• 제목/요약/키워드: Self-Tuning

검색결과 435건 처리시간 0.024초

A Configurable Software-based Approach for Detecting CFEs Caused by Transient Faults

  • Liu, Wei;Ci, LinLin;Liu, LiPing
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권5호
    • /
    • pp.1829-1846
    • /
    • 2021
  • Transient faults occur in computation units of a processor, which can cause control flow errors (CFEs) and compromise system reliability. The software-based methods perform illegal control flow detection by inserting redundant instructions and monitoring signature. However, the existing methods not only have drawbacks in terms of performance overhead, but also lack of configurability. We propose a configurable approach CCFCA for detecting CFEs. The configurability of CCFCA is implemented by analyzing the criticality of each region and tuning the detecting granularity. For critical regions, program blocks are divided according to space-time overhead and reliability constraints, so that protection intensity can be configured flexibly. For other regions, signature detection algorithms are only used in the first basic block and last basic block. This helps to improve the fault-tolerant efficiency of the CCFCA. At the same time, CCFCA also has the function of solving confusion and instruction self-detection. Our experimental results show that CCFCA incurs only 10.61% performance overhead on average for several C benchmark program and the average undetected error rate is only 9.29%. CCFCA has high error coverage and low overhead compared with similar algorithms. This helps to meet different cost requirements and reliability requirements.

Form-finding of lifting self-forming GFRP elastic gridshells based on machine learning interpretability methods

  • Soheila, Kookalani;Sandy, Nyunn;Sheng, Xiang
    • Structural Engineering and Mechanics
    • /
    • 제84권5호
    • /
    • pp.605-618
    • /
    • 2022
  • Glass fiber reinforced polymer (GFRP) elastic gridshells consist of long continuous GFRP tubes that form elastic deformations. In this paper, a method for the form-finding of gridshell structures is presented based on the interpretable machine learning (ML) approaches. A comparative study is conducted on several ML algorithms, including support vector regression (SVR), K-nearest neighbors (KNN), decision tree (DT), random forest (RF), AdaBoost, XGBoost, category boosting (CatBoost), and light gradient boosting machine (LightGBM). A numerical example is presented using a standard double-hump gridshell considering two characteristics of deformation as objective functions. The combination of the grid search approach and k-fold cross-validation (CV) is implemented for fine-tuning the parameters of ML models. The results of the comparative study indicate that the LightGBM model presents the highest prediction accuracy. Finally, interpretable ML approaches, including Shapely additive explanations (SHAP), partial dependence plot (PDP), and accumulated local effects (ALE), are applied to explain the predictions of the ML model since it is essential to understand the effect of various values of input parameters on objective functions. As a result of interpretability approaches, an optimum gridshell structure is obtained and new opportunities are verified for form-finding investigation of GFRP elastic gridshells during lifting construction.

SOFM 신경회로망을 이용한 한국어 음소 인식 (Korean Phoneme Recognition Using Self-Organizing Feature Map)

  • 전용구;양진우;김순협
    • 한국음향학회지
    • /
    • 제14권2호
    • /
    • pp.101-112
    • /
    • 1995
  • 본 논문에서는 패턴 매칭 방법에 근거하여 인식 단위가 음소인 음소 기반 인식 시스템을 구성하였다. 선택한 신경망 구조는 생물학적 신경망인 코호넨(T. Kohonen)의 SOFM(Self-Organizing Feature Map)으로 패턴 매칭 과정 중 클러스터러(clusterer)로 사용하였다. SOFM 신경망은 신호 공간에 대해서 최적의 국소(局所) 해부적 사상(local topographical mapping)에 의한 자기 조직화 과정을 수행하며, 그 결과 인식 문제에 있어서 상당히 높은 정확도를 나타낸다. 따라서 SOFM 신경망은 음소 인식에도 효과적으로 응용될 수 있다. 또한 음소 인식 시스템의 성능 향상을 위해 K-means클러스터링 알고리즘이 결합된 학습 알고리즘을 제안하였다. 제안된 음소 인식 시스템의 성능을 평가하기 위해 먼저, 인식 대상음소는 모음군 17개, 자음의 경우 파열음9개, 마찰음 3개, 파찰음 3개, 유음 및 비음 4개, 음소의 성질이 다른 종성 7개의 음소군으로 모두 43개의 음소를 대상으로 실험하였으며, 각 음소군에 대한 특징 지도를 구성하여 레이블러(labeler)의 기능을 수행하게 하였다. 화자 종속 인식 실험 결과 $87.2\%$의 인식률을 보였으며 제안한 학습법의 빠른 수렴성과 인식률 향상을 확인하였다.

  • PDF

Deep Learning-Enabled Detection of Pneumoperitoneum in Supine and Erect Abdominal Radiography: Modeling Using Transfer Learning and Semi-Supervised Learning

  • Sangjoon Park;Jong Chul Ye;Eun Sun Lee;Gyeongme Cho;Jin Woo Yoon;Joo Hyeok Choi;Ijin Joo;Yoon Jin Lee
    • Korean Journal of Radiology
    • /
    • 제24권6호
    • /
    • pp.541-552
    • /
    • 2023
  • Objective: Detection of pneumoperitoneum using abdominal radiography, particularly in the supine position, is often challenging. This study aimed to develop and externally validate a deep learning model for the detection of pneumoperitoneum using supine and erect abdominal radiography. Materials and Methods: A model that can utilize "pneumoperitoneum" and "non-pneumoperitoneum" classes was developed through knowledge distillation. To train the proposed model with limited training data and weak labels, it was trained using a recently proposed semi-supervised learning method called distillation for self-supervised and self-train learning (DISTL), which leverages the Vision Transformer. The proposed model was first pre-trained with chest radiographs to utilize common knowledge between modalities, fine-tuned, and self-trained on labeled and unlabeled abdominal radiographs. The proposed model was trained using data from supine and erect abdominal radiographs. In total, 191212 chest radiographs (CheXpert data) were used for pre-training, and 5518 labeled and 16671 unlabeled abdominal radiographs were used for fine-tuning and self-supervised learning, respectively. The proposed model was internally validated on 389 abdominal radiographs and externally validated on 475 and 798 abdominal radiographs from the two institutions. We evaluated the performance in diagnosing pneumoperitoneum using the area under the receiver operating characteristic curve (AUC) and compared it with that of radiologists. Results: In the internal validation, the proposed model had an AUC, sensitivity, and specificity of 0.881, 85.4%, and 73.3% and 0.968, 91.1, and 95.0 for supine and erect positions, respectively. In the external validation at the two institutions, the AUCs were 0.835 and 0.852 for the supine position and 0.909 and 0.944 for the erect position. In the reader study, the readers' performances improved with the assistance of the proposed model. Conclusion: The proposed model trained with the DISTL method can accurately detect pneumoperitoneum on abdominal radiography in both the supine and erect positions.

전자유압 비례밸브와 경사센서를 이용한 농용 프론트 로더 버켓 능동수평유지 시스템 개발 (Development of a self-leveling system for the bucket of an agricultural front-end loader using an electro hydraulic proportional valve and a tilt sensor)

  • 이창주;하종우;최덕수;김학진
    • 드라이브 ㆍ 컨트롤
    • /
    • 제12권4호
    • /
    • pp.60-70
    • /
    • 2015
  • A front-end loader (FEL) mounted on an agricultural tractor is one of the most commonly used implements for farm work. However, when the tractor carries material using the bucket attached to the FEL on a sloping ground, the materials can spill or roll back over the operator due to the tilted body, thereby requiring the bucket surface to remain level at a constant value regardless of varying slopes. In this study, an active system for controlling the angle of the FEL bucket on a tractor based on the real-time measurement of ground slopes was developed to enable the bucket to constantly remain level. A FEL simulator operated based on an electro hydraulic proportional valve (EHPV) was constructed in the laboratory to develop a proportional-integral-derivative (PID) controller forming a virtual electronic control unit (ECU) on the computer, which could automatically adjust the bucket angles depending on varying input angles while sending SAE-J1939 associated messages via CAN BUS to the EHPV. The different parameter values for the PID controller due to the gravity effect of the bucket were determined using a manual PID tuning method while assuming that the tractor travels on either an ascending slope or a descending slope. The developed PID control-based self-leveling system showed a mean of steady-state errors of within $1^{\circ}$ and a mean of delayed times of ~ 0.8s when the step input of $+20^{\circ}$ was given, implying that the developed system and control algorithm would be effective in maintaining the bucket angle at a certain value. Future studies include the improvement of the control algorithm to reduce such a time delay as well as the application of the developed algorithm to the FEL mounted on a tractor tested at a testing ground.

유기반도체와 절연체 계면제어를 통한 유기전하변조 트랜지스터의 전기적 특성 향상 연구 (Tuning Electrical Performances of Organic Charge Modulated Field-Effect Transistors Using Semiconductor/Dielectric Interfacial Controls)

  • 박은영;오승택;이화성
    • 접착 및 계면
    • /
    • 제23권2호
    • /
    • pp.53-58
    • /
    • 2022
  • 본 연구는 AlOx유전체 표면에 유기 자립조립 단분자막 (self-assembled monolayer, SAM) 중간층을 도입함으로써 유전체의 표면특성을 제어하고, 최종적으로 유기전하변조트랜지스터 (Organic charge modulated field-effect transistor, OCMFET)의 전기적 특성을 향상시킨 결과를 제시하였다. 유기 중간층을 적용함으로써, OCMFET의 컨트롤 게이트(CG, Control gate)와 플로팅 게이트 (FG, Floating gate) 사이 커패시터 플레이트로 작용하는 산화알루미늄 게이트 유전체의 표면 에너지를 제어하였으며, FET의 가장 중요한 성능변수인 전계효과 이동도(field-effect transistor, μFET)를 향상시켰다. 사용된 SAMs은 네가지의 PA (Octadecylphosphonic acid, Butylphosphonic acid, (3-Bromopropyl)phosphonic acid, (3-Aminopropyl) phosphonic acid)를 사용하여 형성하였으며, 각각 0.73, 0.41, 0.34, 0.15 cm2V-1s-1의 μOCMFET를 나타내었다. 이 연구를 통해 유기 SAM 중간층의 알킬 체인(Alkyl chain)의 길이 및 말단기의 특성이 소자의 전기적 성능을 제어하는데 중요한 요인임을 확인하였으며, 이 결과를 통해 향후 최적의 센서 플랫폼으로서의 OCMFET 소자성능 최적화에 기여할 수 있을 것으로 기대한다.

On discrete nonlinear self-tuning control

  • Mohler, R.-R.;Rajkumar, V.;Zakrzewski, R.-R.
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 22-24 Oct. 1991
    • /
    • pp.1659-1663
    • /
    • 1991
  • A new control design methodology is presented here which is based on a nonlinear time-series reference model. It is indicated by highly nonlinear simulations that such designs successfully stabilize troublesome aircraft maneuvers undergoing large changes in angle of attack as well as large electric power transients due to line faults. In both applications, the nonlinear controller was significantly better than the corresponding linear adaptive controller. For the electric power network, a flexible a.c. transmission system (FACTS) with series capacitor power feedback control is studied. A bilinear auto-regressive moving average (BARMA) reference model is identified from system data and the feedback control manipulated according to a desired reference state. The control is optimized according to a predictive one-step quadratic performance index (J). A similar algorithm is derived for control of rapid changes in aircraft angle of attack over a normally unstable flight regime. In the latter case, however, a generalization of a bilinear time-series model reference includes quadratic and cubic terms in angle of attack. These applications are typical of the numerous plants for which nonlinear adaptive control has the potential to provide significant performance improvements. For aircraft control, significant maneuverability gains can provide safer transportation under large windshear disturbances as well as tactical advantages. For FACTS, there is the potential for significant increase in admissible electric power transmission over available transmission lines along with energy conservation. Electric power systems are inherently nonlinear for significant transient variations from synchronism such as may result for large fault disturbances. In such cases, traditional linear controllers may not stabilize the swing (in rotor angle) without inefficient energy wasting strategies to shed loads, etc. Fortunately, the advent of power electronics (e.g., high-speed thyristors) admits the possibility of adaptive control by means of FACTS. Line admittance manipulation seems to be an effective means to achieve stabilization and high efficiency for such FACTS. This results in parametric (or multiplicative) control of a highly nonlinear plant.

  • PDF

최근 등장한 경락기반 심리치료법의 연원에 대한 기초 연구 (The basic study on the origin of recently emerging Meridian-based Psychotherapy)

  • 이정원;김경철
    • 한국한의학연구원논문집
    • /
    • 제18권2호
    • /
    • pp.123-130
    • /
    • 2012
  • Objectives : The purpose of this study is to identify the origin of meridian-based psychotherapy, and thereby utilize this technique more flexibly and widely, as well as use our findings as the base data for the development of unique and oriental medicine-based psychotherapies. Methods : This study investigated various activities and references of meridian-based psychotherapy developers in historical order. For the books that have been translated into Korean, the translated books were examined as priority. Otherwise, examination was based on original books. Results : The study results were as follows. EFT (Emotional Freedom Techniques) is a technique completed by combining the psychological reversal, acupuncture point tapping, and gamut series in TFT (Thought Field Therapy), and the affirmations that were formed by reflecting the deep understanding on languages derived from NLP (Neuro Linguistic Programming). ESM (Emotional Self Management) can be viewed as having applied the implications of cognitive therapy and hypnosis while accepting the treatment of TFT as it is. Roger J. Callahan developed TFT by adopting theories such as AK(Applied Kinesiology), acupuncture, NLP, quantum mechanics, and split brains. On the EFT, ESM, TFT, the method for stimulating acupuncture points appears to be tapping, which is one technique of the oriental traditional exercise and manual techniques(導引按蹻). Tapping may be the English translation of Bak-beop(拍法). Conclusions : When the oriental medicine techniques that enable meridian tuning are applied along with accommodating Western psychological theories actively, this can not only help use meridian-based psychotherapy more flexibly, but also enable the development of new oriental medicine-based psychotherapies.

A Novel Fast Open-loop Phase Locking Scheme Based on Synchronous Reference Frame for Three-phase Non-ideal Power Grids

  • Xiong, Liansong;Zhuo, Fang;Wang, Feng;Liu, Xiaokang;Zhu, Minghua;Yi, Hao
    • Journal of Power Electronics
    • /
    • 제16권4호
    • /
    • pp.1513-1525
    • /
    • 2016
  • Rapid and accurate phase synchronization is critical for the reliable control of grid-tied inverters. However, the commonly used software phase-locked loop methods do not always satisfy the need for high-speed and accurate phase synchronization under severe grid imbalance conditions. To address this problem, this study develops a novel open-loop phase locking scheme based on a synchronous reference frame. The proposed scheme is characterized by remarkable response speed, high accuracy, and easy implementation. It comprises three functional cascaded blocks: fast orthogonal signal generation block, fast fundamental-frequency positive sequence component construction block, and fast phase calculation block. The developed virtual orthogonal signal generation method in the first block, which is characterized by noise immunity and high accuracy, can effectively avoid approximation errors and noise amplification in a wide range of sampling frequencies. In the second block, which is the foundation for achieving fast phase synchronization within 3 ms, the fundamental-frequency positive sequence components of unsymmetrical grid voltages can be achieved with the developed orthogonal signal construction strategy and the symmetrical component method. The real-time grid phase can be consequently obtained in the third block, which is free from self-tuning closed-loop control and thus improves the dynamic performance of the proposed scheme. The proposed scheme is adaptive to severe unsymmetrical grid voltages with sudden changes in magnitude, phase, and/or frequency. Moreover, this scheme is able to eliminate phase errors induced by harmonics and random noise. The validity and utility of the proposed scheme are verified by the experimental results.

디자인의 전유 행위에 대한 고찰 (Consideration over Appropriation Activity of Design)

  • 김양호
    • 한국콘텐츠학회:학술대회논문집
    • /
    • 한국콘텐츠학회 2009년도 춘계 종합학술대회 논문집
    • /
    • pp.993-997
    • /
    • 2009
  • 모더니즘 시대의 디자인은 효율성과 기능성을 중심으로 사물과 기기의 표준화를 목표로 제작되었으며 생산보다 소비가 많았던 산업 시대에서 디자인 수용자의 의지는 소비의 대상으로서의 역할에 한정되어졌다. 그러나 포스트모더니즘 시대 이후 디지털 환경에서 디자인 수용자는 단지 주어진 것만을 수동적으로 수용하지 않고 적극적인 개입을 하고 능동적인 관리를 할 수 있도록 변화됨으로 디자인 수용과정에 우상화, 관여, 조율, 조작, 흉내 등의 전유행위를 수반하게 된다. 앞으로의 디자인은 전문가들만이 생성하고 관리하는 체계에서 벗어나 수용자들과 함께 협업하는 상황으로 변화되고, 수용자의 다양한 전유 형태는 디자인 생산물을 둘러싼 제작 방법, 배포 행위 등의 디자인 제반 환경을 변동시킬 것이다. 이에 디자인 수용자들의 전유 행위를 동일화, 해체화, 재의미화 등으로 구분하여 고찰함으로써 제작자와 수용자간의 원활한 인식을 통해 획일화, 구조화에 저항하는 수용자들의 문화 환경 변화를 읽어 효과적인 디자인 제작 행위를 유도하고자 한다.

  • PDF