Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts information from texture and shape. This is often inappropriate for fine-grained visual classification (FGVC) since it exhibits high intra-class and low inter-class variances due to occlusions, deformation, illuminations, etc. Thus, an expressive feature representation describing global structural information is a key to characterize an object/scene. To this end, we propose a method that effectively captures subtle changes by aggregating context-aware features from most relevant image-regions and their importance in discriminating fine-grained categories avoiding the bounding-box and/or distinguishable part annotations. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) approaches to include a simple yet effective relation-aware feature transformation and its refinement using a context-aware attention mechanism to boost the discriminability of the transformed feature in an end-to-end learning process. Our model is evaluated on eight benchmark datasets consisting of fine-grained objects and human-object interactions. It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.

Combinatorial optimization problems are typically NP-hard, due to their intrinsic complexity. In this paper, we propose a novel chaotic particle swarm optimization algorithm (CS-PSO), which combines the chaos search method with the particle swarm optimization algorithm (PSO) for solving combinatorial optimization problems. In particular, in the initialization phase, the priori knowledge of the combination optimization problem is used to optimize the initial particles. According to the properties of the combination optimization problem, suitable classification algorithms are implemented to group similar items into categories, thus reducing the number of combinations. This enables a more efficient enumeration of all combination schemes and optimize the overall approach. On the other hand, in the chaos perturbing phase, a brand-new set of rules is presented to perturb the velocities and positions of particles to satisfy the ideal global search capability and adaptability, effectively avoiding the premature convergence problem found frequently in traditional PSO algorithm. In the above two stages, we control the number of selected items in each category to ensure the diversity of the final combination scheme. The fitness function of CS-PSO introduces the concept of the personalized constraints and general constrains to get a personalized interface, which is used to solve a personalized combination optimization problem. As part of our evaluation, we define a personalized dietary recommendation system, called Friend, where CS-PSO is applied to address a healthy diet combination optimization problem. Based on Friend, we implemented a series of experiments to test the performance of CS-PSO. The experimental results show that, compared with the typical HLR-PSO, CS-PSO can recommend dietary schemes more efficiently, while obtaining the global optimum with fewer iterations, and have the better global ergodicity.

There is an increasing interest in Internet of Things (IoT) and healthcare is considered to be one of the most common applications of it. Using the IoT paradigm, various devices including smart-phones and sensor-embedded healthcare applications can be used for monitoring health. In this study, we model an IoT use case scenario with regard to monitoring the activities associated with health. In particular, we present our use case using the SimIoT extended simulation toolkit to demonstrate the various functions and the interactions occurring within the IoT-enabled healthcare context. Specifically, we extend the functionalities of the SimIC simulation toolkit by adding the IoT layer that incorporates IoT devices which generated data for the private clouds. We focus our experimental analysis from the perspective of cloud performance to illustrate the turnaround and make span of the system.

This article presents a novel keypoints-based attention mechanism for visual recognition in still images. Deep Convolutional Neural Networks (CNNs) for recognizing images with distinctive classes have shown great success, but their performance in discriminating fine-grained changes is not at the same level. We address this by proposing an end-to-end CNN model, which learns meaningful features linking fine-grained changes using our novel attention mechanism. It captures the spatial structures in images by identifying semantic regions (SRs) and their spatial distributions, and is proved to be the key to modeling subtle changes in images. We automatically identify these SRs by grouping the detected keypoints in a given image. The “usefulness” of these SRs for image recognition is measured using our innovative attentional mechanism focusing on parts of the image that are most relevant to a given task. This framework applies to traditional and fine-grained image recognition tasks and does not require manually annotated regions (e.g. bounding-box of body parts, objects, etc.) for learning and prediction. Moreover, the proposed keypoints-driven attention mechanism can be easily integrated into the existing CNN models. The framework is evaluated on six diverse benchmark datasets. The model outperforms the state-of-the-art approaches by a considerable margin using Distracted Driver V1 (Acc: 3.39%), Distracted Driver V2 (Acc: 6.58%), Stanford-40 Actions (mAP: 2.15%), People Playing Musical Instruments (mAP: 16.05%), Food-101 (Acc: 6.30%) and Caltech-256 (Acc: 2.59%) datasets.

During the recent years, several advances about smart environments are taking place. The challenge of transforming cities to 'smart' cities aims to combine competitiveness and sustainable urban development simultaneously. This is taking place through the combination of traditional urban environment, governmental and social functions with modern Information and Communication Technologies (ICT) providing e-services. At the same time, next generation technologies community puts efforts on issues associated with the development of community-based services that aim to capture and assess large amounts of data in a systematic collaborative manner. Thus, the concept of crowd sourcing becomes quite popular. In this paper we focus on discussing whether crowd sourcing can be facilitated in the contexts of smart buildings and cities in order to support a more effective and efficient integrated disaster management approach. Within this context, we exemplify the approach using few model architecture diagrams.