Background AI for medical diagnosis has made a tremendous impact by applying convolutional neural networks (CNNs) to medical image classification and momentum plays an essential role in stochastic gradient optimization algorithms for accelerating or improving training convolutional neural networks. In traditional optimizers in CNNs, the momentum is usually weighted by a constant. However, tuning hyperparameters for momentum can be computationally complex. In this paper, we propose a novel adaptive momentum for fast and stable convergence. Method Applying adaptive momentum rate proposes increasing or decreasing based on every epoch's error changes, and it eliminates the need for momentum hyperparameter optimization. We tested the proposed method with 3 different datasets: REMBRANDT Brain Cancer, NIH Chest X-ray, COVID-19 CT scan. We compared the performance of a novel adaptive momentum optimizer with Stochastic gradient descent (SGD) and other adaptive optimizers such as Adam and RMSprop. Results Proposed method improves SGD performance by reducing classification error from 6.12 to 5.44%, and it achieved the lowest error and highest accuracy compared with other optimizers. To strengthen the outcomes of this study, we investigated the performance comparison for the state-of-the-art CNN architectures with adaptive momentum. The results shows that the proposed method achieved the highest with 95% compared to state-of-the-art CNN architectures while using the same dataset. The proposed method improves convergence performance by reducing classification error and achieves high accuracy compared with other optimizers.

No abstract

Online gaming industry is an area where the effects of any change can be seen in a very short time. Therefore, real-time analysis of revenues, analysis of the commercial performance of the developed content, and rapid monitoring of the revenue contributions of the improvements are essential. Therefore, financial forecasting is a crucial part of business plan which can help strategize how much and how quickly the company intend to grow. In financial forecasting of a given time series, revenue estimations for future will become important research in the industry. This research offers a detailed analysis of recent time series models and focused on both deep learning and statistical methods for time series forecasting on real-world revenue data. Results of the study are examined using one of the leading Finland based online gaming companies’ revenue data. In our experiments, we investigated various time series forecast techniques, such as SARIMA, Theta, Holt Winters, Prophet, Dense Neural Network (DNN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), N-Beats and Ensemble models. The experimental evaluations illustrate that deep learning models can optimize the financial forecast operations. The result of the study provides insights to managers and analysts in determining the best model to adopt.