Search

Large-scale benchmark datasets are crucial in advancing research within the computer science communities. They enable the development of more sophisticated AI models and serve as "golden" benchmarks for evaluating their performance. Thus, ensuring the quality of these datasets is of utmost importance for academic research and the progress of AI systems. For the emerging vision-language tasks, some datasets have been created and frequently used, such as Flickr30k, COCO, and NoCaps, which typically contain a large number of images paired with their ground-truth textual descriptions. In this paper, an automatic method is proposed to assess the quality of large-scale benchmark datasets designed for vision-language tasks. In particular, a new cross-modal matching model is developed, which is capable of automatically scoring the textual descriptions of visual images. Subsequently, this model is employed to evaluate the quality of vision-language datasets by automatically assigning a score to each 'ground-truth' description for every image picture. With a good agreement between manual and automated scoring results on the datasets, our findings reveal significant disparities in the quality of the ground-truth descriptions included in the benchmark datasets. Even more surprising, it is evident that a small portion of the descriptions are unsuitable for serving as reliable ground-truth references. These discoveries emphasize the need for careful utilization of these publicly accessible benchmark databases. [ABSTRACT FROM AUTHOR]

Automated generation of image captions is a demanding AI crisis as it necessitates the exploitation of numerous methods from diverse computer science fields. Deep learning (DL) approaches have revealed marvelous results in a lot of diverse appliances. On the other hand, data augmentation in DL that imitates the quantity and the variety of training data without the need of gathering additional data is a hopeful area in machine learning (ML). Producing textual descriptions for a specified image is a demanding task using the computer. This survey makes a critical analysis of about 65 papers regarding image captioning. More particularly, varied performance measures that are contributed in diverse articles are analyzed. In addition, a comprehensive study is made regarding the maximal performances and varied features deployed in each work. Moreover, chronological analysis and dataset analysis are done and finally, the survey extends with the determination of varied research challenges, which might be productive for the analysts to endorse enhanced upcoming works on image captioning. [ABSTRACT FROM AUTHOR]

Deoxyribonucleic Acid (DNA) coding technology is a new research field developed by the combination of computer science and molecular biology, that has been gradually applied in the field of image encryption in recent years. Furthermore, sensitivity to initial conditions, pseudo-random properties, and state ergodicity of coupled chaotic maps can help produce good pseudo-random number generators and meet the requirements of an image encryption system well. In this paper, an image encryption algorithm based on high-dimensional coupled chaotic maps and DNA coding is proposed. A pseudo-random sequence is generated by a long short-term memory (LSTM) architecture using the proposed maps and evaluated through a set of statistical tests to show the high performance of the proposed generator. All intensity values of an input image are converted to a binary sequence, which is scrambled globally by the high-dimensional coupled chaotic maps. The DNA operations are performed on the scrambled binary sequences instead of binary operations to increase the algorithm efficiency. Simulation results and performance analyses demonstrate that the proposed encryption scheme is extremely sensitive to small changes in secret keys, provides high security and can resist differential attack. [ABSTRACT FROM AUTHOR]

Low-rank matrix completion, which aims to recover a matrix with many missing values, has attracted much attention in many fields of computer science. A low-rank matrix fitting (LMaFit) method has been proposed for fast matrix completion recently. However, this method cannot converge accurately on matrices of real-world images. For improving the accuracy of LMaFit method, an improved low-rank matrix fitting (ILMF) method based on the weighted L 1 , p norm minimization is proposed in this paper, where the L 1 , p norm is the summation of the p -power (0 < p < 2) of L 1 norms of rows in a matrix. In the proposed method, i.e. the ILMF method, the incomplete matrix that may be corrupted by noises is decomposed into the summation of a low-rank matrix and a noise matrix at first. Then, a weighted L 1 , p norm minimization problem is solved by using an alternating direction method for improving the accuracy of matrix completion. Experimental results on real-world images show that the ILMF method has much better performances in terms of both the convergence accuracy and convergence speed than the compared methods. [ABSTRACT FROM AUTHOR]

How can non-classical logic contribute to the analysis of complexity in computer science? In this paper, we give a step towards this question, taking a logical model-theoretic approach to the analysis of complexity in fuzzy constraint satisfaction. We study fuzzy positive-primitive sentences, and we present an algebraic characterization of classes axiomatized by this kind of sentences in terms of homomorphisms and direct products. The ultimate goal is to study the expressiveness and reasoning mechanisms of non-classical languages, with respect to constraint satisfaction problems and, in general, in modelling decision scenarios. [ABSTRACT FROM AUTHOR]

In this paper, an efficient image encryption technique using beta chaotic map, nonsubsampled contourlet transform, and genetic algorithm is proposed. Initially, the nonsubsampled contourlet transform is utilized to decompose the input image into subbands. The beta chaotic map is used to develop pseudo-random key that encrypts the coefficients of subbands. However, it requires certain parameters to encrypt these coefficients. A multiobjective fitness function for genetic algorithm is designed to find the optimal parameter of beta chaotic map. The inverse of nonsubsampled contourlet transform is performed to obtain a ciphered image. The performance of the proposed technique is compared with recently developed well-known meta-heuristic based image encryption techniques. Experimental results reveal that the proposed technique provides better computational speed and high encryption intensity. The comparative analyses show effectiveness of the proposed image encryption technique. [ABSTRACT FROM AUTHOR]

Data stream learning in non-stationary environments and skewed class distributions has been receiving more attention in machine learning communities. This paper proposes a novel ensemble classification method (ECSDS) for classifying data streams with skewed class distributions. In the proposed ensemble method, back-propagation neural network is selected as the base classifier. In order to demonstrate the effectiveness of our proposed method, we choose three baseline methods based on ECSDS and evaluate their overall performance on ten datasets from UCI machine learning repository. Moreover, the performance of incremental learning is also evaluated by these datasets. The experimental results show our proposed method can effectively deal with classification problems on non-stationary data streams with class imbalance. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA... [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA... [ABSTRACT FROM AUTHOR]

Verifying and specifying multi-agent systems in an appropriate inconsistency-tolerant logic are of growing importance in Computer Science since computer systems are generally used by or composed of inconsistency-tolerant multi-agents. In this paper, an inconsistency-tolerant logic for representing multi-agents is introduced as a Gentzen-type sequent calculus. This logic (or calculus) has multiple negation connectives that correspond to each agent, and these negation connectives have the property of paraconsistency that guarantees inconsistency-tolerance. The logic proposed is regarded as a modified generalization of trilattice logics, which are known to be useful for expressing fine-grained truth-values in computer networks. The completeness, cut-elimination and decidability theorems for the proposed logic (or sequent calculus) are proved as the main results of this paper. [ABSTRACT FROM AUTHOR]

Since the International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems published its first issue in 1993, it has made important contributions to the research field of computer science. In this study, based on the dataset of the publications published in this journal between 1993 and 2016 retrieved from Web of Science, a general overview of this journal is performed using bibliometric methods and visualized networks. First, the productive and influential publications, authors, institutions, countries/territories, and supraregions are analysed based on the total number of citations, publications, and different citation thresholds. Second, network visualization analysis is applied to illustrate the links and connections between terms by using the VOSviewer software. Moreover, the most cited journals and common author keywords of three continents, including North America, Europe, and Asia, are also presented. This paper will hopefully help researchers understand the research patterns of this journal. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA... [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA... [ABSTRACT FROM AUTHOR]

In this paper a platform is presented, that given a stochastic context-free grammar (SCFG), automatically outputs the description of the parser in synthesizable hardware description language (HDL) which can be downloaded in an Field Programmable Gate Arrays (FPGA) board. Initially, according to our methodology the SCFG is augmented with attributes which store the probability values and can be evaluated through corresponding stack actions. The architecture of the produced system is based on a proposed extension of Earley's parallel algorithm, which given an input string, generates the parse trees in the form of an AND-Or parse tree. This AND-or parse tree is then traversed using a proposed tree traversal technique in order to execute the corresponding actions in the correct order, so as to compute the necessary probabilities. The platform is suitable for embedded systems applications where a natural language interface is required or in pattern recognition tasks. The parser generated by the presented platform has been tested for various SCFGs and compared to software approaches. The performance comparison is one to two orders of magnitude in favor of the presented hardware, compared to previous software approaches, depending on the application, the input string length and the number of produced trees. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA... [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA... [ABSTRACT FROM AUTHOR]

In this paper, we first give the formula of possibility degree to rank the Atanassov's intuitionistic fuzzy numbers. Two methods called Atanassov's intuitionistic fuzzy weighted average (IFWA) and Atanassov's intuitionistic fuzzy weighted geometric mean (IFWGM) are developed to solve the multiple attribute decision making problems under Atanassov's intuitionistic fuzzy environment, in which the performance ratings of alternatives and relative importance of attributes are expressed with Atanassov's intuitionistic fuzzy sets. The IFWA and IFWGM methods, respectively, are treated as an auxiliary pair of fractional programming models and two linear programming (LP) solution procedures are proposed simultaneously by using Charnes and Cooper transformation. Furthermore, two algorithms which are based on the IFWA and IFWGM models, respectively, are developed to solve Atanassov's intuitionistic fuzzy decision making problems where attribute values and weights of attributes are all in Atanassov's intuitionistic fuzzy numbers. The order relationship between IFWA and IFWGM are investigated. Finally, a numerical example is illustrated to show the feasibility and effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA... [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA... [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]