Catálogo de publicaciones - revistas

<jats:p>Visual question generation (VQG) is an interesting problem that has recently received attention. The task of VQG involves generating meaningful questions based on the input image. It is a multi-modal problem involving image understanding and natural language generation, especially using deep learning methods. VQG can be considered as complementary task of visual question answering. In this article, we review the current state of VQG in terms of methods to understand the problem, existing datasets to train the VQG model, evaluation metrics, and algorithms to handle the problem. Finally, we discuss the challenges that need to be conquered and the possible future directions for an effective VQG.</jats:p>

<jats:p>Deep neural networks are a class of powerful machine learning model that uses successive layers of non-linear processing units to extract features from data. However, the training process of such networks is quite computationally intensive and uses commonly used optimization methods that do not guarantee optimum performance. Furthermore, deep learning methods are often sensitive to noise in data and do not operate well in areas where data are incomplete. An alternative, yet little explored, method in enhancing deep learning performance is the use of fuzzy systems. Fuzzy systems have been previously used in conjunction with neural networks. This survey explores the different ways in which deep learning is improved with fuzzy logic systems. The techniques are classified based on how the two paradigms are combined. Finally, the real-life applications of the models are also explored.</jats:p>

<jats:p>Driving can occupy a large portion of daily life and often can elicit negative emotional states like anger or stress, which can significantly impact road safety and long-term human health. In recent decades, the arrival of new tools to help recognize human affect has inspired increasing interest in how to develop emotion-aware systems for cars. To help researchers make needed advances in this area, this article provides a comprehensive literature survey of work addressing the problem of human emotion recognition in an automotive context. We systematically review the literature back to 2002 and identify 63 peer-review published articles on this topic. We overview each study’s methodology to measure and recognize emotions in the context of driving. Across the literature, we find a strong preference toward studying emotional states associated with high arousal and negative valence, monitoring the different states with cardiac, electrodermal activity, and speech signals, and using supervised machine learning to automatically infer the underlying human affective states. This article summarizes the existing work together with publicly available resources (e.g., datasets and tools) to help new researchers get started in this field. We also identify new research opportunities to help advance progress for improving driver emotion recognition.</jats:p>

<jats:p>A realistically inserted virtual object in the real-time physical environment is a desirable feature in augmented reality (AR) applications and mixed reality (MR) in general. This problem is considered a vital research area in computer graphics, a field that is experiencing ongoing discovery. The algorithms and methods used to obtain dynamic and real-time illumination measurement, estimating, and rendering of augmented reality scenes are utilized in many applications to achieve a realistic perception by humans. We cannot deny the powerful impact of the continuous development of computer vision and machine learning techniques accompanied by the original computer graphics and image processing methods to provide a significant range of novel AR/MR techniques. These techniques include methods for light source acquisition through image-based lighting or sampling, registering and estimating the lighting conditions, and composition of global illumination. In this review, we discussed the pipeline stages with the details elaborated about the methods and techniques that contributed to the development of providing a photo-realistic rendering, visual coherence, and interactive real-time illumination results in AR/MR.</jats:p>

<jats:p>Data centers are large-scale, energy-hungry infrastructure serving the increasing computational demands as the world is becoming more connected in smart cities. The emergence of advanced technologies such as cloud-based services, internet of things (IoT), and big data analytics has augmented the growth of global data centers, leading to high energy consumption. This upsurge in energy consumption of the data centers not only incurs the issue of surging high cost (operational and maintenance) but also has an adverse effect on the environment. Dynamic power management in a data center environment requires the cognizance of the correlation between the system and hardware-level performance counters and the power consumption. Power consumption modeling exhibits this correlation and is crucial in designing energy-efficient optimization strategies based on resource utilization. Several works in power modeling are proposed and used in the literature. However, these power models have been evaluated using different benchmarking applications, power-measurement techniques, and error-calculation formulas on different machines. In this work, we present a taxonomy and evaluation of 24 software-based power models using a unified environment, benchmarking applications, power-measurement techniques, and error formulas, with the aim of achieving an objective comparison. We use different server architectures to assess the impact of heterogeneity on the models’ comparison. The performance analysis of these models is elaborated in the article.</jats:p>

<jats:p>The recent diffusion of online education (both MOOCs and e-courses) has led to an increased economic and scientific interest in e-learning environments. As widely documented, online students have a much higher chance of dropping out than those attending conventional classrooms. It is of paramount interest for institutions, students, and faculty members to find more efficient methodologies to mitigate withdrawals. Following the rise of attention on the Student Dropout Prediction (SDP) problem, the literature has witnessed a significant increase in contributions to this subject. In this survey, we present an in-depth analysis of the state-of-the-art literature in the field of SDP, under the central perspective, but not exclusive, of machine learning predictive algorithms. Our main contributions are the following: (i) we propose a comprehensive hierarchical classification of existing literature that follows the workflow of design choices in the SDP; (ii) to facilitate the comparative analysis, we introduce a formal notation to describe in a uniform way the alternative dropout models investigated by the researchers in the field; (iii) we analyse some other relevant aspects to which the literature has given less attention, such as evaluation metrics, gathered data, and privacy concerns; (iv) we pay specific attention to deep sequential machine learning methods—recently proposed by some contributors—which represent one of the most effective solutions in this area. Overall, our survey provides novice readers who address these topics with practical guidance on design choices, as well as directs researchers to the most promising approaches, highlighting current limitations and open challenges in the field.</jats:p>

<jats:p> Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small. Recently, Few-shot Learning (FSL) is proposed to tackle this problem. Using prior knowledge, FSL can rapidly generalize to new tasks containing only a few samples with supervised information. In this article, we conduct a thorough survey to fully understand FSL. Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems. We then point out that the core issue in FSL is that the empirical risk minimizer is unreliable. Based on how prior knowledge can be used to handle this core issue, we categorize FSL methods from three perspectives: (i) data, which uses prior knowledge to augment the supervised experience; (ii) model, which uses prior knowledge to reduce the size of the hypothesis space; and (iii) algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space. With this taxonomy, we review and discuss the pros and cons of each category. Promising directions, in the aspects of the FSL problem setups, techniques, applications, and theories, are also proposed to provide insights for future research. <jats:sup>1</jats:sup> </jats:p>

<jats:p>Deep convolutional networks–based super-resolution is a fast-growing field with numerous practical applications. In this exposition, we extensively compare more than 30 state-of-the-art super-resolution Convolutional Neural Networks (CNNs) over three classical and three recently introduced challenging datasets to benchmark single image super-resolution. We introduce a taxonomy for deep learning–based super-resolution networks that groups existing methods into nine categories including linear, residual, multi-branch, recursive, progressive, attention-based, and adversarial designs. We also provide comparisons between the models in terms of network complexity, memory footprint, model input and output, learning details, the type of network losses, and important architectural differences (e.g., depth, skip-connections, filters). The extensive evaluation performed shows the consistent and rapid growth in the accuracy in the past few years along with a corresponding boost in model complexity and the availability of large-scale datasets. It is also observed that the pioneering methods identified as the benchmarks have been significantly outperformed by the current contenders. Despite the progress in recent years, we identify several shortcomings of existing techniques and provide future research directions towards the solution of these open problems. Datasets and codes for evaluation are publicly available at https://github.com/saeed-anwar/SRsurvey.</jats:p>

<jats:p>To support the large and various applications generated by the Internet of Things (IoT), Fog Computing was introduced to complement the Cloud Computing and offer Cloud-like services at the edge of the network with low latency and real-time responses. Large-scale, geographical distribution, and heterogeneity of edge computational nodes make service placement in such infrastructure a challenging issue. Diversity of user expectations and IoT devices characteristics also complicate the deployment problem. This article presents a survey of current research conducted on Service Placement Problem (SPP) in the Fog/Edge Computing. Based on a new classification scheme, a categorization of current proposals is given and identified issues and challenges are discussed.</jats:p>

<jats:p>The evolution in the design of modern parallel platforms leads to revisit the scheduling jobs on distributed heterogeneous resources. The goal of this survey is to present the main existing algorithms, to classify them based on their underlying principles, and to propose unified implementations to enable their fair comparison, in terms of running time and quality of schedules, on a large set of common benchmarks that we made available for the community. Beyond this comparison, our goal is also to understand the main difficulties that heterogeneity conveys and the shared principles that guide the design of efficient algorithms.</jats:p>