Trimet Graph Optimization (TGO) based methodology for Scalability and Survivability in Wireless Networks

Self Cite

In the present-day scenario, Assessment of educational skills independently is prominently required which can be done by the techniques of Deep Learning. The main objective of the project is to evaluate the performance of the student while coding using his facial expressions. This model initially captures the facial expressions of the student using a camera which is our data set. These inputs are fed into the deep learning classification algorithms to assess the behaviour of the student and then those outputs are fed into the machine learning algorithms to assess his performance. This project supports external evaluation in many of the educational institutions. This model summarizes the successful patterns of a student by avoiding the pitfalls of average student patterns to develop an innovative analysis tool and promotes to develop the best education.

Section: Literature Surveymentioning

confidence: 99%

Detecting Emotions of Student and Assessing the Performance by using Deep Learning

Amiripalli¹

2020

Self Cite

“…CMs are based on the fact that color distribution in an image can be regarded as a distribution of probability, described by different moments. The FE from a large local window is in the form of statistical parameters like mean, variance, covariance, and kurtosis [22].…”

Section: Color Momentsmentioning

confidence: 99%

Design and Implementation of Content-Based Image Retrieval on FPGA card

2020

In recent years, real-time Image Processing (IP) has seen some applications and has posed a fast-growing field of programmable gate arrays (FPGA) implementation that has been the essential subject of the current engineering trend their simplicity and immense potential. One of the main problems of some IP is image extraction, which is that you can retrieve valuable knowledge about the quality of the images from the data effectively. We define the implementation of CBIR in FPGA image processing applications. The fundamental goal behind this initiative is to meet the shortest timeline by the optimum use of services. We are undertaking a review of this embedded approach's benefits and discussing its usefulness with a series of benchmark images. Implementation based on the FPGA indicates the viability of the suggested technique. The practical implementation of all processes using the FPGA Verilog code has been compiled into the ALTERA QUARTUS-II software method. The results obtained show qualitatively and quantitatively the feasibility of the proposed procedure.

“…Zheng et al [28] focused on Type 2 Diabetes Mellitus and developed a semi-automated machine framework to improve the classification performance. Several classifiers are evaluated such as KNN, Naïve Bayes (NB), SVM,Decision Tree (DT), Random Forest and Logistic Regression (LR).Polat et al [31] used PCA for dimension reduction and combination of ANN and Fuzzy logic as adaptive neuro-fuzzy inference for prediction of class. Kahramanli et al [32] presented a novel methodology using ANN and fuzzy Neural Network.…”

Section: Literature Surveymentioning

confidence: 99%

Logistic regression and Random forest-based hybrid classifier with recursive feature elimination technique for diabetes classification

L¹

2020

Diabetes mellitus is a chronic metabolic ailment being considered as one of the deadliest diseases in the world. Millions of cases and deaths have been reported due to diabetes. Initial forecast of diabetes condition helps in reducing the death rate significantly that happen due to it. Current advancements in biomedical techniques have facilitated to store the electronic health record datasets which can be analyzed for better diagnosis. In order to explore these datasets, data mining techniques are considered as promising techniques which examines the data rapidly and provides a desired outcome. In this work, the data mining technique was adopted for diabetes classification using machine learning techniques. The proposed approach comprises of several steps such as missing value imputation, attribute selection and classification which are performed using mean missing value imputation, logistic regression &Recursive Feature Elimination for feature selection and random forest for classification, respectively. The evaluation results demonstrate that projected methods achieve97.39% prediction accuracy which shows a significant improvement in contrast to prevailing current approaches.