Publications

A Service Level Agreement (SLA) is a formal contract between a service provider and a consumer, representing a crucial instrument to define, manage, and maintain relationships between these two parties. The SLA's ability to define the Quality of Service (QoS) expectations, standards, and accountability helps to deliver high-quality services and increase client confidence in disparate application domains, such as Cloud computing and the Internet of Things. An open research direction in this context is related to the possible integration of new metrics to address the security and privacy aspects of services, thus providing protection of sensitive information, mitigating risks, and building trust. This survey paper identifies state of the art covering concepts, approaches, and open problems of SLA management with a distinctive and original focus on the recent development of Security SLA (SecSLA). It contributes by carrying out a comprehensive review and covering the gap between the analyses proposed in existing surveys and the most recent literature on this topic, spanning from 2017 to 2023. Moreover, it proposes a novel classification criterium to organize the analysis based on SLA life cycle phases. This original point of view can help both academics and industrial practitioners to understand and properly locate existing contributions in the advancement of the different aspects of SLA technology. The present work highlights the importance of the covered topics and the need for new research improvements to tackle present and demanding challenges.

Data representation is of significant importance in minimizing multi-label ambiguity. While most researchers intensively investigate label correlation, the research on enhancing model robustness is preliminary. Low-quality data is one of the main reasons that model robustness degrades. Aiming at the cases with noisy features and missing labels, we develop a novel method called robust global and local label correlation (RGLC). In this model, subspace learning reconstructs intrinsic latent features immune from feature noise. The manifold learning ensures that outputs obtained by matrix factorization are similar in the low-rank latent label if the latent features are similar. We examine the co-occurrence of global and local label correlation with the constructed latent features and the latent labels. Extensive experiments demonstrate that the classification performance with integrated information is statistically superior over a collection of state-of-the-art approaches across numerous domains. Additionally, the proposed model shows promising performance on multi-label when noisy features and missing labels occur, demonstrating the robustness of multi-label classification.

The two issues on dynamically generated hierarchical neural networks such as the sort of basic neurons and how to compose a layer are considered in this article. On the first issue, a variant version of the least-square support vector regression (SVR) is chosen as a basic neuron. Support vector machine (SVM) is a representative classifier which usually shows good classification performance. Along with the SVMs, SVR was introduced to deal with the regression problem. Especially, least-square SVR has the advantages of high learning speed due to the substitution of the inequality constraints by the equality constraint in the formulation of the optimization problem. Based on the least-square SVR, the multiple least-square (MLS) SVR, which is a type of a linear combination of least-square SVRs with fuzzy clustering, is proposed to improve the modeling performance. In addition, a hierarchical neural network, where the MLS SVR is utilized as the generic node instead of the conventional polynomial, is developed. The key issues of hierarchical neural networks, which are generated dynamically layer by layer, are discussed on how to retain the diversity of the nodes located at the same layer according to the increase of the layer. In order to maintain the diversity of the nodes, various selection methods such as truncation selection and roulette wheel selection (RWS) to choose the nodes among candidate nodes are proposed. In addition, in order to reduce the computational overhead to determine all candidates which exhibit all compositions of the input variables, a new implementation method is proposed. From the viewpoint of the diversity of the selected nodes and the computational aspects, it is shown that the proposed method is preferred over the conventional design methodology.

Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of patches consisting of split images. However, for complex tasks, Transformer in computer vision not only requires inheriting a bit of dynamic attention and global context, but also needs to introduce features concerning noise reduction, shifting, and scaling invariance of objects. Therefore, here we take a step forward to study the structural characteristics of Transformer and convolution and propose an architecture search method-Vision Transformer with Convolutions Architecture Search (VTCAS). The high-performance backbone network searched by VTCAS introduces the desirable features of convolutional neural networks into the Transformer architecture while maintaining the benefits of the multi-head attention mechanism. The searched block-based backbone network can extract feature maps at different scales. These features are compatible with a wider range of visual tasks, such as image classification (32 M parameters, 82.0% Top-1 accuracy on ImageNet-1K) and object detection (50.4% mAP on COCO2017). The proposed topology based on the multi-head attention mechanism and CNN adaptively associates relational features of pixels with multi-scale features of objects. It enhances the robustness of the neural network for object recognition, especially in the low illumination indoor scene.

Cognitive Computing (CC) is an emerging paradigm of intelligent computing theories and technologies based on cognitive informatics, which implements computational intelligence by autonomous inferences and perceptions mimicking the mechanisms of the brain. The development of Cognitive Computers (cC) is centric in cognitive computing methodologies. A cC is an intelligent computer for knowledge processing as that of a conventional von Neumann computer for data processing. This paper summarizes the presentations of a set of 6 position papers presented in the ICCI’10 Plenary Panel on Cognitive Computing and Applications contributed from invited panelists who are part of the world’s renowned researchers and scholars in the field of cognitive informatics and cognitive computing.

In this study, we are concerned with genetically optimized fuzzy decision trees (G-DTs). Decision trees are fundamental architectures of machine learning, pattern recognition, and system modeling. Starting with the generic decision tree with discrete or interval-valued attributes, we develop its fuzzy set-based generalization. In this generalized structure we admit the values of the attributes that are represented by some membership functions. Such fuzzy decision trees are constructed in the setting of genetic optimization. The underlying genetic algorithm optimizes the parameters of the fuzzy sets associated with the individual nodes where they play a role of fuzzy "switches" by distributing a flow of processing completed within the tree. We discuss various forms of the fitness function that help capture the essence of the problem at hand (that could be either of classification nature when dealing with discrete outputs or regression-like when handling a continuous output variable). We quantify a nature of the generalization of the tree by studying an optimally adjusted spreads of the membership functions located at the nodes of the decision tree. A series of experiments exploiting synthetic and machine learning data is used to illustrate the performance of the G-DTs.