• 전자공학회논문지B
• /
• 제33B권7호
• /
• pp.173-182
• /
• 1996

In this paper, we propose the parallel, self-organizing, hierarchical neural netowrks as a handwritten digit recognition system. This system can absorb the various shape variations of handwritten digits by using the different methods of extracting the features in each stage neural network (SNN) of the PSHNN, and can reduce training time by using the single layer neural network as the SNN, and can obtain high rate of correct recognition by using the certainty area in all the output nodes individually. experiments have been performed with NIST database. In which we use 21, 315 digits (10, 625 digits for training and 10,663 digits for testing). The results show that the correct rate is 97.48% the error rate is 1.72% and the reject rate is 0.78%.

• The Korean Journal of Pain
• /
• 제35권2호
• /
• pp.202-208
• /
• 2022

Background: Neurolytic celiac plexus block (NCPB) is a typical treatment for severe epigastric cancer pain, but the therapeutic effect is often affected by the variation of local anatomical structures induced by the tumor. Greater and lesser splanchnic nerve neurolysis (SNN) had similar effects to the NCPB, and was recently performed with a paravertebral approach under the image guidance, or with the transdiscal approach under the guidance of computed tomography. This study observed the feasibility and safety of SNN via a transdiscal approach under fluoroscopic guidance. Methods: The follow-up records of 34 patients with epigastric cancer pain who underwent the splanchnic nerve block via the T11-12 transdiscal approach under fluoroscopic guidance were investigated retrospectively. The numerical rating scale (NRS), the patient satisfaction scale (PSS) and quality of life (QOL) of the patient, the dose of morphine consumed, and the occurrence and severity of adverse events were recorded preoperatively and 1 day, 1 week, 1 month, and 2 months after surgery. Results: Compared with the preoperative scores, the NRS scores and daily morphine consumption decreased and the QOL and PSS scores increased at each postoperative time point (P < 0.001). No patients experienced serious complications. Conclusions: SNN via the transdiscal approach under flouroscopic guidance was an effective, safe, and easy operation for epigastric cancer pain, with fewer complications.

• 한국인터넷방송통신학회논문지
• /
• 제22권3호
• /
• pp.69-74
• /
• 2022

뉴로모픽 아키텍처에서 동작하는 SNN (Spiking Neural Network) 은 인간의 신경망을 모방하여 만들어졌다. 뉴로모픽 아키텍처 기반의 뉴로모픽 컴퓨팅은 GPU를 이용한 딥러닝 기법보다 상대적으로 낮은 전력을 요구한다. 이와 같은 이유로 뉴로모픽 아키텍처를 이용하여 다양한 인공지능 모델을 지원하고자 하는 연구가 활발히 일어나고 있다. 본 논문에서는 음성 데이터 전처리 기법에 따른 뉴로모픽 아키텍처 기반의 음성 인식 모델의 성능 분석을 진행하였다. 실험 결과 푸리에 변환 기반 음성 데이터 전처리시 최대 84% 정도의 인식 정확도 성능을 보임을 확인하였다. 따라서 뉴로모픽 아키텍처 기반의 음성 인식 서비스가 효과적으로 활용될 수 있음을 확인하였다.

• 전자공학회논문지B
• /
• 제31B권1호
• /
• pp.88-98
• /
• 1994

A new neural network architecture called the Parallel. Self-Organizing Hierarchical Neural Network (PSHNN) is presented. The new architecture involves a number of stages in which each stage can be a particular neural network (SNN). The experiments performed in comparison to multi-layered network with backpropagation training and indicated the superiority of the new architecture in the sense of classification accuracy, training time,parallelism.

• 한국인터넷방송통신학회논문지
• /
• 제21권5호
• /
• pp.71-77
• /
• 2021

최근 이질적인 하드웨어 특성을 고려한 IoT 응용 지원 프레임워크의 효율적인 프로그램 개발이 요구되고 있다. 또한, 인간의 뇌를 모사하여 스스로 학습 및 자율적 컴퓨팅이 가능한 뉴로모픽 아키텍처의 발전으로 하드웨어 지원의 범위가 넓어지고 있다. 하지만 기존 대부분의 IoT 통합개발환경에서는 AI(Artificial Intelligence) 기능을 지원하거나 뉴로모픽 아키텍처와 같은 다양한 하드웨어와 결합된 서비스 지원이 어렵다. 본 논문에서는 2세대 인공 신경망 및 3세대 스파이킹 신경망 모델을 모두 지원하는 AI 컴포넌트 추상화 모델을 설계하고 제안 모델 기반의 자율형 IoT 통합개발환경을 구현하였다. IoT 개발자는 AI 및 스파이킹 신경망에 대한 지식이 없어도 제안 기법을 통해 자동으로 AI 컴포넌트를 생성할 수 있으며 런타임에 따라 코드 변환이 유연하여 개발 생산성이 높다. 제안 기법의 실험을 진행하여 가상 컴포넌트 계층으로 인한 변환 지연시간이 발생할 수 있으나 차이가 크지 않음을 확인하였다.

• 전자통신동향분석
• /
• 제35권3호
• /
• pp.76-84
• /
• 2020

Neuromorphic hardware refers to brain-inspired computers or components that model an artificial neural network comprising densely connected parallel neurons and synapses. The major element in the widespread deployment of neural networks in embedded devices are efficient architecture for neuromorphic hardware with regard to performance, power consumption, and chip area. Spiking neural networks (SiNNs) are brain-inspired in which the communication among neurons is modeled in the form of spikes. Owing to brainlike operating modes, SNNs can be power efficient. However, issues still exist with research and actual application of SNNs. In this issue, we focus on the technology development cases and market trends of two typical tracks, which are listed above, from the point of view of artificial intelligence neuromorphic circuits and subsequently describe their future development prospects.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권2호
• /
• pp.157-163
• /
• 2005

In this paper, we present the multimodal system based on the fusion of two user-friendly biometric modalities: Iris and Face. In order to reach robust identification and verification we are going to combine two different biometric features. we specifically apply 2-D discrete wavelet transform to extract the feature sets of low dimensionality from iris and face. And then to obtain Reduced Joint Feature Vector(RJFV) from these feature sets, Direct Linear Discriminant Analysis (DLDA) is used in our multimodal system. In addition, the Synergetic Neural Network(SNN) is used to obtain matching score of the preprocessed data. This system can operate in two modes: to identify a particular person or to verify a person's claimed identity. Our results for both cases show that the proposed method leads to a reliable person authentication system.

• Journal of Astronomy and Space Sciences
• /
• 제33권4호
• /
• pp.313-318
• /
• 2016

Communication, Ocean And Meteorological Satellite (COMS) Meteorological Imager (MI) images are processed for radiometric and geometric correction from raw image data. When intermediate image data are matched and compared with reference landmark images in the geometrical correction process, various techniques for edge detection can be applied. It is essential to have a precise and correct edged image in this process, since its matching with the reference is directly related to the accuracy of the ground station output images. An edge detection method based on neural networks is applied for the ground processing of MI images for obtaining sharp edges in the correct positions. The simulation results are analyzed and characterized by comparing them with the results of conventional methods, such as Sobel and Canny filters.

• 스마트미디어저널
• /
• 제11권2호
• /
• pp.77-83
• /
• 2022

뉴로모픽 아키텍처는 스파이킹 신경망(SNN, Spiking Neural Network) 모델을 사용하여, 추론 실험을 통해 스파이크 값이 많이 누적될수록 정확한 결과를 도출한다. 추론 결과가 특정 값으로 수렴할 경우, 추론 실험을 더 진행해도 결과의 변화가 작아 소비 전력이 더 커질 수 있다. 특히, 인공지능 기반 IoT 환경에서는 전력 낭비는 큰 문제가 될 수 있다. 따라서 본 논문에서는 뉴로모픽 아키텍처 환경에서 추론 이미지 노출 시간을 조절하여 추론 시간을 단축함으로써 인공지능 기반 IoT의 전력 낭비를 줄이는 기법을 제안한다. 제안한 기법은 추론 정확도의 변화를 반영하여 다음 추론 이미지 노출 시간을 계산한다. 또한, 추론 정확도의 변화량 반영비율을 계수 값으로 조절할 수 있으며, 다양한 계수 값의 비교 실험을 통해 최적의 계수 값을 찾는다. 제안한 기법은 목표 정확도에 해당하는 추론 이미지 노출 시간은 선형 기법보다 크지만 최종 추론 시간은 선형 기법보다 적다. 제안한 기법의 성능을 측정하고 평가한 결과, 제안한 기법을 적용한 추론 실험이 선형 기법을 적용한 추론 실험보다 최종 노출 시간을 약 90% 단축할 수 있음을 확인한다.

• 센서학회지
• /
• 제29권1호
• /
• pp.68-73
• /
• 2020

This paper proposes an asynchronous circuit design methodology using a new Single Gate Sleep Convention Logic (SG-SCL) with advantages such as low area overhead, low power consumption compared with the conventional null convention logic (NCL) methodologies. The delay-insensitive NCL asynchronous circuits consist of dual-rail structures using {DATA0, DATA1, NULL} encoding which carry a significant area overhead by comparison with single-rail structures. The area overhead can lead to high power consumption. In this paper, the proposed single gate SCL deploys a power gating structure for a new {DATA, SLEEP} encoding to achieve low area overhead and low power consumption maintaining high performance during DATA cycle. In this paper, the proposed methodology has been evaluated by a liquid state machine (LSM) for pattern and digit recognition using FPGA and a 0.18 ㎛ CMOS technology with a supply voltage of 1.8 V. the LSM is a neural network (NN) algorithm similar to a spiking neural network (SNN). The experimental results show that the proposed SG-SCL LSM reduced power consumption by 10% compared to the conventional LSM.