• ETRI Journal
• /
• v.38 no.6
• /
• pp.1074-1084
• /
• 2016

This paper presents a transmission method for improving human body communications in terms of spectral efficiency, and the performances of bit-error-rate (BER) and frame synchronization, with a highly simplified structure. Compared to the conventional frequency selective digital transmission supporting IEEE standard 802.15.6 for wireless body area networks, the proposed scheme improves the spectral efficiency from 0.25 bps/Hz to 1 bps/Hz based on the 3-dB bandwidth of the transmit spectral mask, and the signal-to-noise-ratio (SNR) by 0.51 dB at a BER of $10^{-6}$ with an 87.5% reduction in the detection complexity of the length of the Hamming distance computation. The proposed preamble structure using its customized detection algorithm achieves perfect frame synchronization at the SNR of a BER of $10^{-6}$ by applying the proposed pre-processing to compensate for the distortions on the preamble signals due to the band-limit effects by transmit and receive filters.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.224-230
• /
• 2015

This manuscript presents a real-time solution for 3D human body reconstruction with multiple RGB-D cameras. The proposed system uses four consumer RGB/Depth (RGB-D) cameras, each located at approximately $90^{\circ}$ from the next camera around a freely moving human body. A single mesh is constructed from the captured point clouds by iteratively removing the estimated overlapping regions from the boundary. A cell-based mesh construction algorithm is developed, recovering the 3D shape from various conditions, considering the direction of the camera and the mesh boundary. The proposed algorithm also allows problematic holes and/or occluded regions to be recovered from another view. Finally, calibrated RGB data is merged with the constructed mesh so it can be viewed from an arbitrary direction. The proposed algorithm is implemented with general-purpose computation on graphics processing unit (GPGPU) for real-time processing owing to its suitability for parallel processing.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.5
• /
• pp.374-379
• /
• 2004

This paper proposes an algorithm for human sensibility evaluation using 4-channel EEG signals of the prefrontal and the parietal lobes. The algorithm uses an artificial neural network and the multiple templates. The linear prediction coefficients are used as the feature parameters of human sensibility. Comfortableness for chairs and temperature/humidity are evaluated. Many conventional researches have emphasized that a wave of left prefrontal lobe is activated in case of positive sensibility and that of right prefrontal lobe is activated in case of negative sensibility. So the power ratio of a wave is obtained from FFT computation and the results are compared. The results of the comfortableness evaluation for temperature and humidity showed that the outputs of the proposed algorithm coincided with corresponding sensibilities depending on the task of the temperature and the humidity. The . conventional method using a wave is hardly related with comfortableness. And it is also observed that the uncomfortable state due to the high temperature and humidity can be easily changed to the comfortable state by small drop of the temperature and the humidity. It seems to be good results to get 66.7％ of evaluation performance in spite of using EEG and the subject independent approach.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.5
• /
• pp.467-474
• /
• 2019

In this paper, we propose a novel method to improve FPS while maintaining the accuracy of YOLO v2 model in NVIDIA Jetson TX1. In general, in order to reduce the amount of computation, a conversion to an integer operation or reducing the depth of a network have been used. However, the accuracy of recognition can be deteriorated. So, we use methods to reduce computation and memory consumption through adjustment of the filter size and integrated computation of the network The first method is to replace the $3{\times}3$ filter with a $1{\times}1$ filter, which reduces the number of parameters to one-ninth. The second method is to reduce the amount of computation through CBR (Convolution-Add Bias-Relu) among the inference acceleration functions of TensorRT, and the last method is to reduce memory consumption by integrating repeated layers using TensorRT. For the simulation results, although the accuracy is decreased by 1% compared to the existing YOLO v2 model, the FPS has been improved from the existing 3.9 FPS to 11 FPS.

• Journal of Advanced Navigation Technology
• /
• v.25 no.4
• /
• pp.299-304
• /
• 2021

Existing human activity recognition systems detect activities through devices such as wearable sensors and cameras. However, these methods require additional devices and costs, especially for cameras, which cause privacy issue. Using WiFi signals that are already installed can solve this problem. In this paper, we propose a CNN-based human activity recognition system using channel state information of WiFi signals, and present results of designing and implementing accelerated hardware structures. The system defined four possible behaviors during studying in indoor environments, and classified the channel state information of WiFi using convolutional neural network (CNN), showing and average accuracy of 91.86%. In addition, for acceleration, we present the results of an accelerated hardware structure design for fully connected layer with the highest computation volume on CNN classifiers. As a result of performance evaluation on FPGA device, it showed 4.28 times faster calculation time than software-based system.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.455-458
• /
• 2009

The statistical wisp model for hairstyle generation was introduced in [1]. It provided a program to load human models, set parameters, generate wisps and strands, and make constraints. However, the program used hard-coded human models and prescribed constraints so that it was hard to change different models and manipulate constraints. Hence we provide a simple interface by drawing maps and constraints. Also, we can increase the speed of computation by using GPU acceleration.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.9
• /
• pp.1402-1408
• /
• 2017

Recently, services for personal biometric data analysis based on real-time monitoring systems has been increasing and many of them have focused on recognition of emotions. In this paper, we propose a classification model to classify anxiety emotion using biometric data actually collected from people. We propose to deploy the support vector machine to build a classification model. In order to improve the classification accuracy, we propose two data pre-processing procedures, which are normalization and data deletion. The proposed algorithms are actually implemented based on Real-time Traffic Flow Measurement structure, which consists of data collection module, data preprocessing module, and creating classification model module. Our experiment results show that the proposed classification model can infers anxiety emotions of people with the accuracy of 65.18%. Moreover, the proposed model with the proposed pre-processing techniques shows the improved accuracy, which is 78.77%. Therefore, we can conclude that the proposed classification model based on the pre-processing process can improve the classification accuracy with lower computation complexity.

• Journal of Biosystems Engineering
• /
• v.39 no.3
• /
• pp.174-183
• /
• 2014

Purpose: A robust, efficient auto-grading computer vision system for meat carcasses is in high demand by researchers all over the world. In this paper, we discuss our study, in which we developed a system to speed up line processing and provide reliable results for pork grading, comparing the results of our algorithms with visual human subjectivity measurements. Methods: We differentiated fat and lean using an entropic correlation algorithm. We also developed a self-designed robust segmentation algorithm that successfully segmented several porkcut samples; this algorithm can help to eliminate the current issues associated with autothresholding. Results: In this study, we carefully considered the key step of autoextracting lean tissue. We introduced a self-proposed scheme and implemented it in over 200 pork-cut samples. The accuracy and computation time were acceptable, showing excellent potential for use in online commercial systems. Conclusions: This paper summarizes the main results reported in recent application studies, which include modifying and smoothing the lean area of pork-cut sections of commercial fresh pork by human experts for an auto-grading process. The developed algorithms were implemented in a prototype mobile processing unit, which can be implemented at the pork processing site.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.6
• /
• pp.606-611
• /
• 2014

The understanding of another's behavior is a fundamental cognitive ability for primates including humans. Recent neuro-physiological studies suggested that there is a direct matching algorithm from visual observation onto an individual's own motor repertories for interpreting cognitive ability. The mirror neurons are known as core regions and are handled as a functionality of intent recognition on the basis of imitative learning of an observed action which is acquired from visual-information of a goal-directed action. In this paper, we addressed previous works used to model the function and mechanisms of mirror neurons and proposed a computational model of a mirror neuron system which can be used in human-robot interaction environments. The major focus of the computation model is the reproduction of an individual's motor repertory with different embodiments. The model's aim is the design of a continuous process which combines sensory evidence, prior task knowledge and a goal-directed matching of action observation and execution. We also propose a biologically inspired plausible equation model.

• Journal of information and communication convergence engineering
• /
• v.16 no.2
• /
• pp.130-134
• /
• 2018

Wireless capsule endoscopy (WCE) is considered as recent technology for the detection cancer cells in the human digestive system. WCE sends the captured information from inside the body to a sensor on the skin surface through a wireless medium. In WCE, the design of low-power consumption devices is a challenging topic. In the Shannon-Nyquist sampling theorem, the number of samples should be at least twice the highest transmission frequency to reconstruct precise signals. The number of samples is proportional to the power consumption in wireless communication. This paper proposes compressive sensing as a method to reduce power consumption in WCE, by means of a trade-off between samples and reconstruction accuracy. The proposed scheme is validated under channel constraints, expressed as the realistic human body path loss. The results show that the proposed scheme achieves a significant reduction in WCE power consumption and achieves a faster computation time with low signal error reconstruction.