Digitization created a demand for highly efficient handwritten document recognition systems. A handwritten document consists of digits, text, symbols, diagrams, etc. Digits are an essential element of handwritten documents. Accurate recognition of handwritten digits is vital for effective communication and data analysis. Various researchers have attempted to address this issue with modern convolutional neural network (CNN) techniques. Even after training, CNN filter weights remain unchanged despite the high identification accuracy. As a result, the process cannot flexibly adapt to input changes. Hence computer vision researchers have recently become interested in Vision Transformers (ViTs) and Multilayer Perceptrons (MLPs). The shortcomings of CNNs gave rise to a hybrid model revolution that combines the best elements of the two fields. This paper analyzes how the hybrid convolutional ViT model affects the ability to recognize handwritten digits. Also, the real-time data contains noise, distortions, and varying writing styles. Hence, cleaned and uncleaned handwritten digit images are used for evaluation in this paper. The accuracy of the proposed method is compared with the state-of-the-art techniques, and the result shows that the proposed model achieves the highest recognition accuracy. Also, the probable solutions for recognizing other aspects of handwritten documents are discussed in this paper.•Analyzed the effect of convolutional vision transformer on cleaned and real-time handwritten digit images.•The model's performance improved with the implication of cross-validation and hyper-parameter tuning.•The results show that the proposed model is robust, feasible, and effective on cleaned and uncleaned handwritten digits.
The diagnosis of leukemia involves the detection of the abnormal characteristics of blood cells by a trained pathologist. Currently, this is done manually by observing the morphological characteristics of white blood cells in the microscopic images. Though there are some equipment- based and chemical-based tests available, the use and adaptation of the automated computer vision-based system is still an issue. There are certain software frameworks available in the literature; however, they are still not being adopted commercially. So there is a need for an automated and software- based framework for the detection of leukemia. In software-based detection, segmentation is the first critical stage that outputs the region of interest for further accurate diagnosis. Therefore, this paper explores an efficient and hybrid segmentation that proposes a more efficient and effective system for leukemia diagnosis. A very popular publicly available database, the acute lymphoblastic leukemia image database (ALL-IDB), is used in this research. First, the images are pre-processed and segmentation is done using Multilevel thresholding with Otsu and Kapur methods. To further optimize the segmentation performance, the Learning enthusiasm-based teaching-learning-based optimization (LebTLBO) algorithm is employed. Different metrics are used for measuring the system performance. A comparative analysis of the proposed methodology is done with existing benchmarks methods. The proposed approach has proven to be better than earlier techniques with measuring parameters of PSNR and Similarity index. The result shows a significant improvement in the performance measures with optimizing threshold algorithms and the LebTLBO technique.
COVID-19 is a highly contagious disease that has infected over 136 million people worldwide with over 2.9 million deaths as of 11 April 2021. In March 2020, the WHO declared COVID-19 as a pandemic and countries began to implement measures to control the spread of the virus. The spread and the death rates of the virus displayed dramatic differences among countries globally, showing that there are several factors affecting its spread and mortality. By utilizing the cumulative number of cases from John Hopkins University, the recovery rate, death rate, and the number of active, recovered, and death cases were simulated to analyse the trends and patterns within the chosen countries. 10 countries from 3 different case severity categories (high cases, medium cases, and low cases) and 5 continents (Asia, North America, South America, Europe, and Oceania) were studied. A generalized SEIR model which considers control measures such as isolation, and preventive measures such as vaccination is applied in this study. This model is able to capture not only the dynamics between the states, but also the time evolution of the states by using the fourth-order-Runge-Kutta process. This study found no significant patterns in the countries under the same case severity category, suggesting that there are other factors contributing to the pattern in these countries. One of the factors influencing the pattern in each country is the population's age. COVID-19 related deaths were found to be notably higher among older people, indicating that countries comprising of a larger proportion of older age groups have an increased risk of experiencing higher death rates. Tighter governmental control measures led to fewer infections and eventually reduced the number of death cases, while increasing the recovery rate, and early implementations were found to be far more effective in controlling the spread of the virus and produced better outcomes.
As one of the most common female cancers, cervical cancer often develops years after a prolonged and reversible pre-cancerous stage. Traditional classification algorithms used for detection of cervical cancer often require cell segmentation and feature extraction techniques, while convolutional neural network (CNN) models demand a large dataset to mitigate over-fitting and poor generalization problems. To this end, this study aims to develop deep learning models for automated cervical cancer detection that do not rely on segmentation methods or custom features. Due to limited data availability, transfer learning was employed with pre-trained CNN models to directly operate on Pap smear images for a seven-class classification task. Thorough evaluation and comparison of 13 pre-trained deep CNN models were performed using the publicly available Herlev dataset and the Keras package in Google Collaboratory. In terms of accuracy and performance, DenseNet-201 is the best-performing model. The pre-trained CNN models studied in this paper produced good experimental results and required little computing time.
The primary objective of this proposed framework work is to detect and classify various lung diseases such as pneumonia, tuberculosis, and lung cancer from standard X-ray images and Computerized Tomography (CT) scan images with the help of volume datasets. We implemented three deep learning models namely Sequential, Functional & Transfer models and trained them on open-source training datasets. To augment the patient's treatment, deep learning techniques are promising and successful domains that extend the machine learning domain where CNNs are trained to extract features and offers great potential from datasets of images in biomedical application. Our primary aim is to validate our models as a new direction to address the problem on the datasets and then to compare their performance with other existing models. Our models were able to reach higher levels of accuracy for possible solutions and provide effectiveness to humankind for faster detection of diseases and serve as best performing models. The conventional networks have poor performance for tilted, rotated, and other abnormal orientation and have poor learning framework. The results demonstrated that the proposed framework with a sequential model outperforms other existing methods in terms of an F1 score of 98.55%, accuracy of 98.43%, recall of 96.33% for pneumonia and for tuberculosis F1 score of 97.99%, accuracy of 99.4%, and recall of 98.88%. In addition, the functional model for cancer outperformed with an accuracy of 99.9% and specificity of 99.89% and paves way to less number of trained parameters, leading to less computational overhead and less expensive than existing pretrained models. In our work, we implemented a state-of-the art CNN with various models to classify lung diseases accurately.
Human behaviour reflects cognitive abilities. Human cognition is fundamentally linked to the different experiences or characteristics of consciousness/emotions, such as joy, grief, anger, etc., which assists in effective communication with others. Detection and differentiation between thoughts, feelings, and behaviours are paramount in learning to control our emotions and respond more effectively in stressful circumstances. The ability to perceive, analyse, process, interpret, remember, and retrieve information while making judgments to respond correctly is referred to as Cognitive Behavior. After making a significant mark in emotion analysis, deception detection is one of the key areas to connect human behaviour, mainly in the forensic domain. Detection of lies, deception, malicious intent, abnormal behaviour, emotions, stress, etc., have significant roles in advanced stages of behavioral science. Artificial Intelligence and Machine learning (AI/ML) has helped a great deal in pattern recognition, data extraction and analysis, and interpretations. The goal of using AI and ML in behavioral sciences is to infer human behaviour, mainly for mental health or forensic investigations. The presented work provides an extensive review of the research on cognitive behaviour analysis. A parametric study is presented based on different physical characteristics, emotional behaviours, data collection sensing mechanisms, unimodal and multimodal datasets, modelling AI/ML methods, challenges, and future research directions.