption process, the constructed model is used to analyze the security against digital certificates, digital signatures, and the algorithms employed in the communication process of connected computer network. [ABSTRACT FROM AUTHOR]

The availability of high-resolution data and accurate ground truth is essential to evaluate and compare methods and algorithms properly. Moreover, it is often difficult to acquire real data for a given application domain that is sufficiently representative and heterogeneous in terms of scene representation, acquisition conditions, point of view, etc. To overcome the limitations of available datasets, this paper presents a new synthetic, multi-purpose dataset called ENRICH for testing photogrammetric and computer vision algorithms. Compared to existing datasets, ENRICH offers higher resolution images rendered with different lighting conditions, camera orientations, scales, and fields of view. Specifically, ENRICH is composed of three sub-datasets: ENRICH-Aerial, ENRICH-Square, and ENRICH-Statue, each exhibiting different characteristics. We show the usefulness of the proposed dataset on several examples of photogrammetry and computer vision-related tasks such as: evaluation of hand-crafted and deep learning-based local features, effects of ground control points (GCPs) configuration on the 3D accuracy, and monocular depth estimation. We make ENRICH publicly available at: https://github.com/davidemarelli/ENRICH. [ABSTRACT FROM AUTHOR]

Despite the recent progress of 3D human pose estimation, reconstructing an accurate 3D human posture from a single image without 3D annotation is yet challenging due to the following reasons. First, the reconstructing process is inherently ambiguous, as multiple 3D poses can be projected onto the same 2D pose. Second, camera rotation is difficult to measure precisely without laborious camera calibration. Some approaches resort to traditional computer vision algorithms to address these issues, but they are not differentiable and cannot be optimized through training. In this paper, we propose two geometrically explicit modules to solve the problems without any 3D ground-truth or camera parameters. Relative depth estimation module effectively mitigates depth ambiguity, reducing a number of possible depths for each joint to only two candidates. Differentiable pose alignment module calculates camera rotation via aligning poses from different views. The two modules are geometrically interpretable, reducing the training difficulty and leading to superior performance. Our method achieves state-of-the-art on the standard benchmark datasets among self-supervised methods and even outperforms several fully-supervised approaches that rely on 3D annotations. [ABSTRACT FROM AUTHOR]

• Examined whether perceived risk in traffic images can be predicted from computer vision features. • 1378 participants rated the perceived risk of 100 dashcam images. • Population-level perceived risk was found to be statistically reliable. • Used regression analysis to predict perceived risk from detected road users and ego-vehicle speed. Perceived risk, or subjective risk, is an important concept in the field of traffic psychology and automated driving. In this paper, we investigate whether perceived risk in images of traffic scenes can be predicted from computer vision features that may also be used by automated vehicles (AVs). We conducted an international crowdsourcing study with 1378 participants, who rated the perceived risk of 100 randomly selected dashcam images on German roads. The population-level perceived risk was found to be statistically reliable, with a split-half reliability of 0.98. We used linear regression analysis to predict (r = 0.62) perceived risk from two features obtained with the YOLOv4 computer vision algorithm: the number of people in the scene and the mean size of the bounding boxes surrounding other road users. When the ego-vehicle's speed was added as a predictor variable, the prediction strength increased to r = 0.75. Interestingly, the sign of the speed prediction was negative, indicating that a higher vehicle speed was associated with a lower perceived risk. This finding aligns with the principle of self-explaining roads. Our results suggest that computer-vision features and vehicle speed contribute to an accurate prediction of population subjective risk, outperforming the ratings provided by individual participants (mean r = 0.41). These findings may have implications for AV development and the modeling of psychological constructs in traffic psychology. [ABSTRACT FROM AUTHOR]

The computer vision-based analysis of railway superstructure has gained significant attention in railway engineering. This approach utilises advanced image processing and machine learning techniques to extract valuable information from visual data captured in the railway track environment. By analysing images from various sources such as cameras, drones, or sensors, computer vision algorithms can accurately detect and classify different components of the ballast superstructure, including the catenary system support, rail surface and profile, fastening system, sleeper, and ballast layer. This enables the automated assessment of the railway track's condition, stability, and maintenance needs. This paper comprehensively reviews the recent advancements, challenges, and potential applications of computer vision techniques in analysing railway superstructure. It discusses various vision-based methodologies and machine-learning approaches utilised in this context. Furthermore, it examines the benefits and limitations of computer vision-based analysis and presents future research directions for improving its applicability in railway track engineering. • Explores advanced sensing technologies and robotics. • Discusses image preprocessing, segmentation, and detection methods. • Examines track components: ballast, sleeper, fasteners, rail, and catenary system. [ABSTRACT FROM AUTHOR]

Over the past few years, the computer vision domain has evolved and made a revolutionary transition from human-engineered features to automated features to address challenging tasks. Computer vision is an ever-evolving domain with its roots deeply correlated with neuroscience; any new findings that trigger a more intuitive understanding and working of the human visual system generally impact the design strategy of computer vision algorithms. The convolutional neural network is one such algorithm that is currently the de facto standard for most computer vision tasks such as image classification, object detection, image segmentation, etc. As convolutional neural networks are associated with inherent constraints such as the requirement for an immense amount of labeled data and an inefficient data routing policy, capsule networks could be a viable alternative. Upheld by the backpropagation and the dynamic routing algorithm, the capsule network has set the new paradigm for developing reliable computer vision algorithms. Despite the phenomenal theoretical backing from neuroscience and the groundbreaking performance on benchmark datasets, the lack of information concerning the conception and working of capsule networks becomes the major impediment to adopting them for computer vision algorithms. This paper presents a concise overview of capsule network-based classification architectures, routing algorithms, performance analysis, limitations, and future scope, helping the research community to adopt capsule networks at the forefront of modern computer vision research. [ABSTRACT FROM AUTHOR]

Many structural models in chemistry, biology, computer science, sociology, and operations research can be analyzed using graph theory. Some examples of these structure models are species movement between regions, molecular bonds, shortest spanning trees, development of computer algorithms. This paper introduces the edge decomposition of circulant graphs with 2 n vertices by different graph classes. These circulant graphs are denoted as C 2 n , n , where n is the degree of the graph C 2 n , n. We propose two algorithmic approaches for constructing edge decomposition of C 2 n , n. With aid of the proposed algorithmic approaches, we construct paths decompositions, trees decompositions, disjoint unions of cycles and trees decompositions, and complete bipartite graphs decompositions of C 2 n , n. In the end, a recursive construction of an edge decomposition, based on orthogonal edge decompositions, is proposed. This helps in using the mutually orthogonal decompositions of the circulant graphs C 2 n , n in several applications, such as the design of experiments and binary codes generation. [ABSTRACT FROM AUTHOR]

Research in the fields of machine learning and intelligent systems addresses essential problem of developing computer algorithms that can deal with huge amounts of data and then utilize this data in an intellectual way to solve a variety of real-world problems. In many applications, to interpret data with a large number of variables in a meaningful way, it is essential to reduce the number of variables and interpret linear combinations of the data. Principal Component Analysis (PCA) is an unsupervised learning technique that uses sophisticated mathematical principles to reduce the dimensionality of large datasets. The goal of this paper is to provide a complete understanding of the sophisticated PCA in the fields of machine learning and data dimensional reduction. It explains its mathematical aspect and describes its relationship with Singular Value Decomposition (SVD) when PCA is calculated using the covariance matrix. In addition, with the use of MATLAB, the paper shows the usefulness of PCA in representing and visualizing Iris dataset using a smaller number of variables. [ABSTRACT FROM AUTHOR]

Highlights • This paper makes use of a deep CNN for image denoising. • The network is trained using edges given by the canny algorithm. • The proposed method can better recover edges of noisy images. Abstract This paper introduces a novel denoising approach making use of a deep convolutional neural network to preserve image edges. The network is trained by using the edge map obtained from the well-known Canny algorithm and aims at determining if a noisy patch in non-subsampled shearlet domain corresponds to the location of an edge. In the first step of the proposed denoising algorithm, we use the non-subsampled shearlet transform to decompose the noisy image into a low-frequency subband and a series of high-frequency subbands. Subsequently, 3D blocks are formed by stacking 2D blocks of high-frequency subbands along a specific direction. Each 3D patch is then fed to the trained deep convolutional neural network to determine if it belongs to the edge-related class or not. Finally, the NSST (non-subsampled shearlet transform) coefficients belonging to the edge-related class remain unchanged, and those not belonging to the edge-related class are denoised by the shrinkage method using an adaptive threshold. Experimental results on various test images including benchmark grayscale images and medical ultrasound images demonstrate that the proposed method achieves better performance compared to some state-of-the-art denoising approaches. [ABSTRACT FROM AUTHOR]

Highlights • Sampling-based algorithms are commonly used in motion planning problems. • The RRT* algorithm incrementally builds a tree of motion to find a solution. • Taking a shortcut to the ancestry increases the convergence rate to the optimal. • Combination with sampling strategies further improves the performance. Abstract The Rapidly-exploring Random Tree (RRT) algorithm is a popular algorithm in motion planning problems. The optimal RRT (RRT*) is an extended algorithm of RRT, which provides asymptotic optimality. This paper proposes Quick-RRT* (Q-RRT*), a modified RRT* algorithm that generates a better initial solution and converges to the optimal faster than RRT*. Q-RRT* enlarges the set of possible parent vertices by considering not only a set of vertices contained in a hypersphere, as in RRT*, but also their ancestry up to a user-defined parameter, thus, resulting in paths with less cost than those of RRT*. It also applies a similar technique to the rewiring procedure resulting in acceleration of the tendency that near vertices share common parents. Since the algorithm proposed in this paper is a tree extending algorithm, it can be combined with other sampling strategies and graph-pruning algorithms. The effectiveness of Q-RRT* is demonstrated by comparing the algorithm with existing algorithms through numerical simulations. It is also verified that the performance can be further enhanced when combined with other sampling strategies. [ABSTRACT FROM AUTHOR]

Abstract This paper proposes an application of distorted entropy as well-known tools for non-additive expected utility theory in word ranking. Our algorithms for two books "Statistical Inference" by Casella and Berger and "The Origin of Species" by Charles Darwin show that our method on the distorted entropy improves the corresponding ones in the literature. Highlights • An algorithm for word ranking based on distorted entropy is discussed. • This paper proposes an application of distorted probabilities in word ranking. • Our results improve the corresponding ones in the literature. • Our method is new and is applicable to any distorted entropy. [ABSTRACT FROM AUTHOR]

• We design a weighting scheme that considers and integrates citation relevance and author contribution in bibliometric networks. • We propose W-Rank algorithm based on the improved heterogeneous bibliometric networks for scientific article ranking. • We introduce a new perspective to interpret the bibliometric networks based on the practical meaning of the links between the papers, authors and journals. As the volume of scientific articles has grown rapidly over the last decades, evaluating their impact becomes critical for tracing valuable and significant research output. Many studies have proposed various ranking methods to estimate the prestige of academic papers using bibliometric methods. However, the weight of the links in bibliometric networks has been rarely considered for article ranking in existing literature. Such incomplete investigation in bibliometric methods could lead to biased ranking results. Therefore, a novel scientific article ranking algorithm, W-Rank, is introduced in this study proposing a weighting scheme. The scheme assigns weight to the links of citation network and authorship network by measuring citation relevance and author contribution. Combining the weighted bibliometric networks and a propagation algorithm, W-Rank is able to obtain article ranking results that are more reasonable than existing PageRank-based methods. Experiments are conducted on both arXiv hep-th and Microsoft Academic Graph datasets to verify the W-Rank and compare it with three renowned article ranking algorithms. Experimental results prove that the proposed weighting scheme assists the W-Rank in obtaining ranking results of higher accuracy and, in certain perspectives, outperforming the other algorithms. [ABSTRACT FROM AUTHOR]

Highlights • Differentiating between benign and malignant tissues based on image intensities. • Solve the topological problems, the white and the gray areas in patient's image. • Formulate the theoretical data optimization problem by applying curve evolution. • The proposed algorithm saves the operation time in addition to improving accuracy. Abstract Identification of tumor in medical images is an important task which leads to increased survival chances. In many cases, tumor diagnosis in medical images is very complicated since the pixel intensities between benign and malignant tissues may be very close. The identification problem is defined as the intensification of the mutual data between the image pixel intensities and the desired areas (tumors in this paper), depending on a limitation of the overall size of the desired area borders. This paper introduces a new approach for image segmentation in differentiating between benign and malignant tissues through a nonparametric approach. The proposed approach assumes that the probability densities correlated with pixel intensities in the image for each region are not already known. The image intensity is used instead of using the probability. A nonparametric density estimation is proposed and formulates the theoretical data optimization problem by applying curve evolution methods and deriving the correlated gradient flows. It uses level-set techniques to achieve the resulting evolution. The algorithm is applied to 100 sets of different real data in patient images with benign or/and malignant tissues. The experimental results show that the proposed algorithm proved effective in tumor identification with an acceptable accuracy of 93.1%, especially in-patient images diagnosed with carcinoma at an early stage. Graphical abstract Image, graphical abstract In this technique, m level-set functions are used to segment up to 2m areas, and the equation of the resulting evolution curve is proving to be an actual generalization of non-parametric area competition as shown in Fig. 4. [ABSTRACT FROM AUTHOR]

Highlights • We propose the QCdOQR and the l1-QCdOQR algorithms for linear quantile regression problem. • We theoretically study the convergence analyses of the proposed algorithms. • We develop a rule for adaptively adjusting the sparse regularization parameter. Abstract We consider the linear quantile regression problem over networks in this paper. Applying the existing centralized linear quantile regression algorithms to such a problem may encounter some issues, such as the heavy communication burden, the vulnerability to node and/or link failures, and the privacy issues. In a previous work, we proposed a distributed quantile regression algorithm for solving this problem. It is a batch algorithm. However, in practice, each node usually collects data sequentially. To ensure real-time processing, an online manner is preferred. In addition, not only the communication resources of nodes but also the bandwidths of the channels are limited in many real applications over networks. Thus, in these scenarios, only quantized information is allowed for transmission in the channels. In this paper, we propose a quantized communication based distributed online quantile regression (QCdOQR) algorithm. Besides, many natural and artificial systems and signals possess sparsity. We also propose a l 1 -quantized communication based distributed online quantile regression (l 1 -QCdOQR) algorithm to achieve better performance on sparse models. The convergence analyses of the proposed algorithms are studied, and their effectiveness and superiorities are also verified by numerical simulations. [ABSTRACT FROM AUTHOR]

Highlights • An ADMM-based method is devised to solve the general nonsmooth minimization with ℓ 1 /ℓ 0 -norm, without requiring direct computation of subdifferential. • We are the first to combine the LCA and ADMM to solve the smoothed ℓ 1 /ℓ 0 -norm minimization. A challenge is that the LCA is a continuous-time algorithm, and in this paper, we exploit the forward Euler discretization method to approximate the ℓ 1 /ℓ 0 -norm penalty function. • An iterative method has been developed to approximate the matrix inverse for computationally efficient calculation, which is different with the existing ADMM-based algorithms. Abstract This paper considers the problem of sparse recovery whose optimization cost function is a linear combination of a nonsmooth sparsity-inducing term and an ℓ 2 -norm as the metric for the residual error. Since the resultant sparse approximation involves nondifferentiable functions, locally competitive algorithm and forward Euler discretization method are exploited to approximate the nonsmooth objective function, yielding a smooth optimization problem. Alternating direction method of multipliers is then applied as the solver, and Nesterov acceleration trick is integrated for speeding up the computation process. Numerical simulations demonstrate the superiority of the proposed method over several popular sparse recovery schemes in terms of computational complexity and support recovery. [ABSTRACT FROM AUTHOR]

Highlights • QPHTs are applied to color medical image lossless watermarking algorithm for the first time. • Chaotic system is used to enhance the security of the proposed scheme. • The scheme does not make any changes to the original medical image to ensure the integrity of the medical image. • The accurate coefficients selection of QPHTs and the comparison of stability with different choices of μ are discussed in detail. Abstract With the increasingly widespread use of medical images in medical institutions and networks, the copyright protection of medical images has become increasingly urgent. Since traditional embedded watermarking technology degrades the quality of the original images, it is not suitable for medical images. In addition, most medical watermarking algorithms are aimed at grayscale images; therefore, a smaller number of color medical image watermarking algorithms are available. In this paper, we propose a lossless watermarking scheme for color medical image copyright protection based on a chaotic system and quaternion polar harmonic transforms (QPHTs), which is a quaternion orthogonal moment method. In watermark embedding, we compute the QPHTs for the original color medical image and select accurate coefficients to construct a zero-watermark image. Then, the zero-watermark image is stored in the intellectual property right (IPR) database. Experimental results show that the proposed scheme is robust to geometric attacks and common attacks and that it has better performance than similar lossless watermarking schemes. In addition, this paper details the selection of accurate coefficients for QPHTs and compares stability with different choices of unit pure quaternions. [ABSTRACT FROM AUTHOR]

Abstract This paper presents an efficient and accurate Immersed Moving Boundary (IMB) algorithm for solving fluid–particle interactions in the framework of the Lattice Boltzmann Method (LBM). Although the IMB scheme has been widely employed in many fluid–particle coupling problems in a wide range of applications, the algorithm of its implementation, especially in identifying both fluid and solid boundary nodes for particles, is seldom reported. Besides, the computational cost of handling fluid–particle coupling is very expensive. To provide a bridge between theory and application and improve the computing efficiency of IMB, a novel boundary tracing procedure and an efficient method for computing the solid nodal ratio using Gaussian quadrature are proposed in this paper. Both accuracy and efficiency of the proposed algorithm are examined by two benchmark tests. It is also found that the IMB scheme are more efficient and stable compared to another widely used Immersed Boundary Method (IBM) in LBM. Highlights • A robust and efficient boundary tracing procedure is proposed. • The novel tracing procedure is universal and applicable to convex polygons. • Gaussian quadrature for computing solid nodal ratio is accurate and efficient. • The IMB scheme is more stable than the IBM in the framework of LBM. [ABSTRACT FROM AUTHOR]

Abstract This paper first presents an algorithm to compute bounding polytopes of a compact set in arbitrary dimensions. Different from most of the existing work that deals with a finite point set, the compact set handled in this paper can also be an infinite set described by continuous parametric functions. Starting with any bounding polytope of the compact set, the proposed algorithm iteratively finds a sequence of cutting hyperplanes to truncate the polytope and gradually reduce its volume. As a result, a tight bounding polytope of the compact set can be computed and its tightness is controlled by a user-specified tolerance for terminating the iteration. While the algorithm keeps iterating, the polytope can get arbitrarily close to the convex hull of the compact set. Furthermore, the proposed algorithm is extended to computing the maximum distance between compact sets and the diameter of a compact set. Finally, numerical examples show that the proposed algorithms possess linear time complexity with the number of iterations. Highlights • Efficient algorithm is proposed to compute tight bounding polytopes of compact sets. • A sequence of hyperplanes are computed to cut a bounding polytope of a compact set • The algorithm is extended to the maximum distance and the diameter of compact sets • Compact sets can be infinite and described by parametric functions in any dimension • The proposed algorithms have linear time complexity with the number of iterations [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • Rotation Forest (RF) algorithm is based on Decision Tree (DT) classifiers. • RF achieves to a similar performance with hybrid NNs. • In this paper, RF (hybrid NNs) is designed by combining two efficient phenomena. • For this purpose, we examine the use of hybrid NNs as the base classifiers of RF. • Test process is realized on binary-medical pattern classification. • RF (hybrid NNs) is compared with base, hybrid and ensemble classifiers. • As a result, RF (ScPSO-NN) comes to the forefront for classification task. Abstract Neural Network (NN), hybrid NN methods and Rotation Forest (RF) ensemble classifier are preferred in pattern analysis owing to their ability for finding efficient solutions on different problems. NN architecture usually includes backpropagation type algorithms in which error is exposed to fluctuations. Hybrid NN methods are generally designed to improve the classification performance of NN. Scout Particle Swarm Optimization (ScPSO) is one of these optimization algorithms including the effective parts of Particle Swarm Optimization (PSO) and Artificial Bee Colony Optimization (ABC). Moreover, RF algorithm usually indicates the same performance as in hybrid NN methods, although it is comprised of Decision Tree (DT) classifiers. At this point, our paper investigates whether RF using the hybrid NNs can outperform other ensemble classifiers in binary-medical pattern classification, or not. With this intention, PSO, ABC and ScPSO are placed in NN algorithms instead of back propagation, and hybrid methods (PSO-NN, ABC-NN and ScPSO-NN) are realized. As a result, RF (PSO-NN), RF (ABC-NN) and RF (ScPSO-NN) architectures are obtained. Classification Accuracy (CA), Area Under Curve (AUC), Sensitivity, Specificity, F-measure, Gmean and Precision metrics are used for a statistical performance comparison, and a test based on 2-fold cross validation method was realized on five medical datasets. [ABSTRACT FROM AUTHOR]

Abstract This paper presents seven concurrent hash table implementations in Haskell, ranging from low-level synchronization mechanisms to high-level ones such as transactional memories. The hash tables were compared using different initial sizes, load factors, data types and hash functions. We also present a case study on implementing a color palette algorithm using the hash tables. The result of the comparison between the algorithms shows that the implementation using the STM Haskell transactional memory library and fine-grain synchronization provides the best performance and good scalability, followed by the implementation using lock striping and MVars. Highlights • The paper describes seven concurrent hash table implementations in Haskell. • Different abstractions were used: MVars, compare and swap, and transactional memory. • Detailed performance comparison of the hash tables is presented. • STM Haskell with fine-grain synchronization shows the best performance in overall. [ABSTRACT FROM AUTHOR]

Highlights • TLBO-DE-based Elman NN modeling is proposed. • A novel hybrid method based on TLBO and DE is adopted for modeling. • Numerical results indicate its advantage over the referenced methods. Abstract In the present work, an Elman neural network (ENN) is suggested for parameter identification of proton exchange membrane fuel cell (PEMFC), which is optimized by a novel optimization method. Proposed optimization algorithm of this paper is a hybrid algorithm that combined the teaching–learning based optimization (TLBO) and differential evolution (DE) algorithm namely the TLBO-DE method. This paper combined these two effective methods to efficiently estimate the PEM fuel cell model parameters, and it's validated by various validation functions. Performance of this proposed optimization method is confirmed by the obtained results from some well-known benchmarks. Moreover, a TLBO-DE based Elman neural network is implemented for solving the nonlinear parameter identification issue for the PEM fuel cell. According to the obtained results, this proposed network can forecast the stack voltage in various operational situations with high authenticity. [ABSTRACT FROM AUTHOR]

Abstract Following recent paper of the author about polynomial expressions with respect to binomial ideals, the current paper is devoted to the non-binomial case. Beside the established facts in the underlying theory, the correctness and termination of the algorithms are addressed. From the collection of examples, the main large-scale non-binomial one is of particular importance. Application of the new algorithms for the cases of moderately large binomial like cyclic 16-roots and cyclic 18-roots is discussed. A combinatorial analysis for complexity of the proposed algorithms is shown to be at least O (log ⁡ (log ⁡ n) n 2 (log ⁡ n) 2). [ABSTRACT FROM AUTHOR]

Highlights • We train a Fully Convolutional Network (FCN) for text prediction in scene images and fuse it with a text proposal method. • Significantly higher recall rates than SoA text localization pipelines and better quality regions are obtained. • The resulting pipeline reduces the number of proposals resulting to a 4 × speed up compared with the baseline. • Our proposed method yields top performance when integrated in an end-to-end pipeline. • Analysis and results on standard datasets COCO-Text and ICDAR-Challenge 4 are reported. Graphical abstract This paper proposes a fusion of a text proposal technique with Fully Convolutional Networks to efficiently reduce the number of proposals while maintaining the same text recall level and thus gaining a significant speed up.Different fusion strategies are explored, as shown in the figure, that demonstrate that such an approach can yield significantly higher recall rates than state-of-the-art text localization techniques, while also producing better-quality localizations. End-to-end performance shows that this recall margin leads to state-of-the-art results in scene text reading systems. Abstract Class-specific text proposal algorithms can efficiently reduce the search space for possible text object locations in an image. In this paper we combine the Text Proposals algorithm with Fully Convolutional Networks to efficiently reduce the number of proposals while maintaining the same recall level and thus gaining a significant speed up. Our experiments demonstrate that such text proposal approaches yield significantly higher recall rates than state-of-the-art text localization techniques, while also producing better-quality localizations. Our results on the ICDAR 2015 Robust Reading Competition (Challenge 4) and the COCO-text datasets show that, when combined with strong word classifiers, this recall margin leads to state-of-the-art results in end-to-end scene text recognition. [ABSTRACT FROM AUTHOR]