We propose an efficient hand gesture recognition (HGR) algorithm, which can cope with time-dependent data from inertial measurement unit (IMU) sensor and support real-time learning for various human-machine interface (HMI) applications. Although the extracted IMU sensors are time-dependent, most existing HGR algorithms do not consider this characteristic, results in degradation of performance. Because dynamic time warping (DTW) technique considers characteristic data, performance DTW-based...

Recently, human-machine interfaces (HMI) that make life convenient have been studied in many fields. In particular, a hand gesture recognition (HGR) system, which can be implemented as wearable has the advantage users easily and intuitively control device. Among various sensors used HGR surface electromyography (sEMG) sensor is independent of acquisition environment, easy to wear, requires small amount data. Focusing on these advantages, previous sEMG-based systems several or complex...

Most approaches for moving object detection (MOD) based on computer vision are limited to stationary camera environments. In advanced driver assistance systems (ADAS), however, ego-motion is added image frames owing the use of a camera. This results in mixed motion and makes it difficult classify target objects background. this paper, we propose an efficient MOD algorithm that can cope with addition, present hardware design implementation real-time processing proposed algorithm. The detector...

In this paper, we propose an efficient algorithm for reducing the computational complexity of dynamic time warping (DTW) obtaining similarity measures between series. The DTW technique exhibits superior classification accuracy compared to other algorithms but has a limitation high complexity. To reduce standard DTW, constrained and fast techniques have been proposed. reduces by only considering limited alignments prevent excessive two series, which can overall accuracy. However, since...

In this paper, we propose an area-efficient short-time Fourier transform (STFT) processor that can perform time–frequency analysis of non-stationary signals in real time, which is essential for voice or radar-signal processing systems. STFT processors consist a windowing module and fast processor. The length the window function related to resolution, required varies depending on application. addition, needs overlap input data samples minimize loss boundary, ratios 25%, 50%, 75% are generally...

Hand gesture recognition, which is one of the fields human–computer interaction (HCI) research, extracts user’s pattern using sensors. Radio detection and ranging (RADAR) sensors are robust under severe environments convenient to use for hand gestures. The existing studies mostly adopted continuous-wave (CW) radar, only shows a good performance at fixed distance, due its limitation not seeing distance. This paper proposes recognition system that utilizes frequency-shift keying (FSK) allowing...

In this paper, we propose a new efficient FFT algorithm for OFDM/DMT applications and present its pipeline implementation results. Since the proposed is based on radix-4 butterfly unit, processing rate can be twice as fast that radix-23 algorithm. Also, more area-efficient than from conventional due to reduced number of nontrivial multipliers like using radix-2/sup 3/ order compare with algorithm, 64-point MDC pipelined processor was implemented. After logic synthesis 0.35 /spl mu/m CMOS...

Accidents caused by falls among the elderly have become a significant social issue, making fall detection systems increasingly needed. Fall such as internet of things (IoT) devices must be affordable and compact because they installed in various locations around house, bedrooms, living rooms, bathrooms. In this study, we propose lightweight method using continuous-wave (CW) radar sensor binarized neural network (BNN) to meet these requirements. We used CW sensor, which is more than other...

This paper presents a backprojection algorithm (BPA) accelerator implemented on field-programmable gate array (FPGA) for circular synthetic aperture radar (SAR) systems. Although the BPA offers superior image quality, it requires significantly more computation and is memory intensive, necessitating hardware optimization. In particular, accumulates data, leading to high requirements that must be reduced embedded system implementation. To address this issue, we optimized floating-point (FP)...

Precise time-of-arrival (TOA) estimation is one of the most important techniques in RF-based positioning systems that use wireless sensor networks (WSNs). Because accuracy TOA proportional to RF signal bandwidth, using broad bandwidth fundamental approach for achieving higher accuracy. Hence, ultra-wide-band (UWB) with a 500 MHz are commonly used. However, suffer from disadvantages high complexity and power consumption. Therefore, it difficult employ such various WSN applications. In this...

In this paper, a method to detect frames was described that can be used as hand gesture data when configuring real-time recognition system using continuous wave (CW) radar. Detecting valid raises accuracy which recognizes gestures. Therefore, it is essential in the CW The conventional research on systems has not been conducted detecting frames. We took R-wave electrocardiogram (ECG) detection method. probability of 85.04%. It low use system. proposal consists 2-stages improve accuracy....

This paper presents the design and implementation results of an efficient fast Fourier transform (FFT) processor for frequency-modulated continuous wave (FMCW) radar signal processing. The proposed FFT is designed with a memory-based architecture supports variable lengths from 64 to 4096. Moreover, it floating-point operator prevent performance degradation fixed-point operators. FMCW processing requires windowing operations increase target detection rate by reducing clutter side lobes,...

Synthetic aperture radar (SAR), which can generate images of regions or objects, is an important research area radar. The chirp scaling algorithm (CSA) a representative SAR imaging algorithm. CSA has simple structure comprising phase compensation and fast Fourier transform (FFT) operations by replacing interpolation for range cell migration correction (RCMC) with compensation. However, real-time processing still requires many computations long execution time. Therefore, it necessary to...

The constant false-alarm rate (CFAR) algorithm is essential for detecting targets during radar signal processing. It has been improved to accurately detect targets, especially in nonhomogeneous environments, such as multitarget or clutter edge environments. For example, there are sort-based and variable index-based algorithms. However, these algorithms require large amounts of computation, making them difficult apply applications that real-time target detection. We propose a new CFAR...

In this brief, we present the design and implementation results of a digital 120 Mb/s multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) wireless LAN (WLAN) baseband processor based on proposed decoding algorithms. The has two MIMO-OFDM modes, space-frequency block coded OFDM space division multiplexed OFDM. From those, it achieves considerable performance gain as well supports double data rates compared to conventional IEEE 802.11a WLANs. evaluation,...

A design for an integer motion estimator of high-efficiency video coding (HEVC) is presented. HEVC supports the 64 × tree unit, recursive quad-tree unit structure and asymmetric motion-partitioning mode in a high compression ratio. These features require estimation that more complex than H.264/AVC. The new structures memory read controller sum absolute difference (SAD) summation block are proposed. reduces internal time, SAD mode. proposed implemented Verilog HDL synthesised using 65 nm CMOS...

In this paper, we propose a method for reconstructing synthetic aperture radar (SAR) images by applying compressive sensing (CS) technique to sparsely acquired sensor data. general, SAR image reconstruction algorithms require data at regular spatial intervals. However, when the speed of radar-equipped platform is not constant, it difficult consistently perform acquisitions. Therefore, used CS-based signal recovery efficiently reconstruct even acquisition was performed. proposed method,...

The estimation of signal parameters via rotational invariance techniques (ESPRIT) is an algorithm that uses the shift-invariant properties array antenna to estimate direction-of-arrival (DOA) signals received in antenna. Since ESPRIT requires high-complexity operations such as covariance matrix and eigenvalue decomposition, a hardware processor must be implemented DOA estimated real time. Additionally, should support scalable number configuration for various applications because performance...

Binary neural networks (BNNs) have attracted significant interest for the implementation of deep (DNNs) on resource-constrained edge devices, and various BNN accelerator architectures been proposed to achieve higher efficiency. accelerators can be divided into two categories: streaming layer accelerators. Although designed a specific network topology provide high throughput, they are infeasible sensor applications in AI because their complexity inflexibility. In contrast, with reasonable...

This paper proposes a high-speed continuous wavelet transform (CWT) processor to analyze vital signals extracted from frequency-modulated wave (FMCW) radar sensor. The proposed CWT consists of fast Fourier (FFT) module, complex multiplier and inverse FFT (IFFT) module. For high-throughput processing, the IFFT modules are designed with pipeline architecture radix-2 single-path delay feedback (R2SDF) mixed-radix multipath commutator (MRMDC) architecture, respectively. In addition, module...

As various unmanned autonomous driving technologies such as vehicles and drones are being developed, research on FMCW radar, a sensor related to these technologies, is actively conducted. The range resolution, which parameter for accurately detecting an object in the radar system, depends modulation bandwidth. Expensive radars have large bandwidth, use band above 77 GHz, mainly used in-vehicle sensors. However, high-performance disadvantage of expensive burdensome areas that require precise...

This paper presents an efficient technique to considerably reduce pseudonoise (PN) code acquisition time by adjusting threshold values, depending on the pre-estimated correlation energy in direct-sequence spread spectrum (DS-SS) systems. The proposed utilizing a generation mode (TM) prior search is employed conventional double-dwell serial-search algorithm, and TM determines values of both verification modes, its energy. We present mathematical model scheme analyze it with respect mean...

In this brief, a low-complexity hardware architecture for multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) symbol detectors with two transmit and receive antennas is proposed. The support MIMO-OFDM schemes of space-frequency block coded OFDM space-division in order to achieve higher performance throughput. However, detection processes these have high computational complexity, which burden implementation detectors. reduce the proposed detector designed...