International Journal of Artificial Intelligence and Robotics (IJAIR)
International Journal of Artificial Intelligence & Robotics (IJAIR) is One of the journals published by Informatics Department, Universitas Dr Soetomo, was established in November 2019. IJAIR a double-blind peer-reviewed journal, the aim of this journal is to publish high-quality articles dedicated to the field of information and communication technology, Published 2 times a year in November and May. Focus and Scope: Machine Learning & Soft Computing, Data Mining & Big Data, Computer Vision & Pattern Recognition dan Robotics.
Articles
60 Documents
<![CDATA[Knowing Personality Traits on Facebook Status Using the Naïve Bayes Classifier ]]>
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 2 No. 1 (2020): May 2020 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (2169.831 KB)
|
DOI: 10.25139/ijair.v2i1.2636
<![CDATA[With the development of social media trends among students by using Facebook social media, students can communicate and pour out everything that is felt in the form of status. Personality is the character or various characters of a person - therefore, how a person to adjust to the surrounding environment for the achievement of communication smoothly. In the personality category, many things classify a person's category in the psychologist theory. In this exercise, the Big Five, the psychologist theory, is described in five codes, namely Openness, Conscientiousness, Extraversion, Agreeables, Neuroticism. Naive Bayes Classifier is used to determine the highest probability value with the aim to determine the highest value. The data used are two namely training data and testing data obtained from the Facebook status of students. From the data obtained can be tested in the system that the accuracy value is 88%.]]>
<![CDATA[Modified Vegenere Cipher to Enhance Data Security Using Monoalphabetic Cipher ]]>
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 1 No. 1 (2019): November 2019 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (611.85 KB)
|
DOI: 10.25139/ijair.v1i1.2029
<![CDATA[The rapid progression of exchange data by public networks is important, especially in information security. We need to keep our information safe from attackers or intruders. Furthermore, information security becomes needed for us. Many kind cipher methods of cryptography are improved to secure information such as monoalphabetic cipher and polyalphabetic cipher. Cryptography makes readable messages becoming non-readable messages. One of the popular algorithms of a polyalphabetic cipher is Vigenere cipher. Vigenere cipher has been used for a long time, but this algorithm has weaknesses. The calculation of the encryption process is only involving additive cipher, it makes this algorithm vulnerability to attacker based on frequency analysis of the letter. The proposed method of this research is making Vigenere cipher more complex by combining monoalphabetic cipher and Vigenere cipher. One of the monoalphabetic ciphers is Affine cipher. Affine cipher has two steps in the encryption process that are an additive cipher and a multiplicative cipher. Our proposed method has been simulated with Matlab. We also tested the vulnerability of the result of encryption by Vigenere Analyzer and Analysis Monoalphabetic Substitution. It shows that our method overcomes the weakness of Vigenere Cipher. Vigenere cipher and Affine cipher are classical cryptography that has a simple algorithm of cryptography. By combining Vigenere cipher and Affine cipher will make a new method that more complex algorithm.]]>
<![CDATA[Traffic Light Automation with Camera Tracker and Microphone to Recognize Ambulance Using the HAAR Cascade Classifier Method ]]>
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 2 No. 2 (2020): November 2020 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (2519.988 KB)
|
DOI: 10.25139/ijair.v2i2.3194
<![CDATA[Lack of knowledge by road users regarding these priorities, especially when there is a passing ambulance that is often stuck in traffic at a crossroads due to accumulated vehicles and the traffic light is still red. The purpose of this paper is to simulate traffic light automation by giving a green light every time an ambulance passes by using the HAAR and Computer Vision methods. The HAAR method is used for training data from less sharp images as part of the Ambulance object classification process. The Computer Vision method is used as a tool in image processing objects to processing the image captured by the Camera. Hardware through the microphone performs pattern recognition to pick up ambulance sirens. The test result at the average frequency caught by the microphone is 1.3 kHz. The test results of the System to capture ambulance objects received a precision value of 75%, a recall of 100%, and an accuracy of 75%.]]>
<![CDATA[An Implementation of MMS Steganography With The LSB Method ]]>
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 2 No. 1 (2020): May 2020 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1378.483 KB)
|
DOI: 10.25139/ijair.v2i1.2653
<![CDATA[Around the world, the internet (interconnection network) has developed into one of the most popular data communication media. With a variety of illegal information retrieval techniques that are developing, many people are trying to access information that is not their right. Various techniques to protect confidential information from unauthorized persons have been carried out to secure important data. Steganography is a science and art for writing hidden messages so that no other party knows the existence of the message. The three results of tests conducted by the LSB method can be used to hide messages into images. The first test was successful by writing a message that less than 31 characters stored in the picture, the second succeeded in writing a message equal to 31 characters stored in the picture, the third failed to write a message of more than 31 characters stored in the picture.]]>
<![CDATA[Speech to Text Processing for Interactive Agent of Virtual Tour Navigation ]]>
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 1 No. 1 (2019): November 2019 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (271.812 KB)
|
DOI: 10.25139/ijair.v1i1.2030
<![CDATA[The development of science and technology is one way to replace the method of human interaction with computers, one of which is to provide voice input. Conversion of sound into text form with the Backpropagation method can be understood and realized through feature extraction, including the use of Linear Predictive Coding (LPC). Linear Predictive Coding is one way to represent the signal in obtaining the features of each sound pattern. In brief, the way this speech recognition system worked was by inputting human voice through a microphone (analog signal) which then sampled with a sampling speed of 8000 Hz so that it became a digital signal with the assistance of sound card on the computer. The digital signal from the sample then entered the initial process using LPC, so that several LPC coefficients were obtained. The LPC outputs were then trained using the Backpropagation learning method. The results of the learning were classified with a word and stored in a database afterwards. The results of the test were in the form of an introduction program that able display the voice plots. the results of speech recognition with voice recognition percentage of respondents in the database iss 80% of the 100 data in the test in Real Time]]>
<![CDATA[An Efficient Technique for Automation of The NFT (Nutrient Film Technique) Hydroponic System Using Arduino ]]>
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 3 No. 1 (2021): May 2021 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (339.138 KB)
|
DOI: 10.25139/ijair.v3i1.3209
<![CDATA[Hydroponic Nutrient Film Technique (NFT) is most widely applied on a home and industrial scale. One of the drawbacks of the NFT hydroponic system is that it is very dependent on electricity for 24 hours to power the water pump. The basic principle of the NFT hydroponic system is to flow nutrients to plant roots with a shallow and circulating nutrient layer so that plants get enough water, nutrients, and oxygen. Therefore, the role of the water pump in the hydroponic NFT system is crucial. This research makes the automation of the NFT hydroponic system more efficient using Arduino. There are two main parts to this automation system: the control of pH levels and nutrient distribution. The pH sensor is used to control the pH level of nutrients, and the ultrasonic sensor is used for nutrient distribution. Efficiency is emphasized more on the distribution of nutrients because it absorbs more electrical energy. The method used is to flow the nutrients in the reservoir to a storage tank that is located higher than the plant using a water pump with a large discharge. Nutrients are transported to each plant using the force of gravity. The nutrient volume is controlled automatically using an ultrasonic sensor in the storage tank. The water pump is only activated by the ultrasonic sensor readings on the storage tank. So that the need for electricity to turn on the water pump is reduced, based on tests carried out on the use of a 220-volt AC / 50 Hz / 125-watt water pump and the use of a 250-liter nutrient storage tank, it can be concluded that the system that has been created can save 70% of electricity consumption.]]>
<![CDATA[Design Of 4DOF 3D Robotic Arm to Separate the Objects Using a Camera ]]>
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 3 No. 1 (2021): May 2021 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (472.136 KB)
|
DOI: 10.25139/ijair.v3i1.3787
<![CDATA[Nowadays robotic arm is widely used in various industries, especially those engaged in manufacturing. Robotic arms are usually used to perform jobs such as picking up and moving goods from their place of origin to the location desired by the operator. In this study, a 3d 4 DOF (Degree of Freedom) robotic arm. The prototype was made to move goods with random coordinates to places or boxes whose coordinates were determined in advance. The robot can know the coordinates of the object to be taken or moved. The arm robot prototype design is completed with a camera connected to a computer, where the camera is installed statically (fixed position) above the robot's work area. The camera functions like image processing to detect the object's position by taking the coordinates of the object. Then the object coordinates will be input into inverse kinematics that will produce an angle in every point of the servo arm so that the position of the end effector on the robot arm can be founded and reach the intended object. From the results of testing and analysis, it was found that the error in the webcam test to detect object coordinates was 2.58%, the error in the servo motion test was 12.68%, and the error in the inverse kinematics test was 7.85% on the x-axis, the error was 6.31% on the y-axis and an error of 12.77% on the z-axis. The reliability of the whole system is 66.66%.]]>
<![CDATA[Bezier Curve Collision-Free Route Planning Using Meta-Heuristic Optimization ]]>
<![CDATA[1]]>;
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 3 No. 1 (2021): May 2021 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (652.198 KB)
|
DOI: 10.25139/ijair.v3i1.3821
<![CDATA[A collision-free route is very important for achieving sustainability in a manufacturing process and vehicle robot trajectories that commonly operate in a hazardous environment surrounded by obstacles. This paper presents a collision avoidance algorithm using a Bezier curve as a route path. The route planning is modeled as an optimization problem with the objective optimization is to minimize the route length considering an avoiding collision constraint. The collision-avoidance algorithm based on curve point analysis is developed incorporating metaheuristic optimizations, namely a Genetic Algorithm (GA) and a Grey Wolf Optimizer (GWO). In the collision avoidance algorithm, checking of curve point's position is important to evaluate the individual fitness value. The curve points are analyzed in such a way so that only the paths which are outside the obstacle area are selected. In this case, besides the minimum length as a fitness function, the constraint is the position of curve points from an obstacle. With the help of meta-heuristic optimization, the developed collision avoidance algorithm has been applied successfully to different types of obstacle geometries. The optimization problem is converted to the maximization problem so that the highest fitness value is used to measure the performance of the GA and GWO. In general, results show that the GWO outperforms the GA, where it exhibits the highest fitness value. However, the GA has shown better performance for the narrow passage problem than that of the GWO. Thus, for future research, implementing the hybrid technique combining the GA and the GWO to solve the advanced path planning is essential.]]>
<![CDATA[Optimization Design of Coal Dryer Using Genetic Algorithm in Power Plant ]]>
<![CDATA[1]]>;
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 3 No. 1 (2021): May 2021 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (235.244 KB)
|
DOI: 10.25139/ijair.v3i1.3825
<![CDATA[Coal that is often used in Steam Power Plants is a type of Low Rank Coal (Low Rank Coal) which has a caloric value of 4200 kcal / kg with a moisture content of 40%. Coal with water content that reaches 40% can cause the efficiency process of the plant to be not optimal. Low efficiency values will cause the use of electricity to increase and the combustion process to be incomplete so that it can cause many losses to the Steam Power Plant. From this problem, there needs to be a process of drying coal in order to reduce water content, the technology used in the process of drying coal is coal dryer. Design of coal dryer required source of steam or heat for drying process. Steam Power Plant there is steam waste extraction from turbines that can be used as a heat source to heat coal. If this extraction vapor is utilized, it can reduce the load from the condenser. The amount of turbine extraction steam that can be received by the coal dryer depends on the design of the coal dryer, because the design process of the coal dryer will affect the availability of energy in the coal dryer. This paper will discuss about optimization calculation with genetic algorithm method, to obtain the best design of coal dryer so that the heat received can be maximized so that the drying process becomes faster.]]>
<![CDATA[Emotion Detection in Twitter Social Media Using Long Short-Term Memory (LSTM) and Fast Text ]]>
<![CDATA[1]]>
<![CDATA[ International Journal of Artificial Intelligence & Robotics (IJAIR) Vol. 3 No. 1 (2021): May 2021 ]]>
Publisher : <![CDATA[Informatics Department-Universitas Dr. Soetomo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (621.699 KB)
|
DOI: 10.25139/ijair.v3i1.3827
<![CDATA[Emotion detection is important in various fields such as education, business, employee recruitment. In this study, emotions will be detected with text that comes from Twitter because social media makes users tend to express emotions through text posts. One of the social media that has the highest user growth rate in Indonesia is Twitter. This study will use the LSTM method because this method is proven to be better than previous studies. Word embedding fast text will also be used in this study to improve Word2Vec and GloVe that cannot handle the problem of out of vocabulary (OOV). This research produces the best accuracy for each word embedding as follows, Word2Vec produces an accuracy of 73,15%, GloVe produces an accuracy of 60,10%, fast text produces an accuracy of 73,15%. The conclusion in this study is the best accuracy was obtained by Word2Vec and fast text. The fast text has the advantage of handling the problem of out of vocabulary (OOV), but in this study, it cannot improve the accuracy of word 2vec. This study has not been able to produce very good accuracy. This is because of the data used. In future works, to get even better results, it is expected to apply other deep learning methods, such as CNN, BiLSTM, etc. It is hoped that more data will be used in future studies.]]>
