• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.212-216
• /
• 2024

Feature Selection have turned into the main point of investigations particularly in bioinformatics where there are numerous applications. Deep learning technique is a useful asset to choose features, anyway not all calculations are on an equivalent balance with regards to selection of relevant features. To be sure, numerous techniques have been proposed to select multiple features using deep learning techniques. Because of the deep learning, neural systems have profited a gigantic top recovery in the previous couple of years. Anyway neural systems are blackbox models and not many endeavors have been made so as to examine the fundamental procedure. In this proposed work a new calculations so as to do feature selection with deep learning systems is introduced. To evaluate our outcomes, we create relapse and grouping issues which enable us to think about every calculation on various fronts: exhibitions, calculation time and limitations. The outcomes acquired are truly encouraging since we figure out how to accomplish our objective by outperforming irregular backwoods exhibitions for each situation. The results prove that the proposed method exhibits better performance than the traditional methods.

• Journal of Korea Trade
• /
• 제26권7호
• /
• pp.59-76
• /
• 2022

Purpose - As ahigher-order ability, improvisational capability is often employed to help a firm cope with unexpected or unanticipated issues. In light of the severe global business challenges and turbulent environmental changes, this study aimed to explore whether home-based network ties could shape the influence of improvisational capability on international entrepreneurship, alongside investigating the boundary conditions of competitive turbulence in their moderating effects. Design/methodology - The sample for the international entrepreneurship sector was obtained from the Industry and Information Technology Department of Jiangsu. In September 2021, the questionnaires were sent to the targeted ventures and required the top managers to complete the survey by email or telephone. The final research sample comprised 113 international new ventures. To test the hypotheses, moderated hierarchical regression analysis was conducted. Findings - Our empirical results suggested that (1) unlike some previous literature, a positive effect of improvisational capability on the performance of international new ventures was not found; (2) home country-based networks (both political ties and business ties) are contingent factors that may partially stimulate the value creation of improvisational capability; and (3) in a highly competitive environment, the moderating role of business ties at home may become much stronger, however, the contingent role of political ties at home was not found. Originality/value - This study mainly concentrates on the two important types of home country-based networks, political and business ties at home, that may help international new ventures access strategic resources necessary for supporting the performance implications of improvisational capability. Thus, it extends the existing improvisational theory to encompass international entrepreneurship.

• 무역상무연구
• /
• 제15권
• /
• pp.239-261
• /
• 2001

There are many kinds of risk in int'l trade by internet network, such as credit risk, mercantile risk, contingency risk, exchange risk, physical risk and the risk on internet network. Especially, risk management against credit risk and the risk on internet network are very important. The former is conventional but more important these days. The latter is a new risk that has been incurred owing to the int'l trade by internet network. The system of risk management against the former are firstly, to surely research credit of counterpart by internet, secondly, to certify the entity by password or fingerprint, thirdly, to pay the price under a letter of credit, fourthly, to use the system of int'l trade such as bolero, trade card, finally, to use the authority of electronic trade services. The system of risk management against the latter are firstly, to install the firewall on the own computer network, secondly, to entrust the management own computer network to the network security services firm, thirdly, to electronically communicate with counterpart through the certification authority, finally, to insure against the own network risk with the security insurance company.

• International Journal of Advanced Culture Technology
• /
• 제9권2호
• /
• pp.80-85
• /
• 2021

This study is to analyze the structure of the networks of tourism marketing on Twitter, identifying the most prominent users, the flow of information about tourism marketing, and the interaction between the users posting tweets. This study employs NodeXL pro as a visualization software package for social network analysis. The number of vertices or nodes is 171, and the number of the unique edges or links is 128, but there are 101 edges with duplicates, so the total links are 229, which means that there are fewer Twitter accounts in the social network on tourism marketing, but they have a few close relationships by sharing information. The research can map the social network of communicators of tourism marketing using Twitter data. The network has a complicated pattern, including one independent network and some connected networks. Some mediators connect each network and can control the information flow of tourism marketing. More communicators are getting the information than the ones providing it, which means that there is likely to be the dependence of information among communicators that can cause an obstacle and distortion of the information flow system, especially in the independent network.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.23-30
• /
• 2022

Glaucoma is a chronic neuropathy that affects the optic nerve which can lead to blindness. The detection and prediction of glaucoma become possible using deep neural networks. However, the detection performance relies on the availability of a large number of data. Therefore, we propose different frameworks, including a hybrid of a generative adversarial network and a convolutional neural network to automate and increase the performance of glaucoma detection. The proposed frameworks are evaluated using five public glaucoma datasets. The framework which uses a Deconvolutional Generative Adversarial Network (DCGAN) and a DenseNet pre-trained model achieves 99.6%, 99.08%, 99.4%, 98.69%, and 92.95% of classification accuracy on RIMONE, Drishti-GS, ACRIMA, ORIGA-light, and HRF datasets respectively. Based on the experimental results and evaluation, the proposed framework closely competes with the state-of-the-art methods using the five public glaucoma datasets without requiring any manually preprocessing step.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.255-261
• /
• 2022

Routing Protocol for Low-Power and Lossy Networks (RPLs) in Internet of Things (IoT) is currently one of the most popular wireless technologies for sensor communication. RPLs are typically designed for specialized applications, such as monitoring or tracking, in either indoor or outdoor conditions, where battery capacity is a major concern. Several routing techniques have been proposed in recent years to address this issue. Nevertheless, the expansion of the network lifetime in consideration of the sensors' capacities remains an outstanding question. In this research, aANN-CUCKOO based optimization technique is applied to obtain a more efficient and dependable energy efficient solution in IOT-RPL. The proposed method uses time constraints to minimise the distance between source and sink with the objective of a low-cost path. By considering the mobility of the nodes, the technique outperformed with an efficiency of 98% compared with other methods. MATLAB software is used to simulate the proposed model.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.358-366
• /
• 2022

Wireless sensor networks (WSN) are becoming widely used in collecting and sensing information in different fields such as in the medical area, smart phone industry and military environment. The main concern here is reducing the power consumption because it effects in the lifetime of wireless sensor during commutation because it may be work in some environment like sensor in the battlefields where is not easy to change the battery for a node and that may decrease the efficiency of that node and that may affect the network traffic may be interrupted because one or more nodes stop working. In this paper we implement, simulate, and investigate S-MAC protocol with mobility support and show the sequence of events the sender and receiver go through. We tested some parameters and their impacts of on the performance including System throughput, number of packets successfully delivered per second, packet delay, average packet delay before successful transmission.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.223-228
• /
• 2022

Femtocells are being incorporated into heterogeneous networks in order to increase the network capacity. However, intensive deployment of femtocells results in undesired interference, which lowers the system's performance. Controlling the femtocell transmission power is one of of the aspects that can be addressed in order to mitigate the negative effects of the interference. It may also be utilized to facilitate the auto-configuration of the network's conductance, if necessary. This paper proposes the use of an auto-configuration technique for transmission power. The suggested technique is based on the transmission power of macrocells and the coverage provided by femtocells. The simulation findings show that the network's capacity has increased, and the amount of interference has decreased.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.55-60
• /
• 2022

Churn prediction is a critical long-term problem for many business like music, games, magazines etc. The churn probability can be used to study many aspects of a business including proactive customer marketing, sales prediction, and churn-sensitive pricing models. It is quite challenging to design machine learning model to predict the customer churn accurately due to the large volume of the time-series data and the temporal issues of the data. In this paper, a parallel artificial neural network is proposed to create a highly-accurate customer churn model on a large customer dataset. The proposed model has achieved significant improvement in the accuracy of churn prediction. The scalability and effectiveness of the proposed algorithm is also studied.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.97-104
• /
• 2022

In recent years, data privacy has become increasingly important. The goal of network cryptography is to protect data while it is being transmitted over the internet or a network. Social media and smartphone apps collect a lot of personal data which if exposed, might be damaging to privacy. As a result, sensitive data is exposed and data is shared without the data owner's consent. Personal Information is one of the concerns in data privacy. Protecting user data and sensitive information is the first step to keeping user data private. Many applications user data can be found on other websites. In this paper, we discuss the issue of privacy and suggest a mechanism for keeping user data hidden in other applications.