طبق اظهارات سازمان جهانی، مهمترین عامل تهدید کننده انسان آریتمی های قلبی می باشند. بر طبق آخرین آمار جهانی بهداشت نزدیک به 50% موارد مرگ و میر بر اثر عاضه های قلبی می باشند. بر اساس تحقیقات 25% موارد مرگ و میر بر اثر بیماری های قلبی، با تشخیص به موقع و صحیح قابل احیا می باشند. سیگنال الکتروکاردیوگرام مهمترین و وابسته ترین سیگنال وابسته به قلب می باشد. ثبت این سیگنال کم هزینه و و ثمر بخش می باشد و در تشخیص آریتمی ها بسیار توانمند است. استخراج ویژگی ها مهمترین قسمت برای تشخیص و پردازش می باشند. ویژگی های عمیق بر مبنای شبکه عصبی کانولوشن بسیار توانمند بوده و بادون دخالت دست انجام می شود. در این مقاله با استفاده از یادگیری عمیق بر مبنای شبکه عصبی کانولوشن ویژگی های عمیق استخراج می شوند. سپس نتایج طبقه بندی با صحت متوسط 99.3% و حساسیت متوسط 99.1% با اعتبارسنجی متقابل 10 برابری محاسبه شده است. با توجه به نتایج بدست آمده میتوان گفت که روش پیشنهادی، توانایی طبقه بندی آریتمی های قلببی را با صحت قابل قبول دارا می باشد. Manuscript profile

According to the report of the World Health Organization, corona disease is the most dangerous and contagious disease in the world. Currently, the most common method used to diagnose corona disease is the polymer chain reaction laboratory technique of reverse transcription, but since this method requires time to confirm the presence of the virus in the laboratory and also due to the unavailability of diagnostic kits and its high costs, Suspected corona virus patients cannot be identified and treated in time; This, in turn, can increase the likelihood of spreading the disease.Another diagnostic method is the use of X-ray chest imaging technique as well as chest computed tomography scan. Also, the use of deep learning methods can be very important for faster and more accurate diagnosis of the lung problems of the corona virus.In this study, using optimized deep convolutional networks based on X-ray images, patients with corona virus were diagnosed.In this article, using the optimized convolutional neural network of healthy people and those with corona, with 10-Fold cross-validation, average accuracy of 98.9% and average sensitivity of 96.5% were obtained.According to the obtained results, it can be said that the proposed method has the ability to separate healthy and unhealthy signals with acceptable accuracy. Manuscript profile

According to the information of the World Health Organization, today heart diseases are considered the most important threat to humans and are the first cause of death in the world. According to the latest global statistics, 46% of deaths are related to the heart. According to reports and research, a large number of causes of death are caused by heart diseases, while 25% of cases are reversible. Correct and timely diagnosis of patients with acute heart problems can largely prevent sudden death and further problems.Due to the fact that recording an electrocardiogram is inexpensive and fruitful, the use of an electrocardiogram can help a lot in many heart diseases and other diseases.Deep learning is one of the new methods with high accuracy in diagnosis and classification, which is based on the convolutional neural network.Convolutional neural networks have a very high processing and training time, which can be optimized and reduced in order to reduce the time, so that acceptable results can be obtained with high accuracy.In this article, using the optimized convolutional neural network, the healthy and unhealthy signal was obtained with 99.9% accuracy and 99.7% sensitivity with 10-fold cross-validation.According to the obtained results, it can be said that the proposed method has the ability to separate healthy and unhealthy signals with acceptable accuracy. Manuscript profile

Retinal blood vessels include arteries and veins and are usually next to each other. Blood vessels are used to classify the severity of the disease and are also used for guidance during surgery, as retinopathy is one of the dangerous diseases.Diabetic retinopathy can cause the formation of new vessels (neoangiogenesis). This condition causes low vision and even blindness. Therefore, a reliable method for diagnosing and classifying the vessel is needed in order to avoid these complications. Retinopathy is one of the hidden diseases that is usually not known. prevent the next possibility.There are several methods for diagnosis, the most common of which is the use of traditional methods based on manual feature extraction, which requires a lot of feature geometry and expertise, and is usually dependent on data.From this method, neural convolution is a reliable, efficient and reliable method for extracting features without manual intervention, which requires a lot of expertise, which also reduces the dependence on data.In this article, using convolutional neural network, diabetic retinopathy has been diagnosed with accuracy and sensitivity of 98.8% and 97.5%, respectively.The obtained results indicate that the proposed method is suitable for locating blood vessels automatically. Manuscript profile

Sleep stages classification using the signal analysis includes EEG, EOG, EMG, PPG, and ECG. In this study, the proposed method using transfer learning to sleep stages classification. First, we have used the two PPG signals for this method It is important to use a less complex signal. The PPG signal has the least complexity, and in this article, we used this signal for transitional learning. In this study, we extracted 52 features from two signals and prepared them for the classification stage. This method includes two steps, (a) Train data PPG1 and Test data PPG2, (b) Train data PPG2 and Test data PPG1. Results proved that our method has acceptable reliability for classification. The accuracy of 94.26% and 96.49% has been reached. Manuscript profile

Classification of sleep stages is an important method in diagnosing sleep problems. This is done by experts, based on visual inspection of bio-signals such as EEG, EOGs, ECG, EMG, etc. The deep learning method is one of the newest and most important methods for analyzing, separating, and detecting images, which is becoming more and more widespread. In this paper, for the first time, the deep learning method is used to extract the EEG signal time frequency image to classify sleep stages. Here, from the one channel of EEG signal, the time frequency image of the signal is extracted and then feature extraction using the deep learning method is done. Finally, without changing the nature of the signal, the sleep steps are detected with acceptable accuracy. In this article, for the first time, time-frequency image (TFI) was provided from the one channel of the EEG signal. Then, using the AlexNet convolutional neural network by the Wigner-Ville distribution method (ANWVD), using Deeper layers contain higher-level features were extracted, and finally, using the SVM classifier, the sleep steps were classified with acceptable accuracy. The accuracy 97.6% and the time of calculations 0.36s have been reached Manuscript profile