• MALSORI
• /
• no.63
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1269-1276
• /
• 2023

Crop estimation is essential for the multinational meal and powerful demand due to its numerous aspects like soil, rain, climate, atmosphere, and their relations. The consequence of climate shift impacts the farming yield products. We operate the dataset with temperature, rainfall, humidity, etc. The current research focuses on feature selection with multifarious classifiers to assist farmers and agriculturalists. The crop yield estimation utilizing the feature selection approach is 96% accuracy. Feature selection affects a machine learning model's performance. Additionally, the performance of the current graph classifier accepts 81.5%. Eventually, the random forest regressor without feature selections owns 78% accuracy and the decision tree regressor without feature selections retains 67% accuracy. Our research merit is to reveal the experimental results of with and without feature selection significance for the proposed ten algorithms. These findings support learners and students in choosing the appropriate models for crop classification studies.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.362-373
• /
• 2020

Recently, as autonomous vehicles and intelligent CCTV are growing more interest, the efficient object detection is essential technique. The DPM(Deformable Part Models) which is basis of this paper have used a typical object system that represents highly variable objects using mixtures of deformable part for object. Although it shows high detection performance by capturing part shape and configuration of object model, but it is limited to use in real application due to the complicated algorithm. In this paper, instead of image feature pyramid that takes up a large amount of computation in one part of the detector, we propose a method to reduce the computation speed by reconstructing a new image feature pyramid that uses adaptive bilinear interpolation of feature maps obtained on a specific image scale. As a result, the detection performance for object was lowered a little by 2.82%, however, the proposed detection method improved the speed performance by 10% in comparison with original DPM.

• Journal of Advanced Marine Engineering and Technology
• /
• v.23 no.5
• /
• pp.622-629
• /
• 1999

This paper presents the development of an interactive knowledge-based CAM system for design-ing and manufacturing the mold. The system is composed of two functional parts. One is the geo-metric modeller that uses the feature-based models. The models include base plate step, hole, pocket, boss and slot, These are designed by interactive user interface. The other is the expert sys-tem module with inference engine and knowledge database of workpiece material tools manufac-turing machines process an working conditions. With two parts the final mold shape is generated with manufacturing information for effective production.

• Journal of the military operations research society of Korea
• /
• v.26 no.1
• /
• pp.1-14
• /
• 2000

This research studies an attrition rate considering terrain feature in a battlefield. Lanchester-type combat models for heterogeneous forces and the Weapon Effectiveness Index are used in this study. The various environments of the battlefield can be explained by the terrain feature. Attrition rates of heterogeneous model are estimated by applying the battle of Baek-Sek mountain during the Korean War. Estimated attrition rates are checked by the paired samples T-Test. Specific cases are shown in this paper as an example. If we study out the relative influence of the terrain feature upon the performance of individual weapons, these will be a possible alternative to analyze the military operations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.526-537
• /
• 2024

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.6
• /
• pp.176-184
• /
• 2000

Reverse engineering (RE) is a process to create computer aided design (CAD) models from the scanned data of an existing part acquired using 3D position scanners. This paper proposes a novel methodology of extracting geometric features directly from a set of 3D scanned points, which utilizes the concepts of feature-based technology and artificial neural networks (ANNs). The use of ANN has enabled the development of a flexible feature-based RE application that can be trained to deal with various features. The following four main tasks were mainly investigated and implemented: (1) Data reduction; (2) edge detection; (3) ANN-based feature recognition; (4) feature extraction. This approach was validated with a variety of real industrial components. The test results show that the developed feature-based RE application proved to be suitable for reconstructing prismatic features such as block, pocket, step, slot, hole, and boss, which are very common and crucial in mechanical engineering products.

• Korean Journal of Computational Design and Engineering
• /
• v.4 no.1
• /
• pp.43-51
• /
• 1999

Producing the relevant information (features) from the CAD models of CAM, called feature recognition or extraction, is the essential stage for the integration of CAD and CAM. Most feature recognition methods, however, have problems in the recognition of intersecting features because they do not handle the intersection geometry properly. In this paper, we propose a machining feature recognition algorithm, which has a solid model consisting of orthogonal primitives as input. The algorithm calculates candidate features and constitutes the Intersection Geometry Matrix which is necessary to represent the spatial relation of candidate features. Finally, it recognizes machining features from the proposed candidate features dividing and growing systems using half space and Boolean operation. The algorithm has the following characteristics: Though the geometry of part is complex due to the intersections of design primitives, it can recognize the necessary machining features. In addition, it creates the Maximal Feature Volumes independent of the machining sequences at the feature recognition stage so that it can easily accommodate the change of decision criteria of machining orders.

• Phonetics and Speech Sciences
• /
• v.2 no.1
• /
• pp.77-85
• /
• 2010

This paper proposes an efficient feature vector processing technique to guard the Speech Emotion Recognition (SER) system against a variety of noises. In the proposed approach, emotional feature vectors are extracted from speech processed by comb filtering. Then, these extracts are used in a robust model construction based on feature vector classification. We modify conventional comb filtering by using speech presence probability to minimize drawbacks due to incorrect pitch estimation under background noise conditions. The modified comb filtering can correctly enhance the harmonics, which is an important factor used in SER. Feature vector classification technique categorizes feature vectors into either discriminative vectors or non-discriminative vectors based on a log-likelihood criterion. This method can successfully select the discriminative vectors while preserving correct emotional characteristics. Thus, robust emotion models can be constructed by only using such discriminative vectors. On SER experiment using an emotional speech corpus contaminated by various noises, our approach exhibited superior performance to the baseline system.