Detection and identification of un-uniformed shape text from blurred video frames Ravikumar Hodikehosahally Channegowda, Raghavendra Srinivasaiah, Santosh Kumar Jankatti, Meenakshi B, Niranjana Shravanabelagola Jinachandra, et al. Iaes International Journal of Artificial Intelligence, 2024 <p><span lang="EN-GB">The identification and recognition of text from video frames have received a lot of attention recently, that makes many computer vision-based applications conceivable. In this study, we modify the picture mask and the original identification of the mask region convolution neural network and permit detection in three levels, including holistic, sequence, and at the level of pixels. To identify the texts and determine the text forms, semantics at the pixel and holistic levels can be used. With masking and detection, existences of the character and the word are separated and recognised. In addition, text detection using the results of 2-D feature space instance segmentation is done. Moreover, we explore text recognition using an attention-based optical character recognition (OCR) method with mask</span><span lang="EN-US"> r</span><span lang="EN-GB">egion convolution neural networks (R-CNN) to address and detect the problem of smaller and blurrier texts at the sequential level. Using attribute maps of the word occurrences in sequence to seq, the OCR method calculates the character sequence. At last, a fine-grained learning strategy is proposed to constructs models at word level using the annotated datasets, resulting in the training of a more precise and reliable model. The well-known benchmark datasets ICDAR 2013 and ICDAR 2015 are used to test our suggested methodology.</span></p>
Analysis and prediction of seed quality using machine learning Raghavendra Srinivasaiah, Meenakshi Meenakshi, Ravikumar Hodikehosalli Chennegowda, Santosh Kumar Jankatti International Journal of Electrical and Computer Engineering, 2023 <span lang="EN-US">The mainstay of the economy has always been agriculture, and the majority of tasks are still carried out without the use of modern technology. Currently, the ability of human intelligence to forecast seed quality is used. Because it lacks a validation method, the existing seed prediction analysis is ineffective. Here, we have tried to create a prediction model that uses machine learning algorithms to forecast seed quality, leading to high crop yield and high-quality harvests. For precise seed categorization, this model was created using convolutional neural networks and trained using the seed dataset. Using data that can be used to forecast the future, this model is used to learn about whether the seeds are of premium quality, standard quality, or regular quality. While testing data are employed in the algorithm’s predictive analytics, training data and validation data are used for categorization reasons. Thus, by examining the training accuracy of the convolution neural network (CNN) model and the prediction accuracy of the algorithm, the project’s primary goal is to develop the best method for the more accurate prediction of seed quality.</span>
Bio-Inspired Optimization Technique for Feature Selection to Enhance Accuracy of BC Detection V. Kalaiyarasi, Meenakshi, Sanjay Jain, Shagun Jain, Umapriya R, et al. 6th International Conference on Inventive Computation Technologies Icict 2023 Proceedings, 2023 The common type of cancer that results in death across the world is Breast Cancer (BC). It is necessary to detect cancer in its earlier stages when it is more treatable and can be effectively managed The detection of BC can be carried out by employing a variety of different Machine Learning (ML) approaches in the diagnostic process. This study proposes a ML-based strategy for doing automated BC analysis. There are several steps in tumor detection, and feature extraction (FE) is one of them. The tumor condition's existence in an image can be determined using the powerful Gray Level Co-occurrence Matrix (GLCM) feature descriptor identification approach, in addition to the Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) Feature Selection (FS) techniques are employed Techniques from the realm of ML, such as Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF) algorithm, are used throughout the data training and testing phases for tumor classification. The outcome of both optimized FS techniques is given to the ML models for identifying BC. From the experimental result, it is identified that the ACO with SVM gives greater accuracy of 97.4% than all other techniques.
Performance evaluation of Map-reduce jar pig hive and spark with machine learning using big data Santosh Jankatti, Raghavendra B. K., Raghavendra S., Meenakshi Meenakshi International Journal of Electrical and Computer Engineering, 2020 Big data is the biggest challenges as we need huge processing power system and good algorithms to make an decision. We need Hadoop environment with pig hive, machine learning and hadoopecosystem components. The data comes from industries. Many devices around us and sensor, and from social media sites. According to McKinsey There will be a shortage of 15000000 big data professionals by the end of 2020. There are lots of technologies to solve the problem of big data Storage and processing. Such technologies are Apache Hadoop, Apache Spark, Apache Kafka, and many more. Here we analyse the processing speed for the 4GB data on cloudx lab with Hadoop mapreduce with varing mappers and reducers and with pig script and Hive querries and spark environment along with machine learning technology and from the results we can say that machine learning with Hadoop will enhance the processing performance along with with spark, and also we can say that spark is better than Hadoop mapreduce pig and hive, spark with hive and machine learning will be the best performance enhanced compared with pig and hive, Hadoop mapreduce jar.
Big data performance evalution of map-reduce pig and hive Santosh Kumar J*, Dr. Raghavendra S., Dr.Raghavendra B.K, Meenakshi, and International Journal of Engineering and Advanced Technology, 2019 Big data is nothing but unstructured and structured data which is not possible to process by our traditional system its not only have the volume of data also velocity and verity of data, Processing means ( store and analyze for knowledge information to take decision), Every living, non living and each and every device generates tremendous amount of data every fraction of seconds, Hadoop is a software frame work to process big data to get knowledge out of stored data and enhance the business and solve the societal problems, Hadoop basically have two important components HDFS and Map Reduce HDFS for store and mapreduce to process. HDFS includes name node and data nodes for storage, Map-Reduce includes frame works of Job tracker and Task tracker. Whenever client request Hadoop to store name node responds with available free memory data nodes then client will write data to respective data nodes then replication factor of hadoop copies the blocks of data with other data nodes to overcome fault tolerance Name node stores the meta of data nodes. Replication is for back-up as hadoop HDFS uses commodity hardware for storage, also name node have back-up secondary name node as only point of failure the hadoop. Whenever clients want to process the data, client request the name node Job tracker then Name node communicate to Task tracker for task done. All the above components of hadoop are frame works on-top of OS for efficient utilization and manage the system recourses for big data processing. Big data processing performance is measured with bench marks programs in our research work we compared the processing i.e. execution time of bench mark program word count with Hadoop Map-Reduce python Jar code, PIG script and Hive query with same input file big.txt. and we can say that Hive is much faster than PIG and Map-reduce Python jar code Map-reduce execution time is 1m, 29sec Pig Execution time is 57 sec Hive execution time is 31 sec.
Role of Hadoop in Big Data Handling Meenakshi, A. C. Ramachandra, M. N. Thippeswamy, Ajith Bailakare Lecture Notes on Data Engineering and Communications Technologies, 2019
Performance evaluation of Map-reduce jar pig hive and spark with machine learning using big data S Jankatti, BK Raghavendra, S Raghavendra, M Meenakshi International Journal of Electrical and Computer Engineering 10 (4), 3811 , 2020 2020 Citations: 16
MOST CITED SCHOLAR PUBLICATIONS
Performance evaluation of Map-reduce jar pig hive and spark with machine learning using big data S Jankatti, BK Raghavendra, S Raghavendra, M Meenakshi International Journal of Electrical and Computer Engineering 10 (4), 3811 , 2020 2020 Citations: 16
