[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291107-105":59,"doc-detail-291107-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","msc-research-project-configuration-manual","MSc Research Project - Configuration Manual","","Configuration manual for an MSc research project by Ashwin Suresh Babu, dated January 2022, describing an end-to-end machine learning workflow for detecting drowsiness-related states in drivers. It specifies local Jupyter Notebook execution on a MacBook Pro (M1, 8GB RAM, 512GB SSD), the Python and libraries used (NumPy, Pandas, OpenCV, Keras, TensorFlow, Scikit-learn, Matplotlib, Seaborn), dataset acquisition from Kaggle, preprocessing (background removal for yawn/non-yawn), augmentation, model training, and evaluation outputs using confusion matrices.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/msc-research-project-configuration-manual/291107/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/msc-research-project-configuration-manual/291107.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What environment was used to implement the project?","Question",{"text":113,"@type":114},"Implementation ran in a locally hosted Jupyter notebook on a MacBook Pro with an M1 processor, 8GB RAM, and 512GB SSD.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Where was the dataset obtained and what does it contain?",{"text":118,"@type":114},"The data was downloaded locally from Kaggle and includes images representing face-related states such as open eyes, closed eyes, yawn, and no yawn.",{"name":120,"@type":111,"acceptedAnswer":121},"What preprocessing and augmentation steps were applied before training?",{"text":122,"@type":114},"The process removes the background of the face for yawn and no-yawn images, reads images into a NumPy array, and uses image augmentation to artificially increase and diversify training data.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291107,1789643472,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":29,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":105,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","Configuration Manual  \nAshwin Suresh Babu  \nID:19151381  \nMSc Research Project  \nMSCDAD JAN22 B  \nJanuary 2022  \n1 Introduction  \nIn this document, we will discuss the step-by-step process that took to complete this project from setting up the environment to the evaluation process.  \n2 Environment Setup  \n2.1 System Specification  \nImplement of this research was performed on the Jupyter notebook hosted locally on Macbook Pro with 8GB of RAM and 512GB SSD storage with an M1 processor which has inbuilt GPU cores.  \n2.2 Technical Specification  \nPython(3.9.13) was the programming language used to implement this project and the following packages were used.  \nNumpy-1.21.5 Pandas-1.4.4 OpenCV-[4.6.0.66](4.6.0.66)[ ](4.6.0.66)Keras-2.9.0 TensorFlow-2.9.1 Scikit Learn-1.0.2  \nMatplotlib-3.5.2 Sklearn Metric-2021.6.0 Seaborn-0.11.2  \n2.3 Data Source  \nThe data is accessed locally. The data was downloaded from a public website called Kaggle. The data consists of several images that can be used to identify different characteristics of the face such as open eyes, closed eyes, yawn, and no yawn.  \n3 Implementation  \nIn this section the end to end process of the implementation will be discussed from importing the necessary libraries to the results.  \n3.1 Importing Necessary Libraries  \nFigure 1: Necessary Libraries  \n3.2 Implementation Process  \nThe execution process of the data begins with downloading the dataset to the local directory. Once it is in the local directory we then use jupyter lab to lis the directory and print out the contents of the datasets. Once that is established we visulaize each scenario of the open eyes, closed eyes, yawning, and no yawn.  \nOnce that is done we then move onto the preprocessing part. Where we remove the background of the face in yawn and no yawn images to help the models train more easily and reduce the load on the models. then we write a function to read all the images and store it into a numpy array. We then compile both eyes open and close array and yawn and no yawn array together. Then we separate the Labels and Features of the image into two variables.  \nOnce the preprocessing stage is done we move onto split the data to train and test models. We introduce ImageAugmentation to augment the images in random manner so that the model has more data to train and test with.  \nThen we move onto train our first deep learning model using TensorFlow and Keras. And using functions such as MaxPooling2D and Conv2D. After training the deep learning model we print out the results from that test.  \nThen we move on to append the data into 2d array so that we can model and train machine learning algorithms such as Logistic Regression and Support vector Machine( SVM ) .  \n4 Code Snippets  \nIn this section some of the import codings have been displayed to understand the project better.  \nThe below figuire 2 shows the code for removing the background of images of yawn and no yawn since only the face data is necessary.  \nThe figuire 3 show the code for data augmentations so that the we can artifically create more data to make the model train more effectively.  \nFigure 4 explains the code for creating a function that will classify all 4 categories of the images that need to be segregated.  \nFigure 5 explains the code for the confusion matrix of the first model which is the deep learning model.  \nFigure 6 Explain the code of the machine learning techniquie Support vector  \nFigure 2: model to remove the background of the face  \nFigure 3: Data Augmentation  \nFigure 4: Model to classify images into 4 categories  \nFigure 5: Confusion matrix  \nMachine and Figure 7 is the code for the machine learning technique Logistic Regression.  \nFigure 6: Code for Support Vector Machines  \nFigure 7: Code for Logistic Regression","cbCaif3kbEsfpBVN","https://ap.wps.com/l/cbCaif3kbEsfpBVN","pdf",607314,"English","# 1 Introduction\n# 2 Environment Setup\n## 2.1 System Specification\n## 2.2 Technical Specification\n## 2.3 Data Source\n# 3 Implementation\n## 3.1 Importing Necessary Libraries\n## 3.2 Implementation Process\n# 4 Code Snippets\n## Figure 1-7","[{\"question\":\"What environment was used to implement the project?\",\"answer\":\"Implementation ran in a locally hosted Jupyter notebook on a MacBook Pro with an M1 processor, 8GB RAM, and 512GB SSD.\"},{\"question\":\"Where was the dataset obtained and what does it contain?\",\"answer\":\"The data was downloaded locally from Kaggle and includes images representing face-related states such as open eyes, closed eyes, yawn, and no yawn.\"},{\"question\":\"What preprocessing and augmentation steps were applied before training?\",\"answer\":\"The process removes the background of the face for yawn and no-yawn images, reads images into a NumPy array, and uses image augmentation to artificially increase and diversify training data.\"}]","MSc Research Project - Configuration Manual | PDF"]