Though many researchers have studied plant leaf disease, the timely diagnosis of diseases in olive leaves still presents an indisputable challenge. Infected leaves may display different symptoms from one plant to another, or even within the same plant. For this reason, many researchers studied the effects of those diseases on, at most, two plants. Since olive crops are affected by many pathogens, including bacteria welt, olive knot, Aculus olearius, and olive peacock spot, the development of an efficient algorithm to detect the diseases was challenging because the diseases could be defined in many different ways. For this purpose, we introduce an optimal deep learning model for diagnosing olive leaf diseases. This approach is based on an adaptive genetic algorithm for selecting optimal parameters in deep learning model to provide rapid diagnosis. To evaluate our approach, we applied it in three famous deep learning models. For the comparative evaluation, we also tested other well-known machine learning methods. The experimental results presented in this paper show that our model outperformed the other algorithms, achieving an accuracy of approximately 96% for multiclass classification and 98% for binary classification.

Over the last few years, the amount of available information has increased exponentially in all professional fields, including the medical field. Modern-day patients have access to a wealth of medical information, whether it be from brochures, newspapers, television campaigns, or internet documents. To facilitate and accelerate the search for medical information, more precise systems have been implemented, such as visual question-and-answer systems. A visual question-and-answer system is designed to provide direct and precise answers to questions asked in natural language. In this context, we propose an optimal deep neural network model based on an adaptive optimization algorithm, which takes medical images and natural language questions as input, then provides precise answers as output. Our model starts by classifying medical questions following an embedding phase. We then use a deep learning model for visual and textual feature extraction and emergence. In this paper, we aim to maximize the accuracy rate and minimize the number of epochs in order to accelerate the process. This is a multi-objective optimization problem. The selection of deep learning model parameters, such as epoch number and batch size, is an essential step in improving the model, thus, we use an adaptive genetic algorithm to determine the optimal deep learning parameters. Finally, we propose a dense layer for answer retrieval. To evaluate our model, we used the ImageCLEF 2019 VQA data set. Our model outperforms existing visual question-and-answer systems and offers a significantly higher retrieval accuracy rate.

Time series data are significant, and are derived from temporal data, which involve real numbers representing values collected regularly over time. Time series have a great impact on many types of data. However, time series have anomalies. We introduce an anomaly detection paradigm called novel matrix profile (NMP) to solve the all-pairs similarity search problem for time series data in the healthcare. The proposed paradigm inherits the features from two state-of-the-art algorithms: Scalable Time series Anytime Matrix Profile (STAMP) and Scalable Time-series Ordered-search Matrix Profile (STOMP). The proposed NMP caches the output in an easy-to-access fashion for single- and multidimensional data. The proposed NMP can be used on large multivariate data sets and generates approximate solutions of high quality in a reasonable time. It is implemented on a Python platform. To determine its effectiveness, it is compared with the state-of-the-art matrix profile algorithms, i.e., STAMP and STOMP. The results confirm that the proposed NMP provides higher accuracy than the compared algorithms.

Cloud Computing leverages Hadoop framework for processing BigData in parallel. Hadoop has certain limitations that could be exploited to execute the job efficiently. These limitations are mostly because of data locality in the cluster, jobs and tasks scheduling, and resource allocations in Hadoop. Efficient resource allocation remains a challenge in Cloud Computing MapReduce platforms. We propose H2Hadoop, which is an enhanced Hadoop architecture that reduces the computation cost associated with BigData analysis. The proposed architecture also addresses the issue of resource allocation in native Hadoop. H2Hadoop provides a better solution for "text data", such as finding DNA sequence and the motif of a DNA sequence. Also, H2Hadoop provides an efficient Data Mining approach for Cloud Computing environments. H2Hadoop architecture leverages on NameNode's ability to assign jobs to the TaskTrakers (DataNodes) within the cluster. By adding control features to the NameNode, H2Hadoop can intelligently direct and assign tasks to the Data Nodes that contain the required data without sending the job to the whole cluster. Comparing with native Hadoop, H2Hadoop reduces CPU time, number of read operations, and another Hadoop factors.

Wireless Sensor Networks (WSNs) are widely employed to solve several problems in different domains like agriculture, monitoring, health care. An outlier detection method is considered as a task of classifying data that is available during training. Also, this method is considered as a very important step in construction of sensor network systems to ensure data grade for perfect decision making. So, this task helps to create a gainful approach based on Non-Negative Matrix Factorization (NMF) to find out if data is normal regular or an outlier. The latter has been used for nonlinear instance which can give a highest order statistics. Then, it has showed excellent performance with accounts for an attractive capability and has been extensively investigated. In this work, we propose a Non-Negative Matrix Factorization (NMF) as new method for an outlier detection to separate an outlier data from a regular pattern of point distribution. Using real data collected from Grand St-Bernard and Intel Berkeley in wireless sensor networks, our proposed work show a better performance in detecting outliers.