Search

Recent advances in technology and devices have caused a data explosion on the Internet and on our home PCs. This data is predominantly obtained in various modalities (text, image, video, etc.) and is essential for e-commerce websites. The products on these websites have both images and descriptions in text form, making them multimodal in nature. Earlier categorization and information retrieval methods focused mostly on a single modality. This study employs multimodal data for classification using neutrosophic fuzzy sets for uncertainty management for information retrieval tasks. This effort utilizes image and text data and, inspired by past techniques of embedding text over an image, attempts to classify the images using neutrosophic classification algorithms. For classification tasks, Neutrosophic Convolutional Neural Networks (NCNNs) are used to learn feature representations of the produced images. We demonstrate how a pipeline based on NCNN can be utilized to learn representations of the innovative fusion method. Traditional convolutional neural networks are vulnerable to unknown noisy conditions in the test phase, and as a result, their performance for the classification of noisy data declines. Comparing our method against individual sources on two large-scale multi-modal categorization datasets yielded good results. In addition, we have compared our method to two well-known multi-modal fusion methodologies, namely early fusion and late fusion. [ABSTRACT FROM AUTHOR]

In the algorithm selection problem, where the task is to identify the most suitable solving technique for a particular situation, most methods used as performance mapping mechanisms have been relatively simple models such as logistic regression or neural networks. In the latter case, most implementations tend to have a shallow and straightforward architecture and, thus, exhibit a limited ability to extract relevant patterns. This research explores the use of attention-based neural networks as meta-learners to improve the performance mapping mechanism in the algorithm selection problem and fully take advantage of the model's capabilities for pattern extraction. We compare the proposed use of an attention-based meta-learner method as a performance mapping mechanism against five models from the literature: multi-layer perceptron, k-nearest neighbors, softmax regression, support vector machines, and decision trees. We used a meta-data dataset obtained by solving the vehicle routing problem with time window (VRPTW) instances contained in the Solomon benchmark with three different configurations of the simulated annealing meta-heuristic for testing purposes. Overall, the attention-based meta-learner model yields better results when compared to the other benchmark methods in consistently selecting the algorithm that best solves a given VRPTW instance. Moreover, by significantly outperforming the multi-layer perceptron, our findings suggest promising potential in exploring more recent and novel advancements in neural network architectures. [ABSTRACT FROM AUTHOR]

Hyper-heuristics have arisen as methods that increase the generality of existing solvers. They have proven helpful for dealing with complex problems, particularly those related to combinatorial optimization. Their recent growth in popularity has increased the daily amount of text in the related literature. This information is primarily unstructured, mainly text that traditional computer data systems cannot process. Traditional systematic literature review studies exhibit multiple limitations, including high time consumption, lack of replicability, and subjectivity of the results. For this reason, text mining has become essential for researchers in recent years. Therefore, efficient text mining techniques are needed to extract meaningful information, patterns, and relationships. This study adopts a literature review of 963 journal and conference papers on hyper-heuristic-related works. We first describe the essential text mining techniques, including text preprocessing, word clouds, clustering, and frequent association rule learning in hyper-heuristic publications. With that information, we implement visualization tools to understand the most frequent relations and topics in the hyper-heuristic domain. The main findings highlight the most dominant topics in the literature. We use text mining analysis to find widespread manifestations, representing the significance of the different areas of hyper-heuristics. Furthermore, we apply clustering to provide seven categories showing the associations between the topics related to hyper-heuristic literature. The vast amount of data available that we find opens up a new opportunity for researchers to analyze the status of hyper-heuristics and help create strategic plans regarding the scope of hyper-heuristics. Lastly, we remark that future work will address the limitations of collecting information from multiple data sources and analyze book chapters related to hyper-heuristics. [ABSTRACT FROM AUTHOR]

Recent years have witnessed significant achievements and technological advances in citizen science (CS) projects; nevertheless, significant global challenges are present. Proof of this is in the joint efforts of international organizations to achieve the 2030 SDG agenda in a complex environment. Thus, UNESCO has recognized CS as being among the initiatives that could bridge the Science, Technology, and Innovation gap as a substantial resource, given its power to bring the general public closer together. Although tech-based CS projects keep rising, there is limited knowledge about which type of projects might allow participants to develop higher-order complex thinking skills. To that end, this study describes a systematic literature review (SLR) and analysis of 49 CS projects over the last 5 years concerning the technology utilized, the level of citizen involvement, and the intended social impact. The results of the analysis evidenced: (a) broad implementation in Europe on issues of the built environment, disaster risk, and environmental and animal monitoring; (b) prevalence of helix configurations other than the triple, quadruple, and quintuple helix innovation models; (c) a focus on technological developments to improve living conditions in cities; (d) an opportunity to develop applied native technologies; (e) limited development of participants' complex thinking, when constrained to low levels of involvement; and (f) an opportunity to develop native technologies and promote a higher level of citizen participation, leading to more significant impact whilst developing complex thinking. [ABSTRACT FROM AUTHOR]

Security has become a critical issue for complex and expensive systems and day-to-day situations. In this regard, the analysis of surveillance cameras is a critical issue usually restricted to the number of people devoted to such a task, their knowledge and judgment. Nonetheless, different approaches have arisen to automate this task in recent years. These approaches are mainly based on machine learning and benefit from developing neural networks capable of extracting underlying information from input videos. Despite how competent those networks have proved to be, developers must face the challenging task of defining both the architecture and hyperparameters that allow such networks to work adequately and optimize the use of computational resources. In short, this work proposes a model that generates, through a genetic algorithm, neural networks for behavior classification within videos. Two types of neural networks evolved as part of this work, shallow and deep, which are structured on dense and 3D convolutional layers. Each network requires a particular type of input data: the evolution of the pose of people in the video and video sequences, respectively. Shallow neural networks use a direct encoding approach to map each part of the chromosome into a phenotype. In contrast, deep neural networks use indirect encoding, blueprints representing entire networks, and modules to depict layers and their connections. Our approach obtained relevant results when tested on the Kranok-NV dataset and evaluated with standard metrics used for similar classification tasks. [ABSTRACT FROM AUTHOR]

Recent years have witnessed a growing interest in automatic learning mechanisms and applications. The concept of hyper-heuristics, algorithms that either select among existing algorithms or generate new ones, holds high relevance in this matter. Current research suggests that, under certain circumstances, hyper-heuristics outperform single heuristics when evaluated in isolation. When hyper-heuristics are selected among existing algorithms, they map problem states into suitable solvers. Unfortunately, identifying the features that accurately describe the problem state—and thus allow for a proper mapping—requires plenty of domain-specific knowledge, which is not always available. This work proposes a simple yet effective hyper-heuristic model that does not rely on problem features to produce such a mapping. The model defines a fixed sequence of heuristics that improves the solving process of knapsack problems. This research comprises an analysis of feature-independent hyper-heuristic performance under different learning conditions and different problem sets. [ABSTRACT FROM AUTHOR]

Artificial neural networks are efficient learning algorithms that are considered to be universal approximators for solving numerous real-world problems in areas such as computer vision, language processing, or reinforcement learning. To approximate any given function, neural networks train a large number of parameters—up to millions, or even billions in some cases. The large number of parameters and hidden layers in neural networks make them hard to interpret, which is why they are often referred to as black boxes. In the quest to make artificial neural networks interpretable in the field of computer vision, feature visualization stands out as one of the most developed and promising research directions. While feature visualizations are a valuable tool to gain insights about the underlying function learned by the network, they are still considered to be simple visual aids requiring human interpretation. In this paper, we propose that feature visualizations—class visualizations in particular—are analogous to mental imagery in humans, resembling the experience of seeing or perceiving the actual training data. Therefore, we propose that class visualizations contain embedded knowledge that can be exploited in a more automated manner. We present a series of experiments that shed light on the nature of class visualizations and demonstrate that class visualizations can be considered a conceptual compression of the data used to train the underlying model. Finally, we show that class visualizations can be regarded as convolutional filters and experimentally show their potential for extreme model compression purposes. [ABSTRACT FROM AUTHOR]

Many of the works conducted on algorithm selection strategies—methods that choose a suitable solving method for a particular problem—start from scratch since only a few investigations on reusable components of such methods are found in the literature. Additionally, researchers might unintentionally omit some implementation details when documenting the algorithm selection strategy. This makes it difficult for others to reproduce the behavior obtained by such an approach. To address these problems, we propose to rely on existing techniques from the Machine Learning realm to speed-up the generation of algorithm selection strategies while improving the modularity and reproducibility of the research. The proposed solution model is implemented on a domain-independent Machine Learning module that executes the core mechanism of the algorithm selection task. The algorithm selection strategies produced in this work are implemented and tested rapidly compared against the time it would take to build a similar approach from scratch. We produce four novel algorithm selectors based on Machine Learning for constraint satisfaction problems to verify our approach. Our data suggest that these algorithms outperform the best performing algorithm on a set of test instances. For example, the algorithm selectors Multiclass Neural Network (MNN) and Multiclass Logistic Regression (MLR), powered by a neural network and linear regression, respectively, reduced the search cost (in terms of consistency checks) of the best performing heuristic (KAPPA), on average, by 49% for the instances considered for this work. [ABSTRACT FROM AUTHOR]

Hyperheuristics rise as powerful techniques that get good results in less computational time than exact methods like dynamic programming or branch and bound. These exact methods promise the global best solution, but with a high computational time. In this matter, hyperheuristics do not promise the global best solution, but they promise a good solution in a lot less computational time. On the contrary, fuzzy logic provides the tools to model complex problems in a more natural way. With this in mind, this paper proposes a fuzzy hyperheuristic approach, which is a combination of a fuzzy inference system with a selection hyperheuristic. The fuzzy system needs the optimization of its fuzzy rules due to the lack of expert knowledge; indeed, traditional hyperheuristics also need an optimization of their rules. The fuzzy rules are optimized by genetic algorithms, and for the rules of the traditional methods, we use particle swarm optimization. The genetic algorithm will also reduce the number of fuzzy rules, in order to find the best minimal fuzzy rules, whereas traditional methods already use very few rules. Experimental results show the advantage of using our approach instead of a traditional selection hyperheuristic in 3200 instances of the 0/1 knapsack problem. [ABSTRACT FROM AUTHOR]

When solving constraint satisfaction problems (CSPs), it is a common practice to rely on heuristics to decide which variable should be instantiated at each stage of the search. But, this ordering influences the search cost. Even so, and to the best of our knowledge, no earlier work has dealt with how first variable orderings affect the overall cost. In this paper, we explore the cost of finding high-quality orderings of variables within constraint satisfaction problems. We also study differences among the orderings produced by some commonly used heuristics and the way bad first decisions affect the search cost. One of the most important findings of this work confirms the paramount importance of first decisions. Another one is the evidence that many of the existing variable ordering heuristics fail to appropriately select the first variable to instantiate. Another one is the evidence that many of the existing variable ordering heuristics fail to appropriately select the first variable to instantiate. We propose a simple method to improve early decisions of heuristics. By using it, performance of heuristics increases. [ABSTRACT FROM AUTHOR]

Constraint satisfaction problems are of special interest for the artificial intelligence and operations research community due to their many applications. Although heuristics involved in solving these problems have largely been studied in the past, little is known about the relation between instances and the respective performance of the heuristics used to solve them. This paper focuses on both the exploration of the instance space to identify relations between instances and good performing heuristics and how to use such relations to improve the search. Firstly, the document describes a methodology to explore the instance space of constraint satisfaction problems and evaluate the corresponding performance of six variable ordering heuristics for such instances in order to find regions on the instance space where some heuristics outperform the others. Analyzing such regions favors the understanding of how these heuristics work and contribute to their improvement. Secondly, we use the information gathered from the first stage to predict the most suitable heuristic to use according to the features of the instance currently being solved. This approach proved to be competitive when compared against the heuristics applied in isolation on both randomly generated and structured instances of constraint satisfaction problems. [ABSTRACT FROM AUTHOR]