• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.805-809
• /
• 2018

In this paper, we analyze the change of accuracy when fixed point arithmetic is used instead of floating point arithmetic in binary weight network(BWN). We observed the change of accuracy by varying total bit size and fraction bit size. If the integer part is not changed after fixed point approximation, there is no significant decrease in accuracy compared to the floating-point operation. When overflow occurs in the integer part, the approximation to the maximum or minimum of the fixed point representation minimizes the decrease in accuracy. The results of this paper can be applied to the minimization of memory and hardware resource requirement in the implementation of FPGA-based BWN accelerator.

• Journal of Advanced Marine Engineering and Technology
• /
• v.34 no.8
• /
• pp.1172-1179
• /
• 2010

In this paper, we analyze and design requirements of Network Function block and System Function block of MiTS network protocol based on Light-Weight Ethernet, also implement and test the protocol and library files. Light-Weight Ethernet Protocol consists of Network Function block and System Function block. NF receives and sends datagram based on UDP multi-casting communication. SF processes messages after distinguished Sentence and Binary Image Data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.103.2-103
• /
• 2002

1. Introduction 2. Structure of BNN 3. Decision of weight value and threshold value 4. Principle of Extension in the ETL algorithm 5. Approximation problem of one circular region 6. Problem of synthetic image having four class 7. Conclusion

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.225-231
• /
• 2020

In this paper, we propose a method to accelerate BWN based on FPGA with limited resources for embedded system. Because of the limited number of logic elements available, a single computing unit capable of handling Conv-layer, FC-layer of various sizes must be designed and reused. Also, if the input feature map can not be parallel processed at one time, the output must be calculated by reading the inputs several times. Since the number of available BRAM modules is limited, the number of data bits in the BWN accelerator must be minimized. The image classification processing time of the BWN accelerator is superior when compared with a embedded CPU and is faster than a desktop PC and 50% slower than a GPU system. Since the BWN accelerator uses a slow clock of 50MHz, it can be seen that the BWN accelerator is advantageous in performance versus power.

• Journal of KIISE:Information Networking
• /
• v.28 no.4
• /
• pp.631-640
• /
• 2001

Round robin scheduling discipline, which is a sort of frame-based scheduling, is quite simple and straightforward for handling multiple queues, and by putting a different weight on each queue, a network can offer differentiated services such as different bandwidth, or delay bound. The most typical algorithm among this disciplines is the weighted round robin(WRR). Also, WRR algorithm can be implemented efficiently by dynamic binary scheduling wheel(DBSW) architecture. This paper performs the analysis of the DBSW architecture and compares the results with simulation results. The analysis data and simulation data show that the DBSW structure decreases average buffer length because it is capable of maintaining the allocated weight of each VC correctly.

• Journal of Ceramic Processing Research
• /
• v.19 no.5
• /
• pp.413-418
• /
• 2018

All-solid-state lithium batteries (ASSBs) using inorganic sulfide-based solid electrolytes are considered prospective alternatives to existing liquid electrolyte-based batteries owing to benefits such as non-flammability. However, it is difficult to form a favorable solid-solid interface among electrode constituents because all the constituents are solid particles. It is important to form an effective electron conduction network in composite cathode while increasing utilization of active materials and not blocking the lithium ion path, resulting in excellent cell performance. In this study, a mixture of fibrous VGCF and spherical nano-sized Super P was used to improve rate performance by fabricating valid conduction paths in composite cathodes. Then, composite cathodes of ASSBs containing 70% and 80% active materials ($LiNi_{0.6}Co_{0.2}Mn_{0.2}O_2$) were prepared by a solution-based process to achieve uniform dispersion of the electrode components in the slurry. We investigated the influence of binary carbon additives in the cathode of all-solid-state batteries to improve rate performance by constructing an effective electron conduction network.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.38 no.1
• /
• pp.139-152
• /
• 2013

The purpose of this study is to claim the validity of tuning the architecture of neural network models for multi-class classification. A neural network model for multi-class classification is basically constructed by building a series of neural network models for binary classification. Building a neural network model, we are required to set the values of parameters such as number of hidden nodes and weight decay parameter in advance, which draws special attention as the performance of the model can be quite different by the values of the parameters. For better performance of the model, it is absolutely necessary to have a prior process of tuning the parameters every time the neural network model is built. Nonetheless, previous studies have not mentioned the necessity of the tuning process or proved its validity. In this study, we claim that we should tune the parameters every time we build the neural network model for multi-class classification. Through empirical analysis using wine data, we show that the performance of the model with the tuned parameters is superior to those of untuned models.

• Journal of Advanced Navigation Technology
• /
• v.26 no.5
• /
• pp.365-372
• /
• 2022

Compared to sensors mainly used in human activity recognition (HAR) systems, inertial measurement unit (IMU) sensors are small and light, so can achieve lightweight system at low cost. Therefore, in this paper, we propose a binary neural network (BNN) based gait pattern analysis system using IMU sensor, and present the design and implementation results of an FPGA-based accelerator for computational acceleration. Six signals for gait are measured through IMU sensor, and a spectrogram is extracted using a short-time Fourier transform. In order to have a lightweight system with high accuracy, a BNN-based structure was used for gait pattern classification. It is designed as a hardware accelerator structure using FPGA for computation acceleration of binary neural network. The proposed gait pattern analysis system was implemented using 24,158 logics, 14,669 registers, and 13.687 KB of block memory, and it was confirmed that the operation was completed within 1.5 ms at the maximum operating frequency of 62.35 MHz and real-time operation was possible.

• Journal of the Regional Association of Architectural Institute of Korea
• /
• v.20 no.6
• /
• pp.17-23
• /
• 2018

The purpose of this study is to suggest 100MPa class ultra high strength concrete mix design model applying neural network theory, in order to minimize an effort wasted by trials and errors method until now. Mix design model was applied to each of the 70 data using binary binder, ternary binder and quaternary binder. Then being repeatedly applied to back-propagation algorithm in neural network model, optimized connection weight was gained. The completed mix design model was proved, by analyzing and comparing to value predicted from mix design model and value measured from actual compressive strength test. According to the results of this study, more accurate value could be gained through the mix design model, if error rate decreases with the test condition and environment. Also if content of water and binder, slump flow, and air content of concrete apply to mix design model, more accurate and resonable mix design could be gained.

• Journal of Information Technology Application
• /
• v.1
• /
• pp.173-211
• /
• 1999

The task of classification permeates all walks of life, from business and economics to science and public policy. In this context, nonlinear techniques from artificial intelligence have often proven to be more effective than the methods of classical statistics. The objective of knowledge discovery and data mining is to support decision making through the effective use of information. The automated approach to knowledge discovery is especially useful when dealing with large data sets or complex relationships. For many applications, automated software may find subtle patterns which escape the notice of manual analysis, or whose complexity exceeds the cognitive capabilities of humans. This paper explores the utility of a collaborative learning approach involving integrated models in the preprocessing and postprocessing stages. For instance, a genetic algorithm effects feature-weight optimization in a preprocessing module. Moreover, an inductive tree, artificial neural network (ANN), and k-nearest neighbor (kNN) techniques serve as postprocessing modules. More specifically, the postprocessors act as second0order classifiers which determine the best first-order classifier on a case-by-case basis. In addition to the second-order models, a voting scheme is investigated as a simple, but efficient, postprocessing model. The first-order models consist of statistical and machine learning models such as logistic regression (logit), multivariate discriminant analysis (MDA), ANN, and kNN. The genetic algorithm, inductive decision tree, and voting scheme act as kernel modules for collaborative learning. These ideas are explored against the background of a practical application relating to financial fraud management which exemplifies a binary classification problem.