American Journal of Computer Sciences and Applications

Detecting Video Inter-Frame Forgeries Based on Convolutional Neural Network Models

Research Article of American Journal of Computer Sciences and Applications Detecting Video Inter-Frame Forgeries Based on Convolutional Neural Network Models Xuan Hau Nguyena, Yongjian HUb, Khan Gohar Hayatc, Van Thinh Led, Tu D. Truonge a,cResearch Centre of Multimedia Information Security Detection and Intelligent Processing, School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510640, P.R.China. a,dFaculty of Information Technology Central Industrial and Commercial College, Phu Yen 620000, VietNam, eFaculty of Information Technology Ton Duc Thang University, Ho Chi Minh 700000, VietNam In the era of information explosion today, videos are easily captured and made viral in a short time and tampering videos have become easier due to editing software. So, the authenticity of videos become very essential. Video inter-frame forgeries are the most common type of video forgery methods. Until now some algorithms have been suggested for detecting inter-frame forgeries based on handicraft features but the accuracy and speed in processing of suggested algorithms are still challenging. In this paper, we are going to put forward a video forgeries detection method for detecting video inter-frame forgeries based on convolutional neural network (CNN) models by retraining the available CNN models trained on ImageNet dataset. The proposed methods based on CNN models which have been retrained to exploit spatial-temporal relationships in a video to robustly detect inter-frame forgeries. And in order to eliminate the errors due by the network, we have proposed a confidence score instead of the raw output score from networks. Through the results of experiments, we have proven that the proposed method has significantly higher efficiency and accuracy than recent methods. Keywords: Video forensic, video forgery detection, video inter-frame forgery detection, convolutional neural network, video authenticity, passive forensic ...

Hierarchical Model and Characterize Identified E-Commerce Trust to Generate Customer Satisfaction Data

Research Article of American Journal of Computer Sciences and Applications Hierarchical Model and Characterize Identified E-Commerce Trust to Generate Customer Satisfaction Data Solanke Ilesanmi, Adebayo, A.O., Adekunle, Y.A , Okolie, S.O Department of Computer Science, Babcock University The main reason consumers are reluctant to purchase from the internet vendors is the lack of trust. The lack of clues and face-to-face interaction in the online environment has made it more difficult to establish trust with consumers in e-commerce. The e-commerce trust issue is identified as a Multi-Criteria Decision Making (MCDM) problem thereby resulting to MCDM as an approach used to solve the problem because it emphasizes on the integration between fuzzy logic and Analytical Hierarchical Process (AHP) and is commonly used in the research community. This approach is being used to form the bases for the conceptual framework of this study. The literature review used a narrative method to give a direction and scope of the research, while the exploratory research approach is adopted to narrow it down to specific direction in order to be able to determine the research design, sample size, technique, design and data collection method. Such techniques are both implemented in order to give clear answers to lingering questions about the researcher’s mind, to synthesize all the information obtained and to arrive at a stand on which methodology and methods to be used to solve the problem under investigation. A hierarchical model has been developed which can be used to assess trust parameters in application using MCDM techniques. The methodology used can accurately determine both the subjective and objective trust factors and parameters of e-commerce trust applications simultaneously in complex situations where there is an abundance of ambiguity that is highly inherent in the process of human decision making. To evaluate the overall success of any information ...

Airport Taxi Dispatching Based on VISSIM and Multi-objective Programming Model

Research Article of American Journal of Computer Sciences and Applications Airport Taxi Dispatching Based on VISSIM and Multi-objective Programming Model Boying Lv1*, Yishuai Tian1, Botao Liu1 1College of Hydraulic & Environmental Engineering, China Three Gorges University, Yichang, 443002, China. This paper solved the problem of how to manage the distribution of airport taxis and balance the revenue of long- and short-haul passenger taxis. In this research, we established a multi-objective programming model, which was solved using genetic algorithms to obtain a reasonable distribution scheme in airport with the highest riding efficiency: set up a pick-up location in the middle of the pick-up area, requiring all cars to leave uniformly when fully loaded, and release an average of 78 taxis per batch in every single boarding location. In addition, with the queuing theory we set the basic parameters of the road. Taking the income balance difference as the objective function, we used the VISSIM software to simulate the simulation. Then the short-term “priority” arrangement plan was: Calculate the ratio of the travel time of the short-distance taxi to the distance from the airport to the city center. If the ratio is less than 0.0659, the taxis that meet the conditions are allowed to be given priority after return. The results have some guidance and strong practical significance. Keywords: VISSIM; Airport taxi; Genetic algorithm; Short-distance “priority” ...

Application of Artificial Intelligence in Forecasting: A Systematic Review

Review Article of American Journal of Computer Sciences and Applications Application of Artificial Intelligence in Forecasting: A Systematic Review Albert Annor-Antwi and Ayman A. M. Al-Dherasi Supervisor: Dr. Yang Chunting School of Electrical and Electronic Technology and Computer Science, Zhejiang University of Science and Technology Purpose: The aim of this reach is to identify how Artificial Intelligence (AI) could be used in enhancing forecasting to achieve more accurate outcomes. The research also explores the influence that forecasting has on global economy and the reasons why it needs to be accurate. Also, the research explains various pitfalls identified in forecasting. Method: This research implements two research approaches which are review of literature and formulation of hypotheses. Seven hypotheses are created. Findings: AI, when integrated with other technologies such as Machine Learning (ML) and when provided with the right computer power, yields much more accurate results than many other forecasting methods. The technology is costly, however, and it is prone to cyber-attacks. Conclusion: The future of business is highly reliant on forecasting, which directly impacts the global economy. But, not every business will have the power to own the forecasting technology due to the cost, and business will need to increase security to protect the forecasting systems. Keywords: Artificial Intelligence, Forecasting, Business, Finance, Market, Machine Learning ...

Manuscript Title: The title should be a brief phrase.

Author Information: List full names and affiliation of all authors, including Emails and phone numbers of corresponding author.

Abstract: The abstract should be less than 500 words. Following abstract, a list of keywords and abbreviations should be added. The keywords should be no more than 10. Abbreviation are only used for non standard and long terms.

Introduction: The introduction should included a clear statement of current problems.

Materials and Methods: This section should be clearly described.

Results and discussion: Authors may put results and discussion into a single section or show them separately.

Acknowledgement: This section includes a brief acknowledgment of people, grant details, funds

References: References should be listed in a numbered citation order at the end of the manuscript. DOIs and links to referenced articles should be added if available. Abstracts and talks for conferences or papers not yet accepted should not be cited.

Tables and figures: Tables should be used at a minimum with a short descriptive title. The preferred file formats for Figures/Graphics are GIF, TIFF, JPEG or PowerPoint.

Publication fees: We do not charge any submission charges, but authors are required to pay publication fees after their manuscripts are accepted for publication. For authors who receive our invitations, please send us the invitation code.

Proofreading and Publication: A proof will be sent to the corresponding author. Authors should carefully read it to avoid any errors and return any comments. We will update and publish it shortly. One of our goals is to minimize our publication time. For authors who do not return comments of proofreading on time, we may put the proof onlinefirst and replace it later with the final version. 

Withdrawal Policy: When you want to withdraw a published article, please send us your written request by email. We will withdraw/retract it from our system after reviewing the request. Please allow us enough time to process it. 

Terms of Use/Privacy Policy/Disclaimer/Other Policies: you agree that by using or receiving our services, you have read, understood, and agreed to be bound by all of our terms of use/privacy policy/ disclaimer/ other policies(Click here for details).

About the journal
The journal is hosted by eSciPub LLC. Our aim is to provide a platform that encourages publication of the most recent research and reviews for authors from all countries.

About the publisher
eSciPub LLC is a publisher to support Open Access initiative located in Houston, Texas, USA. It is a member of the largest community of professional publishers in the United States: the Independent Book Publishers Association. It hosts more than 100 Open Access journals in Medicine, Business & Economics, Agriculture, Biological Sciences, Chemistry, Education, Physical Sciences, Sociology, and Engineering and Technology.

Rapid Response Team
Please feel free to contact our rapid response team if you have any questions. Our customer representative will answer your questions shortly.

American Journal of Computer Sciences and Applications