Entropy-Based Variational Scheme with Component Splitting for the Efficient Learning of Gamma Mixtures.

Finite Gamma mixture models have proved to be flexible and can take prior information into account to improve generalization capability, which make them interesting for several machine learning and data mining applications. In this study, an efficient Gamma mixture model-based approach for proportional vector clustering is proposed. In particular, a sophisticated entropy-based variational algorithm is developed to learn the model and optimize its complexity simultaneously. Moreover, a component-splitting principle is investigated, here, to handle the problem of model selection and to prevent over-fitting, which is an added advantage, as it is done within the variational framework. The performance and merits of the proposed framework are evaluated on multiple, real-challenging applications including dynamic textures clustering, objects categorization and human gesture recognition.

Discriminative Learning Approach Based on Flexible Mixture Model for Medical Data Categorization and Recognition.

In this paper, we propose a novel hybrid discriminative learning approach based on shifted-scaled Dirichlet mixture model (SSDMM) and Support Vector Machines (SVMs) to address some challenging problems of medical data categorization and recognition. The main goal is to capture accurately the intrinsic nature of biomedical images by considering the desirable properties of both generative and discriminative models. To achieve this objective, we propose to derive new data-based SVM kernels generated from the developed mixture model SSDMM. The proposed approach includes the following steps: the extraction of robust local descriptors, the learning of the developed mixture model via the expectation-maximization (EM) algorithm, and finally the building of three SVM kernels for data categorization and classification. The potential of the implemented framework is illustrated through two challenging problems that concern the categorization of retinal images into normal or diabetic cases and the recognition of lung diseases in chest X-rays (CXR) images. The obtained results demonstrate the merits of our hybrid approach as compared to other methods.

Local analysis of human cortex in MRI brain volume.

This paper describes a method for subcortical identification and labeling of 3D medical MRI images. Indeed, the ability to identify similarities between the most characteristic subcortical structures such as sulci and gyri is helpful for human brain mapping studies in general and medical diagnosis in particular. However, these structures vary greatly from one individual to another because they have different geometric properties. For this purpose, we have developed an efficient tool that allows a user to start with brain imaging, to segment the border gray/white matter, to simplify the obtained cortex surface, and to describe this shape locally in order to identify homogeneous features. In this paper, a segmentation procedure using geometric curvature properties that provide an efficient discrimination for local shape is implemented on the brain cortical surface. Experimental results demonstrate the effectiveness and the validity of our approach.

Dispersed differential hunger games search for high dimensional gene data feature selection.

The realms of modern medicine and biology have provided substantial data sets of genetic roots that exhibit a high dimensionality. Clinical practice and associated processes are primarily dependent on data-driven decision-making. However, the high dimensionality of the data in these domains increases the complexity and size of processing. It can be challenging to determine representative genes while reducing the data's dimensionality. A successful gene selection will serve to mitigate the computing costs and refine the accuracy of the classification by eliminating superfluous or duplicative features. To address this concern, this research suggests a wrapper gene selection approach based on the HGS, combined with a dispersed foraging strategy and a differential evolution strategy, to form a new algorithm named DDHGS. Introducing the DDHGS algorithm to the global optimization field and its binary derivative bDDHGS to the feature selection problem is anticipated to refine the existing search balance between explorative and exploitative cores. We assess and confirm the efficacy of our proposed method, DDHGS, by comparing it with DE and HGS combined with a single strategy, seven classic algorithms, and ten advanced algorithms on the IEEE CEC 2017 test suite. Furthermore, to further evaluate DDHGS' performance, we compare it with several CEC winners and DE-based techniques of great efficiency on 23 popular optimization functions and the IEEE CEC 2014 benchmark test suite. The experimentation asserted that the bDDHGS approach was able to surpass bHGS and a variety of existing methods when applied to fourteen feature selection datasets from the UCI repository. The metrics measured--classification accuracy, the number of selected features, fitness scores, and execution time--all showed marked improvements with the use of bDDHGS. Considering all results, it can be concluded that bDDHGS is an optimal optimizer and an effective feature selection tool in the wrapper mode.

An optimized machine learning method for predicting wogonin therapy for the treatment of pulmonary hypertension.

Human health is at risk from pulmonary hypertension (PH), characterized by decreased pulmonary vascular resistance and constriction of the pulmonary vessels, resulting in right heart failure and dysfunction. Thus, preventing PH and monitoring its progression before treating it is vital. Wogonin, derived from the leaves of Scutellaria baicalensis Georgi, exhibits remarkable pharmacological activity. In this study, we examined the effectiveness of wogonin in mitigating the progression of PH in mice using right heart catheterization and hematoxylin-eosin (HE) staining. As an alternative to minimize the possibility of harming small animals, we present a scientifically effective feature selection method (BSCDWOA-KELM) that will allow us to develop a novel simpler noninvasive prediction method for wogonin in treating PH. In this method, we use the proposed enhanced whale optimizer (SCDWOA) in conjunction with the kernel extreme learning machine (KELM). Initially, we let SCDWOA perform global optimization experiments on the IEEE CEC2014 benchmark function set to verify its core advantages. Lastly, 12 public and PH datasets are examined for feature selection experiments using BSCDWOA-KELM. As shown in the experimental results for global optimization, the proposed SCDWOA has better convergence performance. Meanwhile, the proposed binary SCDWOA (BSCDWOA) significantly improves the ability of KELM to classify data. By utilizing the BSCDWOA-KELM, key indicators such as the Red blood cell (RBC), the Haemoglobin (HGB), the Lymphocyte percentage (LYM%), the Hematocrit (HCT), and the Red blood cell distribution width-size distribution (RDW-SD) can be efficiently screened in the Pulmonary hypertension dataset, and one of its most essential points is its accuracy of greater than 0.98. Consequently, the BSCDWOA-KELM introduced in this study can be used to predict wogonin therapy for treating pulmonary hypertension in a simple and noninvasive manner.

A novel DeepMaskNet model for face mask detection and masked facial recognition.

Coronavirus disease (COVID-19) has significantly affected the daily life activities of people globally. To prevent the spread of COVID-19, the World Health Organization has recommended the people to wear face mask in public places. Manual inspection of people for wearing face masks in public places is a challenging task. Moreover, the use of face masks makes the traditional face recognition techniques ineffective, which are typically designed for unveiled faces. Thus, introduces an urgent need to develop a robust system capable of detecting the people not wearing the face masks and recognizing different persons while wearing the face mask. In this paper, we propose a novel DeepMasknet framework capable of both the face mask detection and masked facial recognition. Moreover, presently there is an absence of a unified and diverse dataset that can be used to evaluate both the face mask detection and masked facial recognition. For this purpose, we also developed a largescale and diverse unified mask detection and masked facial recognition (MDMFR) dataset to measure the performance of both the face mask detection and masked facial recognition methods. Experimental results on multiple datasets including the cross-dataset setting show the superiority of our DeepMasknet framework over the contemporary models.

Meta-Heuristic Algorithm-Tuned Neural Network for Breast Cancer Diagnosis Using Ultrasound Images.

Breast cancer is the most menacing cancer among all types of cancer in women around the globe. Early diagnosis is the only way to increase the treatment options which then decreases the death rate and increases the chance of survival in patients. However, it is a challenging task to differentiate abnormal breast tissues from normal tissues because of their structure and unclear boundaries. Therefore, early and accurate diagnosis and classification of breast lesions into malignant or benign lesions is an active domain of research. Over the decade, numerous artificial neural network (ANN)-based techniques were adopted in order to diagnose and classify breast cancer due to the unique characteristics of learning key features from complex data via a training process. However, these schemes have limitations like slow convergence and longer training time. To address the above mentioned issues, this paper employs a meta-heuristic algorithm for tuning the parameters of the neural network. The main novelty of this work is the computer-aided diagnosis scheme for detecting abnormalities in breast ultrasound images by integrating a wavelet neural network (WNN) and the grey wolf optimization (GWO) algorithm. Here, breast ultrasound (US) images are preprocessed with a sigmoid filter followed by interference-based despeckling and then by anisotropic diffusion. The automatic segmentation algorithm is adopted to extract the region of interest, and subsequently morphological and texture features are computed. Finally, the GWO-tuned WNN is exploited to accomplish the classification task. The classification performance of the proposed scheme is validated on 346 ultrasound images. Efficiency of the proposed methodology is evaluated by computing the confusion matrix and receiver operating characteristic (ROC) curve. Numerical analysis revealed that the proposed work can yield higher classification accuracy when compared to the prevailing methods and thereby proves its potential in effective breast tumor detection and classification. The proposed GWO-WNN method (98%) gives better accuracy than other methods like SOM-SVM (87.5), LOFA-SVM (93.62%), MBA-RF (96.85%), and BAS-BPNN (96.3%).

Evaluation of Neuro Images for the Diagnosis of Alzheimer's Disease Using Deep Learning Neural Network.

Alzheimer's Disease (AD) is a progressive, neurodegenerative brain disease and is an incurable ailment. No drug exists for AD, but its progression can be delayed if the disorder is identified at its initial stage. Therefore, an early analysis of AD is of fundamental importance for patient care and efficient treatment. Neuroimaging techniques aim to assist the physician in the diagnosis of brain disorders by using images. Positron emission tomography (PET) is a kind of neuroimaging technique employed to create 3D images of the brain. Due to many PET images, researchers attempted to develop computer-aided diagnosis (CAD) to differentiate normal control from AD. Most of the earlier methods used image processing techniques for preprocessing and attributes extraction and then developed a model or classifier to classify the brain images. As a result, the retrieved features had a significant impact on the recognition rate of previous techniques. A novel and enhanced CAD system based on a convolutional neural network (CNN) is formulated to address this issue, capable of discriminating normal control from Alzheimer's disease patients. The proposed approach is evaluated using the 18FDG-PET images of 855 patients, including 635 normal control and 220 Alzheimer's disease patients from the ADNI database. The result showed that the proposed CAD system yields an accuracy of 96%, a sensitivity of 96%, and a specificity of 94%, leading to splendid performance when related to the methods already in use that are specified in the literature.

Multilevel threshold image segmentation for COVID-19 chest radiography: A framework using horizontal and vertical multiverse optimization.

COVID-19 is currently raging worldwide, with more patients being diagnosed every day. It usually is diagnosed by examining pathological photographs of the patient's lungs. There is a lot of detailed and essential information on chest radiographs, but manual processing is not as efficient or accurate. As a result, how efficiently analyzing and processing chest radiography of COVID-19 patients is an important research direction to promote COVID-19 diagnosis. To improve the processing efficiency of COVID-19 chest films, a multilevel thresholding image segmentation (MTIS) method based on an enhanced multiverse optimizer (CCMVO) is proposed. CCMVO is improved from the original Multi-Verse Optimizer by introducing horizontal and vertical search mechanisms. It has a more assertive global search ability and can jump out of the local optimum in optimization. The CCMVO-based MTIS method can obtain higher quality segmentation results than HHO, SCA, and other forms and is less prone to stagnation during the segmentation process. To verify the performance of the proposed CCMVO algorithm, CCMVO is first compared with DE, MVO, and other algorithms by 30 benchmark functions; then, the proposed CCMVO is applied to image segmentation of COVID-19 chest radiography; finally, this paper verifies that the combination of MTIS and CCMVO is very successful with good segmentation results by using the Feature Similarity Index (FSIM), the Peak Signal to Noise Ratio (PSNR), and the Structural Similarity Index (SSIM). Therefore, this research can provide an effective segmentation method for a medical organization to process COVID-19 chest radiography and then help doctors diagnose coronavirus pneumonia (COVID-19).

Bayesian Learning of Shifted-Scaled Dirichlet Mixture Models and Its Application to Early COVID-19 Detection in Chest X-ray Images.

Early diagnosis and assessment of fatal diseases and acute infections on chest X-ray (CXR) imaging may have important therapeutic implications and reduce mortality. In fact, many respiratory diseases have a serious impact on the health and lives of people. However, certain types of infections may include high variations in terms of contrast, size and shape which impose a real challenge on classification process. This paper introduces a new statistical framework to discriminate patients who are either negative or positive for certain kinds of virus and pneumonia. We tackle the current problem via a fully Bayesian approach based on a flexible statistical model named shifted-scaled Dirichlet mixture models (SSDMM). This mixture model is encouraged by its effectiveness and robustness recently obtained in various image processing applications. Unlike frequentist learning methods, our developed Bayesian framework has the advantage of taking into account the uncertainty to accurately estimate the model parameters as well as the ability to solve the problem of overfitting. We investigate here a Markov Chain Monte Carlo (MCMC) estimator, which is a computer-driven sampling method, for learning the developed model. The current work shows excellent results when dealing with the challenging problem of biomedical image classification. Indeed, extensive experiments have been carried out on real datasets and the results prove the merits of our Bayesian framework.

IoT-Based Smart Health Monitoring System for COVID-19 Patients.

During the ongoing COVID-19 pandemic, Internet of Things- (IoT-) based health monitoring systems are potentially immensely beneficial for COVID-19 patients. This study presents an IoT-based system that is a real-time health monitoring system utilizing the measured values of body temperature, pulse rate, and oxygen saturation of the patients, which are the most important measurements required for critical care. This system has a liquid crystal display (LCD) that shows the measured temperature, pulse rate, and oxygen saturation level and can be easily synchronized with a mobile application for instant access. The proposed IoT-based method uses an Arduino Uno-based system, and it was tested and verified for five human test subjects. The results obtained from the system were promising: the data acquired from the system are stored very quickly. The results obtained from the system were found to be accurate when compared to other commercially available devices. IoT-based tools may potentially be valuable during the COVID-19 pandemic for saving people's lives.

A Novel and Robust Approach to Detect Tuberculosis Using Transfer Learning.

Deep learning has emerged as a promising technique for a variety of elements of infectious disease monitoring and detection, including tuberculosis. We built a deep convolutional neural network (CNN) model to assess the generalizability of the deep learning model using a publicly accessible tuberculosis dataset. This study was able to reliably detect tuberculosis (TB) from chest X-ray images by utilizing image preprocessing, data augmentation, and deep learning classification techniques. Four distinct deep CNNs (Xception, InceptionV3, InceptionResNetV2, and MobileNetV2) were trained, validated, and evaluated for the classification of tuberculosis and nontuberculosis cases using transfer learning from their pretrained starting weights. With an F1-score of 99 percent, InceptionResNetV2 had the highest accuracy. This research is more accurate than earlier published work. Additionally, it outperforms all other models in terms of reliability. The suggested approach, with its state-of-the-art performance, may be helpful for computer-assisted rapid TB detection.

Development of an IoT-Based Sleep Apnea Monitoring System for Healthcare Applications.

Sleep is an essential and vital element of a person's life and health that helps to refresh and recharge the mind and body of a person. The quality of sleep is very important in every person's lifestyle, removing various diseases. Bad sleep is a big problem for a lot of people for a very long time. People suffering from various diseases are dealing with various sleeping disorders, commonly known as sleep apnea. A lot of people die during sleep because of uneven body changes in the body during sleep. On that note, a system to monitor sleep is very important. Most of the previous systems to monitor sleeping problems cannot deal with the real time sleeping problem, generating data after a certain period of sleep. Real-time monitoring of sleep is the key to detecting sleep apnea. To solve this problem, an Internet of Things- (IoT-) based real-time sleep apnea monitoring system has been developed. It will allow the user to measure different indexes of sleep and will notify them through a mobile application when anything odd occurs. The system contains various sensors to measure the electrocardiogram (ECG), heart rate, pulse rate, skin response, and SpO2 of any person during the entire sleeping period. This research is very useful as it can measure the indexes of sleep without disturbing the person and can also show it in the mobile application simultaneously with the help of a Bluetooth module. The system has been developed in such a way that it can be used by every kind of person. Multiple analog sensors are used with the Arduino UNO to measure different parameters of the sleep factor. The system was examined and tested on different people's bodies. To analyze and detect sleep apnea in real-time, the system monitors several people during the sleeping period. The results are displayed on the monitor of the Arduino boards and in the mobile application. The analysis of the achieved data can detect sleep apnea in some of the people that the system monitored, and it can also display the reason why sleep apnea happens. This research also analyzes the people who are not in the danger of sleeping problems by the achieved data. This paper will help everyone learn about sleep apnea and will help people detect it and take the necessary steps to prevent it.

Development of NLP-Integrated Intelligent Web System for E-Mental Health.

As the COVID-19 pandemic continues, the need for a better health care facility is highlighted more than ever. Besides physical health, mental health conditions have become a significant concern. Unfortunately, there are few opportunities for people to receive mental health care. There are inadequate facilities for seeking mental health support even in big cities, let alone remote areas. This paper presents the structure and implementation procedures for a mental health support system combining technology and professionals. The system is a web platform where mental health seekers can register and use functionalities like NLP-based chatbot for personality assessment, chatting with like-minded people, and one-to-one video conferencing with a mental health professional. The video calling feature of the system has emotion detection capabilities using computer vision. The system also includes downloadable prescription facilities and a payment gateway for secure transactions. From a technological aspect, the conversational NLP-based chatbot and computer vision-powered video calling are the system's most important features. The system has a documentation facility to analyze the mental health condition over time. The web platform is built using React.js for the frontend and Express.js for the backend. MongoDB is used as the database of the platform. The NLP chatbot is built on a three-layered deep neural network model that is programmed in the Python language and uses the NLTK, TensorFlow, and Keras sequential API. Video conference is one of the most important features of the platform. To create the video calling feature, Express.js, Socket.io, and Socket.io-client have been used. The emotion detection feature is implemented on video conferences using computer vision, Haar Cascade, and TensorFlow. All the implemented features are tested and work fine. The targeted users for the platform are teenagers, youth, and the middle-aged population. Mental health-seeking is still considered taboo in some societies today. Apart from basic established facilities, this social dilemma of undergoing treatment for mental health is causing severe damage to individuals. A solution to this problem can be a remote platform for mental health support. With this goal in mind, this system is designed to provide mental health support to people remotely from anywhere worldwide.

Towards the Segmentation and Classification of White Blood Cell Cancer Using Hybrid Mask-Recurrent Neural Network and Transfer Learning.

Inside the bone marrow, plasma cells are created, and they are a type of white blood cells. They are made from B lymphocytes. Antigens are produced by plasma cells to combat bacteria and viruses and prevent inflammation and illness. Multiple myeloma is a plasma cell cancer that starts in the bone marrow and causes the formation of abnormal plasma cells. Multiple myeloma is firmly identified by examining bone marrow samples under a microscope for myeloma cells. To diagnose myeloma cells, pathologists have to be very selective. Furthermore, because the ultimate decision is based on human sight and opinion, there is a possibility of error in the result. The nobility of this research is that it provides a computer-assisted technique for recognizing and detecting myeloma cells in bone marrow smears. For recognizing purposes, we have used Mask-Recurrent Convolutional Neural Network, and for detection purposes, Efficient Net B3 has been used. There are already many studies on white blood cell cancer, but very few with both segmentation and classification. We have designed two models. One is for recognizing myeloma cells, and the other is for differentiating them from nonmyeloma cells. Also, a new data set has been made from the multiple myeloma data sets, which has been used in our classification model. This research focuses on hybrid segmentation models and increases the accuracy level of the classification model. Both of our models are trained pretty well, where the Mask-RCNN model gives a mean average precision (mAP) of 93% and the Efficient Net B3 model gives 94.68% accuracy. The result of this research indicates that the Mask-RCNN model can recognize multiple myeloma and Efficient Net B3 can distinguish between myeloma and nonmyeloma cells and beats most of the state of the art in myeloma recognition and detection.

Classification of COVID-19 and Pneumonia Using Deep Transfer Learning.

The World Health Organization (WHO) recognized COVID-19 as the cause of a global pandemic in 2019. COVID-19 is caused by SARS-CoV-2, which was identified in China in late December 2019 and is indeed referred to as the severe acute respiratory syndrome coronavirus-2. The whole globe was hit within several months. As millions of individuals around the world are infected with COVID-19, it has become a global health concern. The disease is usually contagious, and those who are infected can quickly pass it on to others with whom they come into contact. As a result, monitoring is an effective way to stop the virus from spreading further. Another disease caused by a virus similar to COVID-19 is pneumonia. The severity of pneumonia can range from minor to life-threatening. This is particularly hazardous for children, people over 65 years of age, and those with health problems or immune systems that are affected. In this paper, we have classified COVID-19 and pneumonia using deep transfer learning. Because there has been extensive research on this subject, the developed method concentrates on boosting precision and employs a transfer learning technique as well as a model that is custom-made. Different pretrained deep convolutional neural network (CNN) models were used to extract deep features. The classification accuracy was used to measure performance to a great extent. According to the findings of this study, deep transfer learning can detect COVID-19 and pneumonia from CXR images. Pretrained customized models such as MobileNetV2 had a 98% accuracy, InceptionV3 had a 96.92% accuracy, EffNet threshold had a 94.95% accuracy, and VGG19 had a 92.82% accuracy. MobileNetV2 has the best accuracy of all of these models.

Comparative Analysis for Prediction of Kidney Disease Using Intelligent Machine Learning Methods.

Chronic kidney disease (CKD) is a major burden on the healthcare system because of its increasing prevalence, high risk of progression to end-stage renal disease, and poor morbidity and mortality prognosis. It is rapidly becoming a global health crisis. Unhealthy dietary habits and insufficient water consumption are significant contributors to this disease. Without kidneys, a person can only live for 18 days on average, requiring kidney transplantation and dialysis. It is critical to have reliable techniques at predicting CKD in its early stages. Machine learning (ML) techniques are excellent in predicting CKD. The current study offers a methodology for predicting CKD status using clinical data, which incorporates data preprocessing, a technique for managing missing values, data aggregation, and feature extraction. A number of physiological variables, as well as ML techniques such as logistic regression (LR), decision tree (DT) classification, and K-nearest neighbor (KNN), were used in this work to train three distinct models for reliable prediction. The LR classification method was found to be the most accurate in this role, with an accuracy of about 97 percent in this study. The dataset that was used in the creation of the technique was the CKD dataset, which was made available to the public. Compared to prior research, the accuracy rate of the models employed in this study is considerably greater, implying that they are more trustworthy than the models used in previous studies as well. A large number of model comparisons have shown their resilience, and the scheme may be inferred from the study's results.

Stroke Disease Detection and Prediction Using Robust Learning Approaches.

Stroke is a medical disorder in which the blood arteries in the brain are ruptured, causing damage to the brain. When the supply of blood and other nutrients to the brain is interrupted, symptoms might develop. According to the World Health Organization (WHO), stroke is the greatest cause of death and disability globally. Early recognition of the various warning signs of a stroke can help reduce the severity of the stroke. Different machine learning (ML) models have been developed to predict the likelihood of a stroke occurring in the brain. This research uses a range of physiological parameters and machine learning algorithms, such as Logistic Regression (LR), Decision Tree (DT) Classification, Random Forest (RF) Classification, and Voting Classifier, to train four different models for reliable prediction. Random Forest was the best performing algorithm for this task with an accuracy of approximately 96 percent. The dataset used in the development of the method was the open-access Stroke Prediction dataset. The accuracy percentage of the models used in this investigation is significantly higher than that of previous studies, indicating that the models used in this investigation are more reliable. Numerous model comparisons have established their robustness, and the scheme can be deduced from the study analysis.

A Robust and Novel Approach for Brain Tumor Classification Using Convolutional Neural Network.

Brain tumors are the most common and aggressive illness, with a relatively short life expectancy in their most severe form. Thus, treatment planning is an important step in improving patients' quality of life. In general, image methods such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound images are used to assess tumors in the brain, lung, liver, breast, prostate, and so on. X-ray images, in particular, are utilized in this study to diagnose brain tumors. This paper describes the investigation of the convolutional neural network (CNN) to identify brain tumors from X-ray images. It expedites and increases the reliability of the treatment. Because there has been a significant amount of study in this field, the presented model focuses on boosting accuracy while using a transfer learning strategy. Python and Google Colab were utilized to perform this investigation. Deep feature extraction was accomplished with the help of pretrained deep CNN models, VGG19, InceptionV3, and MobileNetV2. The classification accuracy is used to assess the performance of this paper. MobileNetV2 had the accuracy of 92%, InceptionV3 had the accuracy of 91%, and VGG19 had the accuracy of 88%. MobileNetV2 has offered the highest level of accuracy among these networks. These precisions aid in the early identification of tumors before they produce physical adverse effects such as paralysis and other impairments.

Comparative Analysis of Deepfake Image Detection Method Using Convolutional Neural Network.

Generation Z is a data-driven generation. Everyone has the entirety of humanity's knowledge in their hands. The technological possibilities are endless. However, we use and misuse this blessing to face swap using deepfake. Deepfake is an emerging subdomain of artificial intelligence technology in which one person's face is overlaid over another person's face, which is very prominent across social media. Machine learning is the main element of deepfakes, and it has allowed deepfake images and videos to be generated considerably faster and at a lower cost. Despite the negative connotations associated with the phrase "deepfakes," the technology is being more widely employed commercially and individually. Although it is relatively new, the latest technological advances make it more and more challenging to detect deepfakes and synthesized images from real ones. An increasing sense of unease has developed around the emergence of deepfake technologies. Our main objective is to detect deepfake images from real ones accurately. In this research, we implemented several methods to detect deepfake images and make a comparative analysis. Our model was trained by datasets from Kaggle, which had 70,000 images from the Flickr dataset and 70,000 images produced by styleGAN. For this comparative study of the use of convolutional neural networks (CNN) to identify genuine and deepfake pictures, we trained eight different CNN models. Three of these models were trained using the DenseNet architecture (DenseNet121, DenseNet169, and DenseNet201); two were trained using the VGGNet architecture (VGG16, VGG19); one was with the ResNet50 architecture, one with the VGGFace, and one with a bespoke CNN architecture. We have also implemented a custom model that incorporates methods like dropout and padding that aid in determining whether or not the other models reflect their objectives. The results were categorized by five evaluation metrics: accuracy, precision, recall, F1-score, and area under the ROC (receiver operating characteristic) curve. Amongst all the models, VGGFace performed the best, with 99% accuracy. Besides, we obtained 97% from the ResNet50, 96% from the DenseNet201, 95% from the DenseNet169, 94% from the VGG19, 92% from the VGG16, 97% from the DenseNet121 model, and 90% from the custom model.