The magnetic flux leakage (MFL) technique is commonly used for non-destructive testing of oil and gas pipelines. This testing involves the detection of defects and anomalies in the pipe wall, and the evaluation of the severity of these defects. The difficulty with the MFL method is the extent and complexity of the analysis of the MFL images. In this paper we show how modern machine learning techniques can be used to considerable advantage in this respect. We apply the methods of support vector regression, kernelization techniques, principal component analysis, partial least squares, and methods for reducing the dimensionality of the feature space. We demonstrate the adequacy of the performance of these methods using real MFL data collected from pipelines, with regard to the performance of both the detection of defects, and the accuracy in the estimation of the severity of the defects. We also show how low-dimensional latent variable structures can be effective for visualizing the clustering behaviour of the classifier.

Cardiovascular Disease or coronary illness is one of the significant dangerous infections in India as well as in the entire world. It is estimated that 28.1 % of deaths occur due to heart diseases. It is also the major cause for significant number of deaths which as more than 17.6 million in the year 2016. So proper and timely diagnosis, treatment of such diseases require a system that can predict with precise accuracy and reliability. Intensive research is carried out by various researchers using diverse machine learning algorithms to forecast the heart disease taking different datasets which consists of different attributes that result in heart attack. In this paper we analyzed the dataset collected from kaggle which consists of attributes related to heart disease such as age, gender, blood pressure, cholesterol and so on. We have also investigated the accuracy levels of various machine learning techniques such as Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Decision Trees (DT). The performance and accuracy of above algorithms is not so well when executed using large dataset, so here we tried to improving the prediction accuracy using Artificial Neural Network(ANN), Tensor Flow Keras.

Data mining has become one of the emerging fields in research because of its vast contents. Data mining is used for finding hidden patterns in the database or any other information repository. This information is necessary to generate knowledge from the patterns. The main task is to extract knowledge out of the information. In this paper we use a data mining technique called classification to determine the playing condition based on the current temperature values. Classification technique is a powerful way to classify the attributes of the dataset into different classes. In our approach we use classification algorithms like Decision Tree (J48), REP Tree and Random Tree. Then we compare the efficiencies of these classification algorithms. The tool we use for this approach is WEKA (Waikato Environment for Knowledge Analysis) a collection of open source machine learning algorithms.

No abstract

Internet of Things (IoT) is the fast-growing technology, mostly used in smart mobile devices such as notebooks, tablets, personal digital assistants (PDA), smartphones, etc. Due to its dynamic nature and the limited battery power of the IoT enabled smart mobile nodes, the communication links between intermediate relay nodes may fail frequently, thus affecting the routing performance of the network and also the availability of the nodes. Existing algorithm does not concentrate about communication links and battery power/energy, but these node links are a very important factor for improving the quality of routing in IoT. In this paper, Context-aware Energy Conserving Algorithm for routing (CECA) was proposed which employs QoS routing metrics like Inter-Meeting Time and residual energy and has been applied to IoT enabled smart mobile devices using different technologies with different microcontroller which resulted in an increased network lifetime, throughput and reduced control overhead and the end to end delay. Simulation results show that, with respect to the speed of the mobile nodes from 2 to 10m/s, CECA increases the network lifetime, thereby increasing the average residual energy by 11.1% and increasing throughput there by reduces the average end to end delay by 14.1% over the Energy-Efficient Probabilistic Routing (EEPR) algorithm. With respect to the number of nodes increases from 10 to 100 nodes, CECA algorithms increase the average residual energy by16.1 % reduces the average end to end delay by 15.9% and control overhead by 23.7% over the existing EEPR.