Human gender classification based on biometric features is a major concern for computer vision due to its vast variety of applications. The human ear is popular among researchers as a soft biometric trait, because it ...
详细信息
This paper forecasts the microeconomic level household expenditures using a novel hybrid deep learning approach. In terms of research significance, household finance control has a major influence on the finance system...
详细信息
ISBN:
(数字)9798331530983
ISBN:
(纸本)9798331530990
This paper forecasts the microeconomic level household expenditures using a novel hybrid deep learning approach. In terms of research significance, household finance control has a major influence on the finance system within the economy. Accurate forecasting of household finances assists in maintaining positive financial behavior among individuals and the economy. The DeepBoost multi-output regressor proposed in this paper is based on the 1D CNN-ANN and the XGBoost. The proposed model in this paper is compared with the R 2 , MSE, and MAE since it’s a regression problem. The experimental results reveal that the proposed DeepBoost multi-output regressor has the best application in forecasting the multiple expenditures of households by outperforming the ANN, 1D CNN-ANN, and Random Forest Regressor models. The proposed DeepBoost multi-output regressor evaluated the housing, food, transportation, healthcare, other necessities, childcare, and tax expenditures that had 0.94, 0.98, 0.83, 0.94, 0.97, 0.97, and 0.99 values for the R 2 , 9037.71, 2692.12, 9788, 15077.33, 1373.93, 13629.36, and 1904.52 values for the MSE, and 66.07, 34.05, 73.17, 87.05, 26.25, 78.74, and 29.47 MAE values than the ANN, RFR, and 1D CNN-ANN models.
With the popularization of intelligent education, more and more handwritten homework is required to be photographed and uploaded on the online platform for submission. Teachers need to grade the handwritten homework s...
详细信息
ISBN:
(纸本)9798400712692
With the popularization of intelligent education, more and more handwritten homework is required to be photographed and uploaded on the online platform for submission. Teachers need to grade the handwritten homework submitted by students on the platform. A large number of repetitive grading homework brings a lot of burden to teachers and online grading also causes damage to teachers' eyesight. However, the current research in this area only focuses on the recognition of single font symbols, and cannot effectively and automatically grade the answers submitted by students in the actual teaching environment that contains multiple types of text,symbol and image. To address this problem, we propose an automatic handwritten homework grading system based on a model fusion method to assist teachers in the automatic marking and grading of homework. The model binarizes the collected handwritten tasks to reduce factors such as ambient light. Then the KNN model is used to divide the binarized images into two categories: digital symbols and graphic assignments. The YOLO-CoordAtt model is proposed for graphic homework recognition and automatic grading. The model predicts the target position and category of the scoring points in the answers submitted by students, and scores them according to different step points. Finally, all the step points obtained by the students are added up to output the student's score. In daily teaching environments, there are usually a large number of mathematical symbols in homework. Due to the complex symbol structure and different writing styles, YOLO-CoorAtt is usually difficult to accurately identify them. We proposed CSP-Posformer to solve this problem. CSP-Posformer converts the mathematical symbol homework submitted by students into latex expressions and compares them with the latex expressions of the scoring points entered by the teacher. If they are the same, they will be given scores, realizing automatic grading of handwritten homework containi
In this project, we have tried to develop a system that detects and tracks moving cars on road using cameras. Detected vehicles are given a specific id and information is stored by the system which is further used for...
详细信息
Cancer is the most common disease, which leads to death worldwide. Colon, prostate, breast, bladder, and lung are the common types of cancer among men and women. This work helps researchers to compose an automated cla...
详细信息
Skin cancer is a severe health issue. Thus, the major concern of physicians is to investigate a precise clinical diagnosis. At present, some mechanisms are developed in the area of image processing with the help of al...
详细信息
The study of statistical models and algorithms that computers use to complete a particular task without external guidance or being explicitly programmed is known as machine learning. Lots of applications that we are u...
详细信息
E-commerce, video websites, and social networking sites are just a few examples of where recommendation algorithms are currently being used. As the amount and variety of data used in recommendation systems grows, more...
详细信息
Pressure Ulcers (PU) or Decubitus Ulcers (DU) are localized injuries to the skin or underlying tissue, usually over a bony prominence resulting from unrelieved pressure. They are deep scars that can potentially reach ...
详细信息
In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained ...
详细信息
In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained Convolutional Neural Network (CNN) models, in the field of FR. The study harnesses the power of five pre-trained CNN models—DenseNet201, ResNet152V2, MobileNetV2, SeResNeXt, and Xception—for robust feature extraction, followed by SoftMax classification. A novel weighted average ensemble model, meticulously optimized through a grid search technique, is introduced to augment feature extraction and classification efficacy. Emphasizing the significance of robust data pre-processing, encompassing resizing, data augmentation, splitting, and normalization, the research endeavors to fortify the reliability of FR systems. Methodologically, the study systematically investigates hyperparameters across deep learning models, fine-tuning network depth, learning rate, activation functions, and optimization methods. Comprehensive evaluations unfold across diverse datasets to discern the effectiveness of the proposed models. Key contributions of this work encompass the utilization of pre-trained CNN models for feature extraction, extensive evaluation across multiple datasets, the introduction of a weighted average ensemble model, emphasis on robust data pre-processing, systematic hyperparameter tuning, and the utilization of comprehensive evaluation metrics. The results, meticulously analyzed, unveil the superior performance of the proposed method, consistently outshining alternative models across pivotal metrics, including Recall, Precision, F1 Score, Matthews Correlation Coefficient (MCC), and Accuracy. Notably, the proposed method attains an exceptional accuracy of 99.48% on the labeled faces in the wild (LFW) dataset, surpassing erstwhile state-of-the-art benchmarks. This research represents a significant stride in FR technology, furnishing a dependable and accurate
暂无评论