Search Results (5)

The weights and structure determination (WASD) neuronet (or neural network) is a single-hidden-layer feedforward neuronet that exhibits an excellent approximation ability, despite its simple structure. Thanks to its strong generalization, fast speed, and ease of implementation, the WASD neuronet has been the subject of many modifications, including metaheuristics, and applications in a wide range of scientific fields. As it has garnered significant attention in the last decade, the aim of this study is to provide an extensive overview of the WASD framework. Furthermore, the WASD has been effectively used in numerous real-time learning tasks like regression, multiclass classification, and binary classification due to its exceptional performance. In addition, we present WASD’s applications in social science, business, engineering, economics, and medicine. We aim to report these developments and provide some avenues for further research. Full article

This research presents an essential oil (EO) distillation method with improved efficiency, called recurrent water and steam distillation (RWASD), as well as the testing of a 500 L prototype essential oil distillation machine (500 L PDM). The raw material used was 100 kg of lime fruit. At each distillation time point, the test result was compared with that obtained via water and steam distillation (WASD), and different raw material grid configurations were taken into consideration. It was found that distillation using the RWASD method increased the amount of EO obtained from limes by 53.69 ± 2.68% (or 43.21 ± 2.16 mL) compared with WASD. The results of gas chromatography mass spectrometry (GC-MS) analysis of bioactive compounds from the distilled EO revealed that important compounds were present in amounts close to the standards reported in many studies; namely, β-myrcene (2.72%), limonene (20.72%), α-phellandrene (1.27%), and terpinen-4-ol (3.04%). In addition, it was found that the temperature, state of saturated steam, and heat distribution during distillation were relatively constant. The results showed the design, construction, and heat loss error values of the 500 L PDM were 5.90 ± 0.29% and 7.83 ± 0.39%, respectively, leading to the use and percentage of useful heat energy to stabilize at 29,880 ± 1,494 kJ/s and 22.47 ± 1.12%, respectively. Additionally, the shape of the grid containing the raw material affects the temperature distribution and the amount of EO distilled, with values 10.14 ± 0.51% and 8.07 ± 0.40% higher for the normal grid (NS), respectively, as well as an exergy efficiency of 49.97 ± 2.49%. The highest values found for exergy in, exergy out, and exergy loss were 294.29 ± 14.71 kJ/s, 144.76 ± 7.23 kJ/s, and 150.22 ± 7.51 kJ/s, respectively. The obtained results can be further developed and expanded to promote the application of this method in SMEs, serving as basic information for the development of the EO distillation industry. Full article

Numerous people are applying for bank loans as a result of the banking industry’s expansion, but because banks only have a certain amount of assets to lend to, they can only do so to a certain number of applicants. Therefore, the banking industry is very interested in finding ways to reduce the risk factor involved in choosing the safe applicant in order to save lots of bank resources. These days, machine learning greatly reduces the amount of work needed to choose the safe applicant. Taking this into account, a novel weights and structure determination (WASD) neural network has been built to meet the aforementioned two challenges of credit approval and loan approval, as well as to handle the unique characteristics of each. Motivated by the observation that WASD neural networks outperform conventional back-propagation neural networks in terms of sluggish training speed and being stuck in local minima, we created a bio-inspired WASD algorithm for binary classification problems (BWASD) for best adapting to the credit or loan approval model by utilizing the metaheuristic beetle antennae search (BAS) algorithm to improve the learning procedure of the WASD algorithm. Theoretical and experimental study demonstrate superior performance and problem adaptability. Furthermore, we provide a complete MATLAB package to support our experiments together with full implementation and extensive installation instructions. Full article

Employee attrition, defined as the voluntary resignation of a subset of a company’s workforce, represents a direct threat to the financial health and overall prosperity of a firm. From lost reputation and sales to the undermining of the company’s long-term strategy and corporate secrets, the effects of employee attrition are multidimensional and, in the absence of thorough planning, may endanger the very existence of the firm. It is thus impeccable in today’s competitive environment that a company acquires tools that enable timely prediction of employee attrition and thus leave room either for retention campaigns or for the formulation of strategical maneuvers that will allow the firm to undergo their replacement process with its economic activity left unscathed. To this end, a weights and structure determination (WASD) neural network utilizing Fresnel cosine integrals in the determination of its activation functions, termed FCI-WASD, is developed through a process of three discrete stages. Those consist of populating the hidden layer with a sufficient number of neurons, fine-tuning the obtained structure through a neuron trimming process, and finally, storing the necessary portions of the network that will allow for its successful future recreation and application. Upon testing the FCI-WASD on two publicly available employee attrition datasets and comparing its performance to that of five popular and well-established classifiers, the vast majority of them coming from MATLAB’s classification learner app, the FCI-WASD demonstrated superior performance with the overall results suggesting that it is a competitive as well as reliable model that may be used with confidence in the task of employee attrition classification. Full article

Multiclass classification is one of the most popular machine learning tasks. The main focus of this paper is to classify occupations according to the International Standard Classification of Occupations (ISCO) using a weights and structure determination (WASD)-based neural network. In general, WASD-trained neural networks are known to overcome the drawbacks of conventional back-propagation trained neural networks, such as slow training speed and local minimum. However, WASD-based neural networks have not yet been applied to address the challenges of multiclass classification. As a result, a novel WASD for multiclass classification (WASDMC)-based neural network is introduced in this paper. When applied to two publicly accessible ISCO datasets, the WASDMC-based neural network displayed superior performance across all measures, compared to some of the best-performing classification models that the MATLAB classification learner app has to offer. Full article