With the various applications of the Internet of Things, research into wireless sensor networks (WSNs) has become increasingly important. However, because of their limited energy, the communication abilities of the wireless nodes distributed in the WSN are limited. The main task of WSNs is to collect more data from targets in an energy-efficient way, because the battery replacement of large amounts of nodes is a labor-consuming work. Although the life of WSNs can be prolonged through energy-harvesting (EH) technology, it is necessary to design an energy-efficient routing protocol for the energy harvesting-based wireless sensor networks (EH-WSNs) as the nodes would be unavailable in the energy harvesting phase. A certain number of unavailable nodes would cause a coverage hole, thereby affecting the WSN’s monitoring function of the target environment. In this paper, an adaptive hierarchical-clustering-based routing protocol for EH-WSNs (HCEH-UC) is proposed to achieve uninterrupted coverage of the target region through the distributed adjustment of the data transmission. Firstly, a hierarchical-clustering-based routing protocol is proposed to balance the energy consumption of nodes. Then, a distributed alternation of working modes is proposed to adaptively control the number of nodes in the energy-harvesting mode, which could lead to uninterrupted target coverage. The simulation experimental results verify that the proposed HCEH-UC protocol can prolong the maximal lifetime coverage of WSNs compared with the conventional routing protocol and achieve uninterrupted target coverage using energy-harvesting technology.

The automatic sleep stage classification technique can facilitate the diagnosis of sleep disorders and release the medical expert from labor-consumption work. In this paper, novel improved model based essence features (IMBEFs) were proposed combining locality energy (LE) and dual state space models (DSSMs) for automatic sleep stage detection on single-channel electroencephalograph (EEG) signals. Firstly, each EEG epoch is decomposed into low-level sub-bands (LSBs) and high-level sub-bands (HSBs) by wavelet packet decomposition (WPD), separately. Then, the DSSMs are estimated by the LSBs and the LE calculation is carried out on HSBs. Thirdly, the IMBEFs extracted from the DSSM and LE are fed into the appropriate classifier for sleep stage classification. The performance of the proposed method was evaluated on three public sleep databases. The experimental results show that under the Rechtschaffen’s and Kale’s (R&K) standard, the sleep stage classification accuracies of six classes on the Sleep EDF database and the Dreams Subjects database are 92.04% and 78.92%, respectively. Under the American Academy of Sleep Medicine (AASM) standard, the classification accuracies of five classes in the Dreams Subjects database and the ISRUC database reached 79.90% and 81.65%. The proposed method can be used for reliable sleep stage classification with high accuracy compared with state-of-the-art methods.

Indoor location-based-service is emerging as the crucial application of internet-of-things, which promotes the advance of relevant technology in indoor scenario. Several positioning algorithms are proposed for different indoor configurations in recent years. The fingerprint based indoor positioning algorithm has drawn much attention because of the good positioning performance without additional hardware. However, the false fingerprint matching frequently incurs due to the complexity of indoor positioning environment and affects the positioning accuracy. In this paper, a principal component analysis (PCA) assisted indoor positioning algorithm based on the adaptive hierarchical clustering algorithm (PAHC) is proposed, which can improve the positioning accuracy through aggregating the RPs and conducting the cluster-based-principal-component-analysis (C-PCA) features extraction. More specifically, a clustering termination method is proposed to obtain reasonable RPs clusters adaptively according to the pre-set RPs. And a two-stage fingerprint matching algorithm is proposed based on the C-PCA to further increasing the difference between similar RPs and thus improving the positioning accuracy. To verify the proposed algorithm, an indoor wireless system is established in the practical indoor scenario. Experiment results indicate that the proposed PAHC algorithm can increase the positioning accuracy by 9.3% compared with the conventional fingerprint algorithm.

The classification of sleep stages is the process which helps to evaluate the quality of sleep and detect the sleep related disorders. Through analyzing the electroencephalography, the sleep stages can be discriminated manually by specialists. However, this can be a laboriousness work because of the huge datasets. Until now, several studies have been conducted based on the automatic analysis of electroencephalography. Still, as the development of wearable technology, there is a need for an accurate and single-channel electroencephalography based sleep stages identification system. In this paper, a state-space based sleep stages classification method is proposed using the proposed model based essence features extraction method. This method employed the state-space model to establish the intrinsic models based on the single-channel electroencephalography, from which the features used for further classification can be extracted. For 2-stage to 6-stage classification of sleep states, the verification system can achieve 98.6%, 94.9%, 93.0%, 92.3%, 91.8% accuracy on the Sleep-EDF database, and also reach 94.9%, 87.7%, 82.7%, 80.9%, 78.2% on Dreams Subjects database.

Silicon-based organic light-emitting diode (OLED) microdisplays are widely used in the head-mounted devices. This article proposes a novel atomized scan method for the digital driving silicon-based OLED microdisplays. By eliminating the time redundancy in the digital driving, the proposed method generates the high transmission efficiency, high lighting efficiency, high grayscale efficiency, and good linearity compared with the traditional pulsewidth modulation (PWM) scan methods. Four scan characteristics of the high-efficiency scan sequence are analyzed. The high efficient atomized scan can be obtained by implanting the low grayscale scan into the high grayscale scan. A 1.6 k x 1.6 k full color silicon-based OLED microdisplay, together with the hardware driving platform, is designed and implemented to verify the proposed atomized scan method. By measuring the brightness values of 256 gray levels, the atomized scan method with the blank operation can achieve high scan efficiency with the low clock frequency (57.6 MHz).

The convolutional neural network (CNN) has made great success in many fields, and is gradually being applied in edge-computing systems. Taking the limited budget of the resources in the systems into consideration, the implementation of CNNs on embedded devices is preferred. However, accompanying the increasingly complex CNNs is the huge cost of memory, which constrains its implementation on embedded devices. In this paper, we propose an efficient, pipelined convolution module based on a Brain Floating-Point (BF16) to solve this problem, which is composed of a quantization unit, a serial-to-matrix conversion unit, and a convolution operation unit. The mean error of the convolution module based on BF16 is only 0.1538%, which hardly affects the CNN inference. Additionally, when synthesized at 400 MHz, the area of the BF16 convolution module is 21.23% and 18.54% smaller than that of the INT16 and FP16 convolution modules, respectively. Furthermore, our module using the TSMC 90 nm library can run at 1 GHz by optimizing the critical path. Finally, our module was implemented on the Xilinx PYNQ-Z2 board to evaluate the performance. The experimental results show that at the frequency of 100 MHz, our module is, separately, 783.94 times and 579.35 times faster than the Cortex-M4 with FPU and Hummingbird E203, while maintaining an extremely low error rate.