• Asia pacific journal of information systems
• /
• v.33 no.3
• /
• pp.737-767
• /
• 2023

With the availability of big customer data and advances in machine learning techniques, the prediction of customer behavior at the session-level has attracted considerable attention from marketing practitioners and scholars. This study aims to predict customer purchase conversion at the session-level by employing customer profile, transaction, and clickstream data. For this purpose, we develop a multimodal deep learning fusion model with dynamic and static features (i.e., DS-fusion). Specifically, we base page views within focal visist and recency, frequency, monetary value, and clumpiness (RFMC) for dynamic and static features, respectively, to comprehensively capture customer characteristics for buying behaviors. Our model with deep learning architectures combines these features for conversion prediction. We validate the proposed model using real-world e-commerce data. The experimental results reveal that our model outperforms unimodal classifiers with each feature and the classical machine learning models with dynamic and static features, including random forest and logistic regression. In this regard, this study sheds light on the promise of the machine learning approach with the complementary method for different modalities in predicting customer behaviors.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.458-476
• /
• 2024

To address the issue of class imbalance in network traffic data, which affects the network intrusion detection performance, a combined framework using transformers is proposed. First, Tomek Links, SMOTE, and WGAN are used to preprocess the data to solve the class-imbalance problem. Second, the transformer is used to encode traffic data to extract the correlation between network traffic. Finally, a hybrid deep learning network model combining a bidirectional gated current unit and deep neural network is proposed, which is used to extract long-dependence features. A DNN is used to extract deep level features, and softmax is used to complete classification. Experiments were conducted on the NSLKDD, UNSWNB15, and CICIDS2017 datasets, and the detection accuracy rates of the proposed model were 99.72%, 84.86%, and 99.89% on three datasets, respectively. Compared with other relatively new deep-learning network models, it effectively improved the intrusion detection performance, thereby improving the communication security of network data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2188-2203
• /
• 2021

With the rapid development of mobile Internet, smart phones have been widely popularized, among which Android platform dominates. Due to it is open source, malware on the Android platform is rampant. In order to improve the efficiency of malware detection, this paper proposes deep learning Android malicious detection system based on behavior features. First of all, the detection system adopts the static analysis method to extract different types of behavior features from Android applications, and extract sensitive behavior features through Term frequency-inverse Document Frequency algorithm for each extracted behavior feature to construct detection features through unified abstract expression. Secondly, Long Short-Term Memory neural network model is established to select and learn from the extracted attributes and the learned attributes are used to detect Android malicious applications, Analysis and further optimization of the application behavior parameters, so as to build a deep learning Android malicious detection method based on feature analysis. We use different types of features to evaluate our method and compare it with various machine learning-based methods. Study shows that it outperforms most existing machine learning based approaches and detects 95.31% of the malware.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.556-570
• /
• 2021

The existing video expression recognition methods mainly focus on the spatial feature extraction of video expression images, but tend to ignore the dynamic features of video sequences. To solve this problem, a multi-mode convolution neural network method is proposed to effectively improve the performance of facial expression recognition in video. Firstly, OpenFace 2.0 is used to detect face images in video, and two deep convolution neural networks are used to extract spatiotemporal expression features. Furthermore, spatial convolution neural network is used to extract the spatial information features of each static expression image, and the dynamic information feature is extracted from the optical flow information of multiple expression images based on temporal convolution neural network. Then, the spatiotemporal features learned by the two deep convolution neural networks are fused by multiplication. Finally, the fused features are input into support vector machine to realize the facial expression classification. Experimental results show that the recognition accuracy of the proposed method can reach 64.57% and 60.89%, respectively on RML and Baum-ls datasets. It is better than that of other contrast methods.

• KIISE Transactions on Computing Practices
• /
• v.23 no.11
• /
• pp.625-631
• /
• 2017

The stock price prediction for stock markets remains an unsolved problem. Although there have been various overtures and studies to predict the price of stocks scientifically, it is impossible to predict the future precisely. However, stock price predictions have been a subject of interest in a variety of related fields such as economics, mathematics, physics, and computer science. In this paper, we will study fluctuation patterns of stock prices and predict future trends using the Deep learning. Therefore, this study presents the three deep learning models using Tensorflow, an open source framework in which each learning model accepts different input features. We expand the previous study that used simple price data. We measured the performance of three predictive models increasing the number of priced-based input features. Through this experiment, we measured the performance change of the predictive model depending on the price-based input features. Finally, we compared and analyzed the experiment result to evaluate the impact of the price-based input features in stock price prediction.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.9-16
• /
• 2015

In this paper, several experiments are performed according to deep neural network (DNN) based features for the performance comparison of speaker verification (SV) systems. To this end, input features for a DNN, such as mel-frequency cepstral coefficient (MFCC), linear-frequency cepstral coefficient (LFCC), and perceptual linear prediction (PLP), are first compared in a view of the SV performance. After that, the effect of a DNN training method and a structure of hidden layers of DNNs on the SV performance is investigated depending on the type of features. The performance of an SV system is then evaluated on the basis of I-vector or probabilistic linear discriminant analysis (PLDA) scoring method. It is shown from SV experiments that a tandem feature of DNN bottleneck feature and MFCC feature gives the best performance when DNNs are configured using a rectangular type of hidden layers and trained with a supervised training method.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.61-69
• /
• 2018

Multi-tracking of general objects and specific faces is an important topic in the field of computer vision applicable to many branches of industry such as biometrics, security, etc. The rapid development of deep neural networks has resulted in a dramatic improvement in face recognition and object detection problems, which helps improve the multiple-face tracking techniques exploiting the tracking-by-detection method. Our proposed method uses face detection trained with a head dataset to resolve the face deformation problem in the tracking process. Further, we use robust face features extracted from the deep face recognition network to match the tracklets with tracking faces using Hungarian matching method. We achieved promising results regarding the usage of deep face features and head detection in a face tracking benchmark.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.225-231
• /
• 2023

With the recent surge in the autonomous driving market, the significance of lane detection technology has escalated. Lane detection plays a pivotal role in autonomous driving systems by identifying lanes to ensure safe vehicle operation. Traditional lane detection models rely on engineers manually extracting lane features from predefined environments. However, real-world road conditions present diverse challenges, hampering the engineers' ability to extract adaptable lane features, resulting in limited performance. Consequently, recent research has focused on developing deep learning based lane detection models to extract lane features directly from data. In this paper, we classify lane detection models into four categories: cluster-based, curve-based, information propagation-based, and anchor-based methods. We conduct an extensive analysis of the strengths and weaknesses of each approach, evaluate the model's performance on an embedded board, and assess their practicality and effectiveness. Based on our findings, we propose future research directions and potential enhancements.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• Journal of Korean Academy of Nursing
• /
• v.42 no.3
• /
• pp.396-404
• /
• 2012

Purpose: The purpose of this study was to identify the features, risk scores and risk factors for deep vein thrombosis in critically ill patients who developed deep vein thrombosis in their lower extremities. Methods: The participants in this prospective descriptive study were 175 adult patients who did not receive any prophylactic medication or mechanical therapy during their admission in the intensive care unit. Results: The mean age was 62.24 (${\pm}17.28$) years. Men made up 54.9% of the participating patients. There were significant differences in age, body mass index, and leg swelling between patients who developed deep vein thrombosis and those who did not have deep vein thrombosis. The mean risk score was 6.71(${\pm}2.94$) and they had on average 4.01(${\pm}1.35$) risk factors. In the multiple logistic regression, body mass index (odds ratio=1.14) and leg swelling (odds ratio=6.05) were significant predictors of deep vein thrombosis. Conclusion: Most critically ill patients are in the potentially high risk group for deep vein thrombosis. However, patients who are elderly, obese or have leg edema should be closely assessed and more than one type of active prophylactic intervention should be provided.