• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.99-109
• /
• 2023

The darknet is frequently referred to as the hub of illicit online activity. In order to keep track of real-time applications and activities taking place on Darknet, traffic on that network must be analysed. It is without a doubt important to recognise network traffic tied to an unused Internet address in order to spot and investigate malicious online activity. Any observed network traffic is the result of mis-configuration from faked source addresses and another methods that monitor the unused space address because there are no genuine devices or hosts in an unused address block. Digital systems can now detect and identify darknet activity on their own thanks to recent advances in artificial intelligence. In this paper, offer a generalised method for deep learning-based detection and classification of darknet traffic. Furthermore, analyse a cutting-edge complicated dataset that contains a lot of information about darknet traffic. Next, examine various feature selection strategies to choose a best attribute for detecting and classifying darknet traffic. For the purpose of identifying threats using network properties acquired from darknet traffic, devised a hybrid deep learning (DL) approach that combines Recurrent Neural Network (RNN) and Bidirectional LSTM (BiLSTM). This probing technique can tell malicious traffic from legitimate traffic. The results show that the suggested strategy works better than the existing ways by producing the highest level of accuracy for categorising darknet traffic using the Black widow optimization algorithm as a feature selection approach and RNN-BiLSTM as a recognition model.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.12C
• /
• pp.1660-1668
• /
• 2004

This paper proposes a Voice Activity Detection (VAD) algorithm based on Radial Basis Function (RBF) network using dual threshold. The k-means clustering and Least Mean Square (LMS) algorithm are used to upade the RBF network to the underlying speech condition. The inputs for RBF are the three parameters in a Code Exited Linear Prediction (CELP) coder, which works stably under various background noise levels. Dual hangover threshold applies in BRF-VAD for reducing error, because threshold value has trade off effect in VAD decision. The experimental result show that the proposed VAD algorithm achieves better performance than G.729 Annex B at any noise level.

• International journal of advanced smart convergence
• /
• v.10 no.3
• /
• pp.131-142
• /
• 2021

Recently, there has been an active service that provides customized news to news subscribers. In this study, we intend to design a customized news service system through Deep Learning-based Social Network Service (SNS) activity analysis, applying real news and avoiding fake news. In other words, the core of this study is the study of delivery methods and delivery devices to provide customized news services based on analysis of users, SNS activities. First of all, this research method consists of a total of five steps. In the first stage, social network service site access records are received from user terminals, and in the second stage, SNS sites are searched based on SNS site access records received to obtain user profile information and user SNS activity information. In step 3, the user's propensity is analyzed based on user profile information and SNS activity information, and in step 4, user-tailored news is selected through news search based on user propensity analysis results. Finally, in step 5, custom news is sent to the user terminal. This study will be of great help to news service providers to increase the number of news subscribers.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.416-422
• /
• 2021

Due to the large differences in human activity within classes, the large similarity between classes, and the problems of visual angle and occlusion, it is difficult to extract features manually, and the detection rate of human behavior is low. In order to better solve these problems, an improved Faster R-CNN-based detection algorithm is proposed in this paper. It achieves multi-object recognition and localization through a second-order detection network, and replaces the original feature extraction module with Dense-Net, which can fuse multi-level feature information, increase network depth and avoid disappearance of network gradients. Meanwhile, the proposal merging strategy is improved with Soft-NMS, where an attenuation function is designed to replace the conventional NMS algorithm, thereby avoiding missed detection of adjacent or overlapping objects, and enhancing the network detection accuracy under multiple objects. During the experiment, the improved Faster R-CNN method in this article has 84.7% target detection result, which is improved compared to other methods, which proves that the target recognition method has significant advantages and potential.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.26-30
• /
• 2019

This paper proposes a new voice activity detection (VAD) method which is based on SNR and non-intrusive speech intelligibility estimation. In the conventional SNR-based VAD methods, voice activity probability is obtained by estimating frame-wise SNR at each spectral component. However these methods lack performance in various noisy environments. We devise a hybrid VAD method that uses non-intrusive speech intelligibility estimation as well as SNR estimation, where the speech intelligibility score is estimated based on deep neural network. In order to train model parameters of deep neural network, we use MFCC vector and the intrusive speech intelligibility score, STOI (Short-Time Objective Intelligent Measure), as input and output, respectively. We developed speech presence measure to classify each noisy frame as voice or non-voice by calculating the weighted average of the estimated STOI value and the conventional SNR-based VAD value at each frame. Experimental results show that the proposed method has better performance than the conventional VAD method in various noisy environments, especially when the SNR is very low.

• Journal of Communications and Networks
• /
• v.13 no.2
• /
• pp.86-94
• /
• 2011

In recent years, there has been a rise in epidemiological evidence suggesting the health benefits of a physically active lifestyle. However, it is not always easy for individuals to personally recognize the optimal conditions for exercise and physical activity. Wearable acceleration-based pedometers have become widely used in estimating the amount of physical activity, and to a limited extent, providing information regarding exercise intensity, but they have never been used to assess adaptation to exercise. In order to realize simultaneous activity monitoring for multiple users exercising outdoors, we developed a prototype wireless local area network (WLAN) based system. In our system, a WLAN is deployed outside, and a user wearing a smart phone and monitoring device exercises freely within the coverage area of the wireless network. By doing so, the developed system is able to monitor the activity of each user andmeasures various parameters including those related to exercise adaptation. In a demonstration experiment, the developed system was evaluated and used to monitor users enjoying a Nordic walk, after which users were immediately able to receive their exercise report. In this paper, we discuss the requirements and issues in developing an activity monitoring system and report the findings we obtained through the demonstration experiment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3477-3483
• /
• 2015

A reasonable process for the activity duration estimation is required for the successful construction management because it directly affects the entire construction duration and budget. However, the activity duration is being generally estimated by the experience of the construction manager. This study suggests an estimation model of construction activity duration using neural network theory. This model estimates the activity duration by considering both the quantitative and qualitative elements, and the model is verified by a case study. Because the suggested model estimates the activity duration by a reasonable schedule plan, it is expected to reduce the error between planning duration and actual duration in a construction project.

• Journal of Radiation Protection and Research
• /
• v.46 no.3
• /
• pp.143-150
• /
• 2021

Since its establishment in 2018, the Young Generation Network (YGN) has been dedicated, with support of the International Radiation Protection Association (IRPA), to a variety of activities to promote communication, collaboration and professional development of students and young professionals in the area of radiation protection and its allied fields. This article reports our recent activities from the middle of 2018 to the beginning of 2021, with highlights on some important events: "Joint JHPS-SRP-KARP Workshop of Young Generation Network" (December 2019 in Japan); contribution to "Nuclear Energy Agency Workshop on Optimization: Rethinking the Art of Reasonable" (January 2020 in Portugal); survey on the impact of coronavirus disease 2019 (COVID-19) on radiation protection among IRPA YGN members (March 2020); and contribution to IRPA15 (15^th International Congress of the IRPA; January-February 2021, online). The discussion and insight obtained from each activity are also summarized. The IRPA YGN will aim to achieve its on-going activities and continue to follow the ways paved in the Strategic Agenda and despite the challenges raised by the COVID-19 pandemic. Namely, running an international survey (for example, on the usage of social media in radiation protection, and on the long-term consequences of the COVID-19 pandemic), engaging national YGNs, extending the network, finding new relationships with networks with an interest in the young generation and participation in (remote) events will be aspired for.

• Journal of Microbiology and Biotechnology
• /
• v.22 no.7
• /
• pp.923-929
• /
• 2012

Optimization of culture conditions for L-asparaginase production by submerged fermentation of Aspergillus terreus MTCC 1782 was studied using a 3-level central composite design of response surface methodology and artificial neural network linked genetic algorithm. The artificial neural network linked genetic algorithm was found to be more efficient than response surface methodology. The experimental $_L$-asparaginase activity of 43.29 IU/ml was obtained at the optimum culture conditions of temperature $35^{\circ}C$, initial pH 6.3, inoculum size 1% (v/v), agitation rate 140 rpm, and incubation time 58.5 h of the artificial neural network linked genetic algorithm, which was close to the predicted activity of 44.38 IU/ml. Characteristics of $_L$-asparaginase production by A. terreus MTCC 1782 were studied in a 3 L bench-scale bioreactor.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.205-211
• /
• 2024

The increasing number of botnet attacks incorporating new evasion techniques making it infeasible to completely secure complex computer network system. The botnet infections are likely to be happen, the timely detection and response to these infections helps to stop attackers before any damage is done. The current practice in traditional IP networks require manual intervention to response to any detected malicious infection. This manual response process is more probable to delay and increase the risk of damage. To automate this manual process, this paper proposes to automatically select relevant countermeasures for detected botnet infection. The propose approach uses the concept of flow trace to detect botnet behavior patterns from current and historical network activity. The approach uses the multiclass machine learning based approach to detect and classify the botnet activity into IRC, HTTP, and P2P botnet. This classification helps to calculate the risk score of the detected botnet infection. The relevant countermeasures selected from available pool based on risk score of detected infection.