Categories
Education Report Writings Tech

Technical Report Sample

This is a technical report sample. Here is the details report on a deep learning-based project collected from https://github.com. This is not the main project but it is a standard template for showing your project report. You can edit as you want it. Thank you.

Technical Report Sample on ANN:

Abstract

With the help of sensor data collected from a mobile or other devices, a neural network can guess patterns on the data and predict any activity anyone done. Today, it is one of the most demanding sites of artificial intelligence. Moreover, collecting human activity data through sensors, one can implement it to a bot. Raw data collected from different sensors of a mobile, smartwatch and other sensors active device enhance the classification of human activities with machine learning algorithms. In this paper, I observed a model on its mile activity recognition, usually the motion sensors, such as accelerometer and gyroscope. The performance of the model is great; however, I have tried to tune the model and observed the changes one by one. Hence, the model validation accuracy is 97.98 % and precision is 95%. This was achieved from the data learning from a cellphone attached to the waist. LSTM model has been used for this purpose to learn the sequence of data.

Table of Contents

Abstract

Table of Contents

List of Figures

1 Introduction

2       Background

3       Datasets

4       Methodology

5       Results and discussion

6       Conclusions and recommendations

7       Acknowledgments

8       References.

Appendix A: Place the title of appendix here

List of Figures

1.            Different Activity Related Sensor Data                    

2.            Model Summary                                                              

3.            Model Accuracy                                                               

4.            Model loss                                                                         

1       Introduction

Artificial Neural Network with a validation accuracy of 97.98 % and a precision of 95% was achieved from the data to learn (as a cellphone attached on the waist) to recognize the type of activity that the user is doing. My work is inspired by Guillaume-chevalier/LSTM-Human-Activity-Recognition but he used RNN-LSTM to recognize the activity whereas I used ANN for the same. And had achieved a better confusion matrix as well as the validation accuracy than the RNN-LSTM. Bidirectional LSTM on the other hand gave around 94 % but which is still less. The above VALIDATION ACCURACY is also best on KAGGLE. The approach might be a little different.

2       Background

There are much research has been done over the years. I review some of them for learning the background of my task.

Paniagua et al. describe different sensors like accelerometer, magnetic field, and air pressure meter equipped by mobile, which can help in the operation of the evoking context of the user like location, situation, etc. Moreover, processing the evoked sensor data is generally a resource-hungry task, which can be uploaded to the public cloud storage from mobile devices. This paper specifically targets at evoking useful information from the accelerometer sensor data. The paper defines the usages of parallel computing using Map Reduce on the cloud for training and recognizing human activities based on machine learning classifiers that can scale in performance and accuracy easily. The sensor data is collected from the mobile devices, uploaded to the cloud and processed using different classification algorithms such as Iterative Dichotomizer 3, Naive Bayes Classifier, and K-Nearest-Neighbors. The guessed activities can be used in mobile applications like this paper model Zompopo that utilizes the data in creating an intelligent calendar [1].

On the other hand, human exercises are inalienably interpretation invariant and various levels. Human action acknowledgment (HAR), a field that has earned a great deal of consideration as of late because of its appeal in different application spaces, utilizes time-arrangement sensor information to construe exercises. In this paper, a profound convolutional neural system (convnet) is proposed to perform productive and powerful HAR utilizing cell phone sensors by abusing the innate attributes of exercises and 1D time-arrangement signals, simultaneously giving an approach to naturally and information adaptively remove vigorous highlights from crude information. Analyses show that convnets to sure determine applicable and progressively complex highlights with each extra layer, even though the distinction of highlight multifaceted nature level abatements with each extra layer.

Moreover, A more extensive time length of transient nearby connection can be abused (1 × 9-1 × 14) and a low pooling size (1 × 2-1 × 3) is demonstrated to be useful. Convnets likewise accomplished a practically ideal order on moving exercises, particularly fundamentally the same as ones that were recently seen to be extremely hard to characterize. In conclusion, convnets beat other best in class information-digging strategies in HAR for the benchmark dataset gathered from 30 volunteer subjects, accomplishing a general presentation of 94.79% on the test set with crude sensor information, and 95.75% with extra data of worldly quick Fourier change of the HAR informational index [2].

3       Dataset

The mobile sensor signals such as accelerometer and gyroscope were pre-processed by using noise filters and then crated samples in fixed-width sliding windows of 2.56 sec and 50% overlap. The mobile sensor acceleration signal having gravitational and body motion components were separated using a Butterworth low-pass filter into body acceleration and gravity. The G-force is adopted to have only low-frequency components, whereas a filter with 0.3 Hz cutoff frequency has been used. From each window, a vector of features was obtained by computing variables from the time and frequency domain [3].

Figure 1: Different Activity Related Sensor Data

View More Technical Report Sample on ANN or Software Engineering Here!

4       Methodology

For feature selection, “extra tree classifier has been used with and I1 selection, but the results were somewhat better with all features only when manually tune the hyperparameters of the model to its almost utmost level which took some time. Though having fewer features will also take less time to train, but in this case, manual selection of features regarding circumstance can’t be done and the other techniques” [4].

The model design is as well as could be expected and concocted after continued tuning and changes in network architecture. By taking exceptional consideration of learning rate and clump size to which the model is touchy and need to overcharge them, to get a standout amongst another outcome in front. Here is the model summary:

Figure 2: Model Summary

In this sequential model 1st layer is a dense layer having an activation layer as Rectified Linear Unit (Relu). After the 2nd layer, batch normalization is used. The final layer uses sigmoid as activation fiction as the loss needs to be minimized. Adam optimizer has been used. In particular, some of the layers I have changed to see the changes and add other layers as well. The layer has in total of 80k+ parameters.

View More technical report sample on ANN or Other Course Here!

5       Results and discussion

I have tune hyperparameters such as epoch, batch size, etc. Batch size = 256 and epoch = 22 has been given as it is achieving good accuracy.

Technical Report Sample; ANN: model-accuracy

Figure 3: Model accuracy

This curve shows that both the train and test accuracy is good. After 22 epoch, the loss is .03, accuracy is 98.9%, validation loss is 0.06, and validation accuracy is 97.3% which is a great result indeed.

Technical Report Sample on ANN - Model loss
Technical Report Sample; ANN

Figure 4: Model loss

The pictures show there is no over-fitting. The model is efficient in results.

6       Conclusions and recommendations

Mobile Sensor data can play a revolutionary role, additionally, with the neural network, it can be helpful to detach any unexpected activity. Alike the apple smartwatch is the best example of a device. Its model is also trained using this type of sequence learning. Though my tuning does not any special effects on accurse and loss, I have learned all those practices. By tuning the hyperparameters, the model’s validation accuracy can be increased from 97.98% to 99% and precision can be increased from 95% to 97%.

7       Acknowledgments on Technical Report Sample on ANN

The main implementation of codes collected from Kaggle.com and the dataset is collected from UCI machinery. I owe nothing, I have just experimented and try to implement a sequence learning model such as LSTM.

8       References 

[1]H. F. S. N. S. Carlos Paniagua∗, “Mobile Sensor Data Classification for Human Activity Recognition,” Elsevier, The 9th International Conference on Mobile Web Information Systems (MobiWIS 2012), p. 585 – 592, 2012.
[2]S.-B. C. Charissa Ann Ronao, “Human activity recognition with smartphone sensors using deep learning neural networks,” Expert Systems with Applications, p. 59, 2016.
[3]A. G. L. O. X. P. a. J. L. R.-O. Davide Anguita, “Human Activity Recognition Using Smartphones Data Set,” 21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013., Bruges, Belgium 24-26 April 2013. .
[4]deadskull7, “Human-Activity-Recognition-with-Neural-Network-using-Gyroscopic-and-Accelerometer-variables,” GitHub, [Online]. Available: https://github.com/deadskull7/Human-Activity-Recognition-with-Neural-Network-using-Gyroscopic-and-Accelerometer-variables.

Appendix A: Technical Report Sample

This is a technical report sample on ANN. Thank You for Reading!

Categories
Education Report Writings

Project Report for Software Engineering Course

Course full name: Software Design Patterns and Analysis. This is my project report for the course CSE327 at my university. I am sharing this for the juniors to get an idea about writing a good report with different details.

Introduction:

With the advent of computer technology and the internet, consumers prefer to conduct their studies or business online. Student Resource Forum is a question and answer website where one can ask questions, answers, suggests and organizes.  Users can collaborate by editing questions and suggesting edits to the answers of others. Users on the Student Resource Forum can comment and write a blog post and like answers.

There are 10 use cases used in this project. These are as follows:

  • 1. Make Question.
  • 2. Do Searching.
  • 3. Give Comment.
  • 4. Upload File.
  • 5. Download File.
  • 6. Add third-party for login.
  • 7. Select Categories.
  • 8. See Profile.
  • 9. See Questions.
  • 10. Complete Registration.

Use Case Diagram

Use case – 1:

Use Case SectionMake Question
Use Case Name  Recent, Most Votes, Most Answers, and Most Views into the website
LevelUser-goal
Primary ActorEnd user
Stakeholders and InterestsEnd user wants to successfully see/vote/answer into the website  
Preconditions1. Website must be properly connected to online. 2. User is using website for first time, he/she will have to sign-up.
Main Success Scenario1. User opens the website. 2. User ask questions. 3. User see recent questions. 4. User answer and vote for questions. 5. User gets most views into the website. 6. User log out successfully from system.
Extensions2a. User cannot ask question, there must be a database management problem and system is showing an error message. 2a.1: User re-enters question.

Use case – 2 :

Use Case Name  Give Comment
LevelUser-goal
Primary ActorEnd user
Stakeholders and InterestsUser wants to successfully comment into the system.  
Preconditions1. System must be properly connected to online. 2. User must be logged in.
Main Success Scenario1. User comment on a question. 2. User get up vote or down vote for comment. 3. User get a score from up vote and down vote. 4. System gives user rank based on vote and score. 5. User successfully log out.
Extensions1a. User cannot comment while database does not process comment and system show error message. 1a.1: User re-enters comment.

 

Use case – 3:

Use Case Name  Do Searching
LevelUser-goal
Primary ActorEnd user
Stakeholders and InterestsEnd user wants to successfully search into the website  
Preconditions1. User must be logged in. 2. System must be properly connected to online.
Main Success Scenario1. User search for needed content. 2. User search for books, questions and answers and successfully get contents from website. 3. User download or upload needed content. 4. User successfully log out from system.
Extensions2a. System database not working, the site will stop serving content properly and this happens while the database’s disk fills up and system show error message. 2b. User do not get searched content, because of the content is not uploaded yet.  

Use case – 4:

Use case NameUpload File
LevelUser-Goal
Primary ActorEnd User
Stakeholders and InterestsEnd user wants the file to be uploaded successfully.
Preconditions1. User should be logged in into website. 2. User should be connected with online.
Success GuaranteeOn successful completion selected file will be uploaded to the database storage.
Main Success scenario1. User selects database storage. 2. User enters valid database storage credentials. 3. System and third party system validates the credentials and displays the files in the database storage. 4. User clicks on the upload function on the toolbar. 5. User selects file to be uploaded. 6. System uploads selected file to the database storage and updates list.
Extensions                  3a. system displays an error message for Invalid credentials. 5a. System unable to get file name and file size, it displays error message.  

Use case – 5:

Use case NameDownload File
Level User-Goal
Primary ActorEnd User
Stakeholders and InterestsEnd user wants the file to be download successfully.
Preconditions1. Website should be properly connected to online. 2. User should be logged in.
Success GuaranteeOn successful completion selected file will be download.
Main Success scenario1. User selects database storage. 2. User enters valid database storage credentials. 3. System and third party system validates the credentials and displays the files in the database storage. 4. User clicks on the download function on the website. 5. User selects file to be download. 6. System download selected file.
Extensions                  3a. system displays an error message for Invalid credentials. 5a. System unable to get file name and file size, it displays error message.  

Use case – 6:

Use case NameAdd third-party for login
LevelUser-Goal
Primary ActorEnd User
Stakeholders and InterestsEnd user wants to connect with website easily through Gmail/Facebook
PreconditionsUser should have online connection.
Success GuaranteeOn successful completion user will log in into website account.
Main Success scenario1. User selects Gmail/Facebook function. 2. Gmail/Facebook login option comes. 3. User login into Gmail/Facebook account. 4. User than logged in into website account through third party information.
Extensions                  3a. User are not connected with Gmail/Facebook and system displays an error message. 3b. System cannot verify user name and password. 3b.1: User re-enters the user name and password.

Use case – 7:

Use Case Name  Select categories
LevelUser-goal
Primary ActorEnd user
Stakeholders and InterestsEnd user wants to search different subject and option.  
Preconditions1. User have to be logged in into website account. 2. User have to connect with online.
Success GuaranteeUser will successfully explore different categories.
Main Success Scenario1. User selects categories function. 2. User selects option of his or her choice. 3. User collect needed knowledge. 4. User upload or download different content in different categories. 5. User successfully log out from website.
Extensions2a. User do not get his needed content, because the content is not uploaded yet in that category. 2b. System is crush because of overload of user and error message will be shown.

 

Use case – 8:

Use Case Name  See Profile
LevelUser-goal
Primary ActorEnd user
Stakeholders and InterestsUser wants to see other user’s wall, all questions, all answer, comments, gave out, receive and score.  
Preconditions1. User have to be logged in into website account. 2. User have to be connected with online.
Success GuaranteeUser will be see what other user’s opinions, questions and answer.
Main Success Scenario1. User selects user function. 2. User selects another user’s profile. 3. User see other user’s wall, question, answer, comments, up vote, down vote and score. 4. User leave successfully from another user’s profile.
Extensions   2a. User won’t able to visit another user’s account due to database connection problem. 2a.1: User re-click another user profile option.

Use case – 9:

Use Case Name  See Questions
LevelUser-goal
Primary ActorEnd user
Stakeholders and InterestsUser wants to see other user’s answer, up vote, down vote and tag.  
Preconditions1. User have to be logged in into website account. 2. User have to be connected with online.
Success GuaranteeUser will be see what other user’s questions and answer.
Main Success Scenario1. User selects unanswered function. 2. User can see unanswered question, related up vote, down vote, tagged link and tagged person. 3. User can answer of questions, give comments, also can give up vote, down vote and tag.
Extensions   3a. System detects failure to communicate with database system services and show error message.  

Use case – 10:

Use Case Name  Complete Registration
LevelUser-goal
Primary ActorEnd user
Stakeholders and InterestsUser wants to sign up at website for open an account.  
Preconditions1. User have to be connected with online. 2. User have to provide Gmail account or Facebook account to open an account.
Success GuaranteeUser will be successfully log in into account.
Main Success Scenario1. User select user name for website. 2. User provide email account or Facebook account. 3. User verify link that is sent from website to Gmail account. 4. User log in into website and see website content. 5. User log out from website.
Extensions   3a. User will get error message if registration information is not right. 3a.1: User re-enters registration information.

Domain Model Diagram:

Class Diagram:

Sequence Diagram:

Technologies Used:

  • Framework
  • XAMPP Control panel
  • PHP (Laravel Framework)
  • GitHub
  • Bootstrap (Less)
  • MySQL (Database)
  • HTML5
  • CSS3.

Technical Challenges:

o   We had issues while integrating PHPmyadmin database management.

Project GitHub Repository Link:

https://github.com/arnobtanjim/student-resouce-forum

1St Iteration Presentation Link (Online):

https://prezi.com/gy4oadxqm2i0/student-resource-forum

Here, our group has also hosted the site online in a free domain hosting site. The link is: http://studentrf.rf.gd

Project Snapshots:

Conclusion:

Student Resource Forum website’s advantages:

  • This website is an open-source and free.
  • Suitable for sharing studying materials.
  • Suitable for easy access and get materials.
  • Easy upload /Download features of any course materials.
  • Update according to user needs.
  • Large number of collection and resources.
  • Can request for solution to problems etc.