• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.51-65
• /
• 2024

Accurate electrical load forecasting is important to the effective operation of power systems in smart grids. With the recent development in machine learning, artificial intelligence-based models for predicting power demand are being actively researched. However, since existing models get input variables as numerical features, the accuracy of the forecasting model may decrease because they do not reflect the semantic relationship between these features. In this paper, we propose a scheme for short-term load forecasting by using features extracted through the large language models for input data. We firstly convert input variables into a sentence-like prompt format. Then, we use the large language model with frozen weights to derive the embedding vectors that represent the features of the prompt. These vectors are used to train the forecasting model. Experimental results show that the proposed scheme outperformed models based on numerical data, and by visualizing the attention weights in the large language models on the prompts, we identified the information that significantly influences predictions.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.25-37
• /
• 2000

The trajectories of feature points can be defined by the correspondences between points in consecutive frames. The correspondence problem is known to be difficult to solve because false positives and false negatives almost always exist in real image sequences. In this paper, we propose a robust feature tracking algorithm considering incomplete trajectories such as entering and/or vanishing trajectories. The trajectories of feature points are determined by calculating the matching measure, which is defined as the minimum weighted Euclidean distance between two feature points. The weights are automatically updated in order to properly reflect the motion characteristics. We solve the correspondence problem as an optimal graph search problem, considering that the existence of false feature points may have serious effect on the correspondence search. The proposed algorithm finds a local optimal correspondence so that the effect of false feature point can be minimized in the decision process. The time complexity of the proposed graph search algorithm is given by O(mn) in the best case and O($m^2n$) in the worst case, where m and n arc the number of feature points in two consecutive frames. By considering false feature points and by properly reflecting motion characteristics, the proposed algorithm can find trajectories correctly and robustly, which has been shown by experimental results.

• The Journal of the Korea Contents Association
• /
• v.11 no.5
• /
• pp.125-137
• /
• 2011

Recently the research on the system using images taken from camera phones as input is actively conducted. This paper proposed a system that shows wine pictures which are similar to the input wine label in order. For the calculation of the similarity of images, the representative color of each cell of the image, the recognized text color, background color and distribution of feature points are used as the features. In order to calculate the difference of the colors, RGB is converted into CIE-Lab and the feature points are extracted by using Harris Corner Detection Algorithm. The weights of representative color of each cell of image, text color and background color are applied. The image similarity is calculated by normalizing the difference of color similarity and distribution of feature points. After calculating the similarity between the input image and the images in the database, the images in Database are shown in the descent order of the similarity so that the effort of users to search for similar wine labels again from the searched result is reduced.

• Journal of KIISE:Software and Applications
• /
• v.32 no.1
• /
• pp.1-9
• /
• 2005

In this paper we propose a modified fuzzy min-max neural network model for pattern classification and discuss the usefulness of the model. We define a new hypercube membership function which has a weight factor to each of the feature within a hyperbox. The weight factor makes it possible to consider the degree of relevance of each feature to a class during the classification process. Based on the proposed model, a knowledge extraction method is presented. In this method, a list of relevant features for a given class is extracted from the trained network using the hyperbox membership functions and connection weights. Ft)r this purpose we define a Relevance Factor that represents a degree of relevance of a feature to the given class and a similarity measure between fuzzy membership functions of the hyperboxes. Experimental results for the proposed methods and discussions are presented for the evaluation of the effectiveness and feasibility of the proposed methods.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1175-1186
• /
• 2017

Human emotion recognition is one of the promising applications in the era of artificial super intelligence. Thus far, facial expression traits are considered to be the most widely used information cues for realizing automated emotion recognition. This paper proposes a novel facial expression recognition (FER) method that works well for recognizing emotion from image sequences. To this end, we develop the so-called weighted soft voting classification (WSVC) algorithm. In the proposed WSVC, a number of classifiers are first constructed using different and multiple feature representations. In next, multiple classifiers are used for generating the recognition result (namely, soft voting) of each face image within a face sequence, yielding multiple soft voting outputs. Finally, these soft voting outputs are combined through using a weighted combination to decide the emotion class (e.g., anger) of a given face sequence. The weights for combination are effectively determined by measuring the quality of each face image, namely "peak expression intensity" and "frontal-pose degree". To test the proposed WSVC, CK+ FER database was used to perform extensive and comparative experimentations. The feasibility of our WSVC algorithm has been successfully demonstrated by comparing recently developed FER algorithms.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.76-82
• /
• 2005

Speech signal has various features of speakers. This feature is extracted from speech signal processing. The speaker is identified by the speaker identification system. In this paper, we propose the speaker identification system that uses the incremental learning based on neural network. Recorded speech signal through the microphone is blocked to the frame of 1024 speech samples. Energy is divided speech signal to voiced signal and unvoiced signal. The extracted 12 orders LPC cpestrum coefficients are used with input data for neural network. The speakers are identified with the speaker identification system using the neural network. The neural network has the structure of MLP which consists of 12 input nodes, 8 hidden nodes, and 4 output nodes. The number of output node means the identified speakers. The first output node is excited to the first speaker. Incremental learning begins when the new speaker is identified. Incremental learning is the learning algorithm that already learned weights are remembered and only the new weights that are created as adding new speaker are trained. It is learning algorithm that overcomes the fault of neural network. The neural network repeats the learning when the new speaker is entered to it. The architecture of neural network is extended with the number of speakers. Therefore, this system can learn without the restricted number of speakers.

• The Korean Journal of Applied Statistics
• /
• v.25 no.5
• /
• pp.829-835
• /
• 2012

When the input features are generated by factors in a classification problem, it is more meaningful to identify important factors, rather than individual features. The $F_{\infty}$-norm support vector machine(SVM) has been developed to perform automatic factor selection in classification. However, the $F_{\infty}$-norm SVM may suffer from estimation inefficiency and model selection inconsistency because it applies the same amount of shrinkage to each factor without assessing its relative importance. To overcome such a limitation, we propose the adaptive $F_{\infty}$-norm ($AF_{\infty}$-norm) SVM, which penalizes the empirical hinge loss by the sum of the adaptively weighted factor-wise $L_{\infty}$-norm penalty. The $AF_{\infty}$-norm SVM computes the weights by the 2-norm SVM estimator and can be formulated as a linear programming(LP) problem which is similar to the one of the $F_{\infty}$-norm SVM. The simulation studies show that the proposed $AF_{\infty}$-norm SVM improves upon the $F_{\infty}$-norm SVM in terms of classification accuracy and factor selection performance.

• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.920-926
• /
• 2005

Nearest neighbor algorithms classify an unseen input instance by selecting similar cases and use the discovered membership to make predictions about the unknown features of the input instance. The usefulness of the nearest neighbor algorithms have been demonstrated sufficiently in many real-world domains. In nearest neighbor algorithms, it is an important issue to assign proper weights to the attributes. Therefore, in this paper, we propose a new method which can automatically assigns to each attribute a weight of its importance with respect to the target attribute. The method has been implemented as a computer program and its effectiveness has been tested on a number of machine learning databases publicly available.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.75-86
• /
• 2022

The existing image quality assessment (IQA) datasets have a small number of samples. Some methods based on transfer learning or data augmentation cannot make good use of image quality-related features. A No Reference (NR)-IQA method based on multi-task training and quality awareness is proposed. First, single or multiple distortion types and levels are imposed on the original image, and different strategies are used to augment different types of distortion datasets. With the idea of weak supervision, we use the Full Reference (FR)-IQA methods to obtain the pseudo-score label of the generated image. Then, we combine the classification information of the distortion type, level, and the information of the image quality score. The ResNet50 network is trained in the pre-train stage on the augmented dataset to obtain more quality-aware pre-training weights. Finally, the fine-tuning stage training is performed on the target IQA dataset using the quality-aware weights to predicate the final prediction score. Various experiments designed on the synthetic distortions and authentic distortions datasets (LIVE, CSIQ, TID2013, LIVEC, KonIQ-10K) prove that the proposed method can utilize the image quality-related features better than the method using only single-task training. The extracted quality-aware features improve the accuracy of the model.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.461-469
• /
• 2020

In this paper, we propose a PCA-based feature feedback method for extracting important areas of handwritten numeric data sets and face data sets. A PCA-based feature feedback method is proposed by extending the previous LDA-based feature feedback method. In the proposed method, the data is reduced to important feature dimensions by applying the PCA technique, one of the dimension reduction machine learning algorithms. Through the weights derived during the dimensional reduction process, the important points of data in each reduced dimensional axis are identified. Each dimension axis has a different weight in the total data according to the size of the eigenvalue of the axis. Accordingly, a weight proportional to the size of the eigenvalues of each dimension axis is given, and an operation process is performed to add important points of data in each dimension axis. The critical area of the data is calculated by applying a threshold to the data obtained through the calculation process. After that, induces reverse mapping to the original data in the important area of the derived data, and selects the important area in the original data space. The results of the experiment on the MNIST dataset are checked, and the effectiveness and possibility of the pattern recognition method based on PCA-based feature feedback are verified by comparing the results with the existing LDA-based feature feedback method.