Wheat yield prediction based on weather parameters using multiple linear, neural network and penalised regression models

Wheat yield production is largely attributed by weather parameters. Model developed by multiple linear, neural network and penalised regression techniques using weather data have the potential to provide reliable, timely and cost-effective prediction of wheat yield. Wheat yield data and weather parameter during crop growing period (46th to 15th SMW) for more than 30 years were collected for study area and model was developed using stepwise multiple linear regression (SMLR), principal component analysis (PCA) in combination with SMLR, artificial neural network (ANN) alone and in combination with PCA, least absolute shrinkage and selection operator (LASSO) and elastic net (ENET) techniques. Analysis was carried out by fixing 70% of the data for calibration and remaining dataset for validation. On examining these models, LASSO and elastic net are performing excellent having nRMSE value less than 10 % for four out of five location and good for one location, because of prevention in over fitting and reducing regression coefficient by penalization.

Development of the Enhanced Piece-Wise Linear Neural Network Algorithm

This chapter discusses development, application, and enhancement of a decomposition neural network rule extraction algorithm for nonlinear regression problems. The dual objectives of developing the algorithms are (1) to generate good predictive models comparable in performance to the original artificial neural network (ANN) models and (2) to “open up” the black box of a neural network model and provide explicit information in the form of rules that are expressed as linear equations. The enhanced PWL-ANN algorithm improves upon the PWL-ANN algorithm because it can locate more than two breakpoints and better approximate the hidden sigmoid activation functions of the ANN. Comparison of the results produced by the two versions of the PWL-ANN algorithm showed that the enhanced PWL-ANN models provide higher predictive accuracies and improved fidelities compared to the originally trained ANN models than the PWL-ANN models.

An MRI Study on Effects of Math Education on Brain Development Using Multi-Instance Contrastive Learning

This paper explores whether mathematical education has effects on brain development from the perspective of brain MRIs. While biochemical changes in the left middle front gyrus region of the brain have been investigated, we proposed to classify students by using MRIs from the intraparietal sulcus (IPS) region that was left untouched in the previous study. On the cropped IPS regions, the proposed model developed popular contrastive learning (CL) to solve the problem of multi-instance representation learning. The resulted data representations were then fed into a linear neural network to identify whether students were in the math group or the non-math group. Experiments were conducted on 123 adolescent students, including 72 math students and 51 non-math students. The proposed model achieved an accuracy of 90.24 % for student classification, gaining more than 5% improvements compared to the classical CL frame. Our study provides not only a multi-instance extension to CL and but also an MRI insight into the impact of mathematical studying on brain development.

Forecasting of Market Clearing Volume Using Wavelet Packet-Based Neural Networks with Tracking Signals

In order to analyze the nature of electrical demand series in deregulated electricity markets, various forecasting tools have been used. All these forecasting models have been developed to improve the accuracy of the reliability of the model. Therefore, a Wavelet Packet Decomposition (WPD) was implemented to decompose the demand series into subseries. Each subseries has been forecasted individually with the help of the features of that series, and features were chosen on the basis of mutual correlation among all-time lags using an Auto Correlation Function (ACF). Thus, in this context, a new hybrid WPD-based Linear Neural Network with Tapped Delay (LNNTD) model, with a cyclic one-month moving window for a one-year market clearing volume (MCV) forecasting has been proposed. The proposed model has been effectively implemented in two years (2015–2016) and unconstrained MCV data collected from the Indian Energy Exchange (IEX) for 12 grid regions of India. The results presented by the proposed models are better in terms of accuracy, with a yearly average MAPE of 0.201%, MAE of 9.056 MWh, and coefficient of regression (R2) of 0.9996. Further, forecasts of the proposed model have been validated using tracking signals (TS’s) in which the values of TS’s lie within a balanced limit between −492 to 6.83, and universality of the model has been carried out effectively using multiple steps-ahead forecasting up to the sixth step. It has been found out that hybrid models are powerful forecasting tools for demand forecasting.

Word-embedding-based query expansion: Incorporating Deep Averaging Networks in Arabic document retrieval

One of the main issues associated with search engines is the query–document vocabulary mismatch problem, a long-standing problem in Information Retrieval (IR). This problem occurs when a user query does not match the content of stored documents, and it affects most search tasks. Automatic query expansion (AQE) is one of the most common approaches used to address this problem. Various AQE techniques have been proposed; these mainly involve finding synonyms or related words for the query terms. Word embedding (WE) is one of the methods that are currently receiving significant attention. Most of the existing AQE techniques focus on expanding the individual query terms rather the entire query during the expansion process, and this can lead to query drift if poor expansion terms are selected. In this article, we introduce Deep Averaging Networks (DANs), an architecture that feeds the average of the WE vectors produced by the Word2Vec toolkit for the terms in a query through several linear neural network layers. This average vector is assumed to represent the meaning of the query as a whole and can be used to find expansion terms that are relevant to the complete query. We explore the potential of DANs for AQE in Arabic document retrieval. We experiment with using DANs for AQE in the classic probabilistic BM25 model as well as for two recent expansion strategies: Embedding-Based Query Expansion approach (EQE1) and Prospect-Guided Query Expansion Strategy (V2Q). Although DANs did not improve all outcomes when used in the BM25 model, it outperformed all baselines when incorporated into the EQE1 and V2Q expansion strategies.

IoT for smart home system

<p>This paper examines the integration of smart home and solar panel system that is controlled and monitored using IoT (internet ofthings). To enable the smart home system to monitor the activity within the house and act according to the current conditions, it is equipped with several sensors, actuators and smart appliances. All of these devices have to be connected to a communication network, so they can communicate and provide services forthe smart home’s in habitants. The smart home system was first introduced to provide comfort and convenience, but later it should also address many other things, e.g. the importance of the efficient use of energy or electricity and hybrid use of energy sources. A solar panel is added to the smart home prototype and its addition is studied. Adaptive linear neural network is implemented in the prototype as an algorithm for predicting decisions based on the current conditions. The construction of the proposed integrated systemis carried out through several procedures, i.e. the implementation of the adaptive linear neural network (ADALINE) as the neural network method, the design of the prototype and the testing process. This prototype integrates functionalities of several household appliances into one application controlled by an Android-based framework.</p>

A Brain-Inspired Decision-Making Linear Neural Network and Its Application in Automatic Drive

Brain-like intelligent decision-making is a prevailing trend in today’s world. However, inspired by bionics and computer science, the linear neural network has become one of the main means to realize human-like decision-making and control. This paper proposes a method for classifying drivers’ driving behaviors based on the fuzzy algorithm and establish a brain-inspired decision-making linear neural network. Firstly, different driver experimental data samples were obtained through the driving simulator. Then, an objective fuzzy classification algorithm was designed to distinguish different driving behaviors in terms of experimental data. In addition, a brain-inspired linear neural network was established to realize human-like decision-making and control. Finally, the accuracy of the proposed method was verified by training and testing. This study extracts the driving characteristics of drivers through driving simulator tests, which provides a driving behavior reference for the human-like decision-making of an intelligent vehicle.