• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.284-290
• /
• 2024

Speech emotion recognition (SER) is a technique that is used to analyze the speaker's voice patterns, including vibration, intensity, and tone, to determine their emotional state. There has been an increase in interest in artificial intelligence (AI) techniques, which are now widely used in medicine, education, industry, and the military. Nevertheless, existing researchers have attained impressive results by utilizing acted-out speech from skilled actors in a controlled environment for various scenarios. In particular, there is a mismatch between acted and spontaneous speech since acted speech includes more explicit emotional expressions than spontaneous speech. For this reason, spontaneous speech-emotion recognition remains a challenging task. This paper aims to conduct emotion recognition and improve performance using spontaneous speech data. To this end, we implement deep learning-based speech emotion recognition using the VGG (Visual Geometry Group) after converting 1-dimensional audio signals into a 2-dimensional spectrogram image. The experimental evaluations are performed on the Korean spontaneous emotional speech database from AI-Hub, consisting of 7 emotions, i.e., joy, love, anger, fear, sadness, surprise, and neutral. As a result, we achieved an average accuracy of 83.5% and 73.0% for adults and young people using a time-frequency 2-dimension spectrogram, respectively. In conclusion, our findings demonstrated that the suggested framework outperformed current state-of-the-art techniques for spontaneous speech and showed a promising performance despite the difficulty in quantifying spontaneous speech emotional expression.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.48-59
• /
• 2024

As functions that support virtualization on their own in hardware are developed, user applications having various workloads are operating efficiently in the virtualization system. SR-IOV is a virtualization support function that takes direct access to PCI devices, thus giving a high I/O performance by minimizing the need for hypervisor or operating system interventions. With SR-IOV, network I/O acceleration can be realized in virtualization systems that have relatively long I/O paths compared to bare-metal systems and frequent context switches between the user area and kernel area. To take performance advantages of SR-IOV, network resource management policies that can derive optimal network performance when SR-IOV is applied to an instance such as a virtual machine(VM) or container are being actively studied.This paper evaluates and analyzes the network performance of SR-IOV implementing I/O acceleration is compared with Virtio in terms of 1) network delay, 2) network throughput, 3) network fairness, 4) performance interference, and 5) multi-network. The contributions of this paper are as follows. First, the network I/O process of Virtio and SR-IOV was clearly explained in the virtualization system, and second, the evaluation results of the network performance of Virtio and SR-IOV were analyzed based on various performance metrics. Third, the system overhead and the possibility of optimization for the SR-IOV network in a virtualization system with high VM density were experimentally confirmed. The experimental results and analysis of the paper are expected to be referenced in the network resource management policy for virtualization systems that operate network-intensive services such as smart factories, connected cars, deep learning inference models, and crowdsourcing.

• Information Systems Review
• /
• v.21 no.4
• /
• pp.125-141
• /
• 2019

With the advent of deep learning technology, which is represented by AlphaGo, artificial intelligence (A.I.) has quickly emerged as a key theme of digital transformation to secure competitive advantage for businesses. In order to understand the trends of A.I. based digital transformation, a clear comprehension of the A.I. business ecosystem should precede. Therefore, this study analyzed the A.I. business ecosystem from the multi-actor network perspective and identified the A.I. platform strategy type. Within internal three layers of A.I. business ecosystem (infrastructure & hardware, software & application, service & data layers), this study identified four types of A.I. platform strategy (Tech. vertical × Biz. horizontal, Tech. vertical × Biz. vertical, Tech. horizontal × Biz. horizontal, Tech. horizontal × Biz. vertical). Then, outside of A.I. platform, this study presented five actors (users, investors, policy makers, consortiums & innovators, CSOs/NGOs) and their roles to support sustainable A.I. business ecosystem in symbiosis with human. This study identified A.I. business ecosystem framework and platform strategy type. The roles of government and academia to create a sustainable A.I. business ecosystem were also suggested. These results will help to find proper strategy direction of A.I. business ecosystem and digital transformation.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.73-82
• /
• 2023

With 78% of current fisheries workers being elderly, there's a pressing need to address labor shortages. Consequently, active research on smart aquaculture technologies, centered on object detection and tracking algorithms, is underway. These technologies allow for fish size analysis and behavior pattern forecasting, facilitating the development of real-time monitoring and automated systems. Our study utilized video data from cameras outside aquaculture facilities and implemented fish detection and tracking algorithms. We aimed to tackle high maintenance costs due to underwater conditions and camera corrosion from ammonia and pH levels. We evaluated the performance of a real-time system using YOLOv7 for fish detection and the SORT algorithm for movement tracking. YOLOv7 results demonstrated a trade-off between Recall and Precision, minimizing false detections from lighting, water currents, and shadows. Effective tracking was ascertained through re-identification. This research holds promise for enhancing smart aquaculture's operational efficiency and improving fishery facility management.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.189-198
• /
• 2024

Research combining deep learning-based models and physical simulations is making important advances in the medical field. This extracts the necessary information from medical image data and enables fast and accurate prediction of deformation of the skeleton and soft tissue based on physical laws. This study proposes a system that integrates Neural Radiance Fields (NeRF), Position-Based Dynamics (PBD), and Parallel Resampling to generate 3D volume data, and deform and visualize them in real-time. NeRF uses 2D images and camera coordinates to produce high-resolution 3D volume data, while PBD enables real-time deformation and interaction through physics-based simulation. Parallel Resampling improves rendering efficiency by dividing the volume into tetrahedral meshes and utilizing GPU parallel processing. This system renders the deformed volume data using ray casting, leveraging GPU parallel processing for fast real-time visualization. Experimental results show that this system can generate and deform 3D data without expensive equipment, demonstrating potential applications in engineering, education, and medicine.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1463-1478
• /
• 2022

Maritime transport accounts for 99.7% of the exports and imports of the Republic of Korea; therefore, developing a vessel monitoring system for efficient operation is of significant interest. Several studies have focused on tracking and monitoring vessel movements based on automatic identification system (AIS) data; however, ships without AIS have limited monitoring and tracking ability. High-resolution optical satellite images can provide the missing layer of information in AIS-based monitoring systems because they can identify non-AIS vessels and small ships over a wide range. Therefore, it is necessary to investigate vessel monitoring and small vessel classification systems using high-resolution optical satellite images. This study examined the possibility of developing ship monitoring systems using Compact Advanced Satellite 500-1 (CAS500-1) satellite images by first training a deep learning model using satellite image data and then performing detection in other images. To determine the effectiveness of the proposed method, the learning data was acquired from ships in the Yellow Sea and its major ports, and the detection model was established using the You Only Look Once (YOLO) algorithm. The ship detection performance was evaluated for a domestic and an international port. The results obtained using the detection model in ships in the anchorage and berth areas were compared with the ship classification information obtained using AIS, and an accuracy of 85.5% and 70% was achieved using domestic and international classification models, respectively. The results indicate that high-resolution satellite images can be used in mooring ships for vessel monitoring. The developed approach can potentially be used in vessel tracking and monitoring systems at major ports around the world if the accuracy of the detection model is improved through continuous learning data construction.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.167-183
• /
• 2023

In the recent field of recommendation systems, various studies have been conducted to model sparse data effectively. Among these, GLocal-K(Global and Local Kernels for Recommender Systems) is a research endeavor combining global and local kernels to provide personalized recommendations by considering global data patterns and individual user characteristics. However, due to its utilization of kernel tricks, GLocal-K exhibits diminished performance on highly sparse data and struggles to offer recommendations for new users or items due to the absence of side information. In this paper, to address these limitations of GLocal-K, we propose the GEase-K (Global and EASE kernels for Recommender Systems) model, incorporating the EASE(Embarrassingly Shallow Autoencoders for Sparse Data) model and leveraging side information. Initially, we substitute EASE for the local kernel in GLocal-K to enhance recommendation performance on highly sparse data. EASE, functioning as a simple linear operational structure, is an autoencoder that performs highly on extremely sparse data through regularization and learning item similarity. Additionally, we utilize side information to alleviate the cold-start problem. We enhance the understanding of user-item similarities by employing a conditional autoencoder structure during the training process to incorporate side information. In conclusion, GEase-K demonstrates resilience in highly sparse data and cold-start situations by combining linear and nonlinear structures and utilizing side information. Experimental results show that GEase-K outperforms GLocal-K based on the RMSE and MAE metrics on the highly sparse GoodReads and ModCloth datasets. Furthermore, in cold-start experiments divided into four groups using the GoodReads and ModCloth datasets, GEase-K denotes superior performance compared to GLocal-K.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.71-88
• /
• 2017

Language models were originally developed for speech recognition and language processing. Using a set of example sentences, a language model predicts the next word or character based on sequential input data. N-gram models have been widely used but this model cannot model the correlation between the input units efficiently since it is a probabilistic model which are based on the frequency of each unit in the training set. Recently, as the deep learning algorithm has been developed, a recurrent neural network (RNN) model and a long short-term memory (LSTM) model have been widely used for the neural language model (Ahn, 2016; Kim et al., 2016; Lee et al., 2016). These models can reflect dependency between the objects that are entered sequentially into the model (Gers and Schmidhuber, 2001; Mikolov et al., 2010; Sundermeyer et al., 2012). In order to learning the neural language model, texts need to be decomposed into words or morphemes. Since, however, a training set of sentences includes a huge number of words or morphemes in general, the size of dictionary is very large and so it increases model complexity. In addition, word-level or morpheme-level models are able to generate vocabularies only which are contained in the training set. Furthermore, with highly morphological languages such as Turkish, Hungarian, Russian, Finnish or Korean, morpheme analyzers have more chance to cause errors in decomposition process (Lankinen et al., 2016). Therefore, this paper proposes a phoneme-level language model for Korean language based on LSTM models. A phoneme such as a vowel or a consonant is the smallest unit that comprises Korean texts. We construct the language model using three or four LSTM layers. Each model was trained using Stochastic Gradient Algorithm and more advanced optimization algorithms such as Adagrad, RMSprop, Adadelta, Adam, Adamax, and Nadam. Simulation study was done with Old Testament texts using a deep learning package Keras based the Theano. After pre-processing the texts, the dataset included 74 of unique characters including vowels, consonants, and punctuation marks. Then we constructed an input vector with 20 consecutive characters and an output with a following 21st character. Finally, total 1,023,411 sets of input-output vectors were included in the dataset and we divided them into training, validation, testsets with proportion 70:15:15. All the simulation were conducted on a system equipped with an Intel Xeon CPU (16 cores) and a NVIDIA GeForce GTX 1080 GPU. We compared the loss function evaluated for the validation set, the perplexity evaluated for the test set, and the time to be taken for training each model. As a result, all the optimization algorithms but the stochastic gradient algorithm showed similar validation loss and perplexity, which are clearly superior to those of the stochastic gradient algorithm. The stochastic gradient algorithm took the longest time to be trained for both 3- and 4-LSTM models. On average, the 4-LSTM layer model took 69% longer training time than the 3-LSTM layer model. However, the validation loss and perplexity were not improved significantly or became even worse for specific conditions. On the other hand, when comparing the automatically generated sentences, the 4-LSTM layer model tended to generate the sentences which are closer to the natural language than the 3-LSTM model. Although there were slight differences in the completeness of the generated sentences between the models, the sentence generation performance was quite satisfactory in any simulation conditions: they generated only legitimate Korean letters and the use of postposition and the conjugation of verbs were almost perfect in the sense of grammar. The results of this study are expected to be widely used for the processing of Korean language in the field of language processing and speech recognition, which are the basis of artificial intelligence systems.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.