Search

Data embedding into DNA is a conventional encryption technology since it gives the system security and consumes less energy. This work proposes a model that uses the silent mutation method to apply data embedding into DNA within an encryption model. To produce the key, hash functions are applied first to the original image and its metadata followed by the Arnold Transform technique. The key is then sent to LLCS, which uses it to produce a series of coding rules, and transmitted to HCS, which uses it to generate three chaotic sequences. Five chaotic maps are then used to diffuse the output image of the Arnold Transform. DNA operations are applied to the final image using the chaotic HCS sequences followed by the coding rules sequence. After the image has been decoded and silently mutated into a gene sequence, the altered gene is then obtained. Seven evaluation measures are used on ten grayscale images incorporated with two DNA sequences to assess the proposed model's performance. Results indicate a positive improvement in performance as a result of the model's increased security. [ABSTRACT FROM AUTHOR]

A crucial field in software development and testing is Software Defect Prediction (SDP) because the quality, dependability, efficiency, and cost of the software are all improved by forecasting software defects at an earlier stage. Many existing models predict defects to facilitate software testing process for testers. A comprehensive review of these models from different perspectives is crucial to help new researchers enter this field and learn about its latest developments. Algorithms, method types, datasets, and tools were the only perspectives discussed in the current literature. A comprehensive study that takes into account a wide spectrum of viewpoints hasn't yet been published. Examining the development and advancement of SDP-related studies is the goal of this literature review. It provides a comprehensive and updated state-of-the-art that satisfies all stated criteria. Out of 591 papers retrieved from 6 reputable databases, 73 papers were eligible for analysis. This review addresses relevant research questions regarding techniques & method types, data details, tools, code syntax, semantics, structural and domain information. Motivation to conduct this comprehensive review is to equip the readers with the necessary information and keep them informed about the software defect prediction domain. [ABSTRACT FROM AUTHOR]

Bioinformaticians face an issue in analyzing and studying protein similarity as the number of proteins grows. Protein sequence analysis helps in the prediction of protein functions. It is critical for the analysis process to be able to appropriately categorize proteins based on their sequences. The extraction of features from protein sequences is done using a variety of methods. The goal of this study is to investigate the different variations of data on the classification performance of a deep learning model employing 3D data. First, few research questions were formulated regarding the impact of the following criteria: dataset size, IMF importance, feature size, and preprocessing on the proposed deep learning classification process. Second, comprehensive experiments were conducted to answer the research questions. Six feature extraction methods were utilized to create 3D features with two sizes (7x7x7 and 9x9x9), which were then fed into a convolutional neural network. Three datasets different in their sorts, sizes, and balance state were used. Accuracy, precision, recall and F1-score are the standard assessment metrics used. Experimental results draw significant conclusions. First, the 7x7x7 feature matrix has a positive correlation between its dimensions, which improved the results. Second, using the sum of the first three IMF components had better impact than using the first IMF component. Third, the classification process did not benefit from the normalization of features for small datasets unlike the large dataset. Finally, the dataset size had a significant impact on training the CNN model, with a training accuracy reaching 84.03%. [ABSTRACT FROM AUTHOR]

Image understanding and scene classification are keystone tasks in computer vision. The advancement of technology and the abundance of available datasets in the field of image classification and recognition study provide plenty of attempts for advancement. In the scene classification problem, transfer learning is commonly utilized as a branch of machine learning. Despite existing machine learning models' superior performance in image interpretation and scene classification, there are still challenges to overcome. The weights and current models aren't suitable in most circumstances. Instead of using the weights of data-dependent models, in this work, a novel machine learning model for the scene classification task is provided that converges rapidly. The proposed model has been tested on the Intel scenes dataset for a comprehensive evaluation of our model. The proposed model RepConv over-performed four existing benchmark models in a low number of epochs and training parameters, and it achieved 93.55 ± 0.11, 75.54 ± 0.14 accuracies for training and validation data respectively. Furthermore, re-categorization of the data set is performed for a new classification problem that is not previously reported in the literature (natural scenes; real scenes). The accuracy of the proposed model on the binary model was 98.08 ± 0.05 on training data and 92.70 ± 0.08 on validation data which is not reported previously in any other publication. [ABSTRACT FROM AUTHOR]

Named entity recognition has been regarded as an important task in natural language processing. Extracting biomedical entities such as RNAs, DNAs, cell lines, proteins, and cell types has been recognized as a challenging task. Most of the existing research focuses on the extraction of flat named entities only and ignores the nested entities. Nested entities, on the other hand, are commonly used in real world biomedical applications due to their ability to represent semantic meaning of the named entity. This paper proposes an approach to improve the performance of nested biomedical named entity recognition by using a combination of diverse types of features namely morphological, orthographical, context, part of speech and word representation features while using Structured Support Vector Machine as a machine learning technique. The results obtained from the proposed approach were compared with those from popular benchmark approaches. The popular dataset "Genia" is utilized to evaluate the proposed approach which achieved Recall, Precision and F1- Measure of 84.033%, 85.946 %, and 84.113% respectively. [ABSTRACT FROM AUTHOR]

Named entity recognition is an information extraction subtask that aims to discover named items referenced in unstructured text and classify them into predefined class labels. Identifying biomedical entities such as proteins, cell lines, cell types, DNAs and RNAs has been recognized as a challenging task in named entity recognition. In this paper, the applicability of using structured support vector machine to classify biomedical named entity recognition is thoroughly investigated. This is achieved by utilizing a combination of various types of features such as morphological, part of speech, orthographical, context and word representation to explore the classification performance. Comprehensive experiments were conducted on two popular datasets based on multiple evaluation metrics. Experimental results revealed that the performance of the structured support vector machine surpasses that of different benchmark approaches in the literature. [ABSTRACT FROM AUTHOR]

In this paper, we propose the Software-as-a-Service (SaaS) Recommender (SaaSRec), a personalized reputation-based QoS-aware recommender system (RS) for SaaS services. SaaSRec semantically processes user requests in order to find business-oriented matching services, which are then filtered to satisfy the user QoS requirements and service characteristics. Subsequently, hybrid filtering is utilized to validate the services set on the basis of services metadata, reputation and user interests. Finally, the recommended set of services is ranked using a unique combination of factors: Relevance to user profile, service reputations and service cost. Moreover, we propose a new method for calculating the service reputation from the objective time-weighted user feedbacks. SaaSRec addresses many challenges faced by the generic RSs: User cold-start problem, limited content analysis and low performance. In respect of service RSs, SaaSRec tackles the disregarding of relevant factors to services recommendation: Cloud service characteristics, user physical location, service reputation and user interests. Moreover, SaaSRec provides a hybrid justification for the recommended services to increase the user's acceptance. Experimental evaluation against a real-world services dataset has been carried out, and the results show that the proposed recommendation approach surpasses other collaborative filtering-based recommendation approaches in respect of both precision and recall. This performance improvement was verified using different matrix density levels and number of recommendations. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]