The Dynamic Spectrum Sharing (DSS) system, which uses the frequency band allocated to incumbent systems (i.e., primary users) has attracted attention to expand the available bandwidth of the fifth-generation mobile communication (5G) systems in the sub-6GHz band. In Japan, a DSS system in the 2.3GHz band, in which the ARIB STD-B57-based Field Pickup Unit (FPU) is assigned as an incumbent system, has been studied for the secondary use of 5G systems. In this case, the incumbent FPU is a mobile system, and thus, the DSS system needs to use not only a spectrum sharing database but also radio sensors to detect primary signals with high accuracy, protect the primary system from interference, and achieve more secure spectrum sharing. This paper proposes highly efficient sensing methods for detecting the ARIB STD-B57-based FPU signals in the 2.3GHz band. The proposed methods can be applied to two types of the FPU signal; those that apply the Continuous Pilot (CP) mode pilot and the Scattered Pilot (SP) mode pilot. Moreover, we apply a sample addition method and a symbol addition method for improving the detection performance. Even in the 3GPP EVA channel environment, the proposed method can, with a probability of more than 99%, detect the FPU signal with an SNR of -10dB. In addition, we propose a quantized reference signal for reducing the implementation complexity of the complex cross-correlation circuit. The proposed reference signal can reduce the number of quantization bits of the reference signal to 2 bits for in-phase and 3 bits for orthogonal components.

An autoencoder is trained to generate the background from the surveillance image by setting the training label as the shuffled input, instead of the input itself in a traditional autoencoder. Then the multi-scale features are extracted by a sparse autoencoder from the surveillance image and the corresponding background to detect foreground.

A method for detecting the timing of photodiode (PD) saturation without using an in-pixel time-to-digital converter (TDC) is proposed. Detecting PD saturation time is an approach to extend the dynamic range of a CMOS image sensor (CIS) without multiple exposures. In addition to accumulated charges in a PD, PD saturation time can be used as a signal related to light intensity. However, in previously reported CISs with detecting PD saturation time, an in-pixel TDC is used to detect and store PD saturation time. That makes the resolution of a CIS lower because an in-pixel TDC requires a large area. As for the proposed pixel circuit, PD saturation time is detected and stored as a voltage in a capacitor. The voltage is read and converted to a digital code by a column ADC after an exposure. As a result, an in-pixel TDC is not required. A signal-processing and calibration method for combining two signals, which are saturation time and accumulated charges, linearly are also proposed. Circuit simulations confirmed that the proposed method extends the dynamic range by 36 dB and its total dynamic range to 95 dB. Effectiveness of the calibration was also confirmed through circuit simulations.

This letter reports on the effectiveness of applying the K-singular value decomposition (SVD) dictionary learning to the electroencephalogram (EEG) compressed sensing framework with outlier detection and independent component analysis. Using the K-SVD dictionary matrix with our design parameter optimization, for example, at compression ratio of four, we improved the normalized mean square error value by 31.4% compared with that of the discrete cosine transform dictionary for CHB-MIT Scalp EEG Database.

The automatic analysis of retinal fundus images is of great significance in large-scale ocular pathologies screening, of which optic disc (OD) location is a prerequisite step. In this paper, we propose a method based on saliency detection and attention convolutional neural network for OD detection. Firstly, the wavelet transform based saliency detection method is used to detect the OD candidate regions to the maximum extent such that the intensity, edge and texture features of the fundus images are all considered into the OD detection process. Then, the attention mechanism that can emphasize the representation of OD region is combined into the dense network. Finally, it is determined whether the detected candidate regions are OD region or non-OD region. The proposed method is implemented on DIARETDB0, DIARETDB1 and MESSIDOR datasets, the experimental results of which demonstrate its superiority and robustness.

Well annotated dataset is crucial to the training of object detectors. However, the production of finely annotated datasets for object detection tasks is extremely labor-intensive, therefore, cloud sourcing is often used to create datasets, which leads to these datasets tending to contain incorrect annotations such as inaccurate localization bounding boxes. In this study, we highlight a problem of object detection with noisy bounding box annotations and show that these noisy annotations are harmful to the performance of deep neural networks. To solve this problem, we further propose a framework to allow the network to modify the noisy datasets by alternating refinement. The experimental results demonstrate that our proposed framework can significantly alleviate the influences of noise on model performance.

Feature detection and matching procedure require most of processing time in image matching where the time dramatically increases according to the number of feature points. The number of features is needed to be controlled for specific applications because of their processing time. This paper proposes a feature detection method based on significancy of local features. The feature significancy is computed for all pixels and higher significant features are chosen considering spatial distribution. The method contributes to reduce the number of features in order to match two images with maintaining high matching accuracy. It was shown that this approach was faster about two times in average processing time than FAST detector for natural scene images in the experiments.

In a multiple-input multiple-output (MIMO) system, maximum likelihood detection (MLD) is the best demodulation scheme if no a priori information is available. However, the complexity of MLD increases exponentially with the number of signal streams. Therefore, various demodulation schemes with less complexity have been proposed and some of those schemes show performance close to that of MLD. One kind of those schemes uses a Gibbs sampling (GS) algorithm. GS MIMO detection that combines feedback from turbo decoding has been proposed. In this scheme, the accuracy of GS MIMO detection is improved by feeding back loglikelihood ratios (LLRs) from a turbo decoder. In this paper, GS MIMO detection using only feedback LLRs from a turbo decoder is proposed. Through extrinsic information transfer (EXIT) chart analysis, it is shown that the EXIT curves with and without metrics calculated from received signals overlap as the feedback LLR values increase. Therefore, the proposed scheme calculates the metrics from received signals only for the first GS MIMO detection and the selection probabilities of GS MIMO detection in the following iterations are calculated based only on the LLRs from turbo decoders. Numerical results obtained through computer simulation show that the performance of proposed GS turbo MIMO detection is worse than that of conventional GS turbo MIMO detection when the number of GS iterations is small. However the performance improves as the number of GS iterations increases. When the number of GS iterations is 30 or more, the bit error rate (BER) performance of the proposed scheme is equivalent to that of the conventional scheme. Therefore, the proposed scheme can reduce the computational complexity of selection probability calculation in GS turbo MIMO detection.

Predicting the malfunction timing of wind turbines is essential for maintaining the high profitability of the wind power generation business. Machine learning methods have been studied using condition monitoring system data, such as vibration data, and supervisory control and data acquisition (SCADA) data, to detect and predict anomalies in wind turbines automatically. Autoencoder-based techniques have attracted significant interest in the detection or prediction of anomalies through unsupervised learning, in which the anomaly pattern is unknown. Although autoencoder-based techniques have been proven to detect anomalies effectively using relatively stable SCADA data, they perform poorly in the case of deteriorated SCADA data. In this letter, we propose a power-curve filtering method, which is a preprocessing technique used before the application of an autoencoder-based technique, to mitigate the dirtiness of SCADA data and improve the prediction performance of wind turbine degradation. We have evaluated its performance using SCADA data obtained from a real wind-farm.

Advancements in portable electrocardiographs have allowed electrocardiogram (ECG) signals to be recorded in everyday life. Machine-learning techniques, including deep learning, have been used in numerous studies to analyze ECG signals because they exhibit superior performance to conventional methods. A mobile ECG analysis device is needed so that abnormal ECG waves can be detected anywhere. Such mobile device requires a real-time performance and low power consumption, however, deep-learning based models often have too many parameters to implement on mobile hardware, its amount of hardware is too large and dissipates much power consumption. We propose a design flow to implement the outlier detector using an autoencoder on a low-end FPGA. To shorten the preparation time of ECG data used in training an autoencoder, an unsupervised learning technique is applied. Additionally, to minimize the volume of the weight parameters, a weight sparseness technique is applied, and all the parameters are converted into fixed-point values. We show that even if the parameters are reduced converted into fixed-point values, the outlier detection performance degradation is only 0.83 points. By reducing the volume of the weight parameters, all the parameters can be stored in on-chip memory. We design the architecture according to the CRS format, which is the well-known data structure of a sparse matrix, minimizing the hardware size and reducing the power consumption. We use weight sharing to further reduce the weight-parameter volumes. By using weight sharing, we could reduce the bit width of the memories by 60% while maintaining the outlier detection performance. We implemented the autoencoder on a Digilent Inc. ZedBoard and compared the results with those for the ARM mobile CPU for a built-in device. The results indicated that our FPGA implementation of the outlier detector was 12 times faster and 106 times more energy-efficient.

This paper proposes out-of-bound signal demapping for lattice reduction-aided iterative linear receivers in overloaded MIMO channels. While lattice reduction aided linear receivers sometimes output hard-decision signals that are not contained in the modulation constellation, the proposed demapping converts those hard-decision signals into binary digits that can be mapped onto the modulation constellation. Even though the proposed demapping can be implemented with almost no additional complexity, the proposed demapping achieves more gain as the linear reception is iterated. Furthermore, we show that the transmission performance depends on bit mapping in modulations such as the Gray mapping and the natural mapping. The transmission performance is confirmed by computer simulation in a 6 × 2 MIMO system, i.e., the overloading ratio of 3. One of the proposed demapping called “modulo demapping” attains a gain of about 2 dB at the packet error rate (PER) of 10-1 when the 64QAM is applied.

Advanced information-processing services such as computer vision require a high-performance digital circuit to perform high-load processing at high speed. To achieve high-speed processing, several image-processing applications use an approximate computing technique to reduce idle time of the circuit. However, it is difficult to design the high-speed image-processing circuit while controlling the error rate so as not to degrade service quality, and this technique is used for only a few applications. In this paper, we propose a method that achieves high-speed processing effectively in which processing time for each task is changed by roughly detecting its completion. Using this method, a high-speed processing circuit with a low error rate can be designed. The error rate is controllable, and a circuit design method to minimize the error rate is also presented in this paper. To confirm the effectiveness of our proposal, a ripple-carry adder (RCA), 2-dimensional discrete cosine transform (2D-DCT) circuit, and histogram of oriented gradients (HOG) feature calculation circuit are evaluated. Effective clock periods of these circuits obtained by our method with around 1% error rate are improved about 64%, 6%, and 12%, respectively, compared with circuits without error. Furthermore, the impact of the miscalculation on a video monitoring service using an object detection application is investigated. As a result, more than 99% of detection points required to be obtained are detected, and it is confirmed the miscalculation hardly degrades the service quality.

Source retrieval is the primary task of plagiarism detection. It searches the documents that may be the sources of plagiarism to a suspicious document. The state-of-the-art approaches usually rely on the classical information retrieval models, such as the probability model or vector space model, to get the plagiarism sources. However, the goal of source retrieval is to obtain the source documents that contain the plagiarism parts of the suspicious document, rather than to rank the documents relevant to the whole suspicious document. To model the “partial matching” between documents, this paper proposes a Partial Matching Convolution Neural Network (PMCNN) for source retrieval. In detail, PMCNN exploits a sequential convolution neural network to extract the plagiarism patterns of contiguous text segments. The experimental results on PAN 2013 and PAN 2014 plagiarism source retrieval corpus show that PMCNN boosts the performance of source retrieval significantly, outperforming other state-of-the-art document models.

This paper proposes a change detection method for buildings based on convolutional neural networks. The proposed method detects building changes from pairs of optical aerial images and past map information concerning buildings. Using high-resolution image pair and past map information seamlessly, the proposed method can capture the building areas more precisely compared to a conventional method. Our experimental results show that the proposed method outperforms the conventional change detection method that uses optical aerial images to detect building changes.

Laser speech detection uses a non-contact Laser Doppler Vibrometry (LDV)-based acoustic sensor to obtain speech signals by precisely measuring voice-generated surface vibrations. Over long distances, however, the detected signal is very weak and full of speckle noise. To enhance the quality and intelligibility of the detected signal, we designed a two-sided Linear Prediction Coding (LPC)-based locator and interpolator to detect and replace speckle noise. We first studied the characteristics of speckle noise in detected signals and developed a binary-state statistical model for speckle noise generation. A two-sided LPC-based locator was then designed to locate the polluted samples, composed of an inverse decorrelator, nonlinear filter and threshold estimator. This greatly improves the detectability of speckle noise and avoids false/missed detection by improving the noise-to-signal-ratio (NSR). Finally, samples from both sides of the speckle noise were used to estimate the parameters of the interpolator and to code samples for replacing the polluted samples. Real-world speckle noise removal experiments and simulation-based comparative experiments were conducted and the results show that the proposed method is better able to locate speckle noise in laser detected speech and highly effective at replacing it.

Since most sensor data depend on each other, time-series anomaly detection is one of practical applications of IoT devices. Such tasks are handled by Recurrent Neural Networks (RNNs) with a feedback structure, such as Long Short Term Memory. However, their learning phase based on Stochastic Gradient Descent (SGD) is computationally expensive for such edge devices. This issue is addressed by executing their learning on high-performance server machines, but it introduces a communication overhead and additional power consumption. On the other hand, Recursive Least-Squares Echo State Network (RLS-ESN) is a simple RNN that can be trained at low cost using the least-squares method rather than SGD. In this paper, we propose its area-efficient hardware implementation for edge devices and adapt it to human activity anomaly detection as an example of interdependent time-series sensor data. The model is implemented in Verilog HDL, synthesized with a 45 nm process technology, and evaluated in terms of the anomaly capability, hardware amount, and performance. The evaluation results demonstrate that the RLS-ESN core with a feedback structure is more robust to hyper parameters than an existing Online Sequential Extreme Learning Machine (OS-ELM) core. It consumes only 1.25 times larger hardware amount and 1.11 times longer latency than the existing OS-ELM core.

We previously developed a new terahertz (THz) wave detection method that utilizes the effect of nonlinear optical (NLO) polymers. The new method provided us with a gapless detection, a wide detection bandwidth, and a simpler optical geometry in the THz wave detection. In this paper, polarization dependences in THz wave detection by the Stark effect were investigated. The projection model was employed to analyze the polarization dependences and the consistency with experiments was observed qualitatively, surely supporting the use of the first-order Stark effect in this method. The relations between THz wave detection by the Stark effect and Stark spectroscopy or electroabsorption spectroscopy are also discussed.

With the development of the Internet of Vehicles, License plate detection technology is widely used, e.g., smart city and edge senor monitor. However, traditional license plate detection methods are based on the license plate edge detection, only suitable for limited situation, such as, wealthy light and favorable camera's angle. Fortunately, deep learning networks represented by YOLOv3 can solve the problem, relying on strict condition. Although YOLOv3 make it better to detect large targets, its low performance in detecting small targets and lack of the real-time interactively. Motivated by this, we present a faster and lightweight YOLOv3 model for multi-vehicle or under-illuminated images scenario. Generally, our model can serves as a guideline for optimizing neural network in multi-vehicle scenario.

In this letter, a two-stage QR decomposition scheme based on Givens rotation with novel modified real-value decomposition (RVD) is presented. With the modified RVD applied to the result from complex Givens rotation at first stage, the number of non-zero terms needed to be eliminated by real Givens rotation at second stage decreases greatly and the computational complexity is thereby reduced significantly compared to the decomposition scheme with the conventional RVD. Besides, the proposed scheme is suitable for the hardware design of QR decomposition. Evaluation shows that the proposed QR decomposition scheme is superior to the related works in terms of computational complexity.

Automatic tracking and classification are essential for studying the behaviors of wild animals. Owing to dynamic far-shooting photos, the occlusion problem, protective coloration, the background noise is irregular interference for designing a computerized algorithm for reducing human labeling resources. Moreover, wild dolphin images are hard-acquired by on-the-spot investigations, which takes a lot of waiting time and hardly sets the fixed camera to automatic monitoring dolphins on the ocean in several days. It is challenging tasks to detect well and classify a dolphin from polluted photos by a single famous deep learning method in a small dataset. Therefore, in this study, we propose a generic Cascade Small Object Detection (CSOD) algorithm for dolphin detection to handle small object problems and develop visualization to backbone based classification (V2BC) for removing noise, highlighting features of dolphin and classifying the name of dolphin. The architecture of CSOD consists of the P-net and the F-net. The P-net uses the crude Yolov3 detector to be a core network to predict all the regions of interest (ROIs) at lower resolution images. Then, the F-net, which is more robust, is applied to capture the ROIs from high-resolution photos to solve single detector problems. Moreover, a visualization to backbone based classification (V2BC) method focuses on extracting significant regions of occluded dolphin and design significant post-processing by referencing the backbone of dolphins to facilitate for classification. Compared to the state of the art methods, including faster-rcnn, yolov3 detection and Alexnet, the Vgg, and the Resnet classification. All experiments show that the proposed algorithm based on CSOD and V2BC has an excellent performance in dolphin detection and classification. Consequently, compared to the related works of classification, the accuracy of the proposed designation is over 14% higher. Moreover, our proposed CSOD detection system has 42% higher performance than that of the original Yolov3 architecture.