دانلود مقاله بررسی جامع درباره تشخیص بیماری گیاهان
خلاصه
1. مقدمه
2. تشخیص بیماری گیاهی با استفاده از تکنیک های یادگیری ماشینی
3. رگرسیون لجستیک (LR)
4. تشخیص بیماری های گیاهی مبتنی بر هوش مصنوعی و یادگیری عمیق
5. شبکه عصبی پیچیدگی (CNN)
6. بررسی تطبیقی تکنیک های یادگیری ماشینی و عمیق
7. نتیجه گیری
بیانیه مشارکت نویسنده CRediT
اعلامیه منافع رقابتی
منابع
Abstract
1. Introduction
2. Plant disease detection using machine learning techniques
3. Logistic regression (LR)
4. Artificial intelligence and deep learning based plant disease detection
5. Convolution neural network (CNN)
6. Comparative review on machine and deep learning techniques
7. Conclusion
CRediT authorship contribution statement
Declaration of Competing interest
References
چکیده
امروزه در دنیای واقعی می توان مشاهده کرد که بسیاری از دانشجویان پس از فارغ التحصیلی از دانشگاه بیکار می شوند. دو مهارت نرم برای تعیین موفقیت فارغ التحصیلان در کار آموزش داده می شود، یعنی رهبری و روحیه کارآفرینی. هدف این پژوهش بررسی تأثیر ساختاری انگیزه پیشرفت و پیشرفت رهبری و روحیه کارآفرینی دانشجویان بود. این پژوهش در اندونزی با تعداد 789 دانش آموز به روش نمونه گیری تصادفی انجام شد. برای جمع آوری داده ها از پرسشنامه و تکنیک های اسنادی استفاده شد و سپس داده ها با استفاده از آمار توصیفی و مدل سازی معادلات ساختاری مورد تجزیه و تحلیل قرار گرفت. نتایج نشان داد که هر دو متغیر برونزا، یعنی انگیزه پیشرفت و پیشرفت، بر هر دو متغیر درونزا تأثیر می‌گذارند، اما انگیزه پیشرفت تأثیر قوی‌تری بر رهبری و روحیه کارآفرینی دانش‌آموز دارد. علاوه بر این، تأثیر انگیزه پیشرفت بر روحیه کارآفرینی بیشتر از رهبری بود، در حالی که رهبری تنها تا حد کمی بر روحیه کارآفرینی دانشجویان تأثیر داشت. سپس تأثیرات این متغیرها با توجه به نظریه ها و تحقیقات مربوطه به طور کامل مورد بحث قرار گرفت.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
Agriculture plays a significant part in India due to their population growth and increased food demands. Hence, there is a need to enhance the yield of crop. One of these important effects on low crop yields is diseases caused by bacteria, fungi and viruses. This can be prevented and handled by means of applying plant disease detection approaches. Machine learning techniques will be employed in the process of disease identification on plants as it mostly applies information themselves and offers fabulous techniques for detection of plant diseases. Methods based on Machine learning can be employed for the identification of diseases because it mainly applies on data superiority outcomes for specified task. In this approach, a comprehensive review has been made on the various techniques employed in plant disease detection using artificial intelligence (AI) based machine learning and deep learning techniques. Likewise, deep learning has also gained a great deal of significance in offering better performance outcome for detecting plant disease in the computer vision field. The deep learning advancements were employed to a range of domains that leads to great attainment in the machine learning and computer vision areas. The comparative study is made in terms of machine and deep learning techniques and their performance and usage in various research papers is related to show the effectiveness of deep learning model over machine learning model. In order to prevent major crop losses, the deep learning technique can be used to detect the leaf diseases from captured images.
Introduction
The advancements of IoT, AI and the Unmanned Aerial Vehicles are integrated together to provide the support to agricultural fields to detect the plant leaf diseases and report that properly to the respective individuals with proper accuracy ranges. In this modern civilization, nobody is interested in farming and agriculture due to the hurdles the farmers are facing every day. So, that all young generation people are switch over their residence to modern cities to lead a safe life and avoid such agriculture field hurdles. The issue of the proficient plant diseases protection is closely linked to viable change in climate and agriculture [13]. Studies show that climate change may vary pathogenic stages and rates; host resistance may also be altered, leading to physiological variations in host-pathogen co-operations [23]. The actuality that nowadays, diseases more freely transferred around the globe than ever before complicates the situation. New diseases may occur where they have not been identified previously and, inherently, where local expertise to combat them is not available [27] (see Table 1).
Conclusion
An extensive research study is conceded out on various kinds of machine and deep learning techniques for plant disease recognition and classification. After this, other techniques of classification in machine learning might be employed for may be used for plants disease detection and in the intellect of aiding the farmers an automatic disease detection of all kinds of disease in the crop that were to be detected. This analysis discusses various approaches of DL for the plant diseases detection. Furthermore, several techniques/mappings were summarized for recognizing the disease symptoms. Here the development of deep learning technologies in recent years for the identification of plant leaf diseases. We anticipate that this work will be a useful tool for scientists looking into plant disease detection. Also, a comparative study is also made between machine and deep learning techniques. Though a great deal of noteworthy progress was noticed in recent years, there were still some research gaps that should be addressed and to implement effective techniques for plant disease detection.