Data collection is one of the paramount concerns in wireless sensor networks (WSNs). Many data collection algorithms have been proposed for collecting data in particular monitoring regions. However, the efficiency of the paths for such data collection can be improved. This paper proposes an energy-aware path construction algorithm (EAPC), which selects an appropriate set of data collection points, constructs a data collection path, and collects data from the points burdened with data. EAPC is intended to prolong the network lifetime, it accounts for the path cost from its current data collection point to the next point and the forwarding load of each sensor node. Performance evaluation reveals that the proposed EAPC has more efficient performance than existing data collection mechanisms in terms of network lifetime, energy consumption, fairness index, and efficiency index.

Smart parking problems have received much attention in recent years. In literature, many smart parking allocation algorithms that considered the parking grid reservation and recommendation have been proposed. However, the parking policies for maximizing parking rate and benefits still can be improved. This paper proposes a smart parking allocation algorithm (SPA), which aims to maximize the benefits created by a given parking lot while guaranteeing the quality of parking services. The proposed SPA algorithm predicts the driver behavior and estimated parking traffic in the near future based on the historical parking records. These predictions help SPA to better match the parking demands and the resource of available parking grids and, hence, improve the utilization and the created benefit of each parking grid. The proposed SPA applies three policies, namely worst-fit (WF-SPA), best-fit (BF-SPA), and parking behavior forecast (PBF-SPA), to allocate the available grids to the vehicles. Performance evaluations reveal that the proposed SPA outperforms exiting work in terms of accumulated parking rate and service quality and, hence, improves the benefits of a given parking lot.

Unmanned Aerial Vehicle (UAV) swarm networks have been presented as a promising paradigm for conducting monitoring, and inter-connecting tasks in unattended or even hostile environments. However, harsh deployment scenario may make the UAVs susceptible to large-scale damage, and thus degrades the connectivity and performance of the network. None of existing technologies can effectively re-organize the surviving UAVs in a severely damaged UAV swarm into a unified UAV Swarm Network (USNET), this paper presents and analyzes the damage-resilience problem of USNETs for the first time, and put forwards a Swarm Intelligence-based Damage-Resilient (SIDR) mechanism. First, a damage model of USNETs and several metrics are defined before the problem is formally formulated. Second, the SIDR mechanism is detailed based on comprehensively utilizing the storage, communication, positioning, and maneuvering capabilities of UAVs. Third, a potential-field-based solution to the proposed SIDR mechanism is presented, aiming to recover a USNET rapidly and elastically. At last, an evaluation environment is built on the OMNeT++ platform, and the proposed SIDR mechanism is implemented. Extensive simulations are conducted in both dynamic and static scenarios. Simulation results demonstrate that SIDR outperforms the existing algorithms in terms of resilience capability, convergence time and communication overhead. Even if a USNET is divided into multiple disjoint subnets with arbitrary shape, SIDR can aggregate the surviving nodes into a connected network while the network is still flying along the flight path during the recovery process.

The inherent complexity of human physical activities makes it difficult to accurately recognize activities with wearable sensors. To this end, this paper proposes a hierarchical activity recognition framework and two different feature selection methods to improve the recognition performance. Specifically, according to the characteristics of human activities, predefined activities of interest are organized into a hierarchical tree structure, where each internal node represents different groups of activities and each leaf node represents a specific activity label. Then, the proposed feature selection methods are appropriately integrated to optimize the feature space of each node. Finally, we train corresponding classifiers to distinguish different activity groups and to classify a new unseen sample into one of the leaf-nodes in a top-down fashion to predict its activity label. To evaluate the performance of the proposed framework and feature selection methods, we conduct extensive comparative experiments on publicly available datasets and analyze the model complexity. Experimental results show that the proposed method reduces the dimensionality of original feature space and contributes to enhancement of the overall recognition accuracy. In addition, for feature selection, returning multiple activity-specific feature subsets generally outperforms the case of returning a common subset of features for all activities.

Network communication and micro-electro-mechanical embedded technologies have attracted much attention in recent years. Through these technologies, the capabilities of sensing, identification, and communication can be embedded in various smart devices. These smart devices can automatically connect to the Internet and form an intelligent network called Internet of Things (IoT). However, these devices are embedded with different wireless communication interfaces such as Wi-Fi and ZigBee. This paper presents the design and implementation of an IoT access point that supports functionalities of coordination of various wireless transmission protocols. Based on the existing Wi-Fi access point, we have embedded a ZigBee module and implemented ZigBee and UPnP protocols into the designed IoT access point, which supports ZigBee communication capabilities over the Internet.

The power of end-to-end deep learning techniques to automatically learn latent high-level features from raw signals has been demonstrated in numerous application fields, however, few studies systematically investigate how to properly encode the time-series firings of binary environment sensors that typically work in an event-triggering scheme and have irregular sampling rates for in-home human activity recognition. To this end, we here propose two different methods to process the streaming sensor readings and accordingly evaluate their combinations with deep learning models. Specifically, we divide the multichannel sensor events into segments and encode each segment into either a vector or two-dimensional matrix. Particularly, three different feature representations are presented for the vector form. Afterwards, we combine the encoded features with four typical deep learning models and optimize corresponding activity recognizers to study their sensitivity to different feature encodings. Furthermore, we include seven commonly used shallow classification models for comparison purposes. Finally, we conduct extensive experiments on three publicly available smart home datasets. Results indicate that the performance of both deep learning and shallow models is closely associated with the raw signal encodings and demonstrate the superiority of one-dimensional convolutional neural networks over its competitors in terms of generalization across scenarios. Besides, we preliminarily explore the influence of NULL class on an activity recognizer and experimentally show its negative impact on overall accuracy, enlightening relevant studies to consider it in developing a practical activity recognition system.