Artificial Neural Networks (ANNs)

In this paper, we presents an armington based partial equilibrium mode techniques for exploration of rice cultivation and opportunities in Sierra Leone: The rising import bill of rice and the dependence of Sierra Leone on imported rice coupled with the growing sophistication of the rice consumer for quality rice and the agronomic advantages in rice cultivation initiated this research into Sierra Leone's rice sub-sector. The research question for this study is what opportunities do the current state of Sierra Leone's rice sub-sector offer compared with the rice imports? Therefore, the first objective is to analyze the development of Sierra Leone's rice sub-sector through a trend analysis of production levels, acreage under cultivation, and yield per hectare and rice import penetration ratio from 2000 to 2018. The results show that although rice cultivation in Sierra Leone is increasing at a rate of about 5.8 percent annually between t h e y e a r s 2000 and 2018, Sierra Leone still depends heavily on imported rice. The import penetration ratio in 2011 was about 66 percent. Secondly, the study shows analysis of the rice distribution network and identify the opportunities to shift to rice varieties demanded by consumers thanks to a schema of the rice distribution network. The analysis of the rice distribution network shows that the imported rice channel is more efficient than the local rice channel. The most influential operators in the imported rice channel is the rice importer whiles the rice wholesalers (market women) are the most influential in the local rice channel. There exists some form of oligopolistic system between market women and the rice farmers because the farmers are constrained to sell to the market women due to the lack of greater access to market centers for better competitive prices. Thirdly, the study identified different agricultural and trade policies that could affect production, consumption and imported quantity of rice using a simulation model. A simply Armington based partial equilibrium model of Sierra Leone's rice sub-sector is developed and the simulation results show that the total removal of current taxes on imported rice would lead to 8 and 6 percent decrease in aromatic and non-aromatic rice cultivation respectively. Imports of aromatic and non-aromatic rice would increase by 55 and 63 percent respectively. Overall rice consumption would increase by 21 percent. For a 20 percent increase in land cultivated, rice cultivation will increase by 24 percent and consumption would increase by 9 percent. A 20 percent increase in rice productivity would lead to a 5 percent increase in rice cultivation and 12 percent increase in rice consumption. A 20 percent decrease in world rice prices would lead to a 5 percent decrease in cultivation and 14 percent increase in consumption. For a 20 percent increase in world rice prices, cultivation would increase by 4 percent and consumption will decrease by 9 percent. This research recommends that land expansion and trade liberalization in the short term should be promoted while improving rice farmers' productivity in the short, medium to long term to boost cultivation levels. Also, for accelerated rice production, government policy should be geared towards encouraging large scale farmers to enter the rice sub-sector while government continues to improve the productivity of the smallholder rice farmers. Government should improve infrastructure especially roads to open up rice farming communities to market centers and reduce transactions costs and reduce the oligopolistic system operated by market women. 444 GSJ© 2020 www.globalscientificjournal.com

Nowadays, it is evident that signature is commonly used for personal verification, this justifies the necessity for an Automatic Verification System (AVS). Based on the application, verification could either be achieved Offline or Online. An online system uses the signature's dynamic information; such information is captured at the instant the signature is generated. An offline system, on the other hand, uses an image (the signature is scanned). In this paper, some set of simple shaped geometric features are used in achieving offline Verification of signatures. These features include Baseline Slant Angle (BSA), Aspect Ratio (AR), and Normalized Area (NA), Center of Gravity as well as the line's Slope that joins the Center of Gravities of the signature's image two splits. Before the features extraction, a signature preprocessing is necessary to segregate its parts as well as to eliminate any available spurious noise. Primarily, System training is achieved via a signature record which was acquired from personalities whose signatures had to be validated through the system. An average signature is acquired for each subject as a result of incorporating the aforementioned features which were derived from a sample set of the subject's true signatures. Therefore, a signature functions as the prototype for authentication against a requested test signature. The similarity measure within the feature space between the two signatures is determined by Euclidian distance. If the Euclidian distance is lower than a set threshold (i.e. analogous to the minimum acceptable degree of similarity), the test signature is certified as that of the claiming subject otherwise detected as a forgery. Details on the stated features, pre-processing, implementation, and the results are presented in this work.

Stock Market is the market for security where organized issuance and trading of Stocks take place either through ex- change or over the counter in electronic or physical form. It plays an important role in canalizing capital from the in- vestors to the business houses, which consequently leads to the availability of funds for business expansion. In this pa- per, we investigate to predict the daily excess returns of Bombay Stock Exchange (BSE) indices over the respective Treasury bill rate returns. Initially, we prove that the excess return time series do not fluctuate randomly. We are apply- ing the prediction models of Autoregressive feed forward Artificial Neural Networks (ANN) to predict the excess return time series using lagged value. For the Artificial Neural Networks model using a Genetic Algorithm is constructed to choose the optimal topology. This paper examines the feasibility of the prediction task and provides evidence that the markets are not fluctuating randomly and finally, to apply the most suitable prediction model and measure their effi- ciency.

Image recognition refers to methods and technologies that identify digital images such as places, logos, people, objects, buildings, and several other variables in images. Users are sharing vast amounts of data through applications, social networks, and websites. The large volume of digital data is being used by companies to deliver better and smarter services to the people accessing it. In this paper we will introduce a methodology of image recognition and retrieval process based on using ANN as a recognizer capable to identify digital image index. ANN will be implemented and tested in order to select an optimal ANN which must give the accurate image index with minimum MSE and maximum PSNR.

The rapid advancement of web technology has led to an exponential increase in the volume of data present online for internet users. Travellers book their hotels only after extensive scrutinisation of hotel reviews on online websites. Hence, it is an absolute necessity for hotel's management board to gain insights from customer reviews and feedbacks to improve upon their services for a better customer satisfaction index. This research explores the use of Artificial Neural Networks (ANN) powered by Google's Word2Vec skip-gram algorithm for customer sentiment analysis and review classification. The proposed model achieves a high test accuracy of 0.9248, with an average F1-Score of 0.925. Unsupervised sentiment clustering effectively classifies the reviews into four distinct categories and enables the Hotel Management to work out the major problems experienced by the customers.

In this work, deep CNN based model have been suggested for face recognition. CNN is employed to extract unique facial features and softmax classifier is applied to classify facial images in a fully connected layer of CNN. The experiments conducted in Extended YALE B and FERET databases for smaller batch sizes and low value of learning rate, showed that the proposed model has improved the face recognition
accuracy. Accuracy rates of up to 96.2% is achieved using the proposed model in Extended Yale B database. To improve the accuracy rate further, preprocessing techniques like SQI, HE, LTISN, GIC and
DoG are applied to the CNN model. After the application of preprocessing techniques, the improved accuracy of 99.8% is achieved with deep CNN model for the YALE B Extended Database. In FERET
Database with frontal face, before the application of preprocessing techniques, CNN model yields the maximum accuracy of 71.4%. After applying the above-mentioned preprocessing techniques, the accuracy
is improved to 76.3%

With the advent of time, automation is becoming an inevitable component of human lives. Our homes, industries, offices, market areas, etc. are being mechanized and human power is slowly being replaced by machines. Although it has increased the system efficiency manifold, but the probability of system breakdowns has also increased, since machines are more susceptible to faults. Hence, a continuous monitoring system is therefore required. Many techniques have since been devised for better maintenance of machines throughout their operation so as to increase their useful life. This paper presents the use and comparison of two different machine learning techniques for fault sensing ahead of time and prognostic maintenance of a turbine System. The data is acquired from the turbine of a hydro power plant installed in Dargai, Malakand Agency, Pakistan. The machine learning techniques compared
in this paper for fault sensing and prognostic maintenance of a turbine system are support vector machines and artificial neural networks.

Modeling Sludge volume index of activated sludge process in municipal WWTP is a difficult task to accomplish due to the high nonlinearity of the plant and the non-uniformity and variability of influent quantity, quality parameters, and operation condition.
ANNs were developed for the prediction of the Sludge Volume Index using influent quality parameters and operating parameters of Batna Wastewater Treatment Plant from 2011 to 2014. The best model given by the neural network for the SVI prediction composed of one input layer with fifteen input variables, one hidden layer with thirteen nodes and one output layer with one output variable with R = 0.8784 and RMSE = 0.443. The results demonstrate the ability of the appropriate Neural Network models for the prediction of SVI.
This provides a very useful tool that can be used by WWTP operators in their daily management to increase treatment process performances and WWTP reliability.

Prediction of tribological characteristics of hybrid composites with A356 matrix using artificial neural networks (ANN) was performed in this paper. During experiment next parameters were varied: sliding speed, load, sliding distance and wt.% of reinforcement. The obtained experimental results were used to form the artificial neural network in which were varied number of neurons in the hidden layer, number of layers, the activation function and the function of training. Training of the neural network was performed for the wear rate, and optimal regression coefficient was equal to 0.994, for the network 4-15-10-1. Using neural networks to predict the wear rate greatly reduces the time and cost of experiment.