• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.26-36
• /
• 2021

The Internet was created as a decentralized and autonomous system of interconnected computer networks used for data exchange across mutually trusted participants. The element technologies on the Internet, such as inter-domain and intra-domain routing and DNS, operated in a distributed manner. With the development of the Web, the Web has become indispensable in daily life. The existing web applications allow us to form online communities, generate private information, access big data, shop online, pay bills, post photos or videos, and even order groceries. This is what has led to centralization of the Web. This centralization is now controlled by the giant social media platforms that provide it as a service, but the original Internet was not like this. These giant companies realized that the decentralized network's huge value involves gathering, organizing, and monetizing information through centralized web applications. The centralized Web applications have heralded some major issues, which will likely worsen shortly. This study focuses on these problems and investigates blockchain's potentials for decentralized web architecture capable of improving conventional web services' critical features, including autonomous, robust, and secure decentralized processing and traceable trustworthiness in tamper-proof transactions. Finally, we review the decentralized web architecture that circumvents the main Internet gatekeepers and controls our data back from the giant social media companies.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.75-80
• /
• 2021

Artificial intelligence is becoming an important part of our lives providing incredible benefits. In this respect, facial expression recognition has been one of the hot topics among computer vision researchers in recent decades. Classifying small dataset of low resolution images requires the development of a new small scale deep CNN model. To do this, we propose a method suitable for small datasets. Compared to the traditional deep CNN models, this model uses only a fraction of the memory in terms of total learnable weights, but it shows very similar results for the FER2013 and FERPlus datasets.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.69-75
• /
• 2022

Due to the increase in the demand for anomaly detection according to the ageing of power generation facilities, the need for developing an anomaly detection method that can provide high-reliability turbine blade anomaly detection performance has been continuously raised. Additionally, the false detection results caused by a human error accelerates the increase of the need. In this paper, we propose an anomaly detection technique for turbine blades in power plants using deep neural networks. Experimental results prove that the proposed technique achieves stable anomaly detection performance while minimizing human factor intervention.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.9-15
• /
• 2022

This paper proposes a coordinated multi-point communication (CoMP) method with channel selection to improve performance of a macro user equipment (MUE) in a dense small-cell network environment in a building located within coverage of a macro base station (MBS). In the proposed CoMP method, in order to improve the performance of the MUE located in the building, A small-cell base station (SBS) selects a channel with lower interference to the neighboring MUE and transmits appropriate signals to the MUE requiring CoMP. Simulation results show that the proposed CoMP method improves the performance of the MUE by up to 164% and 51%, respectivley, compared to a random channel allocation based traditional SBS network and CoMP method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.809-814
• /
• 2022

ADHD is a disorder showing inattentiveness and hyperactivity. Since symptoms diagnosed in childhood continue to the adulthood, it is important to diagnose ADHD and start treatments in early stages. However, it has the problems to acquire enough and accurate data for the diagnosis because the mental state of children is immature using the self-diagnosis method or the computerized test. In this paper, we present the classification method based on the CNN model and execute experiment using the EEG data to improve the objectiveness and the accuracy of ADHD diagnosis. For the experiment, we build the 3D convolutional networks model and exploit the 5-folds cross validation method. The result shows the 97% accuracy on average.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.69-74
• /
• 2022

SNN (Spiking Neural Network) operating in neuromorphic architecture was created by mimicking human neural networks. Neuromorphic computing based on neuromorphic architecture requires relatively lower power than typical deep learning techniques based on GPUs. For this reason, research to support various artificial intelligence models using neuromorphic architecture is actively taking place. This paper conducted a performance analysis of the speech recognition model based on neuromorphic architecture according to the speech data preprocessing technique. As a result of the experiment, it showed up to 84% of speech recognition accuracy performance when preprocessing speech data using the Fourier transform. Therefore, it was confirmed that the speech recognition service based on the neuromorphic architecture can be effectively utilized.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.672-685
• /
• 2022

This article proposes a subject-independent application of brain-computer interfacing (BCI). A 32-channel Electroencephalography (EEG) device is used to measure imagined speech (SI) of four words (sos, stop, medicine, washroom) and one phrase (come-here) across 13 subjects. A deep long short-term memory (LSTM) network has been adopted to recognize the above signals in seven EEG frequency bands individually in nine major regions of the brain. The results show a maximum accuracy of 73.56% and a network prediction time (NPT) of 0.14 s which are superior to other state-of-the-art techniques in the literature. Our analysis reveals that the alpha band can recognize SI better than other EEG frequencies. To reinforce our findings, the above work has been compared by models based on the gated recurrent unit (GRU), convolutional neural network (CNN), and six conventional classifiers. The results show that the LSTM model has 46.86% more average accuracy in the alpha band and 74.54% less average NPT than CNN. The maximum accuracy of GRU was 8.34% less than the LSTM network. Deep networks performed better than traditional classifiers.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.354-362
• /
• 2021

The device to device (D2D) communication is an important and emerging area for future cellular networks. It is concerned about all aspect of secure data transmission between end devices along with originality of the data. In this paradigm, the major concerns are about how keys are delivered between the devices when the devices require the cryptographic keys. Another major concern is how effectively the receiver device verifies the data sent by the sender device which means that the receiver checks the originality of the data. In order to fulfill these requirements, the proposed system able to derive a cryptographic key using a single secret key and these derived keys are securely transmitted to the intended receiver with procedure called mutual authentication. Initially, derived keys are computed by applying robust procedure so that any adversary feel difficulties for cracking the keys. The experimental results shows that both sender and receiver can identify themselves and receiver device will decrypt the data only after verifying the originality of the data. Only the devices which are mutually authenticated each other can interchange the data so that entry of the intruder node at any stage is not possible.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1113-1120
• /
• 2021

Content Central Network (CCN) appeared to improve network efficiency by transforming IP-based network into content name-based network structures. Each router performs caching mechanism to improve network efficiency in the CCN. And the cache replacement policy applied to the CCN router is an important factor that determines the overall performance of the CCN. Therefore various studies has been done relating to cache replacement policy of the CCN. In this paper, we proposed a cache replacement policy that improves the limitations of the LFU policy. The proposal algorithm applies real-time producer popularity-based variables. And through experiments, we proved that the proposed policy shows a better cache hit ratio than existing policies.