Journal 9 Intelligent Systems: Presentation Week

by jerdy on 9/01/2020

In this week, we finalize our final project. We created our presentation slides and did our presentations. Unfortunately, we forgot to make the video. We received several inputs therefore, we will be making several improvements regarding the code and the result. Next, we will also make the video. The Intelligent System course is one of the most difficult courses. Learning artificial intelligence is difficult in my opinion. I really need some time to understand the materials completely. Overall, learning artificial intelligence has been fun. Thank you so much ms. Nurul for teaching us.

No Comments

Journal 8 Intelligent Systems: Finalizing The Project

by jerdy on 9/01/2020

Few weeks ago, I no longer work with Arden and Galastu. I moved to Adrian’s group along with Steven. At first, our team wanted to make the game, monopoly. In the end, we make a a program that will help companies to be able to make a proper estimation of passenger. The main idea is forecasting. The algorithms that we used are Arima and Dicky Fuller’s Test. Both algorithms are difficult in my opinion. The Arima algorithm as well as Dicky Fuller’s Test is an algorithm that is used to predict future time steps based on past time steps. The goal of both algorithm is autoregression.

No Comments

Journal 7 Intelligent Systems: Project Progress

by jerdy on 13/12/2019

For this week, we still continue doing some research and discussions. After continue doing a few researches, our team has found some algorithms, but we are interested most with the monte carlo algorithm. According to our team, the monte carlo algorithm is likely to be efficient and suitable for our final project. We decided to pursue using the monte carlo algorithm. Monte Carlo simulation performs risk analysis by building models of possible results by substituting a range of values for any factor that has inherent uncertainty.

No Comments

Journal 6 Intelligent Systems: Learning by Teaching

by jerdy on 6/12/2019

We are asked to teach computer vision for this week.

Computer vision is one of the subfields of Artificial Intelligence that deals with how computers can be made to gain high-level understanding from digital images or videos. Computer vision seeks to automate tasks that the human visual system can do. Automation basically is making machines do the job of humanbeings. Computer vision allows machines, semi-controlled vehicles, drones, factories and farm equipment to work effectively and safely.

Computer vision has been implemented in several aspects including finance, automotive, healthcare, agriculture, industry, etc. I will be specifically discuss on the aspect of finance. One of the application that has implemented computer vision in the financial area is Cortexia. Cortexia relies on visual Search.

Everyone has probably faced the challenge of liking something but not knowing where to buy it. All we need to do is to take a photo of a magazine page or drag an image from social media, and find a similar or the exact item to buy.

No Comments

Journal 5 Intelligent Systems: Project Progress

by jerdy on 29/11/2019

For this week, our team has decided to resume making our final project. We did not really made any significant changes and progress. Last week, we learnt about a new algorithm called Naive Bayes in class. Initially we thought maybe Naive Bayes is one of the few algorithms that we should consider to use for our final project. Naive Bayes is not really difficult to be implemented. Searching for another efficient algorithm is also what we plan to do. In the end, we realized that Naive Bayes algorithm is not suitable for our final project.

No Comments

Jorunal 4 Intelligent Systems: Naive Bayes

by jerdy on 23/11/2019

Naive Bayes classifiers are a collection of classification algorithms based on Bayes’ Theorem. Naive Bayes classifier is a family of algorithms where all of the algorithms share a common principle. Every classified feature is independent of each other.

Bayes’ Theorem is a mathematical formula created by Thomas Bayes. Bayes’ Theorem is a mathematical formula for determining conditional probability. The theorem provides a way to revise existing predictions or theories (update probabilities) given new or additional evidence.

Now let us practice

Guess what the class of the given characteristics below:
Give birth = yes, can fly = no, live in water = yes, have legs = no

The first step is to divide the classes into mammals and non-mammals. Then, we determine how many animals in each class.

The Mammals Class

The Non-mammals Class

The second step is to count the prior probability.

In total, there are 7 mammals and 13 non-mammals.

Divide 7 by 20 to get the prior probability of mammals.

Divide 13 by 20 to get the prior probability of non-mammals.

The third step is to count the probability.

Now, let us test the model if the instance is:

Give birth = yes, can fly = no, live in water = yes, have legs = no

Based on the equation:

P(mammals|give birth, can fly, live in water, have legs) = 0.020991254

P(non-mammals|give birth, can fly, live in water, have legs) = 0.002730997

The class that has the highest probability is: Mammals.

No Comments

Journal 3 Intelligent System: Project Progress

by jerdy on 2/11/2019

For this week, our team believed that we still need to do some more researches before making any significant progress to our final project. We had one time a thought of changing the idea for our final project. We spend most of our time doing several researches and discussions. We discussed on which algorithm is suitable and efficient to be implemented to the game called “cangkul”. We have not really distribute the task of each team member. We realized that since mid-exam is approaching, our team decided to pause on doing several research.

No Comments

Journal 2 Intelligent Systems: Understanding Artificial Intelligence

by jerdy on 31/10/2019

What is Artificial Intelligence?

Artificial Intelligence is the ability of a computer to act, think, and perform like a human-being.

There are 2 categories of AI:

  • Narrow AI
  • Artificial General Intelligence (AGI)

Narrow AI

Sometime narrow AI is referred as a “Weak AI”. Narrow AI operates within a limited context and is a simulation of human intelligence. The focus of Narrow AI is performing a specific task extremely well.

Several examples of Narrow AI include:

  • Google search
  • Image recognition software
  • Siri, Alexa and other personal assistants
  • Self-driving cars
  • IBM’s Watson

Artificial General Intelligence (AGI)

Artificial General Intelligence sometimes is referred as “Strong AI”. AGI is the type of artificial intelligence that we see in movies and games. The robots in the movie, I Robot, can be considered as AGI. A movie character, Data, from Star Trek is also an example of AGI.

No Comments

Journal 1 Intelligent Systems: Project Progress

by jerdy on 24/10/2019

Our group consists of three members: Galastu Chandra Utama, Arden Djaja, and myself. During the first week, we spend most of our time on doing several researches and discussion on what we are going to create for our final project. At first, we wanted to create chess with machine learning for our final project. After doing several researches, we realized that other people have already created it. Finally, We decided to make a traditional Indonesian card game called “cangkul” using Python for our final project.

No Comments

Ethical Hacking: Nikto

by jerdy on 1/06/2019

What is Nikto?

Nikto is a simple, open-source web server scanner that examines a website and reports back vulnerabilities that it found which could be used to exploit or hack the site. Also, it’s one of the most widely used website vulnerabilities tools in the industry, and in many circles, considered the industry standard.

Although this tool is extremely effective, it’s not stealthy at all. Any site with an intrusion-detection system or other security measures in place will detect that it’s being scanned. Initially designed for security testing, stealth was never a concern.

How to use Nikto?

Basic syntax: nikto -h <IP or hostname>

Nikto is capable of doing a scan that can go after SSL and port 443, the port that HTTPS websites use.

Scanning an SSL-enabled Site

syntax: nikto -h <IP or hostname> -ssl

let’s start with scanning

After it connects to port 443, we see that there’s some useful information about the cipher and a list of other details like that the server is Nginx.

Scan a HTTP Website

Scan an IP Address

Let us find our IP address using ifconfig.

Then we can run ipcalc to get our network range.

To install ipcalc, type apt install ipcalc

We run Nmap to find services running in the network range.

Let’s scan port 80 with our range and tack on -oG (grepable output) to extract only the hosts that are up and running

Then we’ll save everything to a file, which I’m naming nulbyte.txt, but could be named anything.

We use cat to read the output stored in our nulbyte.txt document (or whatever you named it).

  • awk, a Linux tool that will help search for the following pattern
  • Up means the host is up
  • print $2 means to print out the second word in that line for each

We can now view the contents of our new file with cat to see all the IP addresses that have port 80 open.


No Comments