فهرست مطالب mohammad roustaei

Accurate detection of apple leaf diseases is essential to prevent the reduction in both the quantity and quality of crop yield. With advancements in deep learning methods, the diagnosis of these diseases is improving, but data limitations remain a significant barrier. This research evaluates pretrained deep learning models with precise settings and demonstrates that high accuracy in disease detection is possible even with limited data. The selected models perform better than conventional methods and introduce transfer learning as an effective strategy to combat limited data and the diversity of diseases. These models aid farmers and horticulture specialists in identifying and managing apple leaf diseases more efficiently and rapidly. Additionally, these models are not only beneficial for farmers but also for agricultural consultants, students of agricultural sciences, and researchers in this field. Moreover, these methods are adaptable to other diseases and plants, promising advancements in plant disease detection systems in the future. The present study has the potential to revolutionize horticultural processes through optimization and automation, leading to a transformation in plant disease management.

Analyzing individuals' emotions from the content of social media through text, speech, and images is necessary for various types of applications and purposes. Most recent research studies in the field of sentiment analysis have focused on textual data. However, social media users share more images and videos compared to text. In other words, images are the most effective way to convey emotions to others. Therefore, focusing on the development of a sentiment analysis model based on images in social media is important. In this article, we will use the DenseNet-121 transfer learning model to analyze emotions based on images. To implement this approach, we will utilize the images available in the Image Sentiment dataset. This dataset includes internet links to images along with their emotional polarities. Based on the obtained results, the accuracy of the proposed model in this article is 89%, which, compared to previous work in the field of visual sentiment analysis, shows a 5% to 10% improvement.

COVID-19 is a new virus that causes infection in the upper respiratory tract and lungs, and the number of deaths due to the disease has increased daily on the scale of a global epidemic. Chest X-ray images have been useful for monitoring various lung diseases and have recently been used to monitor COVID-19 disease.

In this research, a multi-stage process was used to recognize COVID-19 from X-ray images. In the first stage, pre-processing was done to normalize the data. In the second step, which is the most important step of the proposed method, feature extraction was done. The feature extraction operation was based on deep learning networks. After feature extraction, machine learning algorithms were used to classify images. The algorithms used in this section are support vector machine, nearest neighbor, and decision tree algorithms. The results of these categories are combined in the fourth step based on the majority vote.

The parameters used in this research are among the classification parameters, including precision, accuracy, recall, and F-criterion, which were obtained as 96.5, 92.25, 94, and 93, respectively.

The results of the experiments show the acceptable efficiency of the proposed method because, in addition to reducing the calculations by the separable layer, the combination of categories and their weighting has been used to obtain the final result.

Social media has become a popular means of following the news. At the same time, they make possible the widespread dissemination of fake news, that is, false and deliberate news and information have significant negative effects on society. Fake news and misinformation are a big challenge in all types of media, especially social media. Most of the information that appears on social media is suspicious and in some cases misleading. Therefore, the possibility of identifying fake content in online resources is an urgent need that must be identified as soon as possible to avoid negative impact on society. The purpose of this study is to increase the accuracy of fake news detection systems on social media. Therefore, in this research, a news recognition system has been designed whose task is to distinguish the main news from the fake. In this research, a three-step process has been used to identify fake news, which has been done in the first stage of preprocessing operations. In the second step, the feature extraction operation is performed. Feature extraction operations are based on semantic relationships. In the final step, classification algorithms are used to classify the news. In this study, the nearest neighbor, decision tree, and support vector classifiers have been used, which have been combined by a majority vote. Classification criteria have been used to evaluate the proposed method. The criteria used in this study include accuracy, precision, recall and F criteria. The results of the experiments show the acceptable efficiency of the proposed method in detecting fake news. The reason for this superiority can be found in the feature extraction and classification section.

Background and Candida species constitute an important group of opportunistic fungi, which cause various clinical diseases. Considering the resistance of some Candida species to conventional antifungal agents, treatment of such cases may be challenging and complicated. The purpose of this study was to evaluate and compare the antifungal activities of Euphorbia macroclada latex and fluconazole against different Candida species.
A total of 150 Candida isolates including C. albicans (n=77), C. glabrata (n=28), C. parapsilosis (n=23), C. tropicalis (n=15), C. krusei (n=4), C. famata (n=1), C. kefyr (n=1) and C. inconspicua (n=1) were included in this study. In vitro antifungal activities of Euphorbia macroclada latex and fluconazole against these Candida species were evaluated, according to M27-A2 protocol on broth macrodilution method by the Clinical and Laboratory Standards Institute (CLSI).
Among 150 Candida isolates, 98 isolates (65.33%), i.e., C. albicans (n=41), C. glabrata (n=23), C. tropicalis (n=12) and C. parapsilosis (n=22) with minimal inhibitory concentration (MIC) ≤ 8 μg/ml were susceptible to fluconazole. Resistance to fluconazole was noted in 15 isolates, i.e., C. albicans (n=10), C. glabrata (n=2), C. krusei (n=1), C. kefyr (n=1), and C. inconspicua (n=1), with MICs of 64 µg/ml. The remaining isolates (n=37) including C. albicans (n=26), C. glabrata (n=3), C. tropicalis (n=3), C. parapsilosis (n=1), C. krusei (n=3) and C. famata (n=1) with MIC= 16-32 µg/ml showed dose-dependent susceptibility. The latex of Euphorbia macroclada was able to inhibit the growth of 30 out of 150 tested Candida isolates with MIC range of 128-512 µg/ml. These isolates were as follows: C. albicans (n=2), C. glabrata (n=4), C. parapsilosis (n=19), C. krusei (n=2) and C. tropicalis (n=3). Compared to other isolates, higher MIC values were noted for C. albicans and C. glabrata (512 µg/ml), respectively.
The latex of Euphorbia macroclada showed notable antifungal activities against some pathogenic Candida species. Therefore, it can be potentially used as an alternative antifungal agent in future. However, further research is required to identify its active components.