• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.9-16
• /
• 2023

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

• Elastomers and Composites
• /
• v.54 no.1
• /
• pp.22-29
• /
• 2019

Chitosan-polyvinyl alcohol (PVA) -bamboo charcoal/silica (CS-PVA-BC/SI) hybrid fillers with compatibilized styrene-butadiene rubber (SBR) composites were fabricated by the interpenetrating polymer network (IPN) method. The structure and composition of the composite samples were characterized by scanning electron microscope (SEM) and Fourier transform infrared spectroscopy (FT-IR). The viscoelastic behaviors of the rubber composites and their vulcanizates were explored using a rubber processing analyzer (RPA) in the rheometer, strain sweep and temperature sweep modes. The storage and loss moduli of SBR increased significantly with the incorporation of different hybrid fillers, which was attributed to the formation of an interphase between the hybrid fillers and rubber matrix, and the effective dispersion of the hybrid fillers. The mechanical properties (hardness, tensile strength, oxygen transmission rate, and swelling rate) of the composite samples were characterized in detail. From the results of the mechanical test, it was found that BC-CS-PVA0SBR had the best mechanical properties. Therefore, the BC-CS-PVA hybrid filler provided the best reinforcement effects for the SBR latex in this research.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.271-281
• /
• 2022

Manual seed classification challenges can be overcome using a reliable and autonomous seed purity identification and classification technique. It is a highly practical and commercially important requirement of the agricultural industry. Researchers can create a new data mining method with improved accuracy using current machine learning and artificial intelligence approaches. Seed classification can help with quality making, seed quality controller, and impurity identification. Seeds have traditionally been classified based on characteristics such as colour, shape, and texture. Generally, this is done by experts by visually examining each model, which is a very time-consuming and tedious task. This approach is simple to automate, making seed sorting far more efficient than manually inspecting them. Computer vision technologies based on machine learning (ML), symmetry, and, more specifically, convolutional neural networks (CNNs) have been widely used in related fields, resulting in greater labour efficiency in many cases. To sort a sample of 3000 seeds, KNN, SVM, CNN and CNN-SVM hybrid classification algorithms were used. A model that uses advanced deep learning techniques to categorise some well-known seeds is included in the proposed hybrid system. In most cases, the CNN-SVM model outperformed the comparable SVM and CNN models, demonstrating the effectiveness of utilising CNN-SVM to evaluate data. The findings of this research revealed that CNN-SVM could be used to analyse data with promising results. Future study should look into more seed kinds to expand the use of CNN-SVMs in data processing.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.249-259
• /
• 2022

Project management and deployment has gone through a long journey from traditional and agile to continuous integration, continuous deployment and continuous monitoring. Software industry benefited with the latest buzzword in the development process, DevOps that not only escalates software productivity but at the same time enhances software quality. But the implementation and assessment of DevOps practices is expository as there are no guidelines to assess and improvise DevOps application in software industries. Hence, there was a need to develop a hybrid model to assist software practitioners in DevOps implementation. The intention behind this paper is to implement the already proposed DevOps hybrid model using suggested tool chains including Jenkins, Selenium, GitLab, Ansible and Nagios automation tools through Jenkins project management environment and plugins. To achieve this implementation objective, a java application is developed with a web-based graphical interface. Further, in this paper, different challenges and benefits of Jenkins implementation shall also be outlined. The paper also presents the effectiveness of DevOps based Model implementation in software organizations. The impact of considering other automation tools and models can also be considered as a part of further research.

• International Journal of Computer Science & Network Security
• /
• v.24 no.3
• /
• pp.12-22
• /
• 2024

The travelling salesman problem is very famous and very difficult combinatorial optimization problem that has several applications in operations research, computer science and industrial engineering. As the problem is difficult, finding its optimal solution is computationally very difficult. Thus, several researchers have developed heuristic/metaheuristic algorithms for finding heuristic solutions to the problem instances. In this present study, a new hybrid genetic algorithm (HGA) is suggested to find heuristic solution to the problem. In our HGA we used comprehensive sequential constructive crossover, adaptive mutation, 2-opt search and a new local search algorithm along with a replacement method, then executed our HGA on some standard TSPLIB problem instances, and finally, we compared our HGA with simple genetic algorithm and an existing state-of-the-art method. The experimental studies show the effectiveness of our proposed HGA for the problem.

• Journal of Korean Society on Water Environment
• /
• v.21 no.2
• /
• pp.132-140
• /
• 2005

The pilot test of a new alternative for small wastewater treatment system has been conducted for two years. It consists of a hybrid bioreactor and the expert system including the process control logic, PLC system, and HMI for the process automation. In order to monitor and remote control its status, the real-time data was transferred from the on-site control center to the central station via a wireless local area network. More efficient and stable performances were observed at automatic operating mode compared with the manual. On an average, COD, SS, T-N and T-P concentrations in the effluent from the hybrid bioreactor were less than 14, 7, 12 and 0.9 mg/L, respectively. According to the result from pilot tests, the quality of treated wastewater with sand filtration was enough to be utilized again.

• ETRI Journal
• /
• v.33 no.6
• /
• pp.897-903
• /
• 2011

A hybrid ${\Delta}{\Sigma}$ modulator for audio applications is presented in this paper. The pulse generator for digital-to-analog converter alleviates the requirement of the external clock jitter and calibrates the coefficient variation due to a process shift and temperature changes. The input resistor network in the first integrator offers a gain control function in a dB-linear fashion. Also, careful chopper stabilization implementation using return-to-zero scheme in the first continuous-time integrator minimizes both the influence of flicker noise and inflow noise due to chopping. The chip is implemented in a 0.13 ${\mu}m$ CMOS technology (I/O devices) and occupies an active area of 0.37 $mm^2$. The ${\Delta}{\Sigma}$ modulator achieves a dynamic range (A-weighted) of 97.8 dB and a peak signal-to-noise-plus-distortion ratio of 90.0 dB over an audio bandwidth of 20 kHz with a 4.4 mW power consumption from 3.3 V. Also, the gain of the modulator is controlled from -9.5 dB to 8.5 dB, and the performance of the modulator is maintained up to 5 nsRMS external clock jitter.

• ETRI Journal
• /
• v.36 no.5
• /
• pp.819-828
• /
• 2014

To solve the increasing popularity of video streaming services over the Internet, recent research activities have addressed the locality of content delivery from a network edge by introducing a storage module into a router. To employ in-network caching and persistent request routing, this paper introduces a hybrid content delivery network (CDN) system combining novel content routers in an underlay together with a traditional CDN server in an overlay. This system first selects the most suitable delivery scheme (that is, multicast or broadcast) for the content in question and then allocates an appropriate number of channels based on a consideration of the content's popularity. The proposed scheme aims to minimize traffic volume and achieve optimal delivery cost, since the most popular content is delivered through broadcast channels and the least popular through multicast channels. The performance of the adaptive scheme is clearly evaluated and compared against both the multicast and broadcast schemes in terms of the optimal in-network caching size and number of unicast channels in a content router to observe the significant impact of our proposed scheme.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.259-274
• /
• 2005

In this paper, we propose a methodology to estimate the number of users in e-Commerce systems. There have been a lot of previous work under the closed-LAN system environment. But the study on the number of acceptable users in real network environment is hard to find in the literature. Our research applies a Hybrid Simulation by using QoS results for end-to-end high-speed Internet service, and experiments are performed with regard to LAN and WAN, network equipments, and various network bandwidth. As result of the experiments we observed that the response time of high-speed Internet service media(Wireless LAN, ADSL, Cable, VDSL) depends heavily on the sequence and depth of transactions and on the ratio of transactional and non-transactional interactions. That is, as the network and application get more loads, the number of acceptable users decreases. By adding a cache server and an L4 switch to the simulation model, we analysed the changes in the number of users and client response time.

• ETRI Journal
• /
• v.35 no.5
• /
• pp.786-796
• /
• 2013

In this paper, we propose a hybrid time-division multiplexing and dense wavelength-division multiplexing scheme to implement a cost-effective and scalable long-reach optical access network (LR-OAN). Our main objectives are to increase fiber plant utilization, handle upstream and downstream flow through the same input/output port, extend the reach, and increase the splitting ratio. To this end, we propose the use of an arrayed waveguide grating (AWG) and an erbium-doped fiber amplifier (EDFA) in one configuration. AWG is employed to achieve the first and second objectives, while EDFA is used to achieve the third and fourth objectives. The performance of the proposed LR-OAN is verified using the Optisystem and Matlab software packages under bit error rate constraints and two different approaches (multifiber and single-fiber). Although the single-fiber approach offers a more cost-effective solution because service is provided to each zone via a common fiber, it imposes additional losses, which leads to a reduction in the length of the feeder fiber from 20 km to 10 km.