• Title/Summary/Keyword: OpenNN

Search Result 23, Processing Time 0.028 seconds

Multiple Discriminative DNNs for I-Vector Based Open-Set Language Recognition (I-벡터 기반 오픈세트 언어 인식을 위한 다중 판별 DNN)

  • Kang, Woo Hyun;Cho, Won Ik;Kang, Tae Gyoon;Kim, Nam Soo
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.41 no.8
    • /
    • pp.958-964
    • /
    • 2016
  • In this paper, we propose an i-vector based language recognition system to identify the spoken language of the speaker, which uses multiple discriminative deep neural network (DNN) models analogous to the multi-class support vector machine (SVM) classification system. The proposed model was trained and tested using the i-vectors included in the NIST 2015 i-vector Machine Learning Challenge database, and shown to outperform the conventional language recognition methods such as cosine distance, SVM and softmax NN classifier in open-set experiments.

Analysis of Tensor Processing Unit and Simulation Using Python (텐서 처리부의 분석 및 파이썬을 이용한 모의실행)

  • Lee, Jongbok
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.19 no.3
    • /
    • pp.165-171
    • /
    • 2019
  • The study of the computer architecture has shown that major improvements in price-to-energy performance stems from domain-specific hardware development. This paper analyzes the tensor processing unit (TPU) ASIC which can accelerate the reasoning of the artificial neural network (NN). The core device of the TPU is a MAC matrix multiplier capable of high-speed operation and software-managed on-chip memory. The execution model of the TPU can meet the reaction time requirements of the artificial neural network better than the existing CPU and the GPU execution models, with the small area and the low power consumption even though it has many MAC and large memory. Utilizing the TPU for the tensor flow benchmark framework, it can achieve higher performance and better power efficiency than the CPU or CPU. In this paper, we analyze TPU, simulate the Python modeled OpenTPU, and synthesize the matrix multiplication unit, which is the key hardware.

Motion Control of a Pneumatic Servo XY-Plotter using Neural Network (신경회로망을 이용한 공압서보 XY-플로터의 운동제어)

  • Hwang, Un-Kyoo;Cho, Seung-Ho
    • Transactions of the Korean Society of Mechanical Engineers A
    • /
    • v.28 no.5
    • /
    • pp.603-609
    • /
    • 2004
  • This paper deals with the issue of Neural Network-based control for a rodless pneumatic cylinder system which is utilized for a pneumatic XY-plotter. In order to identify the system design parameters, the open loop response of a pneumatic rodless cylinder controlled by a pneumatic servovalve is investigated by applying a self-excited oscillation method. Based on the system design parameters, the PD feedback compensator is designed and then Neural Network is incorporated with it. The experiment of a trajectory tracking control using a PD-NN has been performed and proved its excellent performance by comparing with that of a PD feedback compensator.

LQG modeling and GA control of structures subjected to earthquakes

  • Chen, ZY;Jiang, Rong;Wang, Ruei-Yuan;Chen, Timothy
    • Earthquakes and Structures
    • /
    • v.22 no.4
    • /
    • pp.421-430
    • /
    • 2022
  • This paper addresses the stochastic control problem of robots within the framework of parameter uncertainty and uncertain noise covariance. First of all, an open circle deterministic trajectory optimization issue is explained without knowing the unequivocal type of the dynamical framework. Then, a Linear Quadratic Gaussian (LQG) controller is intended for the ostensible trajectory-dependent linearized framework, to such an extent that robust hereditary NN robotic controller made out of the Kalman filter and the fuzzy controller is blended to ensure the asymptotic stability of the non-continuous controlled frameworks. Applicability and performance of the proposed algorithm shown through simulation results in the complex systems which are demonstrate the feasible to improve the performance by the proposed approach.

Stochastic intelligent GA controller design for active TMD shear building

  • Chen, Z.Y.;Peng, Sheng-Hsiang;Wang, Ruei-Yuan;Meng, Yahui;Fu, Qiuli;Chen, Timothy
    • Structural Engineering and Mechanics
    • /
    • v.81 no.1
    • /
    • pp.51-57
    • /
    • 2022
  • The problem of optimal stochastic GA control of the system with uncertain parameters and unsure noise covariates is studied. First, without knowing the explicit form of the dynamic system, the open-loop determinism problem with path optimization is solved. Next, Gaussian linear quadratic controllers (LQG) are designed for linear systems that depend on the nominal path. A robust genetic neural network (NN) fuzzy controller is synthesized, which consists of a Kalman filter and an optimal controller to assure the asymptotic stability of the discrete control system. A simulation is performed to prove the suitability and performance of the recommended algorithm. The results indicated that the recommended method is a feasible method to improve the performance of active tuned mass damper (ATMD) shear buildings under random earthquake disturbances.

High Efficiency Silicon Solar Cell(II)-Computer Modeling on Diffused Silicon Solar Cell (고효율 실리콘 태양전지(II)-확산형 실리콘 태양전지에 대한 모의 실험)

  • 강진영;이종덕
    • Journal of the Korean Institute of Telematics and Electronics
    • /
    • v.18 no.4
    • /
    • pp.49-61
    • /
    • 1981
  • A generally applicable computer simulation program for diffused silicon solar cells has been developed on the basis of the experimental results. The program can be easily used to obtain the spectral response and I-V characteristics for N+P, P+N N+PP+, P+NN+cells by changing various input parameters. The insolated spectra can be taken from AMI and constant intensity and GE - ELH lamp light sources. The options for AR coating are Si3N4 film and materials with constant reflectance including zero reflectance for ideal case. The computer simulation demonstrates successful results compared with the measured values for the short circuit current, open circuit voltage, efficiency, spectral response, quantum efficiency, I-V characteristics, etc. This program was used to optimize doping concentration, cell thickness, light concentration, junction depth, and to obtain the limit values for front surface recornbination velocity, effective carrier life time in the depletion regions and shunt resistance, and also to drive the changing rate in conversion efficiency depending on operation temperature, series resistance and electric field strength in N+P+ bulk regions.

  • PDF

Uncertainty for Privacy and 2-Dimensional Range Query Distortion

  • Sioutas, Spyros;Magkos, Emmanouil;Karydis, Ioannis;Verykios, Vassilios S.
    • Journal of Computing Science and Engineering
    • /
    • v.5 no.3
    • /
    • pp.210-222
    • /
    • 2011
  • In this work, we study the problem of privacy-preservation data publishing in moving objects databases. In particular, the trajectory of a mobile user in a plane is no longer a polyline in a two-dimensional space, instead it is a two-dimensional surface of fixed width $2A_{min}$, where $A_{min}$ defines the semi-diameter of the minimum spatial circular extent that must replace the real location of the mobile user on the XY-plane, in the anonymized (kNN) request. The desired anonymity is not achieved and the entire system becomes vulnerable to attackers, since a malicious attacker can observe that during the time, many of the neighbors' ids change, except for a small number of users. Thus, we reinforce the privacy model by clustering the mobile users according to their motion patterns in (u, ${\theta}$) plane, where u and ${\theta}$ define the velocity measure and the motion direction (angle) respectively. In this case, the anonymized (kNN) request looks up neighbors, who belong to the same cluster with the mobile requester in (u, ${\theta}$) space: Thus, we know that the trajectory of the k-anonymous mobile user is within this surface, but we do not know exactly where. We transform the surface's boundary poly-lines to dual points and we focus on the information distortion introduced by this space translation. We develop a set of efficient spatiotemporal access methods and we experimentally measure the impact of information distortion by comparing the performance results of the same spatiotemporal range queries executed on the original database and on the anonymized one.

Design and Implementation of a Stereoscopic Image Control System based on User Hand Gesture Recognition (사용자 손 제스처 인식 기반 입체 영상 제어 시스템 설계 및 구현)

  • Song, Bok Deuk;Lee, Seung-Hwan;Choi, HongKyw;Kim, Sung-Hoon
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.3
    • /
    • pp.396-402
    • /
    • 2022
  • User interactions are being developed in various forms, and in particular, interactions using human gestures are being actively studied. Among them, hand gesture recognition is used as a human interface in the field of realistic media based on the 3D Hand Model. The use of interfaces based on hand gesture recognition helps users access media media more easily and conveniently. User interaction using hand gesture recognition should be able to view images by applying fast and accurate hand gesture recognition technology without restrictions on the computer environment. This paper developed a fast and accurate user hand gesture recognition algorithm using the open source media pipe framework and machine learning's k-NN (K-Nearest Neighbor). In addition, in order to minimize the restriction of the computer environment, a stereoscopic image control system based on user hand gesture recognition was designed and implemented using a web service environment capable of Internet service and a docker container, a virtual environment.

A Data Sampling Technique for Secure Dataset Using Weight VAE Oversampling(W-VAE) (가중치 VAE 오버샘플링(W-VAE)을 이용한 보안데이터셋 샘플링 기법 연구)

  • Kang, Hanbada;Lee, Jaewoo
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.12
    • /
    • pp.1872-1879
    • /
    • 2022
  • Recently, with the development of artificial intelligence technology, research to use artificial intelligence to detect hacking attacks is being actively conducted. However, the fact that security data is a representative imbalanced data is recognized as a major obstacle in composing the learning data, which is the key to the development of artificial intelligence models. Therefore, in this paper, we propose a W-VAE oversampling technique that applies VAE, a deep learning generation model, to data extraction for oversampling, and sets the number of oversampling for each class through weight calculation using K-NN for sampling. In this paper, a total of five oversampling techniques such as ROS, SMOTE, and ADASYN were applied through NSL-KDD, an open network security dataset. The oversampling method proposed in this paper proved to be the most effective sampling method compared to the existing oversampling method through the F1-Score evaluation index.

미국공공도서관의 봉사활동에 미친 연방정부의 역할에 관한 고찰-LSA와 LSCA를 중심으로

  • 최달현
    • Journal of Korean Library and Information Science Society
    • /
    • v.3
    • /
    • pp.89-109
    • /
    • 1976
  • In modern times, it has been a most imporant problem for the community to make nation's information resources a\-ailable to all the people ~vithf ree and even access. In Nelson Associate's National platz for library service appeared in 1948, 50 million Americans were served by public libraries with inadequate service and 35 million have had no library service. Library Services Act signed bq- President Eisenhower in 1956 was a result of continuous efforts of AL.1 for 20 years. It aimed to extend public library service to rural population less than ten thousands. LSA was succeeded by LSCA in 1964 and continued with several amendments so far. 620 million dollars of Federal funds were put into local library administrati1.e agencies during 1957-1974 for the extension of library service and construction of library buildings. Federal funds also encouraged local library administrative agencies to ha\-e more interest in library and information service and carry out their own library programs. However, there are many current problems in Amierican pubic libraries still now, that is, uneven growth of public libraries, uneven distribution of information resources, inadequate library service to a large part of population, insufficient supply of library funds, lack of nationwide library network beyond local admini-strative jurisdictions and so on. National Advisory Commission on Libraries, Committee on Libraries, National Conference of Library and Inforination Science are results of government efforts to meet those problems and carry out effecti1.e nation's library policies. In other part, Congress authorized to open the White House Conference on Library and Information Science before 1978 to make a reco:nn:endation fostering the library use. It is expected that the elected President Carter will put more efforts in developing library and information services, for LSA and LSCA were mainly pushed ahead by Democratic Party. In conclusion I could find some factors through these analysis that would be of some help to develop nation's library and information services, especially in developing countries.

  • PDF