• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.667-675
• /
• 2021

The treatments for symptoms of Alzheimer's disease are being provided and for the early diagnosis several researches are undergoing. In this regard, by using T1-weighted images several classification techniques had been proposed to distinguish among AD, MCI, and Healthy Control (HC) patients. In this paper, we also used some traditional Machine Learning (ML) approaches in order to diagnose the AD. This paper consists of an improvised feature selection method which is used to reduce the model complexity which accounted an issue while utilizing the ML approaches. In our presented work, combination of subcortical and cortical features of 308 subjects of ADNI dataset has been used to diagnose AD using structural magnetic resonance (sMRI) images. Three classification experiments were performed: binary classification. i.e., AD vs eMCI, AD vs lMCI, and AD vs HC. Proposed Feature Selection method consist of a combination of Principal Component Analysis and Recursive Feature Elimination method that has been used to reduce the dimension size and selection of best features simultaneously. Experiment on the dataset demonstrated that SVM is best suited for the AD vs lMCI, AD vs HC, and AD vs eMCI classification with the accuracy of 95.83%, 97.83%, and 97.87% respectively.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.101-110
• /
• 2021

In computer vision, single-image super resolution has been an area of research for a significant period. Traditional techniques involve interpolation-based methods such as Nearest-neighbor, Bilinear, and Bicubic for image restoration. Although implementations of convolutional neural networks have provided outstanding results in recent years, efficiency and single model multi-scalability have been its challenges. Furthermore, previous works haven't placed enough emphasis on real-number scalability. Interpolation-based techniques, however, have no limit in terms of scalability as they are able to upscale images to any desired size. In this paper, we propose a convolutional neural network possessing the advantages of the interpolation-based techniques, which is also efficient, deeming it suitable in practical implementations. It consists of convolutional layers applied on the low-resolution space, post-up-sampling along the end hidden layers, and additional layers on high-resolution space. Up-sampling is applied on a multiple channeled feature map via bicubic interpolation using a single model. Experiments on architectural structure, layer reduction, and real-number scale training are executed with results proving efficient amongst multi-scale learning (including scale multi-path-learning) based models.

• Journal of Information Technology Services
• /
• v.20 no.3
• /
• pp.57-73
• /
• 2021

Recently, online job websites have been activated as unemployment problems have emerged as social problems and demand for job openings has increased. However, while the online job platform market is growing, users have difficulty choosing their jobs. When users apply for a job on online job websites, they check various information such as job contents and recruitment conditions to understand the details of the job. When users choose a job, they focus on various details related to the job rather than simply viewing and supporting the job title. However, existing online job websites usually recommend jobs using only quantitative preference information such as ratings. However, if recommendation services are provided using only quantitative information, the recommendation performance is constantly deteriorating. Therefore, job recommendation services should provide personalized services using various information about the job. This study proposes a recommended methodology that improves recommendation performance by elaborating on qualitative preference information, such as details about the job. To this end, this study performs a topic modeling analysis on the job content of the user profile. Also, we apply LDA techniques to explore topics from job content and extract qualitative preferences. Experiments show that the proposed recommendation methodology has better recommendation performance compared to the traditional recommendation methodology.

• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.4_2
• /
• pp.491-499
• /
• 2021

Batteries are widely used for energy storage, such as ESS(Energy Storage System), electric vehicles, electric aircraft, and electric powered ships. Among them, a submarine uses a high power battery for an energy storage. When the battery of a submarine is discharged, a diesel generator generates AC power, and then AC/DC power converter change AC power to DC power for charging the battery. Therefore, in order to lower the current capacity of the diesel generator, it is necessary to use an AC/DC converter with a high input power factor. And, a power converter with a large power capacity must have high stability because it can lead to a major accident when a failure occurs. However, the control algorithm using the traditional PI controller is difficult to satisfy stability and dynamic characteristics. In this paper, we design the high power AC/DC converter with high input power factor for battery charging systems. And, we propose a stable control algorithm. The validity of the proposed method is verified through simulation and experiments.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.411-427
• /
• 2022

Digging historical and cultural information from seals in ancient books is of great significance. However, ancient Chinese seal samples are scarce and carving methods are diverse, and traditional digital image processing methods based on greyscale have difficulty achieving superior segmentation and recognition performance. Recently, some deep learning algorithms have been proposed to address this problem; however, current neural networks are difficult to train owing to the lack of datasets. To solve the afore-mentioned problems, we proposed an SEL-RefineMask which combines selector of feature pyramid network (SEL-FPN) with RefineMask to segment and recognize seals. We designed an SEL-FPN to intelligently select a specific layer which represents different scales in the FPN and reduces the number of anchor frames. We performed experiments on some instance segmentation networks as the baseline method, and the top-1 segmentation result of 64.93% is 5.73% higher than that of humans. The top-1 result of the SEL-RefineMask network reached 67.96% which surpassed the baseline results. After segmentation, a vision transformer was used to recognize the segmentation output, and the accuracy reached 91%. Furthermore, a dataset of seals in ancient Chinese books (SACB) for segmentation and small seal font (SSF) for recognition were established which are publicly available on the website.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.894-907
• /
• 2022

The features extracted by convolutional neural networks are more descriptive of images than traditional features, and their convolutional layers are more suitable for retrieving images than are fully connected layers. The convolutional layer features will consume considerable time and memory if used directly to match an image. Therefore, this paper proposes a feature weighting and region integration method for convolutional layer features to form global feature vectors and subsequently use them for image matching. First, the 3D feature of the last convolutional layer is extracted, and the convolutional feature is subsequently weighted again to highlight the edge information and position information of the image. Next, we integrate several regional eigenvectors that are processed by sliding windows into a global eigenvector. Finally, the initial ranking of the retrieval is obtained by measuring the similarity of the query image and the test image using the cosine distance, and the final mean Average Precision (mAP) is obtained by using the extended query method for rearrangement. We conduct experiments using the Oxford5k and Paris6k datasets and their extended datasets, Paris106k and Oxford105k. These experimental results indicate that the global feature extracted by the new method can better describe an image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.1047-1062
• /
• 2022

Differential power analysis (DPA) is disturbed by ghost peaks. There is a phenomenon that the mean absolute difference (MAD) value of the wrong key is higher than the correct key. We propose a compressed key guessing space (CKGS) scheme to solve this problem and analyze the AES algorithm. The DPA based on this scheme is named CKGS-DPA. Unlike traditional DPA, the CKGS-DPA uses two power leakage points for a combined attack. The first power leakage point is used to determine the key candidate interval, and the second is used for the final attack. First, we study the law of MAD values distribution when the attack point is AddRoundKey and explain why this point is not suitable for DPA. According to this law, we modify the selection function to change the distribution of MAD values. Then a key-related value screening algorithm is proposed to obtain key information. Finally, we construct two key candidate intervals of size 16 and reduce the key guessing space of the SubBytes attack from 256 to 32. Simulation experimental results show that CKGS-DPA reduces the power traces demand by 25% compared with DPA. Experiments performed on the ASCAD dataset show that CKGS-DPA reduces the power traces demand by at least 41% compared with DPA.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.757-770
• /
• 2022

Palmprint recognition has drawn increasingly attentions in the past decade due to its uniqueness and reliability. Traditional palmprint recognition methods usually use high-resolution images as the identification basis so that they can achieve relatively high precision. However, high-resolution images mean more computation cost in the recognition process, which usually cannot be guaranteed in mobile computing. Therefore, this paper proposes an improved low-resolution palmprint image recognition method based on residual networks. The main contributions include: 1) We introduce a channel attention mechanism to refactor the extracted feature maps, which can pay more attention to the informative feature maps and suppress the useless ones. 2) The ResStage group structure proposed by us divides the original residual block into three stages, and we stabilize the signal characteristics before each stage by means of BN normalization operation to enhance the feature channel. Comparison experiments are conducted on a public dataset provided by the Hong Kong Polytechnic University. Experimental results show that the proposed method achieve a rank-1 accuracy of 98.17% when tested on low-resolution images with the size of 12dpi, which outperforms all the compared methods obviously.

• Journal of Microbiology and Biotechnology
• /
• v.32 no.10
• /
• pp.1284-1291
• /
• 2022

The rise of methicillin-resistant Staphylococcus aureus (MRSA) has resulted in significant morbidity and mortality, and clinical treatment of MRSA infections has become extremely difficult. Sortase A (SrtA), a virulence determinant that anchors numerous virulence-related proteins to the cell wall, is a prime druggable target against S. aureus infection due to its crucial role in the pathogenicity of S. aureus. Here, we demonstrate that isovitexin, an active ingredient derived from a variety of traditional Chinese medicines, can reversibly inhibit SrtA activity in vitrowith a low dose (IC₅₀=24.72 ㎍/ml). Fluorescence quenching and molecular simulations proved the interaction between isovitexin and SrtA. Subsequent point mutation experiments further confirmed that the critical amino acid positions for SrtA binding to isovitexin were Ala-92, Ile-182, and Trp-197. In addition, isovitexin treatment dramatically reduced S. aureus invasion of A549 cells. This study shows that treatment with isovitexin could alleviate pathological injury and prolong the life span of mice in an S. aureus pneumonia model. According to our research, isovitexin represents a promising lead molecule for the creation of anti-S. aureus medicines or adjuncts.