Agriculture provides food to all the human beings even in case of rapid increase in the population. It is recommended to predict the plant diseases at their early stage in the field of agriculture is essential to cater the food to the overall population. But it unfortunate to predict the diseases at the early stage of the crops. The idea behind the paper is to bring awareness amongst the farmers about the cutting-edge technologies to reduces diseases in plant leaf. Since tomato is merely available vegetable, the approaches of machine learning and image processing with an accurate algorithm is identified to detect the leaf diseases in the tomato plant. In this investigation, the samples of tomato leaves having disorders are considered. With these disorder samples of tomato leaves, the farmers will easily find the diseases based on the early symptoms. Firstly, the samples of tomato leaves are resized to 256 × 256 pixels and then Histogram Equalization is used to improve the quality of tomato samples. The K-means clustering is introduced for partitioning of dataspace into Voronoi cells. The boundary of leaf samples is extracted using contour tracing. The multiple descriptors viz., Discrete Wavelet Transform, Principal Component Analysis and Grey Level Co-occurrence Matrix are used to extract the informative features of the leaf samples. Finally, the extracted features are classified using machine learning approaches such as Support Vector Machine (SVM), Convolutional Neural Network (CNN) and K-Nearest Neighbor (K-NN). The accuracy of the proposed model is tested using SVM (88%), K-NN (97%) and CNN (99.6%) on tomato disordered samples. 

Plant Leaf Disease Detection using Computer Vision and Machine Learning Algorithms

Transfer learning is used to reuse the pre-trained model. Transfer learning uses the knowledge which was gained from the previous task. Transfer learning is most generally used in image classification, image prediction and natural language processing. Some of the example for the natural language processing it includes sentiment analysis, text auto complete etc. The literature shows that deep learning performance is relatively more when compared with machine learning technique for the large data set. In this paper pre trained models such as MobileNet, MobileNetV2, VGG16, VGG19 and ResNet50 has been used for image classification and prediction. For the image classification and prediction Google Colab notebook has been used. The performance of the system depends on the GPU system hence results are tested in Google colab notebook. The result shows that MobileNetV2 performance is relatively better than other pre trained models. MobileNetV2 uses the less number of parameters as compared with other trained model. ResNet50 accuracy is more when it compared with other trained model with the ImageNet dataset. In the future enhancement transfer learning may be used for natural language processing to obtain highest accuracy.

Image classification and prediction using transfer learning in colab notebook

State of the art: a review of sentiment analysis based on sequential transfer learning

For the past few years, business intelligence has been a major field that uses data analysis to produce key information as part of business decision-making. Data collected from social media sites and blogs are analyzed to make business decisions, a process called social media analytics (SMA). This method, which goes beyond ordinary monitoring or a basic analysis of retweets, develops an in-depth insight into the social consumer. After reading the whole report, add the pertinent figures to the table. Add pertinent data from the Brand24 report to the table. During a social media audit, any followers, impressions, engagement, copy/traffic, and brand mentions are key parameters to analyze. For companies and research institutions, the great interest is to analyse and gain knowledge from user-produced data. These data contain useful knowledge, including customer perceptions feedback and product/service suggestions. Due to content saturation, social media's true meaning regarding business data is hardly ever found. Therefore, in this paper, the business decision making system (BDMS) has been proposed to develop business using social media data analytics. BDMS provides a clear understanding of the key principles, issues and functionality, and big social data developments. Besides, BDMS concentrates on marketing and describes an operational approach for obtaining valuable information from social data. BDMS performs a short and precise description of current use scenarios from the evidence, as per the help of decisions and investment opportunities companies get when using social data analytics. The experimental result shows that BDMS achieves the highest competitive results. With greater accuracy, system dependability, F-1 measurement, and deviation rate of 85.5%, the BDMS system guarantees 93.7%, 86.8%, and 7.0%.

Social media data analytics for business decision making system to competitive analysis

Business is based on manufacturing, purchasing, selling a product, and earning or making profits. Social media analytics collect and analyze data from various social networks such as Facebook, Instagram, and Twitter. Social media data analysis can help companies identify consumer desires and preferences, improve customer service and market analytics on social networks, and smarter product development and marketing investments. The business decision-making process is a step-by-step process that enables employees to resolve challenges by weighing evidence, evaluating possible solutions, and selecting a route. In this paper, Big Data-assisted Social Media Analytics for Business (BD-SMAB) Model increases awareness and affects decision-makers in marketing strategies. Companies can use big data analytics in many ways to enhance management. It can evaluate its competitors in real-time and change prices, make deals better than its competitors' sales, analyze competitors' unfavorable feedback and see if they can outperform that competitor. The proposed method examines social media analysis impacts on different areas such as real estate, organizations, and beauty trade fairs. This diversity of these companies shows the effects of social media and how positive decisions can be developed. Take better marketing decisions and develop a strategic approach. As a result, the BD-SMAB method enhance customer satisfaction and experience and develop brand awareness.

Big data-assisted social media analytics for business model for business decision making system competitive analysis

The analysis of sentiments is essential in identifying and classifying opinions regarding a source material that is, a product or service. The analysis of these sentiments finds a variety of applications like product reviews, opinion polls, movie reviews on YouTube, news video analysis, and health care applications including stress and depression analysis. The traditional approach of sentiment analysis which is based on text involves the collection of large textual data and different algorithms to extract the sentiment information from it. But multimodal sentimental analysis provides methods to carry out opinion analysis based on the combination of video, audio, and text which goes a way beyond the conventional text‐based sentimental analysis in understanding human behaviors. The remarkable increase in the use of social media provides a large collection of multimodal data that reflects the user's sentiment on certain aspects. This multimodal sentimental analysis approach helps in classifying the polarity (positive, negative, and neutral) of the individual sentiments. Our work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve human–machine interaction and challenges involved in analyzing them. A detailed survey on sentimental dataset, feature extraction algorithms, data fusion methods, and efficiency of different classification techniques are presented in this work.

Multimodal sentimental analysis for social media applications: A comprehensive review

Recommendation systems have become a vital area of research in recent times These recommendation systems are very much needed for e-commerce applications to identify the products liked by a customer which helps the companies to promote product sales and improve their product quality It also helps the users to arrive at the purchasing decision without reading the online reviews about the product The key idea behind the proposed work is to analyze the user preference for the products from the online data by employing the collaborative filtering-based recommendation framework The concept of collaborative filtering is best suited for recommendation systems involving a large set of product users It generates a user-item matrix and finds the list of products liked by the individual users It gives prediction regarding the product that a user could buy in the future and also recommends the products which are liked by the customers who have similar interests It gives a comparative analysis in terms of performance metrics and accuracy of different collaborative filtering techniques

An Intelligent Framework for Online Product Recommendation Using Collaborative Filtering

Sentiment analysis of images is becoming very important with the increase in the use of social media by people. Many existing works in the literature focus on textual sentiment analysis with the text being extracted from the social media sites like Twitter, Facebook, Amazon and Movie reviews, etc. But sharing of images and videos through social media is increasing compared to text. Images reflect the sentiment in a much better way compared to the text and thus are preferred in analyzing the sentiment. So, there is a need to develop a robust model to carry out image sentiment prediction. In this paper, we employ a transfer learning model based on VGG-16 architecture to carry out the image sentiment analysis. The dataset employed is the Crowdflower database that has more than 15,000 images (Twitter) URLs with its polarity label (Positive, Negative). The proposed model can handle a large set of data as it is based on deep learning and there is no need for explicit feature extraction. The results show the effectiveness of our proposed model in performing sentiment prediction on images.

Ganesh Chandrasekaran

Papers

Multimodal sentimental analysis for social media applications: A comprehensive review

An Intelligent Framework for Online Product Recommendation Using Collaborative Filtering

Efficient Visual Sentiment Prediction Approaches Using Deep Learning Models.