This paper proposed feature level fusion technique to develop a robust multimodal human identification system. The humane face-iris traits are fused together to improve system accuracy in recognizing 40 persons taken from ORL and CASIA-V1 database. Also, low quality iris images of MMU-1 database are considered in this proposal for further test of recognition accuracy. The face-iris features are extracted using four comparative methods. The texture analysis methods like Gray Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) are both gained 100% accuracy rate, while the Principle Component Analysis (PCA) and Fourier Descriptors (FDs) methods achieved 97.5% accuracy rate only.

In the last two decades many document management systems have evolved and have been deployed for use in business areas such as marketing, production, sales, shipping, banking, education, etc. The demand for electronic document management system has continued to rise with new application areas discovered from day to day. This paper is the first of a two-part study that dwells on the conceptualization, development and deployment of an online documentation system for trade facilitation applications. This paper demonstrates how an organization can build a cost-effective and efficient electronic document management system using open source like MySQL and PHP. The domain of application stressed in this paper is X-ray Cargo Scanning operations as conducted by Government agencies especially the Customs and Excise or their appointees during imports, exports inspection and cargo clearance at the ports. In this paper, the authors investigated various operations that preceed clearance of shipments at ports in Lagos Nigeria. The role of Cargo scanners, image acquisition and subsequent analysis as well as challenges were buttressed. Following the investigation, analysis and design of a solution were done. This paper presents the results of the analysis as well as the system specifications which are considered vital for the implementation of a realtime integrated solution. The proposed system would provide a platform that enhances productivity in a risk management and scanning service organization especially in managing and exchanging large volumes of scanner-generated documentation across a network as well as with other agencies.

Scrum is a well-known agile model due to its strong management practices. It can be mingled with many software development models such as extreme programming (XP), Agile Unified Process, and Feature Driven Development (FDD). Lean is a very popular known process in the automobile industry due to its effective practices such as Kanban bard and smooth workflow. Lean development is gaining popularity in the software industry from the last few years. Lean development is rational, convenient, responsive, and team-based and it adds value to the enterprise. Scrum is useable and practical for small and medium projects but it does not render positive support for the large size projects. In order to adopt Scrum for large size projects, there is a need to integrate Lean and Scrum. It is required to inherit some properties of the Lean into Scrum, without compromising the speed, quality, efficiency, and standards, to accomplish large size projects successfully such as enterprise resource planning (ERP) systems. It is anticipated that the proposed Lean Scrum integration will make it suitable to develop large size projects. The same is accomplished by purposing an integrated LScrum model in this research. The proposed model is validated using a survey to conclude the results. The results of the survey support the proposed integration of Lean and Scrum for the development of large size projects.

With the increase of digital data on the internet, computers are at higher risk of getting corrupted through cyber-attacks. Criminals are adopting more and more sophisticated techniques to steal sensitive information from the web. The botnet is one of the most aggressive threats as it combines lots of advanced malicious techniques. Detection of the botnet is one of the most serious concerns and prominent research area among the researchers. This paper proposes a detection model using the clustering algorithm to group bot traffic and normal traffic into two different clusters. Our contribution focused on applying K-means clustering algorithm to detect botnets based on their detection rate (true and false positives). Experimental results clearly demonstrate the fact that with the help of clustering we were able to separate the complete dataset into two entirely distinguishable clusters, where one cluster is representing the botnet traffic and other one representing the normal traffic.

There are various libraries that facilitate the design and development of recommender systems (RSs) research in both the academia and industry. Different libraries provide a different set of functionalities based on their foundational design principles. When new algorithms are proposed, researchers need to compare these against prior algorithms considering many challenges such as reproducibility of results, evaluation metrics, test harnesses, etc. Although many open source RS libraries exist to carry out research experiments and provide a varying degree of features such as extensibility, performance, scalability, flexibility, etc. To that end, this paper describes a recently introduced open-source RS library, Collaborative Filtering for Java (CF4J), which is specially designed for collaborative recommendations. Firstly, the brief internals of the CF4J framework are explained and it has been compared with other related libraries such as LibRec, LensKit, and Apache Mahout based on the recommendation approaches and evaluation tools. Secondly, we have summarized all the state-of-art similarity measures provided by the CF4J library. Finally, in order to determine the accuracy of these similarity measures, several experiments have been conducted using standardized benchmark datasets such as MovieLens-1M, MovieLens-10M, and MovieLens-20M. Empirically obtained results demonstrate that the Jaccard-Mean Squared Difference (JMSD) similarity measure provides better recommendation accuracy among all similarity measures.

Synchronous and asynchronous e-learning are two popular e-learning modes that are commonly used in distant learning education. The study investigates how synchronous and asynchronous e-learning affect the academic performance of students. A questionnaire was used to collect data for this study from some students of the National Open University of Nigeria. The findings showed that students' attitude to synchronous and asynchronous e-learning affect their academic performance. The results demonstrated that only 60% of the respondents understand what asynchronous and synchronous e-learning means. Also, only 55% of the respondents believed that asynchronous and synchronous e-learning mode has a positive impact on their academic performance. Moreover, only 52% of the respondents are of the opinion that the curriculum in use at National Open University needs to be updated to increase the impact of the e-learning mode on the learners.