Cloud computing is the fastest growing and most promising field in the service provisioning segment. It has become a challenging task to provide security in the cloud. The purpose of this article is to suggest a better and efficient integrity verification technique for data referred to as cloud audit. The deployment of cloud storage services has significant benefits in the management of data for users. However, this raises many security concerns, and one of them is data integrity. Though public verification techniques serve the purpose they are vulnerable to procrastinating auditors who may not perform verifications on time. In this article, a cloud data auditing system is proposed. The proposed cloud data auditing system integrates Merkle Tree-based Cloud audit and the blockchain-based audit recording system, thus the core idea is to record each verification result into a blockchain as a transaction. Utilizing the time-sensitive nature of blockchain, the verifications are time-stamped after the corresponding transaction is recorded into the blockchain, which enables users to check whether auditors have performed the verifications at the prescribed time. The proposed cloud data auditing system is experimentally validated. The investigations with varied dataset size revealed less time taken, on an average of 0.25 milliseconds with the use of Merkle Tree. Further results reveal consistency of the data integrity checking.

Any user can navigate outdoors by using online maps with the help of a GPS signal, but navigation in an indoor environment is difficult as the GPS signals can be weak inside a building. In this article, a system for providing a solution for indoor navigation with the help of augmented reality technology based on a computer vision approach is developed so as to provide navigational assistance to users in any new or unknown environment. This is done with an android based mobile phone application. This can be done by using augmented reality technology along with a computer vision-based approach to find where the user is and what is present in front of the user. Using this information, the user can get to navigate inside the building.

Fruit detection using deep learning is yielding very good performance, the goal of this work is to detect small fruits in images under these occlusion and overlapping conditions. The overlap among fruits and their occlusion can lead to false and missing detection, which decreases the accuracy and generalization ability of the model. Therefore, a small orange fruit recognition method based on improved Feature Pyramid Network was developed. To begin with, multi-scale feature fusion was used to fuse the detailed bottom features and high-level semantic features to detect small-sized orange to improve recognition rate. And then repulsion loss was used to take place of the original smooth L1 loss function. Besides, Soft non-maximum suppression was adopted to replace non-maximum suppression to screen the bounding boxes of orange to construct a recognition model of orange fruits. Finally, the network was trained and verified on the collected image data set. The results showed that compared with the traditional detection models, the mean average precision was improved from 79.7 to 82.8%.

Plant leaf recognition has been carried out widely using low-level features. Scale invariant feature transform technique has been used to extract the low-level features. Leaves that match based on low-level features but do not do so in semantic perspective cannot be recognized. To address this, global features are extracted and used. Similarly, convolutional neural networks, deep learning networks, and transfer learning-based neural networks have been used for leaf image recognition. Even then there are issues like leaf images in various illuminations, rotations, taken in different angle, and so on. To address such issues, the closeness among low-level features and global features are computed using multiple distance measures, and a leaf recognition framework has been proposed. Two deep network models, namely Densenet and Xception, are used in the experiments. The matched patches are evaluated both quantitatively and qualitatively. Experimental results obtained are promising for the closeness-based leaf recognition framework as well as the Densenet-based leaf recognition.

Test case selection helps in improving quality of test suites by removing ambiguous, redundant test cases, thereby reducing the cost of software testing. Various works carried out have chosen test cases based on single parameter and optimized the test cases using single objective employing single strategies. In this article, a parameter selection technique is combined with an optimization technique for optimizing the selection of test cases. A two-step approach has been employed. In first step, the fuzzy entropy-based filtration is used for test case fitness evaluation and selection. In second step, the improvised ant colony optimization is employed to select test cases from the previously reduced test suite. The experimental evaluation using coverage parameters namely, average percentage statement coverage and average percentage decision coverage along with suite size reduction, demonstrate that by using this proposed approach, test suite size can be reduced, reducing further the computational effort incurred.