International journal of information technology : an official journal of Bharati Vidyapeeth's Institute of Computer Applications and Management最新文献

A COVID-19 news covers subtopics like infections, deaths, the economy, jobs, and more. The proposed method generates a news summary based on the subtopics of a reader's interest. It extracts a centroid having the lexical pattern of the sentences on those subtopics by the frequently used words in them. The centroid is then used as a query in the vector space model (VSM) for sentence classification and extraction, producing a query focused summarization (QFS) of the documents. Three approaches, TF-IDF, word vector averaging, and auto-encoder are experimented to generate sentence embedding that are used in VSM. These embeddings are ranked depending on their similarities with the query embedding. A Novel approach has been introduced to find the value for the similarity parameter using a supervised technique to classify the sentences. Finally, the performance of the method has been assessed in two different ways. All the sentences of the dataset are considered together in the first assessment and in the second, each document wise group of sentences is considered separately using fivefold cross-validation. The proposed method has achieved a minimum of 0.60 to a maximum of 0.63 mean F1 scores with the three sentence encoding approaches on the test dataset.

Credit card fraud is a growing problem nowadays and it has escalated during COVID-19 due to the authorities in many countries requiring people to use cashless transactions. Every year, billions of Euros are lost due to credit card fraud transactions, therefore, fraud detection systems are essential for financial institutions. As the classes' distribution is not equally represented in the credit card dataset, the machine learning trains the model according to the majority class which leads to inaccurate fraud predictions. For that, in this research, we mainly focus on processing unbalanced data by using an under-sampling technique to get more accurate and better results with different machine learning algorithms. We propose a framework that is based on clustering the dataset using fuzzy C-means and selecting similar fraud and normal instances that have the same features, which guarantees the integrity between the data features.

Literature suggests that by fusing multiple features there is immense improvement in the recognition rates as compared to the recognition rates of single descriptor. This motivate researchers to develop more and more fused descriptors by joining multiple features. Inspiring from the literature work, the proposed work launch novel local descriptor so-called Improved Local Descriptor (ILD), by joining features of 4 local descriptors. These are LBP, ELBP, MBP and LPQ. LBP captures local details. ELBP capture robust features in horizontal and vertical directions (elliptically) by using 3 × 5 and 5 × 3 patches. MBP minimizes image noise by median comparison to all the pixels and LPQ quantize the frequency components for obtaining feature size. These essential merits of 4 descriptors are encapsulated in one framework in the form of histogram feature. PCA is used further for compression and SVMs and NN are used for classification. Results on ORL, GT and Faces94 confirms strength of ILD, which beats separately implemented descriptors and various benchmark methods.

The demand for agricultural products increased exponentially as the global population grew. The rapid development of computer vision-based artificial intelligence and deep learning-related technologies has impacted a wide range of industries, including disease detection and classification. This paper introduces a novel neural network-based hybrid model (GCL). GCL is a dataset-augmentation fusion of long-short term memory (LSTM) and convolutional neural network (CNN) with generative adversarial network (GAN). GAN is used for the augmentation of the dataset, CNN extracts the features and LSTM classifies the various paddy diseases. The GCL model is being investigated to improve the classification model's accuracy and reliability. The dataset was compiled using secondary resources such as Mendeley, Kaggle, UCI, and GitHub, having images of bacterial blight, leaf smut, and rice blast. The experimental setup for proving the efficacy of the GCL model demonstrates that the GCL is suitable for disease classification and works with 97% testing accuracy. GCL can further be used for the classification of more diseases of paddy.

Children may benefit from automatic speaker identification in a variety of applications, including child security, safety, and education. The key focus of this study is to develop a closed-set child speaker identification system for non-native speakers of English in both text-dependent and text-independent speech tasks in order to track how the speaker's fluency affects the system. The multi-scale wavelet scattering transform is used to compensate for concerns like the loss of high-frequency information caused by the most widely used mel frequency cepstral coefficients feature extractor. The proposed large-scale speaker identification system succeeds well by employing wavelet scattered Bi-LSTM. While this procedure is used to identify non-native children in multiple classes, average values of accuracy, precision, recall, and F-measure are being used to assess the performance of the model in text-independent and text-dependent tasks, which outperforms the existing models.

Counting stock is one of the warehouse's methods for preventing insatiable stock. Moreover, it could help the company forecast how many products they need to store and predict the replenished goods for customers. However, stock count in the medical business, which sells specialized medical equipment, needs more focus on, because it uses to treat the patient. So that lack of inventory should not happen. In a normal situation, stock count at some hospitals is quite hard for salespeople, especially hospitals in upcountry that far away. During the COVID-19 situation, many limits need to be strict. At this point, it causes a shortage of goods in many hospitals. In this paper, we represent how computer vision can help this process. When the hospital's officer sends images of stock to our system. The system will recognize the quantity and lot number of goods that remain in the hospital. Therefore, salespeople can decrease the times to visit hospitals. The result showed that for text detection and text recognition in a specific use case. Our prototype system achieves 84.17% in accuracy.

Detecting influential nodes in complex social networks is crucial due to the enormous amount of data and the constantly changing behavior of existing topologies. Centrality-based and machine-learning approaches focus mostly on node topologies or feature values in their evaluation of nodes' relevance. However, both network topologies and node attributes should be taken into account when determining the influential value of nodes. This research has proposed a deep learning model called Graph Convolutional Networks (GCN) to discover the significant nodes in graph-based large datasets. A deep learning framework for identifying influential nodes with structural centrality via Graph Convolutional Networks called DeepInfNode has been developed. The proposed approach measures up contextual information from Susceptible-Infected-Recovered (SIR) model trials to measure the rate of infection to develop node representations. In the experimental section, acquired experimental results indicate that the suggested model has a higher F1 and Area under the curve (AUC) value. The findings indicate that the strategy is both effective and precise in terms of suggesting new linkages. The proposed DeepInfNode model outperforms state-of-the-art approaches on a variety of publicly available standard graph datasets, achieving an increase in performance of up to 99.1% of accuracy.

Topic modelling is a machine learning technique that is extensively used in Natural Language Processing (NLP) applications to infer topics within unstructured textual data. Latent Dirichlet Allocation (LDA) is one of the most used topic modeling techniques that can automatically detect topics from a huge collection of text documents. However, the LDA-based topic models alone do not always provide promising results. Clustering is one of the effective unsupervised machine learning algorithms that are extensively used in applications including extracting information from unstructured textual data and topic modeling. A hybrid model of Bidirectional Encoder Representations from Transformers (BERT) and Latent Dirichlet Allocation (LDA) in topic modeling with clustering based on dimensionality reduction have been studied in detail. As the clustering algorithms are computationally complex, the complexity increases with the higher number of features, the PCA, t-SNE and UMAP based dimensionality reduction methods are also performed. Finally, a unified clustering-based framework using BERT and LDA is proposed as part of this study for mining a set of meaningful topics from the massive text corpora. The experiments are conducted to demonstrate the effectiveness of the cluster-informed topic modeling framework using BERT and LDA by simulating user input on benchmark datasets. The experimental results show that clustering with dimensionality reduction would help infer more coherent topics and hence this unified clustering and BERT-LDA based approach can be effectively utilized for building topic modeling applications.