1 8 Southeast Missouri State University Department of Computer Science Name of the Instructor: Dr.
1
8
Southeast Missouri State University Department of Computer Science Name of the Instructor: Dr. Reshmi Mitra CS – 609 Graduate Project December 2021 Team Member List Jing Ma Manoj Thapa Nagendra Mokara Contents Machine learning on Stock Predition 0 Abstract 4 1 INTRODUCTION 4 1.1 LSTM Prediction 5 2 BACKGROUND AND RELATED WORK 6 2.1 Overview of the design 7 3 RESEARCH DESIGN AND METHODS 8 3.1 Stock Price Prediction Project using LSTM 8 3.2 Build the dashboard using plotly 9 4 EVALUTION, VALIDATION ANF KEYRESULTS 9 4.1 Screenshot of Result 10 5 CONCLUSIONS 11 References 12 Sound Classification using Deep Learning ………………………………………………13 Abstract ………………………………………………………………………………….14 6 INTRODUCTION …………………………………………………………………….14 6.1 Keywords ……………………………………………………………………………15 7 COLLECTION OF DATA FROM THE DATASET …………………………………..15 7.1 Dataset ……………………………………………………………………………….15 7.2 Segregation of Data into Various Folders ..………………………………………….15 8 WRITING CODE AND DATA MODELING/TRAINING……………………………16 8.1 Design Diagram of the Project……………………………………………………….16 9 RESULT ……………………………………………………………………………….17 10 CONCLUSION/FUTURE WORK …………………………………………………..18
Machine learning on stock prediction
Jing Ma
December 2021
Southeast Missouri State University
Advisor: Dr Robert Lowe
Course: Research Method
Abstract
Machine learning has significant applications in the stock price prediction. A better prediction will be of great importance of finding the most informative indicators and thus maximum the gain profit. In this work we use machine learning architectures to build a Long Short-Term Memory (LSTM) neural network models to predict stock price of National Stock Exchange (NSE) listed companies and build a dashboard using Plotly for stock analysis to compares their performance. The NSE TATA GLOBAL data set will be used to build the stock price prediction model. We develop the dashboard for stock analysis we will use another stock data set with multiple stocks like Apple, Microsoft, Facebook. The performance of LSTM model was evaluated by comparing the predicted value to the actual stocks and we observed a good performance as the predicted stocks almost like actual stocks.
Keywords: machine learning, stock prediction, LSTMmodel, Plotly
1. INTRODUCTION
Stock price prediction has always been a hot but challenging task due to the market price is typically influenced by various complexity and randomness factors Li et al. (2018), Traditional prediction is mostly based on make use of both linear (AR,MA,ARIMA) and nonlinear algorithms (ARCH, GARCH, Neural Networks), but they focus on predicting the stock index movement or price forecasting fora single company using the daily close price Selvin et al. (2017).Long Short-Term memory is one of the most successful machine learning architectures. LSTM introduces the memory cell, a unit of computation that replaces traditional artificial neurons in the hidden layer of the network, with these memory cells, networks are able to effectively associate memories and input remote in time, hence suit to grasp the structure of data dynamically over time with high prediction capacity Roondiwala et al. (2017). In this paper we have presented a dynamically LSTM model and predicted the stock return of NSE listed companies. We collected 5 years of historical data and used it for the training and validation purposes for the model.
1.1 LSTM Prediction
Recurrent Neural networks are a class of artificial neural networks, they have shown to be effective sequential input memory used for data recognition [1], one obstacle that met RNN is the vanishing gradient problem, a solution was introduced to tackle such problem such as LSTM and GRU [4].
In 1997 LSTM was introduced for language models, it made big contribution to the performance and the power to memorize long-term dependencies [4], Although the complicated structural model of the LSTM gave advantages for memory and the dissemination of the vanishing gradient problem it still had a big disadvantage and that is the time it takes to processes information [1]. LSTM was used in many prediction experiments before, in 2016, Fu, Zhang and Li produced an experiment that concluded the success rate of LSTM and GRU methods for traffic flow prediction [5] in the experiment they found that LSTM outperformed other model such as ARIMA by 10 percent [5]. LSTM prediction shown great accuracy In November 2020 through a research paper on motion trajectory prediction based on a CNN-LSTM sequential model, in the research paper Xie, Shangguan, Fei, Ji, Ma and Hei concluded that CNN and LSTM can accurately predict the trajectories of surrounding vehicles to high degree thus providing more precise trajectories for self-driving cars [13]. Recurrent neural networks with long short-term memory (LSTM) have emerged as an effective and scalable model for several learning problems related to sequential data. Earlier methods for attacking these problems have either been tailored toward a specific problem or did not scale to long time dependencies.[11] With the existing sequential data, with using LSTM on the other hand are both general and effective at capture. by using plotly we are monitoring the previous shares data based on data we started predicting the stock price and frequently compares our predicted data with actual market prices. The success rate of LSTM in prediction allowed to be used in multiple recognition platforms such as protein structure prediction [2], handwriting recognition [7] and speech recognition [2]. From all the previous related work we concluded to further investigate and do research on LSTM and how an important aspect of finance such as the stock market can be benefited by its high level of accuracy.
2. BACKGROUND AND RELATED WORK
The purpose of this study is not just to prove that LSTM is one of the most successful type of forecasting long time data Hochreiter and Schmidhuber (1997), but also to show that there is room for improvements especially when it comes to predicting volatile data Li and Cao (2018). Improving accuracy is one of the main objectives of this project thus implementing previous work in the same field and expanding on it to better predict this type of capricious prediction is the main objective of this paper Hegazy et al. (2014). The reason we decided to carry on such research project is the uprising demand in creating financial opportunities between investors in multiple platforms Li et al. (2018), that require nothing but a computer and internet connection, The world witnessed the recent lock down due to the COVID pandemic which pushed more and more people to come up with creative ideas to generate an income through being locked down at home, that’s why investors should implement the time and effort to enhance such aspect of stock prediction in order to be able to provide reliable and efficient programs that support such needs. Such LSTM prediction was addressed through many previous research Graves and Schmid-huber (2005), knew that specific problems arise when using existing sequential data, that’s why enhancing predictions by utilizing LSTM is a must but in this paper, we pose the question of rooms for improvements must be utilized since the ongoing pandemic is pushing investors to work for home and remote locations.
2.1 Overview of the design
Stock prediction and forecasting is becoming more and more popular amongst research which
LSTM can store long time memory based on “memory” proved to be very useful in forecasting cases with long time data. IN a LSTM the memorization of earlier stages can be performed through gates with along memory line incorporated. The ability of memorizing sequence of data makes the LSTM a special kind of RNNs. Every LSTM node most be consisting of a set of cells responsible of storing passed data streams, the upper line in each cell links the models as transport line handing over data from the past to the present ones, the independency of cells helps the model dispose filter of add values of a cell to another [3]. In 2017 Zhuge, Xu, and Zhang proposed LSTM for a variant of RNN from the ANN to improve the accuracy of stock market forecasting during opening days [14] they were able to increase the accuracy through implementation of emotional analysis. Li and Tam argue that in 2017 recurrent neural networks like the LSTM and the SVM are the widely used method to predict the stock price forecast in China and other countries [6] Support vector machines was applied to build a regression model of historical stock data and to predict the trend of stocks. LSTM was combined with naive Bayesian method to extract market emotion factors to improve the performance of prediction. This method can be used to predict financial markets in completely different time scales with other variables. The emotional analysis model integrated with the LSTM time series learning model to obtain a robust time series model for predicting the opening price of stocks, and the results showed that this model could improve the accuracy of prediction. We can start predicting based on the existing data which we collected and stored on plotly, we start storing that data and matching with the current market. So that we can achieve the market trends. [8] The major advantage of LSTM is that it could learn selectively and can remember or forget the required historical data. The stock price data can be highly volatile, therefore, to provide some smoothing effect, the moving average algorithm can be considered along with the SVM and LSTM algorithms. The algorithm learns the outputs for the given features in the training data and predicts the outputs for the corresponding features in the test data [10]. In the point of time series prediction which is a particularly hard problem to solve due to the presence of long-term trend. A data set was created to analyses stock market and an LSTM model [12].
3. RESEARCH DESIGN AND METHODS
The design of the project will be divided into two parts, the first part is Stock Price Prediction Project using LSTM and the second part is Build the dashboard using Plotly dash. Stock Price Prediction Project using LSTM.
3.1 Stock Price Prediction Project using LSTM
1. Import package and read dataset.
2. Analyze the closing prices from data frame.
3. Sort the dataset on date time and filter “Date” and “Close” columns.
4. Normalize the new filtered dataset.
5. Build and train the LSTM model.
6. Take a sample of a dataset to make stock price predictions using the LSTM model.
7. Save the LSTM model and visualize the predicted stock costs with actual stock costs.
3.2 Build the dashboard using plotly
In this section, we will build a dashboard to analyze stocks. Dash is a python framework that provides an abstraction over flask and react.js to build analytical web applications.
1. Install dash.
2. Make a new python file and paste the script. 3. run this file and open the app in the browser.
4. EVALUTION, VALIDATION AND KEYRESULTS
The accuracy of LSTM is subjective, our LSTM model is off by 0.12 on average, which is much better than random guessing and traditional prediction model such as linear (AR, MA, ARIMA) and nonlinear algorithms (ARCH, GARCH, Neural Networks). As we have increased the hidden layers in the LSTM node and added another layer of the LSTM to improve the accuracy.
4.1 Screenshot of Result
1. All the necessity packages were installed, and data set has been read successfully.
Text Description automatically generated
Fig 1:
2. Successfully Analyzed the closing prices from data frame.
Graphical user interface, chart Description automatically generated
Fig 2:
3. Successfully built and trained the LSTM model, LSTM has predicted stocks almost like actual stocks.
Chart, scatter chart Description automatically generated
Fig 3:
4. A dashboard was successfully built using plotly to analyze stocks.
Graphical user interface, chart Description automatically generated
Fig 4:
5. CONCLUSIONS
In this paper for stock prediction method based on attempting LSTM based on reviews common filter-based feature selection algorithms and stock prediction models and compares related data with help of plotly. The paper presents a general approach to stock market prediction with the help of the plotly we can store analyses the data and it helps us in more accurate and effective way with help of dashboard information we will confirm the data and compare with the actual stock price for better results.
References [1] Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014). [2] Alex Graves and Jürgen Schmidhuber. 2005. Framewise phoneme classification with bidirectional LSTM networks. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., Vol. 4. IEEE, 2047–2052. [3] Adil Moghar; Mhamed Hamiche. 2020. Stock Market Prediction Using LSTM Recurrent Neural Network. https://doi.org/10.1016/j.procs.2020.03.049. [4] Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780. [5] YiFei Li and Han Cao. 2018. Prediction for tourism flow based on LSTM neural network. Procedia Computer Science 129 (2018), 277–283. [6] Zhixi Li and Vincent Tam. 2017. A comparative study of a recurrent neural network and support vector machine for predicting price movements of stocks of different volatilites. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 1–8. [7] Marcus Liwicki, Alex Graves, Santiago Fernàndez, Horst Bunke, and Jürgen Schmidhuber. 2007. A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks. In Proceedings of the 9th International Conference on Document Analysis and Recognition, ICDAR 2007. [8] Guanavu Ding; Liangxi Qin. 2019. Study on the prediction of stock price based on the associated network model of LSTM. [9] Murtaza Roondiwala, Harshal Patel, and Shraddha Varma. 2017. Predicting stock prices using LSTM. International Journal of Science and Research (IJSR) 6, 4 (2017), 1754–1756. [10] John McCrae Sai Krishna Lakshminarayanan. 2019. A Comparative Study of SVM and LSTM Deep Learning Algorithms for Stock Market Prediction. [11] Klaus Greef; Rupesh K Srivastava; Jan Kautnik; Bas R Steunebrink; Jurgen Schmidhuber. 2016. LSTM: A Search Space. 10.1109/TNNLS.2016.2582924, 2222–2232. [12] Anita Yadav; C K Jha; Aditi Sharma. 2020. Optimizing LSTM for time series prediction in Indian stock market. https://doi.org/10.1016/j.procs.2020.03.257. [13] Guo Xie, Anqi Shangguan, Rong Fei, Wenjiang Ji, Weigang Ma, and Xinhong Hei. 2020. Motion trajectory prediction based on a CNN-LSTM sequential model. Science China Information Sciences 63, 11 (2020), 1–21. [14] Qun Zhuge, Lingyu Xu, and Gaowei Zhang. 2017. LSTM Neural Network with Emotional Analysis for prediction of stock price. Engineering letters 25, 2 (2017).
Sound Classification using Deep Learning
Manoj Thapa
December 2021
Southeast Missouri State University
Advisor: Dr David (Wei) Dai
Course: CS 591
ABSTRACT
The project was done in the Spring 2021 semester for the Advanced Artificial Intelligence (CS 591) Class. The project topic was “Sound Classification using Deep Learning”. I choose this project because Sound Classification is one of the most generally used applications in Audio Deep Learning. Deep learning is a subset of machine learning in which multi-layered neural networks are modeled to work like the human brain – ‘learn’ from a large amount of data. The use of deep learning in an automation environment is growing. Such as personal security to critical surveillance, classifying music clips to identify the genre of the music, or classifying short utterances by a set of speakers to identify the speaker based on the voice. The learning capabilities of the deep learning architectures can be used to develop sound classification systems to overcome the efficiency issues of the traditional systems. The project demonstrates the use of a deep learning algorithm, and CNN (Conventional neural network) to find the accuracy of the sound. Furthermore, python programming and its libraries, google collab was used to implement sound classification.
6. INTRODUCTION
The project goal is to differentiate the various type of sound (Urban Sound 8K dataset) using a Deep learning algorithm and visualizing them in the electromagnetic spectrum. Audio/Sound signals are all around us. Humans can differentiate, recognize sound through their and hearing senses, imagine how it will feel when a computer differentiates the sound using machine learning algorithms. There is a growing interest in sound classification for different scenarios. For example, fire alarm detection for hearing impaired people, engine sound analysis for maintenance and patient monitoring in hospitals, etc. The project shows the use of Deep Learning techniques for the classification of different environmental sounds, specifically focusing on the identification of Urban Sounds. The result shows the accuracy of the sound, higher accuracy better prediction.
6.1 Keywords
1. Deep Learning algorithm to find the accuracy (Sound Classification).
2. Google Colab, Python programing, packages, and its libraries.
3. Dataset, Urban Sound 8K, CSV that contains sound files.
4. Dataset contains 8732 sound excerpts (< = 4s) of urban sounds from 10 classes.
5. Visualization of sound prediction, accuracy in spectrogram using matplotlib.
7. COLLECTIONS OF DATA FROM THE DATASET
7.1 Dataset
Project starts with the collection of the dataset downloaded from the given source UrbanSounds website.
Graphical user interface, text Description automatically generated
Fig 5:
7.2 Segregation of Data into Various Folders
Segregate data into various folders, and then metadata is prepared (CSV file).
Table Description automatically generated
Fig 6:
8. WRITING CODE AND DATA MODELING/TRAINING
The python programming and jyputer notebook with the package Librosa, Keras, pandas, and matplotlib for visualization. The data sets are used to build and train a deep neural network for prediction. Three parameters are used for the model compile where it finds pre-training accuracy of 6.9834%.
Table Description automatically generated
Fig 6:
8.1 Design Diagram of the Project
Diagram Description automatically generated
Fig 7:
9. RESULT
The dataset “Urban Sound 8K” was used for the data training, where the metadata contains information about each audio file in CSV files. The dataset contains about 8732 sound excerpts (< = 4s) of urban sounds from 10 classes. 1. Air Conditioner 2. Car Horn 3. Dog Bark 4. Drilling 5. Engine Idling 6. Gun Shot 7. Jackhammer 8. Siren 9. Street Music 10. Children Playing. The sound excerpts are digital audio files in.wav format. Sound waves are digitized by sampling rate (typically 44.1kHz for CD-quality audio – 44,100 times per second). The audio files are modified with helpers.wav filehelper that reads and writes into .wav audio files. Audio files are converted with the help of pandas data frame features with two columns ‘feature’ and ‘class_label’ that extract 8732 files. A sequential model is used with a sample model architecture which consists of four Conv2D convolution layers with the final output layer. Table Description automatically generated
Fig 8:
After successfully implementing Deep learning algorithms and training datasets. The result showed the training accuracy 93.43% and testing accuracy 89.24%, which is considered as good accuracy. Good data provides better accuracy and better prediction. In the scenario of the project, the Gunshot sound was clear and had high accuracy among 10 other sounds (class).
Graphical user interface Description automatically generated
Fig 9: Police Siren Chart, box and whisker chart Description automatically generated Fig 10: Gun Shot
10. CONCLUSION/FUTURE WORK
However, the project was successfully implemented, it took some time to gather information and set up the environment because of the large files, dataset, new data science tools. The project taught me more about how to use python programming and its libraries in data science (Machine Learning, Deep Learning, and AI). Moreover, it gave a clear understanding of how AI can play important role in sound classification/prediction, which can be useful for various tasks like fire alarm detection for hearing impaired people, engine sound analysis for maintenance and patient monitoring in hospitals, etc.
Future work would be examining how we can extend the project (Sound Classification) both real-time streaming audio and real-world sounds. As we know, audio is complex because it accounts for various background sounds, target sound volume levels, and different types of echoes. The model and MFCC (Mel Frequency Cepstral Coefficient) measurement should work well with low latency while synchronizing with the audio buffer thread without any delays. As I learned from the project, I would suggest next-generation students have a clear understanding of the project requirements. Such as, gathering information, programming tools, and resources before you start the project. Since the project is one of the best projects I have done so far, I would suggest implementing (collecting) a good dataset and finding high accuracy from the selected sound file (class) for better prediction.
REFERENCES
[1] F.Rong, “Audio Classification Method Bases on Machine Learning” 2016 International Confrence on Intelligent Transportation, Big Data & Smart City (ICTBS), Changsha, China, 2016, pp. 81-84, doi: 10.1109/ICITBS.2016.98.
[2] Kons, Zvi & Toledo-Ronen, Orith. (2013) Audio event classification using deep neural networks. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEACH. 1482-1486.
[3] Malowany, Dan. “Audio Classification” towards data science, oct 18, 2020.
https://towardsdatascience.com/tagged/audio-classification
[4] Smales, Mike. “Sound Classification using Deep Learning” Feb 26, 2019.
https://mikesmales.medium.com/sound-classification-using-deep-learning- 8bc2aa1990b7
[5] K. Jaiswal and D. Kalpeshbhai Patel, “Sound Classification Using Convolutional Neural Networks,” 2018 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM), 2018, pp. 81-84, doi: 10.1109/CCEM.2018.00021.
Fruits, Vegetables and Deep Learning Processing Image Datasets
with Neural Convolutional Networks using PyTorch
Nagendra Mokara
December 2021
Southeast Missouri State University
Advisor: Dr Wei Dai
Course: Advance Artificial Intelligence
ABSTRACT
Artificial Intelligence (AI) is a significant technological achievement that is currently in widespread use. Deep Learning has a wide range of applications due to its ability to construct robust representations from images. A Convolutional Neural Network (CNN) is a Deep Learning system that commands an input image, assigns meaning to various aspects/objects in the image and can distinguish between them. For picture categorization, CNN is the most used Deep Learning architecture. To improve our outcomes, we used a variety of automated processing actions for fruit and vegetable photos. The amount of pre-processing required by a CNN model is far smaller than that required by other deep learning techniques for categorization. The learning capabilities of Deep Learning architectures can also be used to improve sound classification to address efficiency difficulties. The CNN is used in this project, and layers are created to classify images into different categories.
Keywords: convolutional neural network; deep learning; image classification.
11. INTRODUCTION
Everything you can think of can be classified into a classification or class, and we humans enjoy examining things. It is a common occurrence in business; the daily routine necessitates the analysis of parts, installations, gatherings, and products. To automate the arranging period, people have invented procedures such as Machine Learning (ML), Neural Networks (NN), and Deep Learning (DL), among other calculations. One of the topics we’ll look into is deep learning. Deep learning is an AI function that mimics how the human brain processes data and creates patterns in order to make judgments. It is extremely difficult to classify images of fruits and vegetables with the naked eye. As a result, we’re using pyTorch to do Deep Learning on image datasets. Using these datasets, we’re building a CNN model for picture detection and categorization. For the purposes of this study, a custom CNN is introduced and then compared to a ResNet CNN.
12. BACKGROUND AND RELATED WORK
Convolutional Neural Networks or Deep Learning architectures were inspired by the human brain and how it processes information. CNNs are a type of Neural Network that excels at image processing, recognition, and categorization. As the title of this article suggests, a CNN model is necessary in this situation.
Convolutional Neural Networks are a subset of Deep Learning. The human brain and how it processes information inspired Convolutional Neural Networks. CNNs (Convolutional Neural Networks) are a form of Neural Network that excel at image processing, recognition, and classification. As the title of the article suggests, a CNN model is necessary. CNNs are a sort of artificial neural network that filters data using convolutional layers. To create a changed image, the input data (feature map) is combined with a convolution kernel (filter).
The input layer, hidden layers (which can range from 1 to the number required by the application), and output layer are the three basic components of a CNN. The fact that the layers of a CNN are structured in three dimensions distinguishes it from a standard Neural Network (width, height, and depth). Convolution, pooling, normalizing, and completely linked layers make up the hidden layers.
Convolution
ReLU
Rec
fi
ed linear units
MaxPooling
Kernels
Convolution
ReLU
Rec
fi
ed linear units
MaxPooling
Kernels
convolutional
ReLU
Rec
fi
ed linear units
MaxPooling
Kernels
Fully Connected Layers
Output
Label
L
o
s
s
F
u
n
c
o
n
Backward Propaga
on
Stage 1
Stage 2
Stage
n
Input Image
Forward Propaga
on
Fig: General Representation of CNN Model.
To put it another way, a CNN is a Deep Learning algorithm that can take images as input, check them for patterns or artifacts in a variety of methods, and then output the ability to distinguish one image from another.
13. IMPLEMENTATION
The main purpose of this challenge is to classify fruits and vegetables using CNN and the PyTorch library.
The “Fruits 360 Dataset” will be used because the purpose of this Question is to explore image categorization. This dataset, which is available on Kaggle, contains images of fruits and vegetables with the following essential properties:
· There are a total of 90483 photographs.
· The training set contains 67692 photographs (one fruit or vegetable per image).
· In the test set, there are 22688 images (one fruit or vegetable per image).
· 103 pictures in the multi-fruits series (each image contains multiple fruits (or fruit classes)) There are a total of 131 classes (fruits and vegetables).
· The image size is 100×100 pixels.
· Dataset Size: 700 MB
Go to the toggling sidebar and look for the add data option to add this dataset to Kaggle. Click it, then search for and add the dataset fruits360.
We need a GPU processor to execute our models quickly because our study covers a large dataset. For new users on Kaggle, the first 40 hours are free. In Kaggle’s settings, we must also make sure that the internet is turned on.
Now that the data set has been added, we’ll continue on to the programming procedure. To begin, we must load the dataset’s directory paths and ensure that each directory has the same number of classes. To make room, we’ll place all of the classes, as well as images, in each folder in the root directory.
When creating certifiable AI models, partitioning the dataset into three parts is extremely simple: The training set is utilized to get the model ready for jobs like digesting the misfortune and modifying the model’s burdens with the inclination drop.
Validation set for evaluating the model while it’s being developed, modifying hyperparameters (for example, learning rate), and selecting the best model form.
Test set: utilized to compare multiple models or demonstration methods, as well as to report on the model’s most current accuracy.
While loading photographs from the training dataset, “Randomized Data Augmentations” will apply transformations at random. Before being flipped horizontally 50% of the time, each image will be paid by 10 pixels. Finally, a random 20-degree rotation will be applied. Because each time a new image is loaded, the alteration is applied at random and dynamically.
While running AI models, you’ll be dealing with a lot of data. A computer should be able to manage such data, but computers have limited resources. In order for a machine to process all 67692 photos in this dataset in real time, it would be impossible. Data loaders will be required as a result. Fortunately, PyTorch has them. We’ll need to use CNN to develop a model. It’ll be our own version of CNN. Let’s create an ImageClassificationBase class and an accuracy function before diving into the details of each model.
The model’s performance will be evaluated using the accuracy function. Counting the number of labels that were successfully predicted, or the precision of the forecasts, is a natural way to achieve this. Residual Blocks and Batch Normalization will be used to build the architecture of this custom CNN model. This enables for a comparison of the effects of the bespoke CNN and the ResNet model (ResNet stands for residual neural networks, which are pre-trained models in the ImageNet dataset). The original input is added back to the output feature map formed by moving the input through one or more convolutional layers via Residual Block. Batch normalization reduces the size of the convolutional layers’ inputs to the same size, as the name implies. This cuts down on the time it takes to train the neural network.
14. RESULTS
Following the creation of the custom model, we must use data to train the custom CNN model. The ResNet CNN Model, which operates similarly to the custom CNN model, must then be trained. The training results are used to calculate the Learning Rate, Training Loss, Validation Loss, and Validation Accuracy. The accuracy of our models must be more than 90% to be utilized in forecasts.
With the validation dataset, you can now use the trained models to generate predictions. The forecasts would be identical because both models achieved greater than 90% accuracy.
14.1 Screenshot Of Result
Fig 1: Shows the image of Cantaloupe 1 (22)
Graphical user interface, text, application Description automatically generated
Fig 2: Shows Apple Braeburn (0)
Graphical user interface, application Description automatically generated
Graphical user interface, text, application Description automatically generated Fig 3: Shows the CNN Model Graph for Accuracy vs No. of epochs
Graphical user interface Description automatically generated Fig 4: Graph between Loss vs No. of epochs of CNN Model
Fig 5: Graph between Learning Rate vs Batch number of CNN Model
Graphical user interface, application Description automatically generated Graphical user interface, application Description automatically generated
Fig (a) Fig (b)
Fig 6: (a) and (b) shows the Graph for ResNet CNN Model for Accuracy, Loss and No. of epochs
Graphical user interface Description automatically generated
Fig 7: Graph between Learning Rate vs Batch no.
Graphical user interface, application Description automatically generated
Graphical user interface, application Description automatically generatedFig 8: Shows the image of ResNet CNN Trained Predicted.
Fig 9: CNN Trained Model Prediction of Avocado ripe.
15. FUTURE WORKS
Even when the outcomes are excellent, there are still areas where improvements can be made:
· With the ResNet Model, you can reduce training and validation losses.
· Reduce the amount of time it takes to train the Custom Model.
· To evaluate the Custom Model’s performance, use a different dataset.
16.CONCLUSION
In this work, we show two alternative Convolutional Neural Network (CNN) architectures for image classification. The author’s Custom Model and a ResNet Model available in the PyTorch module.
The findings revealed that the Custom Model produced better results than the ResNet Model implemented in the PyTorch module, even when training took longer.
The results demonstrate that, despite the greater training time, the Custom Model beat the ResNet Model implemented in the PyTorch module. The Custom Model was 99.21% accurate, whereas the ResNet Model was just 92.45% accurate.
Unlike the ResNet Model, the Custom Model was able to reduce training and validation losses.
REFERENCES
[1] Aguilar, F. (2020, July 19). Fruits, Vegetables and Deep Learning – Level Up Coding. Medium. https://levelup.gitconnected.com/fruits-vegetables-and-deep-learningc5814c59fcc9.
[2] https://medium.com/swlh/building-a-deep-learning-model-with-pytorch-to-classify-fruits-and-vegetables-30e1a8ffbe8c
[3] https://towardsdatascience.com/classification-of-fruit-images-using-neural-networks-pytorch-1d34d49342c7
[4] https://blog.jovian.ai/fruits-classification-using-cnn-and-pytorch-bc583e6052d3
[5] Sharma, V. “Deep Learning — Introduction to Convolutional Neural Networks”, 2018. https://vinodsblog.com/2018/10/15/everything-you-need-to-know-about-convolutional-neural-networks/.
Collepals.com Plagiarism Free Papers
Are you looking for custom essay writing service or even dissertation writing services? Just request for our write my paper service, and we'll match you with the best essay writer in your subject! With an exceptional team of professional academic experts in a wide range of subjects, we can guarantee you an unrivaled quality of custom-written papers.
Get ZERO PLAGIARISM, HUMAN WRITTEN ESSAYS
Why Hire Collepals.com writers to do your paper?
Quality- We are experienced and have access to ample research materials.
We write plagiarism Free Content
Confidential- We never share or sell your personal information to third parties.
Support-Chat with us today! We are always waiting to answer all your questions.
