savvyingthesignals

[savvyingthesignals]

A screenshot of our completed journal.

[savvyingthesignals]

Week 19

This is my last long post for this subject. (Awww.) Last December 12, 2017, we have submitted our final requirement for the subject, which is the journal about coffee using image processing and artificial intelligence. I and my partner in making the journal decided to change our original idea about the title which we are working with. Consecutively, we used coffee leaves instead of beans. Our journal went on like this: We would be identifying Robusta coffee leaves among different species of tree leaves using 3 classifiers namely, ANN, KNN, and SVM. So have picked sample of Robusta coffee leaves from Barangay Pulong Bunga, Silang, Cavite. Then we also acquired samples from the trees of guava, avocado, and mango. We placed them on the white part of the illustration board and took photos of them. Afterwards, the images were processed on Matlab, and we obtained several morphological features and tabulated them. The dataset were then subjected to the classifiers. The classification was effectively done and the three successfully identified the Robusta coffee leaves when mixed up with other fruit trees. Hopefully, Sir Arboleda would be satisfied with the content of our work.

The whole semester was a blast. Most of the time, we were busy doing our schoolworks. But this subject taught us to persevere with our work, to continue to do our best to become 'legendary' because that is what an ECE looks forward to. When the time comes, I would just be reading this blog, reminiscing the college moments while savoring the things I have already achieved.

This is Digital Signal Processing Laboratory, now signing off. 👋

[savvyingthesignals]

This is the screenshot of our Major Activity 3.

[savvyingthesignals]

Week 18

December 5, 2017

It was finals week and we did not have our classes for today. Our instructor told us that he would be at the UCC during our class hours and in case that we have some question in our mind, we could ask him. We could also use our time for our final project.

[savvyingthesignals]

Week 17

November 28, 2017

We did not have a class today again because Sir Arboleda had some things to do regarding his outline defense. So he told us to continue doing our final requirement for the subject.

[savvyingthesignals]

Week 16

November 21, 2017

Finally, we had our meeting for the class today. Our instructor gave us a file about different methods on how images can be processed. What we have to do is to choose a topic that would be suitable for our written journal article. 

The Matlab application on the laboratory’s computers was already expired so most of our classmates were not able to try the codes included on the file. So instead, our professor explained to us some of the things that we can do for our journal. We also tried our acquired data from the past week for testing since we are doubtful about the results of our previous work. We wanted to try another topic where we could obtain better results so we are thinking of a more credible title.

[savvyingthesignals]

Week 13 to Week 15

October 31, 2017

November 7, 2017

November 14, 2017

I haven't posted on my blog for the said dates because we did not have meetings for our Laboratory class. This was because of different circumstances that happened such as the availability of our instructor. Nevertheless we used our time to do continue doing our final requirement for the subject, which is to write our own journal article regarding the coffee beans of the Philippines. Last October 24, our instructor encouraged us to write our own abstracts to be submitted online on or before 6 pm. The abstracts that we had submitted were eventually forwarded by Sir Arboleda to the National Coffee Congress committee. If ever our article would be published, our instructor said that he will automatically give us a grade of 1. The first National Coffee Congress Week was held by the way last November 6 to November 9 at Cavite State University itself. So we get to see the exhibits of different coffee varieties from schools and universities and witness the prosperous culture of the Philippines through the various products displayed.

[savvyingthesignals]

Week 12

October 24, 2017

After several weeks of having no classes, we finally had our laboratory class in our subject. We performed what is due today which is the presentation of our chosen article about feature extraction and classification using image processing. We spent the first half of our class on presenting our articles but not everyone were able to report because Sir Arboleda used the remaining time to discuss about another topic on us. So the presentation will be continued next meeting. I did not presented my report today which is somehow a blessing in disguise because I feel sick today becuase of my dysmenorrhea. Sir Arboleda introduced to us the nntool command which can be used to identify various objects with classification. The Neural Network tool is a means of implementing artificial intelligence because it can train samples in order to classify them. Sir Arboleda gave us a tutorial video about using the nntool command using a dataset of features of Iris flower. The input data used are the extracted features of training images and the output data are the classification of the flowers treated as numbers. The test data came from the the 15 test samples of the iris data set. By training the network and clicking on the regression button, the percentage of accuracy of classifying the iris flowers were shown. Upon learning this, Sir Arboleda gave us an assignment where we will used the dataset we obtained from our second major activity. Our instructor also gave us our Major Activity 3 for groups of 2 persons with Sir Arboleda as the first author, wherein we will make a journal about coffee bean classification from the features extracted from Matlab and we will utilize the Neural Network Tool, or the Artificial Neural Network classifier. After obtaining the results, we will be creating the abstract of our article to be submitted through email on Saturday night. We are also told that the abstracts that we will submit will be forwarded to the Philippine National Coffee Congress. If ever that our journal article will be published, our instructor will give us a grade of 1 on our laboratory class.

[savvyingthesignals]

Week 11

October 18, 2017

We are supposed to present our chosen articles regarding the application of image processing on feature extraction today. However, we did not have classes again due to another unexpected reason: the nationwide transport strike of the jeepney drivers. Of course, the commuters would have limited means of transportation since the public vehicles that should be available for them are lacking due to the strike.

Again, our activity is postponed and will resume until we have classes for the subject.

[savvyingthesignals]

Major Activity 2

First picture: Sample labelling Second picture: Table of Data for Robusta coffee in Magallanes, Cavite

[savvyingthesignals]

First Major Activity 1 (final)

[savvyingthesignals]

Week 10

October 10, 2017

Today is the second day of the University Games 2017. So we had some short break on our academics. Some time to refresh after months full of schoolworks. After this week, we will be back to reality again. At least, we will have enough rest and energy to get back to work again as a student.

Sir Arboleda told us to give him the compiled soft copies of our first major activity so he can check our work during the Intrams week. So our class representative copied each of our folders and placed it on a flash drive, which are then transferred to Sir Arboleda’s laptop.

[savvyingthesignals]

Week 9

October 3, 2017

Today, we did not have our class for DSP lab because of an unfortunate circumstance that happened to our instructor. (Get well soon sir.) Nevertheless, the submission of our major activities were not postponed. We placed the hard copies of our Major Activity 1, which is the journal formatting, and Major Activity 2, which is about the morphological extraction of the coffee beans from the photos given to us, to Sir Arboleda’s table on their faculty. And we have sent the soft copies through e-mail. Last weekend until yesterday, I have worked for the major activity 2 which somehow required a meticulous effort because we needed to extract parameters from the 30 samples from each of the 19 photos. I used the downloaded photos from the laptop so the pixels of the photos would be uniform with each other and it would use the maximum size. The size of the photos can change when downloaded from phone and aside from this, Sir Arboleda told us not to resize the photos because the area and the perimeter would also change in dimensions. Upon extracting the features using Matlab, some of the photos displayed after using the vislabels command showed a lot of numbers as labels which are treated as noise. To reduce the noise, my classmates and I discovered that the value for c on the Matlab command can be changed. So Instead of c=255-b, I also used c=250-b, c=280-b, and c=285-b on other photos. After this modification, the labels of the photos were already clear enough to distinguish so their area and perimeter could be identified. However, there are coffee beans which really have 2 numbers placed on it so both labels were checked using the g(n) command where n is the label of the coffee bean. When g(n) is entered, the area and perimeter of the coffee bean would show up. One label indicated a very small value for area and the other one shown an objective number of pixels so the latter is preferred to be used. So the data were recorded on an excel file. The properties, equivalent diameter and roundness were obtained by using their formulas which were executed on the excel file and by utilizing the values of area and perimeter. After the tables on the excel file were filled with the data, I transferred them to Microsoft Word to make them ready for printing. Also, I placed my name, section, and instructor’s name on the document.

[savvyingthesignals]

Week 8

September 26, 2017 We did not have classes again today because our instructor had dissertation matters to attend. Nonetheless, he gave us our Major Activity No. 2 which involves image processing using Matlab through our Fb group. We would be extracting the features of different varieties of coffee beans by obtaining their surface area, perimeter, equivalent diameter, and roundness. In this activity, we would be using the commands and mfile that we have learned from the previous lessons when dealing with image processing. The submission of our Major Activity 1 and other requirements would also be extended until next week. :)

[savvyingthesignals]

A panoramic view from a corner of our classroom. (Week 5)

[savvyingthesignals]

A view from the back of our classroom. (Week 5)

[savvyingthesignals]

Week 7

September 19, 2017

Today is a research day so we did not have a laboratory class. Sir Arboleda provided us more time to do our journal for our first major activity. But last Saturday, September 16, 2017, I already edited my work. Our instructor told us to include at least 4 journals from the family of the journal publisher we had chosen on our references. So I searched for more journals from TELKOMNIKA and luckily I found 4 journals that are suitable for my chosen thesis. I also got 1 journal from BEEI and another one from IJECE. Then I changed the format of the citations from parenthesis into brackets and put a dash between numbers to show a range of multiple citations. I also revised the references wherein I placed brackets on the numbers and followed the text styles of the Vancouver format. If the article is a journal, the title of the journal publisher should be italicised. If the article came from conference proceedings, the italicised part is the title of the work itself. When the source came from a textbook, nothing should be italicised. The TELKOMNIKA template and the sample journal that Sir Arboleda gave us served as my basis for the citations and references of my work. I also used Mendeley for the preliminary format of the references and also for an easy access to citations. But for finalization, I edited them manually on the Microsoft Word itself. After I checked all the possible faults that may exist on my journal, I already printed my work on a short bondpaper. I also compiled the soft copies of my references on a folder together with the soft copies of my finished work both in .docx and .pdf format. The hard copy and the soft copies will eventually be passed next Tuesday.