Search

Saliency prediction models aim to mimic the human visual system’s attention process, and the research has made significant progress due to recent advancements in deep convolution neural networks. However, the high memory requirements and intensive computational demands make these approaches less suitable for Internet-of-Things (IoT) devices, and there is a need for an improved computational efficiency and reduced memory footprint to facilitate distributed IoT intelligence. This article proposes a pseudoknowledge distillation (PKD) training method for creating a compact real-time saliency prediction model. The proposed method can effectively transfer knowledge from computationally expensive once-for-all (OFA-595) as a single teacher model and a combination of OFA-595 and EfficientNet-B7 as a multiteacher model to an early exit evolutionary algorithm network student model by utilizing knowledge distillation and pseudolabeling. Five saliency benchmark datasets are used to demonstrate PKD’s improved prediction performance and its reduced inference time without modifying the original student model. [ABSTRACT FROM AUTHOR]

Industrial advancement has introduced a significant impact on ecological balance and natural resources; thus, pollution monitoring using smart sensors in the industrial Internet of Things (IIoT) has recently attracted growing interests in the era of Industry 4.0. However, the effective detection and location of polluted areas remains a major challenge for collecting and processing a massive amount of sensor data in the IIoT especially in far sea, danger zone, and mountain zone, where there is no communication infrastructure. In this article, we establish a satellite-terrestrial framework to detect and locate industrial pollution areas by integrating the satellite with the IIoT, and the massive amount of sensor data can be delivered to the satellite via a ground base station. Local attribute detection inspired by recent advances in graph signal processing provides a promising way for solving this problem. A subgraph can be formed by grouping the vertices with identical attributes, and these vertices can be easily separated from other vertices based on local attribute detection. In this article, new methods based on local attribute detection are proposed to detect and locate pollution areas. First, a stable wavelet statistic (SWS) is proposed by modeling the classical wavelet basis as a graph-based wavelet basis. To improve the generalization ability of the SWS, a new cluster center discovery method is proposed to minimize the distance between any vertex and the remaining vertices of the same cluster. Second, a smooth scan statistic is proposed by introducing a new constraint to simplify the problem formulation of the likelihood ratio test. The effectiveness of the two graph-based statistical methods is evaluated using real datasets for detecting and locating industrial pollution. [ABSTRACT FROM AUTHOR]

The Internet of Things integrates a large number of distributed nodes to collect or transmit data. When the network scale increases, individuals use multiple sink nodes to construct the network. This increases the complexity of the network and leads to significant challenges in terms of the existing methods with respect to the aspect of data forwarding and collection. In order to address the issue, this paper proposes a Shortcut Addition strategy based on the Particle Swarm algorithm (SAPS) for multisink network. It constructs a network topology with multiple sinks based on a small-world network. In the SAPS, we create a fitness function by combining the average path length and load of the sink node, to evaluate the quality of a particle. Subsequently, crossover and mutation are used to update the particles to determine the optimal solution. The simulation results indicate that the SAPS is superior both to the greedy model with small world and the load-balanced multigateway aware long link addition strategy in terms of the average path length, load balance, and number of added shortcuts. [ABSTRACT FROM AUTHOR]

A backpressure-based data collecting scheme has been applied in the Internet of Things, which can control the network congestion effectively and increase the network throughput. However, there is an obvious shortcoming in the traditional backpressure data collecting scheme for the network service chain. It attempts to search all possible paths between source node and destination node in the networks, causing an unnecessary long path for data collection, which results in large end-toend delay and redundant energy consumption. To address this shortcoming of backpressure data collecting scheme in the Internet of Things, this article proposes an energy-aware and distance-aware data collecting scheme to enhance the lifetime of backpressure-based data collecting schemes. We propose an energy- and distance-based model that combines the factors of queue backlog, hop counts, and residual energy for making routing decisions. It not only reduces the unnecessary energy consumption, but also balances the residual energy. The experiment results show that the proposed scheme can reduce unnecessary energy consumption and end-to-end delay compared to the traditional and LIFO-based schemes. Meanwhile, it balances the energy of nodes and extends the lifetime of an Internet of Things. [ABSTRACT FROM PUBLISHER]

This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in other systems can take the form of hand-crafted features or user-based track initialization. We then classify the tracked objects with a fast-learning image classifier, that is based on a shallow convolutional neural network architecture and demonstrate that object recognition improves when this is combined with object state information from the tracking algorithm. We argue that by transferring the use of prior knowledge from the detection and tracking stages to the classification stage, we can design a robust, general purpose object recognition system with the ability to detect and track a variety of object types. We describe our biologically inspired implementation, which adaptively learns the shape and motion of tracked objects, and apply it to the Neovision2 Tower benchmark data set, which contains multiple object types. An experimental evaluation demonstrates that our approach is competitive with the state-of-the-art video object recognition systems that do make use of object-specific prior knowledge in detection and tracking, while providing additional practical advantages by virtue of its generality. [ABSTRACT FROM PUBLISHER]

Cross-view data are collected from two different views or sources about the same subjects. As the information from these views often consolidate and/or complement each other, cross-view data analysis can gain more insights for decision making. A main challenge of cross-view data analysis is how to effectively explore the inherently correlated and high-dimensional data. Dimension reduction offers an effective solution for this problem. However, how to choose right models and parameters involved for dimension reduction is still an open problem. In this paper, we propose an effective sparse learning algorithm for cross-view dimensionality reduction. A distinguished character of our model selection is that it is nonparametric and automatic. Specifically, we represent the correlation of cross-view data using a covariance matrix. Then, we decompose the matrix into a sequence of low-rank ones by solving an optimization problem in an alternating least squares manner. More importantly, a new and nonparametric sparsity-inducing function is developed to derive a parsimonious model. Extensive experiments are conducted on real-world data sets to evaluate the effectiveness of the proposed algorithm. The results show that our method is competitive with the state-of-the-art sparse learning algorithms. [ABSTRACT FROM PUBLISHER]

Socially aware networking (SAN) is a new communication paradigm, in which the social characteristics of mobile nodes are exploited to improve the performance of data distribution. In SAN, mobile carriers may exhibit selfish behaviors and refuse to relay messages for others for various reasons, such as limited resources (e.g., buffer, energy, and bandwidth) or social relationships. Several incentive schemes have recently been investigated to stimulate selfish users for cooperation in data forwarding. However, a majority of the existing methods have not fully studied nodes' social relationships in their selfish behaviors. In this paper, we propose a copy adjustable incentive scheme (CAIS), which adopts the virtual credit concept to stimulate selfish nodes to cooperate in data forwarding. In CAIS, we consider a network in which the nodes are divided into certain communities based on their social relationships. Then, we apply two types of credits, i.e., social credit and nonsocial credit, to reward the nodes when they relay data for other nodes inside their community or outsiders, respectively. Based on our mechanism, the number of messages a node can replicate to other nodes is adjusted according to its cooperation level and earned credits. To further improve the performance of CAIS, a single-copy data replication policy is employed, which manages the credit distribution of each node according to its available resources. The results of our extensive experiments using both synthetic and trace-driven simulations illustrate that CAIS copes well with node selfishness in community-based networks and outperforms other benchmark protocols with high data delivery ratio, low communication overhead, and short data delivery latency. [ABSTRACT FROM PUBLISHER]

Accidental falls have been identified as a cause of mortality for elders who live alone around the globe. Following a fall, additional injury can be sustained if proper fall recovery techniques are not followed. These secondary complications can be reduced if the person had access to safe recovery procedures or were assisted, either by a person or a robot. We propose a framework for in situ robotic assistance for post fall recovery scenarios. In order to assist autonomously robots need to recognize an individual's posture and subactivities (e.g., falling, rolling, move to hands and knees, crawling, and push up through legs, sitting or standing). Human body skeleton tracking through RGB-D pose estimation methods fail to identify the body parts during key phases of fall recovery due to high occlusion rates in fallen, and recovering, postures. To address this issue, we investigated how low-level image features can be leveraged to recognize an individual's subactivities. Depth cuboid similarity features (DCSFs) approach was improved with M-partitioned histograms of depth cuboid prototypes, integration of activity progression direction, and outlier spatiotemporal interest point removal. Our modified DCSF algorithm was evaluated on a unique RGB-D multiview dataset, achieving 87.43 ± 1.74% accuracy in the extensive 3003 $({{\boldsymbol{C}}_{10}^{15}})$ combinations of training-test groups of 15 subjects in 10 trials. This result was significantly larger than the nearest competitor, and faster in the training phase. This work could lead to more accurate in situ robotic assistance for fall recovery, saving lives for victims of falls. [ABSTRACT FROM PUBLISHER]