• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.352-358
• /
• 2022

Text mining is an important process used for analyzing the data collected from different sources like videos, audio, social media, and so on. The tools like Natural Language Processing (NLP) are mostly used in real-time applications. In the earlier research, text mining approaches were implemented using long-short memory (LSTM) networks. In this paper, text mining is performed using average-stochastic gradient descent weight-dropped (AWD)-LSTM techniques to obtain better accuracy and performance. The proposed model is effectively demonstrated by considering the internet movie database (IMDB) reviews. To implement the proposed model Python language was used due to easy adaptability and flexibility while dealing with massive data sets/databases. From the results, it is seen that the proposed LSTM plus weight dropped plus embedding model demonstrated an accuracy of 88.36% as compared to the previous models of AWD LSTM as 85.64. This result proved to be far better when compared with the results obtained by just LSTM model (with 85.16%) accuracy. Finally, the loss function proved to decrease from 0.341 to 0.299 using the proposed model

• Journal of Biomedical Engineering Research
• /
• v.42 no.5
• /
• pp.232-240
• /
• 2021

Heterogeneity in cancer is the major obstacle for precision medicine and has become a critical issue in the field of a cancer diagnosis. Many attempts were made to disentangle the complexity by molecular classification. However, multi-dimensional information from dynamic responses of cancer poses fundamental limitations on biomolecular marker-based conventional approaches. Cell morphology, which reflects the physiological state of the cell, can be used to track the temporal behavior of cancer cells conveniently. Here, we first present a hybrid learning-based platform that extracts cell morphology in a time-dependent manner using a deep convolutional neural network to incorporate multivariate data. Feature selection from more than 200 morphological features is conducted, which filters out less significant variables to enhance interpretation. Our platform then performs unsupervised clustering to unveil dynamic behavior patterns hidden from a high-dimensional dataset. As a result, we visualize morphology state-space by two-dimensional embedding as well as representative morphology clusters and trajectories. This cell morphology profiling strategy by hybrid learning enables simplification of the heterogeneous population of cancer.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1075-1084
• /
• 2022

Internet of Things(IoT) has become a key available technology for efficiently implementing device to device(D2D) services in various domains such as smart home, healthcare, smart city, agriculture, energy, logistics, and transportation. A lightweight publish/subscribe(Pub/Sub) messaging protocol not only establishes data dissemination pattern but also supports connectivity between IoT devices and their applications. Also, a Pub/Sub broker is deployed to facilitate data exchange among IoT devices. A scalable edge-based publish/subscribe (Pub/Sub) broker overlay networks support latency-sensitive IoT applications. In this paper, we design a hypercube grid quorum(HGQ) for distributed Pub/Sub systems based IoT applications. In designing HGQ, the network of hypercube structures suitable for the publish/subscribe model is built in the edge layer, and the proposed HGQ is designed by embedding a mesh overlay network in the hypercube. As their applications, we propose an HGQ-based mechansim for dissemination of the data of sensors or the message/event of IoT devices in IoT environments. The performance of HGQ is evaluated by analytical models. As the results, the latency and load balancing of applications based on the distributed Pub/Sub system using HGQ are improved.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.120-128
• /
• 2023

In this work, we have presented ATSA, a hierarchical attention deep learning model for Arabic sentiment analysis. ATSA was proposed by addressing several challenges and limitations that arise when applying the classical models to perform opinion mining in Arabic. Arabic-specific challenges including the morphological complexity and language sparsity were addressed by modeling semantic composition at the Arabic morphological analysis after performing tokenization. ATSA proposed to perform phrase-chunks sentiment embedding to provide a broader set of features that cover syntactic, semantic, and sentiment information. We used phrase structure parser to generate syntactic parse trees that are used as a reference for ATSA. This allowed modeling semantic and sentiment composition following the natural order in which words and phrase-chunks are combined in a sentence. The proposed model was evaluated on three Arabic corpora that correspond to different genres (newswire, online comments, and tweets) and different writing styles (MSA and dialectal Arabic). Experiments showed that each of the proposed contributions in ATSA was able to achieve significant improvement. The combination of all contributions, which makes up for the complete ATSA model, was able to improve the classification accuracy by 3% and 2% on Tweets and Hotel reviews datasets, respectively, compared to the existing models.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.42 no.4 s.334
• /
• pp.45-52
• /
• 2005

This paper presents the characterization of through hole vias on printed circuit board (PCB) through the time domain and frequency domain measurements. The time domain measurement was performed on a single via using the TDR, and the model parameters were extracted by the fitting simulation using HSPICE. The frequency domain measurement was also performed by using 2 port VNA, and the model parameters were extracted by fitting simulation with ADS. Using the ABCD matrices, the do-embedding equations were derived probing in the same plane in the VNA measurement. Based on the single via characterization, the differential via characterization was also performed by using TDR measurements. The time domain measurements were performed by using the odd mode and even mode sources in TDR module, and the Parameter values were extracted by fitting with HSPICE. Comparing measurements with simulations, the maximum calculated differences were $14\%$ for single vias and $17\%$ for differential vias.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.5 s.311
• /
• pp.62-71
• /
• 2006

Development of an artificial reverberation algorithm with low memory requirements has been an issue of importance in applications such as mobile multimedia devices. One possible solution to this problem is to embed a time-varying all-pass filter to the feedback loop of the comb filter. In this paper, theoretical and perceptual analyses of reverberators embedding time-varying all-pass filters are presented. The analyses are to iud a perceptually acceptable degree of phase variation by the all-pass filter. Based on the analyses, we propose a new methodology of designing reverberators embedding time-varying all-pass filters. Through the subjective tests, we showed that, even with smaller memory, the proposed method is capable of providing perceptually comparable sound quality to the conventional methods involving time-invariant parameters.

• Journal of Korea Multimedia Society
• /
• v.6 no.5
• /
• pp.861-869
• /
• 2003

The rapid growth of multimedia network systems has caused overflowing illegal copies of digital contents. Among digital contents, watermarking technique can be used to protect ownership about the image. Copyright protection involves the authentication of image ownership and the identification of illegal copies of image. In this paper, a new digital watermarking technique using HVS and adaptive scale factor based on the wavelet transform is proposed to use the binary image watermark. The original image is decomposed by 3-level wavelet transform. It is embedded to baseband and high frequency band. The embedding in the baseband is considered robustness, the embedding in the high frequency band is concerned about HVS and invisibility. The watermarking of a visually recognizable binary image used the HVS and random permutation to protect the copyright. From the experimental results, we confirm that the proposed technique is strong to various attacks such as joint photographic experts ground(JPEG) compression, cropping, collusion, and inversion of lines.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.4
• /
• pp.202-209
• /
• 2005

The rapid development of digital media and communication network urgently brings about the need of data certification technology to protect IPR (Intellectual property right). This paper proposed a new watermarking method for embedding owner's audio signal. Because this method uses an audio signal as a watermark to be embedded, it is very useful to claim the ownership aurally. And it has the advantage of restoring audio signal modified and especially removed by image removing attacks by applying our LBX(Linear Bit-expansion) interleaving. Three basic stages of our watermarking include: 1) Encode . analogue owner's audio signal by PCM and create new digital audio watermark, 2) Interleave an audio watermark by our LBX; and 3) Embed the interleaved audio watermark in the low frequency band on DTn (Discrete Haar Wavelet Transform) of image. The experimental results prove that this method is resistant to lossy JPEG compression as standard image compression and especially to cropping and rotation which remove a part of Image.