Sensors

Kim, Juhyung;Cho, Doo-Hyun;Lee, Woo-Cheol;Park, Soon-Seo;Choi, Han-Lim

doi: 10.3390/s19204555pmid: 31635128

This paper proposes a binary linear programming formulation for multiple target assignment of a radar network and demonstrates its applicability to obtain optimal solutions using an off-the-shelf mixed-integer linear programming solver. The goal of radar resource scheduling in this paper is to assign the maximum number of targets by handing over targets between networked radar systems to overcome physical limitations such as the detection range and simultaneous tracking capability of each radar. To achieve this, time windows are generated considering the relation between each radar and target considering incoming target information. Numerical experiments using a local-scale simulation were performed to verify the functionality of the formulation and a sensitivity analysis was conducted to identify the trend of the results with respect to several parameters. Additional experiments performed for a large-scale (battlefield) scenario confirmed that the proposed formulation is valid and applicable for hundreds of targets and corresponding radar network systems composed of five distributed radars. The performance of the scheduling solutions using the proposed formulation was better than that of the general greedy algorithm as a heuristic approach in terms of objective value as well as the number of handovers.

Kang, Hanwen;Chen, Chao

doi: 10.3390/s19204599pmid: 31652634

Autonomous harvesting shows a promising prospect in the future development of the agriculture industry, while the vision system is one of the most challenging components in the autonomous harvesting technologies. This work proposes a multi-function network to perform the real-time detection and semantic segmentation of apples and branches in orchard environments by using the visual sensor. The developed detection and segmentation network utilises the atrous spatial pyramid pooling and the gate feature pyramid network to enhance feature extraction ability of the network. To improve the real-time computation performance of the network model, a lightweight backbone network based on the residual network architecture is developed. From the experimental results, the detection and segmentation network with ResNet-101 backbone outperformed on the detection and segmentation tasks, achieving an F 1 score of 0.832 on the detection of apples and 87.6% and 77.2% on the semantic segmentation of apples and branches, respectively. The network model with lightweight backbone showed the best computation efficiency in the results. It achieved an F 1 score of 0.827 on the detection of apples and 86.5% and 75.7% on the segmentation of apples and branches, respectively. The weights size and computation time of the network model with lightweight backbone were 12.8 M and 32 ms, respectively. The experimental results show that the detection and segmentation network can effectively perform the real-time detection and segmentation of apples and branches in orchards.

Cuevas-Martinez, Juan-Carlos;Yuste-Delgado, Antonio-Jesus;Leon-Sanchez, Antonio-Jose;Saez-Castillo, Antonio-Jose;Triviño-Cabrera, Alicia

doi: 10.3390/s19204391pmid: 31614457

Clustering is presently one of the main routing techniques employed in randomly deployed wireless sensor networks. This paper describes a novel centralized unequal clustering method for wireless sensor networks. The goals of the algorithm are to prolong the network lifetime and increase the reliability of the network while not compromising the data transmission. In the proposed method, the Base Station decides on the cluster heads according to the best scores obtained from a Type-2 Fuzzy system. The input parameters of the fuzzy system are estimated by the base station or gathered from the network with a careful design that reduces the control message exchange. The whole network is controlled by the base station in a rounds-based schedule that alternates rounds when the base station elects cluster heads, with other rounds in which the cluster heads previously elected, gather data from their contributing nodes and forward them to the base station. The setting of the number of rounds in which the Base Station keeps the same set of cluster heads is another contribution of the present paper. The results show significant improvements achieved by the proposal when compared to other current clustering methods.

Du, Yegang;Lim, Yuto;Tan, Yasuo

doi: 10.3390/s19204474pmid: 31619005

Smart Homes are generally considered the final solution for living problem, especially for the health care of the elderly and disabled, power saving, etc. Human activity recognition in smart homes is the key to achieving home automation, which enables the smart services to automatically run according to the human mind. Recent research has made a lot of progress in this field; however, most of them can only recognize default activities, which is probably not needed by smart homes services. In addition, low scalability makes such research infeasible to be used outside the laboratory. In this study, we unwrap this issue and propose a novel framework to not only recognize human activity but also predict it. The framework contains three stages: recognition after the activity, recognition in progress, and activity prediction in advance. Furthermore, using passive RFID tags, the hardware cost of our framework is sufficiently low to popularize the framework. In addition, the experimental result demonstrates that our framework can realize good performance in both activity recognition and prediction with high scalability.

Liu, Mingqian;Zhang, Bingchen;Xu, Zhongqiu;Wu, Yirong

doi: 10.3390/s19204549pmid: 31635086

Sparse signal processing theory has been applied to synthetic aperture radar (SAR) imaging. In compressive sensing (CS), the sparsity is usually considered as a known parameter. However, it is unknown practically. For many functions of CS, we need to know this parameter. Therefore, the estimation of sparsity is crucial for sparse SAR imaging. The sparsity is determined by the size of regularization parameter. Several methods have been presented for automatically estimating the regularization parameter, and have been applied to sparse SAR imaging. However, these methods are deduced based on an observation matrix, which will entail huge computational and memory costs. In this paper, to enhance the computational efficiency, an efficient adaptive parameter estimation method for sparse SAR imaging is proposed. The complex image-based sparse SAR imaging method only considers the threshold operation of the complex image, which can reduce the computational costs significantly. By utilizing this feature, the parameter is pre-estimated based on a complex image. In order to estimate the sparsity accurately, adaptive parameter estimation is then processed in the raw data domain, combining with the pre-estimated parameter and azimuth-range decouple operators. The proposed method can reduce the computational complexity from a quadratic square order to a linear logarithm order, which can be used in the large-scale scene. Simulated and Gaofen-3 SAR data processing results demonstrate the validity of the proposed method.

Chowdhury, Alok Kumar;Tjondronegoro, Dian;Chandran, Vinod;Zhang, Jinglan;Trost, Stewart G.

doi: 10.3390/s19204509pmid: 31627335

This study examined the feasibility of a non-laboratory approach that uses machine learning on multimodal sensor data to predict relative physical activity (PA) intensity. A total of 22 participants completed up to 7 PA sessions, where each session comprised 5 trials (sitting and standing, comfortable walk, brisk walk, jogging, running). Participants wore a wrist-strapped sensor that recorded heart-rate (HR), electrodermal activity (Eda) and skin temperature (Temp). After each trial, participants provided ratings of perceived exertion (RPE). Three classifiers, including random forest (RF), neural network (NN) and support vector machine (SVM), were applied independently on each feature set to predict relative PA intensity as low (RPE ≤ 11), moderate (RPE 12–14), or high (RPE ≥ 15). Then, both feature fusion and decision fusion of all combinations of sensor modalities were carried out to investigate the best combination. Among the single modality feature sets, HR provided the best performance. The combination of modalities using feature fusion provided a small improvement in performance. Decision fusion did not improve performance over HR features alone. A machine learning approach using features from HR provided acceptable predictions of relative PA intensity. Adding features from other sensing modalities did not significantly improve performance.

Park, Young-Geun;Lee, Sangil;Park, Jang-Ung

doi: 10.3390/s19204353pmid: 31600870

The development of wearable electronics has emphasized user-comfort, convenience, security, and improved medical functionality. Several previous research studies transformed various types of sensors into a wearable form to more closely monitor body signals and enable real-time, continuous sensing. In order to realize these wearable sensing platforms, it is essential to integrate wireless power supplies and data communication systems with the wearable sensors. This review article discusses recent progress in wireless technologies and various types of wearable sensors. Also, state-of-the-art research related to the application of wearable sensor systems with wireless functionality is discussed, including electronic skin, smart contact lenses, neural interfaces, and retinal prostheses. Current challenges and prospects of wireless sensor systems are discussed.

Zhong, Yan;Fong, Simon;Hu, Shimin;Wong, Raymond;Lin, Weiwei

doi: 10.3390/s19204536pmid: 31635371

The Internet of Things (IoT) and sensors are becoming increasingly popular, especially in monitoring large and ambient environments. Applications that embrace IoT and sensors often require mining the data feeds that are collected at frequent intervals for intelligence. Despite the fact that such sensor data are massive, most of the data contents are identical and repetitive; for example, human traffic in a park at night. Most of the traditional classification algorithms were originally formulated decades ago, and they were not designed to handle such sensor data effectively. Hence, the performance of the learned model is often poor because of the small granularity in classification and the sporadic patterns in the data. To improve the quality of data mining from the IoT data, a new pre-processing methodology based on subspace similarity detection is proposed. Our method can be well integrated with traditional data mining algorithms and anomaly detection methods. The pre-processing method is flexible for handling similar kinds of sensor data that are sporadic in nature that exist in many ambient sensing applications. The proposed methodology is evaluated by extensive experiment with a collection of classical data mining models. An improvement over the precision rate is shown by using the proposed method.

Zhao, Yuan;Peng, Minglei;Liu, Jiemin

doi: 10.3390/s19204398pmid: 31614519

Cognitive radio networks (CRNs) can improve spectrum utilization by allowing secondary users (SUs) to dynamically access channels unoccupied by primary users (PUs). The spectrum access strategy, as a point to enhance user performance, has received much attention. In this paper, we propose a hybrid access mode for network users in multichannel CRNs. For meeting different SU demands, SUs are classified as SU1s and SU2s. We further introduce a channel bonding scheme for high-priority (PU and SU1) user packets to enhance transmission efficiency. At the same time, we propose a hybrid spectrum access strategy for SU2 packets to improve their transmission stability. By establishing a Markov chain model, some important SU2 packets’ performance measures are derived. Furthermore, we display the comparison of hybrid, overlay and underlay modes by numerical results to analyze the advantages of different modes.

Wang, WeiZheng;Deng, Zhuo;Wang, Jin;Sangaiah, Arun Kumar;Cai, Shuo;Almakhadmeh, Zafer;Tolba, Amr

doi: 10.3390/s19204598pmid: 31652631

Wireless sensor networks (WSN) have deeply influenced the working and living styles of human beings. Information security and privacy for WSN is particularly crucial. Cryptographic algorithms are extensively exploited in WSN applications to ensure the security. They are usually implemented in specific chips to achieve high data throughout with less computational resources. Cryptographic hardware should be rigidly tested to guarantee the correctness of encryption operation. Scan design improves significantly the test quality of chips and thus is widely used in semiconductor industry. Nevertheless, scan design provides a backdoor for attackers to deduce the cipher key of a cryptographic core. To protect the security of the cryptographic system we first present a secure scan architecture, in which an automatic test control circuitry is inserted to isolate the cipher key in test mode and clear the sensitive information at mode switching. Then, the weaknesses of this architecture are analyzed and an enhanced scheme using concept of test authorization is proposed. If the correct authorization key is applied within the specific time, the normal test can be performed. Otherwise, only secure scan test can be performed. The enhanced scan scheme ensures the security of cryptographic chips while remaining the advantages of scan design.