Convolution Neural Networks To Describe Internet Of Things
Authors: Dr. Kanaka Durga Returi, Dr. Vaka Murali Mohan
Abstract
As the field of pattern recognition and machine learning gains attention, deep learning (DL) is becoming quite popular. DL is being used by mobile devices in novel ways because of its unparalleled ability to handle difficult machine learning issues. Next-generation smart apps are possible because to the availability of sophisticated pattern recognition technologies. Data-driven learning and feature extraction is enabled by CNNs, which use a large collection of representative visual features extracted from relevant training data. On the other hand, certain data sets require further changes to the CNN structure and parameters in order to utilize the CNN technique effectively. For running duration and network weight, a mobile machine must meet specific parameters. To show you what can be done with a CNN and a mobile device, we developed an image processing module that can be used in the design of an operating system. After we teach the steps for using the mobile to gather data, analyze the data, and create the data set, we go on to teaching those same steps on the web, as that method is essentially the same. As stated previously, as mobile devices run on a different computer environment and have different data properties, we believe a different network topology for optical character recognition (OCR) to be more advantageous.
Causes of Delay in Construction Projects: An Empirical Study
Authors: Brajesh Singh Rajawat, B.P. Mudgal
Abstract
The objective of the present study was to explore the causes of delay in construction projects. Effects of various delaying factors related to the contractor, client/owner, consultant, material, equipment, labor and general environment factors on delay in constructions projects have been measured. Data on the study variables has been collected through structured questionnaire from thirty seven Construction Company. Participants were approached personally to collect the data. Various statistical tools such as reliability test, factor analysis and regression have been applied for data analysis and inference. The results of the study reveal that the factors related to contractor, client, consultant, material and equipment have significant impact on delay in construction project whereas labor and general environment factors found to have no effects on delay. The findings of the study provide significant insights to construction industry so that they may formulate strategies in order to avoid delay and its consequences. The recommendations and limitations are also discussed in the conclusion part of the study.
Prediction of Rice leaf Diseases
Authors: Dr. R. Sunnetha Rani, D. Sri Vinithri Chowdary, K. Deekshith, V. Alekhya, V. Pavan Kalyan
Abstract
Rice diseases has adverse consequences on crop yield, and the right finding of rice illnesses is the way to stay away from these impacts. In any case, the current sickness analysis techniques for rice are neither precise nor effective, and exceptional hardware is frequently required. In this review, a programmed finding strategy was created and executed in a cell phone application. The strategy was created utilizing profound learning in view of a huge dataset that contained 33,026 pictures of six sorts of rice infections: leaf impact, bogus filth, neck impact, sheath curse, bacterial stripe illness, and earthy colored spot. The center of the strategy was the Ensemble Model in which submodels were coordinated. At long last, the Ensemble Model was approved utilizing a different arrangement of pictures. Results showed that the three best submodels were DenseNet-121, SE-ResNet-50, and ResNeSt-50, as far as a few credits, for example, learning rate, accuracy, review, and illness acknowledgment exactness. In this way, these three submodels were chosen and incorporated in the Ensemble Model. The Ensemble Model limited disarray among the various sorts of infection, diminishing misdiagnosis of the illness. Utilizing the Ensemble Model to analyze six kinds of rice illnesses, a general exactness of 91% was accomplished, which is viewed as sensibly great, thinking about the appearance likenesses in certain sorts of rice infection. The cell phone application permitted the client to utilize the Ensemble Model on the web server through an organization, which was helpful and proficient for the field determination of rice leaf impact, bogus muck, neck impact, sheath scourge, bacterial stripe illness, and earthy colored spot.
Optimization of Pulsed TIG Welding Process Parameters on 2. 25Cr - 1Mo Steel Pipe Using Multivariate Linear Regression
Authors: G Prakasham, J Kandasamy, L Siva Rama Krishna, A Seshu Kumar
Abstract
When compared to constant current gas tungsten arc welding (TIG welding), the pulsed TIG welding process has huge advantages in welding of thin materials with low heat input and thus a decrease in distortion and war page. Also, it allows for greater control of the weld pool, greater weld penetration, and weld quality. In structural applications of nuclear power plants and boilers, 2.25 Cr-1 Mo steel pipes are employed in operating temperatures greater than 5500CUsing multivariate linear regression, the parameters of the pulsed TIG welding process on pipe joints were optimized in this work. The goal of the research is to find the best set of welding process parameters for a 2.25 Cr- 1 Mo steel weld using a pulsed TIG welding technique, as well as a relationship between the four welding process parameters and ultimate tensile strength, impact strength, and microhardness. As a result, experimental research using the L9 orthogonal array was conducted. At 220 A, 120 A, 4Hz, and 40% pulse on time, the experimental and predicted results show that pulse current and background current have an effect on ultimate tensile strength. It was also found that as the pulse current & impact strength increase, the ultimate tensile strength increases, whereas microhardness values decrease.