Deep learning models for solar irradiance forecasting: A comprehensive review

The recent outbreak of COVID-19 has brought the entire world to a standstill. The rapid pace at which the virus has spread across the world is unprecedented. The sheer number of infected cases and fatalities in such a short period of time has overwhelmed medical facilities across the globe. The rapid pace of the spread of the novel coronavirus makes it imperative that its' spread be forecasted well in advance in order to plan for eventualities. An accurate early forecasting of the number of cases would certainly assist governments and various other organizations to strategize and prepare for the newly infected cases, well in advance. In this work, a novel method of forecasting the future cases of infection, based on the study of data mined from the internet search terms of people in the affected region, is proposed. The study utilizes relevant Google Trends of specific search terms related to COVID-19 pandemic along with European Centre for Disease prevention and Control (ECDC) data on COVID-19 spread, to forecast the future trends of daily new cases, cumulative cases and deaths for India, USA and UK. For this purpose, a hybrid GWO-LSTM model is developed, where the network parameters of Long Short Term Memory (LSTM) network are optimized using Grey Wolf Optimizer (GWO). The results of the proposed model are compared with the baseline models including Auto Regressive Integrated Moving Average (ARIMA), and it is observed that the proposed model achieves much better results in forecasting the future trends of the spread of infection. Using the proposed hybrid GWO-LSTM model incorporating online big data from Google Trends, a reduction in Mean Absolute Percentage Error (MAPE) values for forecasting results to the extent of about 98% have been observed. Further, reduction in MAPE by 74% for models incorporating Google Trends was observed, thus, confirming the efficacy of utilizing public sentiments in terms of search frequencies of relevant terms online, in forecasting pandemic numbers.

Forecasting spread of COVID-19 using Google Trends: A hybrid GWO-Deep learning approach.

It is hard to trust any data entry on online websites as some websites may be malicious, and gather data for illegal or unintended use. For example, bank login and credit card information can be misused for financial theft. To make users aware of the digital safety of websites, we have tried to identify and learn the pattern on a dataset consisting of features of malicious and benign websites. We treated the problem of differentiation between malicious and benign websites as a classification problem and applied several machine learning techniques, for example, random forest, decision tree, logistic regression, and support vector machines to this data. Several evaluation metrics such as accuracy, precision, recall, F1 score, and false positive rate, were used to evaluate the performance of each classification technique. Since the dataset was imbalanced, the machine learning models developed a bias during training toward a specific class of websites. Multiple data balancing techniques, for example, undersampling, oversampling, and SMOTE, were applied for balancing the dataset and removing the bias. Our experiments showed that after balancing the data, the random forest algorithm using the oversampling technique showed the best results in all evaluation metrics for the benign and malicious website feature dataset.

/pdf/significance-of-machine-learning-for-detection-of-malicious-68n597ea.pdf

Significance of Machine Learning for Detection of Malicious Websites on an Unbalanced Dataset

In the last two decades, renewable energy has been paid immeasurable attention to toward the attainment of electricity requirements for domestic, industrial, and agriculture sectors. Solar forecasting plays a vital role in smooth operation, scheduling, and balancing of electricity production by standalone PV plants as well as grid interconnected solar PV plants. Numerous models and techniques have been developed in short, mid and long-term solar forecasting. This paper analyzes some of the potential solar forecasting models based on various methodologies discussed in literature, by mainly focusing on investigating the influence of meteorological variables, time horizon, climatic zone, pre-processing techniques, air pollution, and sample size on the complexity and accuracy of the model. To make the paper reader-friendly, it presents all-important parameters and findings of the models revealed from different studies in a tabular mode having the year of publication, time resolution, input parameters, forecasted parameters, error metrics, and performance. The literature studied showed that ANN-based models outperform the others due to their nonlinear complex problemsolving capabilities. Their accuracy can be further improved by hybridization of the two models or by performing pre-processing on the input data. Besides, it also discusses the diverse key constituents that affect the accuracy of a model. It has been observed that the proper selection of training and testing period along with the correlated dependent variables also enhances the accuracy of the model.

A comprehensive review and analysis of solar forecasting techniques

The utility model discloses a novel capacitive soil moisture sensor using a Hartley three-point oscillating circuit. The capacitive soil moisture sensor comprises a detection module, a reference frequency signal generating circuit, a frequency conversion circuit, a frequency computing circuit and a power supply, wherein the detection module and the reference frequency signal generating circuit are respectively connected with the frequency conversion circuit, and the frequency conversion circuit is connected with the frequency computing circuit; the detection module comprises a probe and a Hartley oscillating module which are connected, and the Hartley oscillating module comprises a Hartley oscillating circuit and a temperature compensation circuit; the frequency conversion circuit is used for receiving signals transmitted by the Hartley oscillating module and the reference frequency signal generating circuit, and the power supply supplies power to the above components. The capacitive soil moisture sensor provided by the utility model has the advantages of simple structure, reliable signal transmission and capability of avoiding interference; the Hartley three-point oscillating circuit and a temperature compensation design are adopted, so that the stable oscillation starting is realized; the pin type detection module hardly damages soil, and the measurement results are relatively accurate after the detection module is inserted into soil.

Capacitive soil moisture sensor

Stock Closing Price Prediction using Machine Learning Techniques

Multi-step ahead forecasting of global solar radiation for arid zones using deep learning

We went from 56kbps wired ARPANET connections limited to the US military in the 1960s, to unimaginably fast wireless 100 Mbps connections in the 2010s. But what the future holds will certainly blow your mind 1Gbps or more and that is still an understatement LIGHT FIDELITY it is or popularly known as Li-Fi. The two-major prospect being aimed is extension or enhancement of the wireless services and to support the number of the exponentially growing user which the RF spectrum is unable to provide due to a limited spectrum of radio waves. So, Li-fi that is based on the visible light spectrum is being designed. It uses a LED and a photodiode or phototransistor to transmit and receive data respectively. Li-fi can be compared with the existing wireless technology i.e. Wi-Fi in terms of speed and security which the former provides better. The aspiration of this research paper is cunning a prototype of Li-fi transmitter and receiver to transmit data. The schematic design was made using Proteus 8 professional. Software coding was done on C language and PIC microcontroller is used. Successful transfer of image and text were achieved. As a deduction, this work gives an originative way of scheming a Li-Fi Prototype.

Image Transmission Using Li-Fi

Stock market’s volatile and complex nature makes it difficult to predict the market situation. Deep Learning is capable of simulating and analyzing complex patterns in unstructured data. Deep learning models have applications in image recognition, speech recognition, natural language processing (NLP), and many more. Its application in stock market prediction is gaining attention because of its capacity to handle large datasets and data mapping with accurate prediction. However, most methods ignore the impact of mass media on the company’s stock and investors’ behaviours. This work proposes a hybrid deep learning model combining Word2Vec and long short-term memory (LSTM) algorithms. The main objective is to design an intelligent tool to forecast the directional movement of stock market prices based on financial time series and news headlines as inputs. The binary predicted output obtained using the proposed model would aid investors in making better decisions. The effectiveness of the proposed model is assessed in terms of accuracy of the prediction of directional movement of stock prices of five companies from different sectors of operation. 

/pdf/forecasting-directional-movement-of-stock-prices-using-deep-ruiqadj0.pdf

Forecasting Directional Movement of Stock Prices using Deep Learning

In recent years, recommendation systems have started to gain significant attention and popularity. A recommendation system plays a significant role in various applications and services such as e-co...

Deeksha Chandola

Papers

Stock Closing Price Prediction using Machine Learning Techniques

Multi-step ahead forecasting of global solar radiation for arid zones using deep learning

Image Transmission Using Li-Fi

Forecasting Directional Movement of Stock Prices using Deep Learning

Contextual Bandit Approach-based Recommendation System for Personalized Web-based Services