Hardhat-Wearing Detection Based on a Lightweight Convolutional Neural Network with Multi-Scale Features and a Top-Down Module.

Construction sites are dangerous due to the complex interaction of workers with equipment, building materials, vehicles, etc. As a kind of protective gear, hardhats are crucial for the safety of people on construction sites. Therefore, it is necessary for administrators to identify the people that do not wear hardhats and send out alarms to them. As manual inspection is labor-intensive and expensive, it is ideal to handle this issue by a real-time automatic detector. As such, in this paper, we present an end-to-end convolutional neural network to solve the problem of detecting if workers are wearing hardhats. The proposed method focuses on localizing a person's head and deciding whether they are wearing a hardhat. The MobileNet model is employed as the backbone network, which allows the detector to run in real time. A top-down module is leveraged to enhance the feature-extraction process. Finally, heads with and without hardhats are detected on multi-scale features using a residual-block-based prediction module. Experimental results on a dataset that we have established show that the proposed method could produce an average precision of 87.4%/89.4% at 62 frames per second for detecting people without/with a hardhat worn on the head.

A Novel Synchronization Scheme Based on a Dynamic Superframe for an Industrial Internet of Things in Underground Mining.

The Industrial Internet of Things (IIoT) has a wide range of applications, such as intelligent manufacturing, production process optimization, production equipment monitoring, etc. Due to the complex circumstance in underground mining, the performance of WSNs faces enormous challenges, such as data transmission delay, packet loss rate, and so on. The MAC (Media Access Control) protocol based on TDMA (Time Division Multiple Access) is an effective solution, but it needs to ensure the clock synchronization between the transmission nodes. As the key technology of IIoT, synchronization needs to consider the factors of tunnel structure, energy consumption, etc. Traditional synchronization methods, such as TPSN (Timing-sync Protocol for Sensor Networks), RBS (Reference Broadcast Synchronization), mainly focus on improving synchronization accuracy, ignoring the impact of the actual environment, cannot be directly applied to the IIoT in underground mining. In underground mining, there are two kinds of nodes: base-station node and sensor node, which have different topologies, so they constitute a hybrid topology. In this paper, according to hybrid topology of unground mining, a clock synchronization scheme based on a dynamic superframe is designed. In this scheme, the base-station and sensor have different synchronization methods, improving the TPSN and RBS algorithm, respectively, and adjusts the period of the superframe dynamically by estimating the clock offset. The synchronization scheme presented in this paper can reduce the network communication overhead and energy consumption, ensuring the synchronization accuracy. Based on theCC2530 (Asystem-on-chip solution for IEEE 802.15.4, Zigbee and RF4CE applications), the experiments are compared and analyzed, including synchronization accuracy, energy consumption, and robustness tests. Experimental results show that the synchronization accuracy of the proposed method is at least 11% higher than that of the existing methods, and the energy consumption can be reduced by approximately 13%. At the same time, the proposed method has better robustness.

An Artificial Bee Colony-Based Green Routing Mechanism in WBANs for Sensor-Based E-Healthcare Systems.

At present, sensor-based E-Healthcare systems are attracting more and more attention from academia and industry. E-Healthcare systems are usually a Wireless Body Area Network (WBANs), which can monitor or diagnose human health by placing miniaturized, low-power sensor nodes in or on patient's bodies to measure various physiological parameters. However, in this process, WBAN nodes usually use batteries, and especially for implantable flexible nodes, it is difficult to accomplish the battery replacement, so the energy that the node can carry is very limited, making the efficient use of energy the most important problem to consider when designing WBAN routing algorithms. By considering factors such as residual energy of node, the importance level of nodes, path cost and path energy difference ratios, this paper gives a definition of Optimal Path of Energy Consumption (OPEC) in WBANs, and designs the Optimal Energy Consumption routing based on Artificial Bee Colony (ABC) for WBANs (OEABC). A performance simulation is carried out to verify the effectiveness of the OEABC. Simulation results demonstrate that compared with the genetic algorithm and ant colony algorithm, the proposed OEABC has a better energy efficiency and faster convergence rate.

Indoor Trajectory Tracking Scheme Based on Delaunay Triangulation and Heuristic Information in Wireless Sensor Networks.

Object tracking and detection is one of the most significant research areas for wireless sensor networks. Existing indoor trajectory tracking schemes in wireless sensor networks are based on continuous localization and moving object data mining. Indoor trajectory tracking based on the received signal strength indicator (RSSI) has received increased attention because it has low cost and requires no special infrastructure. However, RSSI tracking introduces uncertainty because of the inaccuracies of measurement instruments and the irregularities (unstable, multipath, diffraction) of wireless signal transmissions in indoor environments. Heuristic information includes some key factors for trajectory tracking procedures. This paper proposes a novel trajectory tracking scheme based on Delaunay triangulation and heuristic information (TTDH). In this scheme, the entire field is divided into a series of triangular regions. The common side of adjacent triangular regions is regarded as a regional boundary. Our scheme detects heuristic information related to a moving object's trajectory, including boundaries and triangular regions. Then, the trajectory is formed by means of a dynamic time-warping position-fingerprint-matching algorithm with heuristic information constraints. Field experiments show that the average error distance of our scheme is less than 1.5 m, and that error does not accumulate among the regions.

An Energy-Efficient Skyline Query for Massively Multidimensional Sensing Data.

Cyber physical systems (CPS) sense the environment based on wireless sensor networks. The sensing data of such systems present the characteristics of massiveness and multi-dimensionality. As one of the major monitoring methods used in in safe production monitoring and disaster early-warning applications, skyline query algorithms are extensively adopted for multiple-objective decision analysis of these sensing data. With the expansion of network sizes, the amount of sensing data increases sharply. Then, how to improve the query efficiency of skyline query algorithms and reduce the transmission energy consumption become pressing and difficult to accomplish issues. Therefore, this paper proposes a new energy-efficient skyline query method for massively multidimensional sensing data. First, the method uses a node cut strategy to dynamically generate filtering tuples with little computational overhead when collecting query results instead of issuing queries with filters. It can judge the domination relationship among different nodes, remove the detected data sets of dominated nodes that are irrelevant to the query, modify the query path dynamically, and reduce the data comparison and computational overhead. The efficient dynamic filter generated by this strategy uses little non-skyline data transmission in the network, and the transmission distance is very short. Second, our method also employs the tuple-cutting strategy inside the node and generates the local cutting tuples by the sub-tree with the node itself as the root node, which will be used to cut the detected data within the nodes of the sub-tree. Therefore, it can further control the non-skyline data uploading. A large number of experimental results show that our method can quickly return an overview of the monitored area and reduce the communication overhead. Additionally, it can shorten the response time and improve the efficiency of the query.

Dynamic Information Flow Tracking: Taxonomy, Challenges, and Opportunities.

Dynamic information flow tracking (DIFT) has been proven an effective technique to track data usage; prevent control data attacks and non-control data attacks at runtime; and analyze program performance. Therefore, a series of DIFT techniques have been developed recently. In this paper, we summarize the current DIFT solutions and analyze the features and limitations of these solutions. Based on the analysis, we classify the existing solutions into three categories, i.e., software, hardware, software and hardware co-design. We discuss the DIFT design from the perspective of whole system and point out the limitations of current DIFT frameworks. Potential enhancements to these solutions are also presented. Furthermore, we present suggestions about the possible future direction of DIFT solutions so that DIFT can help improve security levels.