International Journal of Computer Techniques

1-5

Authors: - IJCT T.Karunakaran , J.John Clotilda

Feed is the largest input in any livestock enterprise and the rapid increase in feed prices and shortage of feed resources has been one of the major constraints for farmers, livestock industries, planners and the policy makers. This calls for prudent management of available resources and application of computing techniques can be one of the possible potential approaches. India is endowed with a wide range of feed resources varying widely in their composition and utility for different livestock species. Clustering of feed resource into different groups based on the composition can help in better feed management. To evaluate and to suggest a best technique for clustering feed resources, we have evaluated three clustering techniques viz. K-means, spectral k-means and auto spectral on two different data sets containing 236 and 106 feed resources with major constituents like crude protein, crude fiber ash, fat etc., . The composition of commonly used feed resources (236 and 106) were sourced from the published articles in various scientific journals and based on the composition of the feeds, they were subjected to clustering techniques. A total of three clustering techniques – k means, spectral k means and auto spectral were employed and the outputs were compared against the grouping done by subject matter experts. The outputs of different clustering techniques were validated with the expert grouping using precision, recall and F-measure. Of the three methods used it was found that kmeans was the best and closest to the experts classification. Clustering of feeds into different groups based on their composition will form a sound basis to select different feeds for formulating economic and nutritionally balanced diets leading to better feed management.

10-17

Authors: - IJCT JieWang

In the face of massive Web data, an important task is to integrate relevant data of interest from users in Deep Web into a unified and structured form. In order to facilitate the identification and processing of computers, each data item needs to be annotated. Ontology is the key to semantic tagging. In order to facilitate the sharing and exchange of information, the semantic value of ontology instances must be consistent and compatible. In this paper, a semantic value conversion method based on ontology is proposed. This method is divided into two parts, one is to define the conversion function as the entry point of the semantic value conversion. The second is to use OWL as the ontology language description, and establish an OWL ontology relational database to store the relationship between ontology instances and various semantic values. The semantic value conversion method improves the integrity and consistency of the ontology instance semantic information.

22-25

Authors: - IJCT Yongxing Peng

In recent years, due to the improvement of computing performance and neural network breakthrough, depth learning in the field of picture processing and natural language processing has made a great breakthrough. This paper mainly introduces the related research work of the combination of depth learning in natural language processing, and expounds and analyzes the combination effect and advantages and disadvantages of different depth neural network results in different sub-tasks.

31-35

Authors: - IJCT Muhammad Sholeh , EdhySutanta , Sulistyowati

The educational process provided to children does not have to be delivered formally, as it may be delivered in the form of games. One of the forms of games which can be delivered is the multimedia games. In this research, there was an application developed to be able to use in learning English vocabulary. This game is very suitable for the 7-12 years old Primary school students. The application was developed for android-based running in smartphone. The making of this English educational medium used several tools, they were; Unity 3D as the main developing tool and MonoDevelop as the IDE and C# programming language. This application is named English Rush, as this application contains student exercises regarding vegetables, animals, and fruits. The English Rush application is expected to ease the English learning for the Primary School students as well as getting their interests. The result showed that this game provides knowledge and is easy to use

46-51

Authors: - IJCT He Meng , Huang HongBing , Liu WeiPing

CoAP is a dominant application protocol designed for the constrained devices in IoT (the Internet of Things) which is going to interconnect every physical object in our daily life together to make an intelligent world. To keep the communication between devices in IoT from congestion, CoAP originally provides a simple congestion control mechanism. Since this mechanism can hardly meet the requirements of many IoT applications, an extension called CoCoA is being standardized by IETF(the Internet Engineering Task Force) to optimize CoAP. However, the thresholds underpinned the VBF(variable backoff factor) and RTO(retransmission timeout) aging mechanism in traditional CoCoA are constants and cannot be changed under most conditions which limit the performance of CoCoA; and further the existed estimators of CoCoA ambiguity have the potential risk to cause some unexpected or unpredictable problems. Hence, in this paper, we propose a novel threshold adjustable scheme for the VBF and RTO aging mechanism and a new encapsulation method for message retransmission to solve the above problems in the traditional CoCoA. Our evaluation results show that our modified version CoCoA greatly helps to solve the problem of congestion in IoT which outperforms over the existed CoCoA in terms of throughput and network adaptability.

58-61

Authors: - IJCT Smitha Harikumar

This paper is a study on the relevance of Big Data in Education. In this paper, using the data driven analytics approach. I have analysed how the Big Data analysis can actually involve to professional education and also how the unused data can benefit and improve the teaching and learning process in the present education system