emd_ppt.pptx its about embedded systems ,

Its good

1. Department of ECE Goods Analyzer Tool for Marketing Team Members Batch No: D08 D.Ganesh 21eg104d10 M.Sai Teja 21eg104d49 SK.Aamir 21eg104d42 Under the guidelines of Mr.M.Murali Krishna (Assistant professor).

2. Department of ECE Problem statement The proposed system is a web application which uses deep learning models that will analyse the product reviews to understand the sentiment of the people towards a particular good or product and provide the analysis of how well it is doing in the market to be helpful for both the company and customers. Existing system: In the existing system, lexicon and machine learning based approaches like SVM,Naïve bayes, etc have been implemented.

3. Department of ECE Methodologies: We employed baseline methods such as Convolutional Neural Networks and Long Short-Term Memory (LSTM) networks for review categorization to forecast the emotion of the sentences. Tools and technologies used: Python. Numpy . Keras . Pandas. Tensorflow . Mysql database.

4. Department of ECE Module Description: User Registration Module: This is the module through which users can register into the web application and then login. Login Module: Through this module users and admin can login in to the Goods Analyzer Tool for Marketing application. Preprocessing Module: This module is responsible for preprocessing of data .Then the important features from the goods and products reviews are extracted so that the neural network models can be trained accordingly. Training Module: This module is in charge of using preprocessed data to train neural network models such as CNN and LSTM networks so that they can accurately identify.

5. Department of ECE Profile Management Module: Through this module the registered users can update profile details. Admin Adding Goods Module: Through this module the admin will be able to add new goods into the application and then can view all the available goods or products. User View Goods Module: Through this module the user can see all the available goods and products on the application

6. Department of ECE Block Diagram Figure depicts the overall operation of the proposed system. To begin, the product reviews in the dataset are preprocessed and key attributes are extracted so that the model can accurately forecast. The training and testing phases are the two main segments. The Neural Network Deep Learning models are trained on preprocessed data in the training phase, while the testing phase takes place in the web application “GOODS ANALYSER TOOL FOR MARKETING,” .

7. Department of ECE Flow Chart Figure depicts the flow of events in our proposed system. The user reviews for various things or goods are extracted from the dataset’s csv file and preprocessed with the help of data. Then, to extract the key features,feature extraction is used to extract them so that the neural network models, such as Convolutional neural networks and Long short term memory networks, can be trained appropriately. The two models are then evaluated for accuracy, and the model with the highest accuracy is chosen for sentiment categorization. Finally, for each good or product, an analysis of sentiments is generated.

8. Department of ECE Data flow diagram.

9. Department of ECE