Tea clone classification using deep CNN with residual and densely connections

Tea clone of Gambung series is a superior variety of tea that has high productivity and quality. Smallholder farmers usually plant these clones in the same areas. However, each clone has different productivity or quality, so it is difficult to predict the production quality in the same area. To uniform the variety of clones in an area, smallholder farmers still need experts to identify each plant because one and other clones share the same visual characteristics. We propose a tea clone identification system using deep CNN with skip connection methods, i.e., residual connections and densely connections, to tackle this problem. Our study shows that the proposed method is affected by the hyperparameter setting and the combining feature maps method. For the combining method, the concatenation method on a densely connected network shows better performance than the summation method on a residual connected network.

Comprehensively Meld Code Clone Identifier for Replicated Source Code Identification in Diverse Web Browsers

The emergence and the progress in the process of reusing the software’s, has caused difficulties in the maintaining the software codes and the corresponding depositories. Cloning of software codes is the important reason behind the arising difficulties in the maintenance of the software codes and the depositories. The cloning of codes is a process of replicating the existing codes for utilizing it elsewhere within the software system. The copying and pasting of the fragments of code is also well thought-out as the method of code cloning causing difficulties in the software maintenance. The maintenance of software is described as the alteration performed over the existing software on the completion of the development as well as the implementation process. Utilizing the maintenance process in the software the software companies deliver the improvements and the additional enhancements according to the working circumstance. The maintenance mainly focuses on removing the bugs and to repair the identified faults in the time of execution to enhance the performance. The work focused on the paper is mainly a comprehensive study over the prevailing tools laid out in the process of code-clone identification. The different techniques employed, the challenges incurred, the blunders made in the development, the enhanced refactoring challenges and efforts in the comprehension of codes are explored in the paper. From the study it was understood that the code clone identification using the web based tools are more advantageous than engaging algorithms in identifying the clones. So the a hybridized (meld) web based code clone identifier tool is engaged in the process of identifying the cloning of codes in diverse web browsers in exhibited in the paper. The exhibited tool equips a highly powerful tool for detecting the clones in a precise an efficient manner. The duplication of codes are often vulnerable and could be malicious. So the exhibited work in the future concentrates in developing an extended tool to identify the malicious codes to improvise the process of code clone identification making it concise and effective.