IJMSC Vol. 9, No. 1, Feb. 2023
Cover page and Table of Contents: PDF (size: 612KB)
Among other factors affecting face recognition and verification, the aging of individuals is a particularly challenging one. Unlike other factors such as pose, expression, and illumination, aging is uncontrollable, personalized, and takes place throughout human life. Thus, while the effects of factors such as head pose, illumination, and facial expression on face recognition can be minimized by using images from controlled environments, the effect of aging cannot be so controlled. This work exploits the personalized nature of aging to reduce the effect of aging on face recognition so that an individual can be correctly recognized across his/her different age-separated face images. To achieve this, an individualized face pairing method was developed in this work to pair faces against entire sets of faces grouped by individuals then, similarity score vectors are obtained for both matching and non-matching image-individual pairs, and the vectors are then used for age-invariant face recognition. This model has the advantage of being able to capture all possible face matchings (intra-class and inter-class) within a face dataset without having to compute all possible image-to-image pairs. This reduces the computational demand of the model without compromising the impact of the ageing factor on the identity of the human face. The developed model was evaluated on the publicly available FG-NET dataset, two subsets of the CACD dataset, and a locally obtained FAGE dataset using leave-one-person (LOPO) cross-validation. The model achieved recognition accuracies of 97.01%, 99.89%, 99.92%, and 99.53% respectively. The developed model can be used to improve face recognition models by making them robust to age-variations in individuals in the dataset.[...] Read more.
Information Extraction is an essential task in Natural Language Processing. It is the process of extracting useful information from unstructured text. Information extraction helps in most of the NLP applications like sentiment analysis, named entity recognition, medical data extraction, features extraction from research articles, feature extraction from agriculture, etc. Most of the applications in information extraction are performed by machine learning models. Many research work shave been carried out on machine learning based information extraction from various domain texts in English such as Bio medical, Share market, Weather, Business, Social media, Agriculture, Engineering, and Tourism. However domain specific information extraction for a particular regional language is still a challenge. There are different types of classification algorithms. However, for a selected domain to select the appropriate classification algorithm is very difficult. In this paper three famous classification algorithms are selected to do information extraction by classifying the Gynecological domain data in Tamil Language. The main objective or this research work is to analyze the machine learning methods which is suitable for Tamil domain specific text documents. There are 1635 documents being involved in classification task to extract the features by these selected three algorithms. By evaluating the classification task of each model it has been found that the Naive Bayes classification model provides highest accuracy value (84%) for the gynecological domain data. The F1-Score, Error rate and Execution time also evaluated for the selected machine learning models. The evaluation of performance has proved that the Naïve Bayes classification model gives optimal results. It has been concluded that the Naïve Bayes classification model is the best model to classify the gynaecological domain text in Tamil language[...] Read more.
Currently, every company is concerned about the retention of their staff. They are nevertheless unable to recognize the genuine reasons for their job resignations due to various circumstances. Each business has its approach to treating employees and ensuring their pleasure. As a result, many employees abruptly terminate their employment for no apparent reason. Machine learning (ML) approaches have grown in popularity among researchers in recent decades. It is capable of proposing answers to a wide range of issues. Then, using machine learning, you may generate predictions about staff attrition. In this research, distinct methods are compared to identify which workers are most likely to leave their organization. It uses two approaches to divide the dataset into train and test data: the 70 percent train, the 30 percent test split, and the K-Fold approaches. Cat Boost, LightGBM Boost, and XGBoost are three methods employed for accuracy comparison. These three approaches are accurately generated by using Gradient Boosting Algorithms.[...] Read more.
With the reform of Chinese economic system, the development of enterprises is facing many risks and challenges. In order to understand the state of operation of enterprises, it is necessary to apply relevant methods to evaluate the enterprise performance. Taking Industrial and Commercial Bank of China as an example, this paper selects its financial data from 2018 to 2021. Firstly, DuPont analysis is applied to decompose the return on equity into the product of profit margin on sales, total assets turnover ratio and equity multiplier. Then analyzes the effect of the changes of these three factors on the return on equity respectively by using the Chain substitution method. The results show that the effect of profit margin on sales on return on equity decreases year by year and tends to be positive from negative. The effect of total assets turnover ratio on return on equity changes from positive to negative and then to positive, while the effect of equity multiplier is opposite. These results provide a direction for the adjustment of the return on equity of Industrial and Commercial Bank of China. Finally, according to the results, some suggestions are put forward for the development of Industrial and Commercial Bank of China.[...] Read more.
For any graph G = (V, E),the line graph L(G)of a graph G is a graph whose set of vertices is the union of set of edges of G in which two vertices of L(G) are adjacent if and only if the corresponding edges of G are adjacent. A dominating set D_1 ⊆ V[L(G)] is called coregular perfect dominating set, if the induced subgraph < V[L(G)]-D_1 > is regular. The minimum cardinality of vertices in such a set is called coregular perfect domination number in L(G) and is represented by γ_cop [L(G)].
In this Article, we study the graph theoretic properties of γ_cop [L(G)] and many bounds were obtained in terms of elements of G and its relationship with other domination parameters were found .Our investigation on this work is to establish the application oriented standard results in the field of domination theory for several kinds of new concepts which are playing an important role of application.