Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
28,956
result(s) for
"Spark"
Sort by:
A Recommendation Engine for Predicting Movie Ratings Using a Big Data Approach
In this era of big data, the amount of video content has dramatically increased with an exponential broadening of video streaming services. Hence, it has become very strenuous for end-users to search for their desired videos. Therefore, to attain an accurate and robust clustering of information, a hybrid algorithm was used to introduce a recommender engine with collaborative filtering using Apache Spark and machine learning (ML) libraries. In this study, we implemented a movie recommendation system based on a collaborative filtering approach using the alternating least squared (ALS) model to predict the best-rated movies. Our proposed system uses the last search data of a user regarding movie category and references this to instruct the recommender engine, thereby making a list of predictions for top ratings. The proposed study used a model-based approach of matrix factorization, the ALS algorithm along with a collaborative filtering technique, which solved the cold start, sparse, and scalability problems. In particular, we performed experimental analysis and successfully obtained minimum root mean squared errors (oRMSEs) of 0.8959 to 0.97613, approximately. Moreover, our proposed movie recommendation system showed an accuracy of 97% and predicted the top 1000 ratings for movies.
Journal Article
Analysis of Ignition Spark Parameters Generated by Modern Ignition System in SI Engine Fueled by Ammonia
This paper analyzes the influence of the number of ignition coils and spark discharge energy on the Coefficient of Variation of Indicated Mean Effective Pressure (COVIMEP) of an SI internal combustion piston engine. A modern electronically controlled induction ignition system is used during the test. Two fuels are used in the experiment. The reference fuel is gasoline and the tested fuel is ammonia. For the traditional fuel, using an additional ignition coil does not improve COVIMEP. This parameter for gasoline has an almost constant value for different ignition system charging times. The situation is different for ammonia. This fuel requires high ignition energy. The use of one ignition coil demands a long charging time. For short charging times, unrepeatability of the engine cycles is unacceptable. The use of an additional ignition coil allowed to the charging coil timing to be shortened and the unrepeatable engine cycles to be reduced. This paper determined the maximum charging time of the used ignition coil, above which the spark parameters are worse. In addition, the influence of charging time and number of ignition coils on total spark energy, spark discharge duration, maximum spark power, and voltage during spark discharge for ammonia is presented. The data presented in this paper are developed based on measurements of current and voltage in the secondary winding of the ignition coil. A self-developed electronic device enabling the change in spark energy is used to control the ignition system. This paper also presents the construction of modern ignition systems, describes the functions of selected components, and briefly discusses their diagnostics.
Journal Article
PySpark recipes : a problem-solution approach with PySpark2
Quickly find solutions to common programming problems encountered while processing big data. Content is presented in the popular problem-solution format. Look up the programming problem that you want to solve. Read the solution. Apply the solution directly in your own code. Problem solved! PySpark Recipes covers Hadoop and its shortcomings. The architecture of Spark, PySpark, and RDD are presented. You will learn to apply RDD to solve day-to-day big data problems. Python and NumPy are included and make it easy for new learners of PySpark to understand and adopt the model. What You Will Learn: Understand the advanced features of PySpark and SparkSQL Optimize your code Program SparkSQL with Python Use Spark Streaming and Spark MLlib with Python Perform graph analysis with GraphFrames.
Book
SPARK-X: non-parametric modeling enables scalable and robust detection of spatial expression patterns for large spatial transcriptomic studies
Spatial transcriptomic studies are becoming increasingly common and large, posing important statistical and computational challenges for many analytic tasks. Here, we present SPARK-X, a non-parametric method for rapid and effective detection of spatially expressed genes in large spatial transcriptomic studies. SPARK-X not only produces effective type I error control and high power but also brings orders of magnitude computational savings. We apply SPARK-X to analyze three large datasets, one of which is only analyzable by SPARK-X. In these data, SPARK-X identifies many spatially expressed genes including those that are spatially expressed within the same cell type, revealing new biological insights.
Journal Article
Using the Spark Plug as a Sensor for Analyzing the State of the Combustion System
This article presents a method that uses a spark plug as a sensor to monitor an internal combustion engine. In addition, the voltage sensors measured the high voltage at the spark plugs using a non-contact method. Monitoring can now be performed in a simple way in real time, along with data processing. This method can be effectively used for the monitoring of all cylinders in an internal combustion engine as well as supplementing other measurement methods to optimize engine maintenance and enable correct diagnostic decisions to be made. Experimental analysis focused on the effect of the spark plug gap on the arc duration, flashover voltage, and high-voltage waveforms. It was found that with an increasing gap, the arc duration is shortened, and the breakdown voltage increases linearly, indicating wear of the spark gap. With increasing temperature, the breakdown voltage value decreased. Non-contact measurements at different frequencies showed a relationship between the magnitude of the electric field and the spark plug gap.
Journal Article
Estimating the minimum ignition energy of spark-ignited fuel/air mixtures: preliminary steps towards a novel modelling approach
In spark-ignition (SI) engines, the achievement of a fast combustion with low cycle-to-cycle variation is highly dependent on the successful initiation of a flame kernel from the spark plug. Its growth can be sped up by increasing the electrical energy supply, but at the cost of higher plug wear, whereas too little energy may result in an ignition failure. Therefore, knowledge of the minimum ignition energy (MIE) of a fuel/air mixture is of key importance to guarantee a proper combustion process at minimal cost. To model the MIE several approaches have been proposed in literature, primarily derived from the experiments conducted by Lewis and Von Elbe and their resulting theory of quenching distances. However, these approaches appear in conflict with more recent experimental outcomes, and the impact of the ignition device is neglected. This work proposes a novel approach for modelling the MIE, which is based on a flame kernel expansion model recently proposed in another paper. In this approach, the proposed model, which has general validity, is specialized to the particular case of the estimation of the MIE, supplied via an electrical breakdown. A model advancement is also included that consists in the quantification, albeit at a preliminary level, of the impact of different gap distances and spark plug quenching effects on the flame kernel development. The results are validated against literature models and experimental data for two fuels, propane and hydrogen, and multiple equivalence ratios. In contrast with the noticeable MIE overestimation of literature models, for propane the proposed approach leads to better results compared to the experiments. Instead, for hydrogen a tendency towards a MIE underestimation is observed, especially for lean mixtures. The model is also tested for SI-engine-relevant conditions, showing satisfactory overall trends. The key source of error seems related to the very complex kernel-electrode interaction, the modelling of which will be improved in future developments.
Journal Article