Jafar-Abdollahi

An-artificial-intelligence-system-for-detecting-the-types-of-the-epidemic-from-X-rays-

we propose the adoption of deep learning to detect whether there's a COVID-19 presence in X-ray images by exploiting transfer learning. thus proposes an improved algorithm of convolutional neural network VGG-16 and VGG-19 using deep learning to realize this goal. this may represent a suggestion for the radiologist to right away localize the X-ray areas that may be of interest.

Automated-Classification-of-Lung-Cancer-Types-from-Cytological-Images-Using-Deep-Convolutional-Neura

Lung cancer is a leading cause of death worldwide. Currently, in the differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma) is required. However, improving the accuracy and stability of diagnosis is challenging. In this project, we developed an automated classification scheme for lung cancers presented in ct images using a deep convolutional neural network. In the results obtained, approximately 91% of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.

Automated-detection-of-COVID-19-cases-using-deep-neural-networks-with-CTS-images

The use of advanced artificial intelligence (AI) techniques combined with radiological imaging can be useful for accurate diagnosis of the disease and can also help overcome the shortage of specialist physicians in remote villages. In this project, a new model for automatic detection of covid-19 using raw chest X-ray images is presented. The proposed model is designed to provide an accurate diagnosis for binary classification (COVID vs. pneumonia ) and multi-classification (covid, pneumonia, nodel, boronshit, normal). Our model produces 99.08% classification accuracy for binary classifications and 95.02% for multi-class cases. The DarkNet model was used in our study as a classification where you only look at the real-time object recognition system once (YOLO(v3)). We applied 17 layers of the convolution and applied different filters on each layer. Our model can be used to help radiologists discredit their initial screening and can also be used over the cloud for rapid screening of patients.

cuffless-bp-master-in-python-jupyter-

Blood pressure (BP) is a direct indicator of hypertension, a dangerous and potentially deadly condition. Regular monitoring of BP is thus important, but many people have aversion towards cuff-based devices, and their limitation is that they can only be used at rest. Using just a photoplethysmogram (PPG) to estimate BP is a potential solution investigated in our study.

detection-of-breast-cancer-metastasis-using-a-hybrid-model-

Breast cancer (BC) is a prevalent disease and major cause of mortality among women worldwide. A substantial number of BC patients experience metastasis which in turn leads to treatment failure and death. The survival rate has been significantly increased thanks to the state of the art technologies and detection tools. In this study, we cross-compared the application of advanced artificial intelligence algorithms such as Logistic Regression, K-Nearest Neighbors, Discrete Cosine Transform, Random Forest Classifier, Support Vector Machines, Multilayer Perceptron, and Ensemble to diagnose BC metastasis. We further combined MLP with genetic algorithm (GA) as a hybrid method of intelligent analysis. The core data we used for comparison belonged to the images of both benign and malignant tumors and were taken from Wisconsin Breast Cancer dataset from the UCI repository. Our findings indicate that our MLP-GA hybrid algorithm can speed up diagnosis with higher accuracy rate than the individual patterns of algorithm. Two methods of comparison (Cross-Validation and Holdout) were applied to this study which produced consistent results

Diagnosis-of-diabetes-using-a-Ensemble-learning

In this project, Ensemble learning algorithms with a combination of hybrid feature selection are used to more accurately diagnose and predict diabetes. The results show that the proposed method has a higher performance than the basic methods and has reached 93% accuracy.

Diagnosis-of-heart-disease-using-feature-selection

In this project, a neural network-based genetic algorithm is used to diagnose heart disease using wrapper reduction. A combination of these techniques is used to manage the data set with dimensions and uncertainty that the data is obtained from the uci heart disease data set These data are classified based on different uses. The results show that the accuracy of the proposed method has reached 79% accuracy.

Diagnosis-of-skin-disease-using-machine-vision

Skin diseases are more common than other diseases. Skin diseases may be caused by fungal infection, bacteria, allergy, or viruses, etc. The advancement of lasers and Photonics based medical technology has made it possible to diagnose the skin diseases much more quickly and accurately. But the cost of such diagnosis is still limited and very expensive. So, image processing techniques help to build automated screening system for dermatology at an initial stage. The extraction of features plays a key role in helping to classify skin diseases. Computer vision has a role in the detection of skin diseases in a variety of techniques.

Feature-selection-systems-for-Identify-the-factors-influencing-suicide-

Suicide is a major public health problem, and suicide rates are still on the rise. Current strategies for identifying individuals at risk for suicide, such as the use of a patient's self-reported suicidal ideation or evidence of past suicide attempts, have not been sufficient in reducing suicide rates. The availability of huge amounts of medical data leads to the need for powerful learning tools to help medical experts to diagnose suicide diseases. Machine learning methods are helpful in the diagnosis of suicide disease, showing a reasonable level of efficiency. But these data are redundant and are noisy in nature, which negatively affects the process of observing knowledge and useful patterns. Machine learning techniques have attracted big attention from researchers to turn such data into useful knowledge. Furthermore, relevant data can be extracted from huge records using filter-based feature selection methods.

medicinal-plants

For the protection of natural resources, plants are of central importance. Identification of plant species offers important knowledge on the categorization and properties of plants. Many plants are richly having medicinal ingredients and contain medicinal active ingredients. The identification of these plants is immediately necessary because of the need for mass production. The manual identification of medicinal plants takes time and the assistance of plant identification experts is necessary. To solve this problem, it is essential for human beings to automatically recognize and classify medicinal plants. Among AI technologies, deep learning has demonstrated strong performance in many automated image-recognition applications. The aim of this study was to develop and test a deep learning system capable of Identification of Medicinal Plant.

Jafar-Abdollahi/Automated-detection-of-COVID-19-cases-using-deep-neural-networks-with-CTS-images

The use of advanced artificial intelligence (AI) techniques combined with radiological imaging can be useful for accurate diagnosis of the disease and can also help overcome the shortage of specialist physicians in remote villages. In this project, a new model for automatic detection of covid-19 using raw chest X-ray images is presented. The proposed model is designed to provide an accurate diagnosis for binary classification (COVID vs. pneumonia ) and multi-classification (covid, pneumonia, nodel, boronshit, normal). Our model produces 99.08% classification accuracy for binary classifications and 95.02% for multi-class cases. The DarkNet model was used in our study as a classification where you only look at the real-time object recognition system once (YOLO(v3)). We applied 17 layers of the convolution and applied different filters on each layer. Our model can be used to help radiologists discredit their initial screening and can also be used over the cloud for rapid screening of patients.

Jafar-Abdollahi/cuffless-bp-master-in-python-jupyter-

Blood pressure (BP) is a direct indicator of hypertension, a dangerous and potentially deadly condition. Regular monitoring of BP is thus important, but many people have aversion towards cuff-based devices, and their limitation is that they can only be used at rest. Using just a photoplethysmogram (PPG) to estimate BP is a potential solution investigated in our study.

Jafar-Abdollahi/Diagnosis-of-diabetes-using-a-Ensemble-learning

In this project, Ensemble learning algorithms with a combination of hybrid feature selection are used to more accurately diagnose and predict diabetes. The results show that the proposed method has a higher performance than the basic methods and has reached 93% accuracy.

Jafar-Abdollahi/detection-of-breast-cancer-metastasis-using-a-hybrid-model-

Breast cancer (BC) is a prevalent disease and major cause of mortality among women worldwide. A substantial number of BC patients experience metastasis which in turn leads to treatment failure and death. The survival rate has been significantly increased thanks to the state of the art technologies and detection tools. In this study, we cross-compared the application of advanced artificial intelligence algorithms such as Logistic Regression, K-Nearest Neighbors, Discrete Cosine Transform, Random Forest Classifier, Support Vector Machines, Multilayer Perceptron, and Ensemble to diagnose BC metastasis. We further combined MLP with genetic algorithm (GA) as a hybrid method of intelligent analysis. The core data we used for comparison belonged to the images of both benign and malignant tumors and were taken from Wisconsin Breast Cancer dataset from the UCI repository. Our findings indicate that our MLP-GA hybrid algorithm can speed up diagnosis with higher accuracy rate than the individual patterns of algorithm. Two methods of comparison (Cross-Validation and Holdout) were applied to this study which produced consistent results

Jafar-Abdollahi/Feature-selection-systems-for-Identify-the-factors-influencing-suicide-

Suicide is a major public health problem, and suicide rates are still on the rise. Current strategies for identifying individuals at risk for suicide, such as the use of a patient's self-reported suicidal ideation or evidence of past suicide attempts, have not been sufficient in reducing suicide rates. The availability of huge amounts of medical data leads to the need for powerful learning tools to help medical experts to diagnose suicide diseases. Machine learning methods are helpful in the diagnosis of suicide disease, showing a reasonable level of efficiency. But these data are redundant and are noisy in nature, which negatively affects the process of observing knowledge and useful patterns. Machine learning techniques have attracted big attention from researchers to turn such data into useful knowledge. Furthermore, relevant data can be extracted from huge records using filter-based feature selection methods.

Jafar-Abdollahi/Diagnosis-of-heart-disease-using-feature-selection

In this project, a neural network-based genetic algorithm is used to diagnose heart disease using wrapper reduction. A combination of these techniques is used to manage the data set with dimensions and uncertainty that the data is obtained from the uci heart disease data set These data are classified based on different uses. The results show that the accuracy of the proposed method has reached 79% accuracy.

Jafar-Abdollahi/Diagnosis-of-skin-disease-using-machine-vision

Skin diseases are more common than other diseases. Skin diseases may be caused by fungal infection, bacteria, allergy, or viruses, etc. The advancement of lasers and Photonics based medical technology has made it possible to diagnose the skin diseases much more quickly and accurately. But the cost of such diagnosis is still limited and very expensive. So, image processing techniques help to build automated screening system for dermatology at an initial stage. The extraction of features plays a key role in helping to classify skin diseases. Computer vision has a role in the detection of skin diseases in a variety of techniques.

Jafar-Abdollahi/medicinal-plants

For the protection of natural resources, plants are of central importance. Identification of plant species offers important knowledge on the categorization and properties of plants. Many plants are richly having medicinal ingredients and contain medicinal active ingredients. The identification of these plants is immediately necessary because of the need for mass production. The manual identification of medicinal plants takes time and the assistance of plant identification experts is necessary. To solve this problem, it is essential for human beings to automatically recognize and classify medicinal plants. Among AI technologies, deep learning has demonstrated strong performance in many automated image-recognition applications. The aim of this study was to develop and test a deep learning system capable of Identification of Medicinal Plant.

Jafar-Abdollahi/An-artificial-intelligence-system-for-detecting-the-types-of-the-epidemic-from-X-rays-

we propose the adoption of deep learning to detect whether there's a COVID-19 presence in X-ray images by exploiting transfer learning. thus proposes an improved algorithm of convolutional neural network VGG-16 and VGG-19 using deep learning to realize this goal. this may represent a suggestion for the radiologist to right away localize the X-ray areas that may be of interest.

Jafar-Abdollahi/Automated-Classification-of-Lung-Cancer-Types-from-Cytological-Images-Using-Deep-Convolutional-Neura

Lung cancer is a leading cause of death worldwide. Currently, in the differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma) is required. However, improving the accuracy and stability of diagnosis is challenging. In this project, we developed an automated classification scheme for lung cancers presented in ct images using a deep convolutional neural network. In the results obtained, approximately 91% of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.

Jafar-Abdollahi/casting-product-image-data-for-quality-inspection

casting product image data for quality inspection

Jafar-Abdollahi/detecting-metastatic-breast-cancer-from-whole-slide-pathology-images-

In cancer patients, the main event resulting in death is metastasis. Being time-consuming and labor-intensive, traditional diagnosis approaches utilized for lymph node metastases, a.k.a. LNMets, are not fairly effective. Consequently, diagnostic complexes based upon deep learning (DL) algorithms have turned into a hot trend. The purpose of this study is to design, develop, and evaluate a deep learning system being able to detect metastases related to the lymph node.

Jafar-Abdollahi/Detection-Cars-using-Yolo-v4

Detection Cars using Yolo v4

Jafar-Abdollahi/Esstimation-of-alive-and-death

Esstimation of alive and death using ML

Jafar-Abdollahi/Face-Detection

Face detection is a computer technology being used in a variety of applications that identifies human faces in digital images. Face detection also refers to the psychological process by which humans locate and attend to faces in a visual scene

Jafar-Abdollahi/Feature-selection-Addiction

Feature selection is the process of reducing the number of input variables when developing a predictive model. It is desirable to reduce the number of input variables to both reduce the computational cost of modeling and, in some cases, to improve the performance of the model. In this article, the feature selection approach is extracted to select the effective features in the incidence and guidance of the person towards addiction.

Jafar-Abdollahi/Feature-Selection-Using-GA

Feature Selection Using Genetic Algorithms

Jafar-Abdollahi/Feaure-selection-and-Classification-Mortality-estimates-

In this Project, we use a comprehensive feature selection approach to identify the useful features in people suffering from addiction quickly. The algorithms used in this paper can be summarized as follows. Our goal is to comprehensively review feature selection algorithms to identify useful features and compare the feature selection approach to this data set. This article shows a good solution for other researchers to choose the right algorithm for future research.

Jafar-Abdollahi/Jafar-Abdollahi

Jafar-Abdollahi/Personal-information-registration-system

Personal information registration system Desktop system for recording personal and academic information used in schools, universities and offices and factories

Jafar-Abdollahi/Simple-Chat-Room-using-Python

We've made it through the basics of working with sockets, and now we're ready to try to actually build something with them, so, in this sockets with Python tutorial, we're going to build a console-based chat app.

Jafar-Abdollahi/Source-code-for-fixing-the-slowness-of-Office-and-Windows-programs-in-Python

Source code for fixing the slowness of Office and Windows programs in Python

Jafar-Abdollahi/tracking-Mouse-

The ability to track animals accurately is critical for behavioral experiments. For video-based assays, this is often accomplished by manipulating environmental conditions to increase the contrast between the animal and the background in order to achieve proper foreground/background detection (segmentation). Modifying environmental conditions for experimental scalability opposes ethological relevance. The biobehavioral research community needs methods to monitor behaviors over long periods of time, under dynamic environmental conditions, and in animals that are genetically and behaviorally heterogeneous. To address this need, we applied a state-of-the-art neural network-based tracker for single mice. We compare three different neural network architectures across visually diverse mice and different environmental conditions.

Jafar-Abdollahi/txt-to-excel

Convert Text File To Excel File using Python

Jafar-Abdollahi/Type-2-diabetes-diagnosis-software-using-artificial-intelligence

This software is implemented using the tkinter tool