Search

Improving the precision and pinpointing of stock pricing predictions employing Long Short-Term Memory (LSTM) compared to Logistic Regression (LR) is the primary objective of this study paper. Research Tools and Procedures: This paper's dataset demonstrates the approach's efficacy using the publicly accessible dataset from the National Stock Exchange (NSE). The sample size for improving the accuracy and precision of share market stock price predictions was 280 (140 in Group 1 and 140 in Group 2). The computation was done using G-power 0.8 with alpha and beta values of 0.05 and 0.2, respectively, and a confidence interval of 95%. Both LSTM and LR use a large number of samples (N=10) to forecast stock prices on the stock market with a high degree of accuracy and precision. In comparison to the LR's 82.51% accuracy rate, the LSTM classifier achieves a far better rate of 93.94%. A p-value of 0.971 indicates that the research is not statistically significant (p>0.05). For the purpose of improving accuracy and precision in predicting the marketplace for stock prices, LSTM produces superior results in terms of prediction accuracy than LR. [ABSTRACT FROM AUTHOR]

Improving the accuracy and precision of stock market share price predictions using Innovative Long Short-Term Memory compared to Linear Regression (LR) is the major purpose of this research study. This paper's dataset demonstrates the approach's efficacy using the publicly accessible dataset from the National Stock Exchange (NSE). For this stock market prediction, we used a sample size of 280 (140 in Group 1 and 140 in Group 2), and we used G-power 0.8 with alpha and beta values of 0.05 and 0.2, respectively, and a confidence interval of 95%. With a number of samples (N=10), LR achieves better accuracy and precision in predicting stock prices on the stock market. The LR classifier's accuracy rate is 86.63%, while the Novel Long Short-Term Memory classifier's rate is 93.94%. A relevance score of p<0.05, or p=0.0271, indicates that the research is valid. In conclusion, when it comes to predicting stock prices on the stock market, Novel Long Short-Term Memory outperforms LR in terms of accuracy and precision. [ABSTRACT FROM AUTHOR]

The main goal of this work is to develop a method to improve the accuracy and precision of stock market price forecasts by substituting new Long Short-Term Memory (LSTM) with K-Nearest Neighbor. Using freely available data from the National Stock Exchange (NSE), this paper's dataset demonstrates the method's usefulness. Excellent accuracy and precision in stock market price forecasts were achieved by using the 280-person sample, 95% confidence interval, 0.05 alpha, and 0.2 beta. Both Groups 1 and 2 had 140 participants. Both LSTM and KNN do well when testing their ability to predict stock market values using a large sample set (N=10). The revolutionary LSTM classifier achieves a 93.94% accuracy rate, which is higher than the state-of-the-art KNN. Since the significance criterion is 0.471, the study does not have statistical significance (p>0.05). In terms of stock market price prediction, unique LSTM performs better than KNN, and the findings are more accurate. [ABSTRACT FROM AUTHOR]

Examining how well the Gaussian Algorithm and Novel Long Short-Term Memory (LSTM) perform in predicting stock market outcomes is the main objective of this study. Using freely available data from the National Stock Exchange (NSE), this paper's dataset demonstrates the method's usefulness. To forecast the stock price of a corporation, we used G-power 0.8, alpha=0.05, beta=0.2, and a 95% range of confidence. Two hundred and eighty-two people took part; 140 were split evenly between Group 1 and Group 2. Predictions of stock market prices are made more accurate and precise when a ten-person sample uses the Gaussian Algorithm and Novel Long Short-Term Memory. The results demonstrate that the Novel Long Short-Term Memory classifier achieves a much superior accuracy rate of 93.94% when compared to the Gaussian Algorithm's 74.88%. The study found a significant value of p<0.05, which is the same as p=0.0271. Stock market forecasts made using Novel Long Short-Term Memory are more accurate and precise than those made using the Gaussian Algorithm. [ABSTRACT FROM AUTHOR]

This study looks at how well a recurrent Neural Network and a logistic regression classifier can detect cyberbullying. Methods and Equipment Used in the Study: This approach makes use of two datasets. To find out how effective new cyberbullying deductions are, twenty instances were divided into two groups: one using logistic regression and the other using recurrent neural networks. This sample was calculated using G power and an 80% pretest power. Data pertaining to cyberbullying was used for training purposes using logistic regression and RNN. The two approaches, RNN and logistic regression, vary significantly in their accuracy levels; 94.58% vs. 94.55% (p>0.05). Lastly, the Recurrent Neural Network approach outperforms the logistic regression classifier. [ABSTRACT FROM AUTHOR]

This study compares the accuracy of a random forest classifier with a revolutionary recurrent neural network-based cyber bullying deduction. Supplies and Methods: Two businesses employ this strategy. This research used the Random Forest technique in Group 2 & Recurrent Neural Networks in Group 1 to analyze 20 samples from each group in order to evaluate the validity of the new Deduction of Cyber bullying. G power was used to calculate the sample size, and the pretest power was fixed at 80%. Findings: Random forest has an accuracy of 92.36%, whereas RNN has 94.55%. A statistically significant difference of 0.18 (p>0.05) has been discovered. To sum up, recurrent neural network methods outperform random forest classifiers in terms of accuracy. [ABSTRACT FROM AUTHOR]

A study that pits a novel recurrent neural network-based cyberbullying inference approach against a support vector machine classifier reveals that the new method outperforms the latter. Approach and Substances Employed: This strategy is used by two firms. Twenty instances were assigned to each group so that they could test their cyberbullying deduction skills. While Group 1 made use of recurrent neural networks, Group 2 opted to employ support vector machines. We estimated the sample size using a fixed pretest power of 80% and a G power of 80%. In terms of accuracy, the data shows that RNNs are 94.43% better than support vector machines. There is a statistically significant difference, as shown by the p-value of 0.18 (p>0.05). The results show that recurrent neural network techniques are much superior than support vector machine classifiers. [ABSTRACT FROM AUTHOR]

The effectiveness of recurrent neural networks and adaptive boosting classifiers in deducing novel cyberbullying conclusions is the focus of this study. This approach employs a pair of sets. Group 1 utilized RNNs (Recurrent Neural Networks) to test the accuracy of creative cyber bullying deductions, whereas Group 2 used Ada boost. Each group was given twenty samples to evaluate. An 80% pretest power and G power were used to determine the sample size. Statistical analysis shows that RNN produces a much higher accuracy of 94.7% compared to Ada boost's 93.3% (p>0.05). The Recurrent Neural Network approach outperforms the Ada boost classifier in terms of accuracy. [ABSTRACT FROM AUTHOR]

In this paper novel making use of a CNN to forecast the spread of COVID-19 and comparing its accuracy with Logistic Regression is the main objective. Applying Logistic Regression and Convolutional Neural Networks to Regression are two groups used each with twenty samples to assess the accuracy of COVID-19 forecast. We used G power with an 80% pretest power to decide on the sample size. The CNN and LR algorithms were trained using data models that included both normal and COVID-19 chest X-rays. The accuracy of CNN is 98.5 % and LR has an accuracy of 77.7 % with a statistical significance of 0.496 (p>0.05). Compared to other methods, Convolutional Neural Networks use a to the Logistic Regression. [ABSTRACT FROM AUTHOR]

This study investigates a new method for COVID-19 outbreak prediction by means of an Artificial neural network (ANN) using convolutional layers (CNN). Compared to with an Adaptive boosting classifier. In this method, two groups are used. With the help of CNNs, one group and two more groups with Ada boost method employed a 20-person sample for each research to evaluate the precision of COVID-19 predictions. Applying G power and a pretest power of 80%, we determined the sample size. The CNN and Ada boost algorithms were trained using chest X-rays of both healthy and COVID-19 afflicted people. The results show that CNN achieved 98.5% accuracy and Ada boosted 79% accuracy, with a p-value of less than 0.05 indicating statistical significance. To review: Deep Learning Network algorithm has achieved better accuracy compared to the Ada boost classifier. [ABSTRACT FROM AUTHOR]

This research tests two neural network types—artificial neural networks and convolutional neural networks—to see whether one is better at predicting the spread of COVID-19. We evaluated the performance of Convolutional A Team Approach to COVID-19 Pandemic Forecasting with the Use of ML and CNNs using two sets of 20 samples. G power, which had an 80% pretest power, was used to compute the sample size. Data models were developed using Chest X-rays from healthy individuals and COVID-19 patients were used in conjunction with artificial neural network (ANN) and convolutional neural network (CNN) methods. The results show that CNN has a 98.5% accuracy rate and ANN 95.33% accuracy rate, with a p-value less than 0.05 indicating statistical significance. When compared with the Artificial Neural Network method, the Convolutional Neural Network method yields better results in terms of accuracy. [ABSTRACT FROM AUTHOR]

The Fully Convolutional Network (FCN) and the Support Vector Machine (SVM) are two well-known classifiers that are used for MRI-based novelty liver segmentation classification. This study aims to compare and contrast these two classifiers. To train classifiers using SVM and FCN, twenty samples of liver MRI images were used. Two groups, one using support vector machines (SVMs) and the other using FCNs, were given ten samples each. This study's pretest power is 80%. In MATLAB, FCN has a recognition rate of 97% compared to 86% for SVM. Our statistical study yielded a satisfactory accuracy ratio (P<0.05). Compared to the SVM method, the FCN method achieved superior results on the datasets tested for unique liver segmentation categorization. [ABSTRACT FROM AUTHOR]

The primary objective of this study is to compare the Adaboost method with the Conventional SVM technique in order to provide an accurate prediction about whether or not the fluid is fit for usage by humans. Two sets of twenty samples each were used for this study, totaling forty data. For group 1, we have SVM, while for group 2, we have Adaboost. With a prior test efficiency of 80% and an alpha value of 0.05, the sampling is computed using the results of current research as well as the system clincalc.com. According to the workflow to implement the support vector machine (SVM), the code is implemented and compiled in the Anaconda software with the Jupyter Notebook installed and launched successfully. The proposed work support vector machine (SVM) has got a higher accuracy of 90.75% whereas the existing Adaboost classifier has got an accuracy of 75.14%. The significance 0.000 obtained is less than 0.05 value. Therefore, the suggested study concludes that, when comparing the precision of water quality, SVM outperforms the current classifier, the Adaboost classifier. [ABSTRACT FROM AUTHOR]

To detect forgeries in signature images using a state-of-the-art deep learning Support Vector Machine (SVM) algorithm based on parameters extracted from the data set. 44 samples total are used in the study, which is split into two groups of 22. Group 1 utilizes CNN-xg, whereas Group 2 employs SVM. Colab software specialized for machine learning is used to run the code. According to simulation findings, the CNN-xg Algorithm obtains a greater reliability of 96.82%, while the SVM achieves reliability of 84.80%; both algorithms have the same significance values of 0.0004 (p < 0.05). CNN-xg identifies forged signatures in the provided dataset more correctly than SVM, demonstrating superior performance. [ABSTRACT FROM AUTHOR]