• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.61-66
• /
• 2022

Object classification is one of the main fields in neural networks and has attracted the interest of many researchers. Although there have been vast advancements in this area, still there are many challenges that are faced even in the current era due to its inefficiency in handling large data, linguistic and dimensional complexities. Powerful hardware and software approaches in Neural Networks such as Deep Neural Networks present efficient mechanisms and contribute a lot to the field of object recognition as well as to handle time series classification. Due to the high rate of accuracy in terms of prediction rate, a neural network is often preferred in applications that require identification, segmentation, and detection based on features. Neural networks self-learning ability has revolutionized computing power and has its application in numerous fields such as powering unmanned self-driving vehicles, speech recognition, etc. In this paper, the experiment is conducted to implement a neural approach to identify numbers in different formats without human intervention. Measures are taken to improve the efficiency of the machines to classify and identify numbers. Experimental results show the importance of having training sets to achieve better recognition accuracy.

• Korean Journal of Remote Sensing
• /
• v.18 no.3
• /
• pp.155-162
• /
• 2002

Neural networks have been focused on as a robust classifier for the remotely sensed imagery due to its statistical independency and teaming ability. Also the artificial neural networks have been reported to be more tolerant to noise and missing data. However, unlike the conventional statistical classifiers which use the statistical parameters for the classification, a neural network classifier uses individual training sample in teaming stage. The training performance of a neural network is know to be very sensitive to the discrepancy of the number of the training samples of each class. In this paper, the effect of the population discrepancy of training samples of each class was analyzed with three layered feed forward network. And a method for reducing the effect was proposed and experimented with Landsat TM image. The results showed that the effect of the training sample size discrepancy should be carefully considered for faster and more accurate training of the network. Also, it was found that the proposed method which makes teaming rate as a function of the number of training samples in each class resulted in faster and more accurate training of the network.

• Journal of Sensor Science and Technology
• /
• v.30 no.1
• /
• pp.20-24
• /
• 2021

The electrocardiogram (ECG) is one of the most extensively employed signals used to diagnose and predict cardiovascular diseases (CVDs). In recent years, several deep learning (DL) models have been proposed to improve detection accuracy. Among these, deep neural networks (DNNs) are the most popular, wherein the features are extracted automatically. Despite the increment in classification accuracy, DL models require exorbitant computational resources and power. This causes the mapping of DNNs to be slow; in addition, the mapping is challenging for a wearable device. Embedded systems have constrained power and memory resources. Therefore full-precision DNNs are not easily deployable on devices. To make the neural network faster and more power-efficient, spiking neural networks (SNNs) have been introduced for fewer operations and less complex hardware resources. However, the conventional SNN has low accuracy and high computational cost. Therefore, this paper proposes a new binarized SNN which modifies the synaptic weights of SNN constraining it to be binary (+1 and -1). In the simulation results, this paper compares the DL models and SNNs and evaluates which model is optimal for ECG classification. Although there is a slight compromise in accuracy, the latter proves to be energy-efficient.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.290-294
• /
• 1997

Chromosomes, as the genetic vehicles, provide the basic material for a large proportion of genetic investigations. The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, we propose an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of two-step multi-layer neural network(TMANN). We are employed three morphological feature parameters ; centromeric index(C.I.), relative length ratio(R.L.), and relative area ratio(R.A.), as input in neural network by preprocessing twenty human chromosome images. The results of our experiments show that our TMANN classifier is much more useful in neural network learning and successful in chromosome classification than the other classification methods.

• Journal of Biosystems Engineering
• /
• v.33 no.5
• /
• pp.340-347
• /
• 2008

Dipstick urinalysis is used as a routine test for a screening test of UTI (urinary tract infection) in primary practice because urine dipstick test is simple. The result of dipstick urinalysis brings medical professionals to make a microscopic examination and urine culture for exact UTI diagnosis, therefore it is emphasized on a role of screening test. The objective of this study was to the classification between UTI patients and normal subjects using hybrid neural network classifier with enhanced clustering performance in urine dipstick screening test. In order to propose a classifier, we made a hybrid neural network which combines with RBF layer, summation & normalization layer and L VQ artificial neural network layer. For the demonstration of proposed hybrid neural network, we compared proposed classifier with various artificial neural networks such as back-propagation, RBFNN and PNN method. As a result, classification performance of proposed classifier was able to classify 95.81% of the normal subjects and 83.87% of the UTI patients, total average 90.72% according to validation dataset. The proposed classifier confirms better performance than other classifiers. Therefore the application of such a proposed classifier expect to utilize telemedicine to classify between UTI patients and normal subjects in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.420-437
• /
• 2024

There are some problems in network traffic classification (NTC), such as complicated statistical features and insufficient training samples, which may cause poor classification effect. A NTC architecture based on one-dimensional Convolutional Neural Network (CNN) and transfer learning is proposed to tackle these problems and improve the fine-grained classification performance. The key points of the proposed architecture include: (1) Model classification--by extracting normalized rate feature set from original data, plus existing statistical features to optimize the CNN NTC model. (2) To apply transfer learning in the classification to improve NTC performance. We collect two typical network flows data from Youku and YouTube, and verify the proposed method through extensive experiments. The results show that compared with existing methods, our method could improve the classification accuracy by around 3-5%for Youku, and by about 7 to 27% for YouTube.

• Journal of Mechanical Science and Technology
• /
• v.18 no.11
• /
• pp.1923-1931
• /
• 2004

Manufacturing of complex surface plates in stern and stem is a major factor in cost of a preliminary ship design by computing process. If these hull plate parts are effectively classified, it helps to compute the processing cost and find the way to cut-down the processing cost. This paper presents a new method to classify surface plates effectively in the preliminary ship design using neural network. A neural-network-based ship hull plate classification program was developed and tested for the automatic classification of ship design. The input variables are regarded as Gaussian curvature distributions on the plate. Various applicable rules of network topology are applied in the ship design. In automation of hull plate classification, two different numbers of input variables are used. By observing the results of the proposed method, the effectiveness of the proposed method is discussed. As a result, high prediction rate was achieved in the ship design. Accordingly, to the initial design stage, the ship hull plate classification program can be used to predict the ship production cost. And the proposed method will contribute to reduce the production cost of ship.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.3
• /
• pp.150-158
• /
• 1998

This paper describes the classification of remotely sensed image data using fuzzy neural network, whose algorithm was obtained by replacing real numbers used for inputs and outputs in the standard back propagation algorithm with fuzzy numbers. In the proposed method, fuzzy patterns, generated based on the histogram ofeach category for the training data, are put into the fuzzy neural network with real numbers. The results show that the generalization and appoximation are better than that ofthe conventional network in determining the complex boundary of patterns.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.4
• /
• pp.429-438
• /
• 2011

LiDAR technology is a combination of laser ranging, satellite positioning technology and digital image technology for study and determination with high accuracy of the true earth surface features in 3 D. Laser scanning data is typically a points cloud on the ground, including coordinates, altitude and intensity of laser from the object on the ground to the sensor (Wehr & Lohr, 1999). Data from laser scanning can produce products such as digital elevation model (DEM), digital surface model (DSM) and the intensity data. In Vietnam, the LiDAR technology has been applied since 2005. However, the application of LiDAR in Vietnam is mostly for topological mapping and DEM establishment using point cloud 3D coordinate. In this study, another application of LiDAR data are present. The study use the intensity image combine with some other data sets (elevation data, Panchromatic image, RGB image) in Bacgiang City to perform land cover classification using neural network method. The results show that it is possible to obtain land cover classes from LiDAR data. However, the highest accurate classification can be obtained using LiDAR data with other data set and the neural network classification is more appropriate approach to conventional method such as maximum likelyhood classification.