Emotion Recognition Based on Interval Type-2 Fuzzy Logic from Facial Expression | Author : Mahmut Dirik , Oscar Castillo , A. Fatih Kocamaz | Abstract | Full Text | Abstract :Automatic recognition of facial emotion plays an effective and important role in
Human–Computer Interaction (HCI). There are various emotion recognition approaches have
been proposed in the literature. The analytic face model consisted of a 26-dimensional geometric
feature vector. These properties are used effectively to identify facial changes resulting from
different expressions. The variation and uncertainties of these features make the emotion
recognition problem more complicated. For decreasing these complications, we propose a
distance-based clustering and uncertainty measures of the base new method for Emotion
Recognition from Facial Expression using automatically selects 19 diagnostics of Action Units
(AUs) in a 2D facial image using Type-2 Fuzzy inference system. The proposed system includes
an automated generation scheme of the geometric facial feature vector. The proposed system has
classified six facial expressions using the MUG Facial Expression database. The experimental
results show that the proposed model is very efficient in uncertainty management policy and
recognizes six basic emotions with an average precision rate of 86.175%. |
| Global Vision Based Path Planning for AVGs Using A* Algorithm | Author : Mahmut Dirik , A. Fatih Kocamaz | Abstract | Full Text | Abstract :One of the most studied problems in robotics is robot path planning. Many
strategies have been invented. Image processing and machine vision technology also have been
utilized in this regard. Studies are still underway to improve path planning methods. This paper
proposes an implementing visual servoing-based technique using the A* algorithm to achieve
efficient searching capabilities of path planning in complicated maps with a combination of
LabVIEW and MATLAB software. The proposed algorithm is divided into three parts. Firstly,
the environment model or robot motion environment is conducted. In this stage, the visual
information extracted from a single ceiled camera. Secondly, the position and orientation of the
objects (robot, obstacles etc.) under the visibility of the camera are generated from visual
information. Thirdly, the A* algorithm is used as a path planning method. This algorithm is not
guaranteed the generated path to be safe and desirable with obstacle-free. To solve this problem
image processing techniques are utilized. This gives an effective improvement and high
performance to A* in a complex environment and gives a safe path as a comparison to the
traditional version of A*. The experimental results, considering the optimal path lengths and
execution time, show that the proposed design is more effective and faster to generate the shortest
path.
|
| The effect of STEM application on 21st-century skills of middle school students and student experiences | Author : Mehmet Yavuz , Mehmet Hasançebi , and Funda Yesildag Hasançebi | Abstract | Full Text | Abstract :This study aims to reveal the effect of the STEM approach on 21st-century skills
of middle school students and to determine their experiences about STEM. This application,
which lasted 6 weeks with 7th-grade students, was realized with 35 students. In the study, by
using the explanatory mixed-method, firstly, quantitative data was taken and qualitative data
were tried to be explained. In the first stage of the study, the pre-test and post-test results were
examined in the group by using a dependent group t-test. “Multidimensional 21st Century Skills
Scale” was used as a pre-test and post-test tool. In the second stage of the study, student
experiences for STEM applications were revealed using the semi-structured interview form,
which is one of the qualitative data collection methods. In the findings of the study, it was seen
in the results of the analysis that the STEM approach contributed positively to 21st-century skills.
Besides, a significant difference was observed between the pre-test and post-test in five subdimensions in the scale. However, in the results of the interviews, it was stated that the students
were enjoyable to study with STEM, increased communication within the group, and encouraged
the student to research and think. It was also observed that some students had difficulties during
the application, complained about the lack of time, and had difficulty in designing |
| Recommendation of a New Device for Calculation of Non-Planning Areas | Author : Ferhat Toslak , Mahmut Sari , Emrah Aydemir and Yilmaz Altun | Abstract | Full Text | Abstract :Area calculation is frequently used in engineering areas as well as especially in
the construction sector. It is used in the effectiveness and efficiency research of companies, in
the design and management of work areas and warehouses. In the marketing sector, it is used to
deliver independent areas. The success of the delivery process is measured by customer
satisfaction. In engineering services, area calculation is frequently used during the design phase.
The designs of logistics storage areas and residential independent areas can be exemplified in
the design of independent area. It is very important to calculate the right area when making these
designs. Large area calculation devices are used in geographical area calculations and the
appearance of historical monuments of restoration works. Laser scanners, drones and drones are
used in the app. It is not appropriate to use these devices in small areas, such as specified areas.
It is more suitable to use devices that measure single-axis length in the account of independent
areas of industrial and residential structures. The simple area account is multiplied by data from
two axis measurements. Individual measurement and calculation errors occur in manual
measurements. Mistakes made in the production process cause serious economic problems. At
the same time, companies suffer from prestige losses. A system is needed to eliminate these
errors. For this reason, the idea of designing a device that can measure and calculate with a multiaxis measurement has emerged. Measuring, mapping and calculating planar and non-planar
independent areas can be made with the developed device. Thus, practical and accurate
calculation and mapping can be done at low cost. The laser distance sensor connected to the
microcontroller is made with the help of a stepper motor and an area account with 360° scanning
of the area. 20 different areas were calculated both by making a single-axis measurement and
with the help of the device. These calculations were compared with single-axis measurements
made with the help of civil engineers and error rates were obtained. As a result of the study, it
was observed that the device made measurements with an average error of 3.64%. The lowest
error rate was 1.50%, while the highest error rate was 6.04%. It is thought that better results will
be achieved by using different equipment and methods in the design of the device. It is believed
that it has the potential to pave the way for work to be done in many areas |
| Recommendation of a New Device for Calculation of Non-Planning Areas | Author : Ferhat Toslak , Mahmut Sari , Emrah Aydemir and Yilmaz Altun | Abstract | Full Text | Abstract :Area calculation is frequently used in engineering areas as well as especially in
the construction sector. It is used in the effectiveness and efficiency research of companies, in
the design and management of work areas and warehouses. In the marketing sector, it is used to
deliver independent areas. The success of the delivery process is measured by customer
satisfaction. In engineering services, area calculation is frequently used during the design phase.
The designs of logistics storage areas and residential independent areas can be exemplified in
the design of independent area. It is very important to calculate the right area when making these
designs. Large area calculation devices are used in geographical area calculations and the
appearance of historical monuments of restoration works. Laser scanners, drones and drones are
used in the app. It is not appropriate to use these devices in small areas, such as specified areas.
It is more suitable to use devices that measure single-axis length in the account of independent
areas of industrial and residential structures. The simple area account is multiplied by data from
two axis measurements. Individual measurement and calculation errors occur in manual
measurements. Mistakes made in the production process cause serious economic problems. At
the same time, companies suffer from prestige losses. A system is needed to eliminate these
errors. For this reason, the idea of designing a device that can measure and calculate with a multiaxis measurement has emerged. Measuring, mapping and calculating planar and non-planar
independent areas can be made with the developed device. Thus, practical and accurate
calculation and mapping can be done at low cost. The laser distance sensor connected to the
microcontroller is made with the help of a stepper motor and an area account with 360° scanning
of the area. 20 different areas were calculated both by making a single-axis measurement and
with the help of the device. These calculations were compared with single-axis measurements
made with the help of civil engineers and error rates were obtained. As a result of the study, it
was observed that the device made measurements with an average error of 3.64%. The lowest
error rate was 1.50%, while the highest error rate was 6.04%. It is thought that better results will
be achieved by using different equipment and methods in the design of the device. It is believed
that it has the potential to pave the way for work to be done in many areas |
| Emotion Recognition Based on Interval Type-2 Fuzzy Logic from Facial Expression | Author : Mahmut Dirik , Oscar Castillo , A. Fatih Kocamaz | Abstract | Full Text | Abstract :Automatic recognition of facial emotion plays an effective and important role in
Human–Computer Interaction (HCI). There are various emotion recognition approaches have
been proposed in the literature. The analytic face model consisted of a 26-dimensional geometric
feature vector. These properties are used effectively to identify facial changes resulting from
different expressions. The variation and uncertainties of these features make the emotion
recognition problem more complicated. For decreasing these complications, we propose a
distance-based clustering and uncertainty measures of the base new method for Emotion
Recognition from Facial Expression using automatically selects 19 diagnostics of Action Units
(AUs) in a 2D facial image using Type-2 Fuzzy inference system. The proposed system includes
an automated generation scheme of the geometric facial feature vector. The proposed system has
classified six facial expressions using the MUG Facial Expression database. The experimental
results show that the proposed model is very efficient in uncertainty management policy and
recognizes six basic emotions with an average precision rate of 86.175%. |
| Global Vision Based Path Planning for AVGs Using A* Algorithm | Author : Mahmut Dirik , A. Fatih Kocamaz | Abstract | Full Text | Abstract :One of the most studied problems in robotics is robot path planning. Many
strategies have been invented. Image processing and machine vision technology also have been
utilized in this regard. Studies are still underway to improve path planning methods. This paper
proposes an implementing visual servoing-based technique using the A* algorithm to achieve
efficient searching capabilities of path planning in complicated maps with a combination of
LabVIEW and MATLAB software. The proposed algorithm is divided into three parts. Firstly,
the environment model or robot motion environment is conducted. In this stage, the visual
information extracted from a single ceiled camera. Secondly, the position and orientation of the
objects (robot, obstacles etc.) under the visibility of the camera are generated from visual
information. Thirdly, the A* algorithm is used as a path planning method. This algorithm is not
guaranteed the generated path to be safe and desirable with obstacle-free. To solve this problem
image processing techniques are utilized. This gives an effective improvement and high
performance to A* in a complex environment and gives a safe path as a comparison to the
traditional version of A*. The experimental results, considering the optimal path lengths and
execution time, show that the proposed design is more effective and faster to generate the shortest
path. |
| The effect of STEM application on 21st-century skills of middle school students and student experiences | Author : Mehmet Yavuz , Mehmet Hasançebi , and Funda Yesildag Hasançebi | Abstract | Full Text | Abstract :This study aims to reveal the effect of the STEM approach on 21st-century skills
of middle school students and to determine their experiences about STEM. This application,
which lasted 6 weeks with 7th-grade students, was realized with 35 students. In the study, by
using the explanatory mixed-method, firstly, quantitative data was taken and qualitative data
were tried to be explained. In the first stage of the study, the pre-test and post-test results were
examined in the group by using a dependent group t-test. “Multidimensional 21st Century Skills
Scale” was used as a pre-test and post-test tool. In the second stage of the study, student
experiences for STEM applications were revealed using the semi-structured interview form,
which is one of the qualitative data collection methods. In the findings of the study, it was seen
in the results of the analysis that the STEM approach contributed positively to 21st-century skills.
Besides, a significant difference was observed between the pre-test and post-test in five subdimensions in the scale. However, in the results of the interviews, it was stated that the students
were enjoyable to study with STEM, increased communication within the group, and encouraged
the student to research and think. It was also observed that some students had difficulties during
the application, complained about the lack of time, and had difficulty in designing.
|
| Recommendation of a New Device for Calculation of Non-Planning Areas | Author : Ferhat Toslak , Mahmut Sari , Emrah Aydemir and Yilmaz Altun | Abstract | Full Text | Abstract :Area calculation is frequently used in engineering areas as well as especially in
the construction sector. It is used in the effectiveness and efficiency research of companies, in
the design and management of work areas and warehouses. In the marketing sector, it is used to
deliver independent areas. The success of the delivery process is measured by customer
satisfaction. In engineering services, area calculation is frequently used during the design phase.
The designs of logistics storage areas and residential independent areas can be exemplified in
the design of independent area. It is very important to calculate the right area when making these
designs. Large area calculation devices are used in geographical area calculations and the
appearance of historical monuments of restoration works. Laser scanners, drones and drones are
used in the app. It is not appropriate to use these devices in small areas, such as specified areas.
It is more suitable to use devices that measure single-axis length in the account of independent
areas of industrial and residential structures. The simple area account is multiplied by data from
two axis measurements. Individual measurement and calculation errors occur in manual
measurements. Mistakes made in the production process cause serious economic problems. At
the same time, companies suffer from prestige losses. A system is needed to eliminate these
errors. For this reason, the idea of designing a device that can measure and calculate with a multiaxis measurement has emerged. Measuring, mapping and calculating planar and non-planar
independent areas can be made with the developed device. Thus, practical and accurate
calculation and mapping can be done at low cost. The laser distance sensor connected to the
microcontroller is made with the help of a stepper motor and an area account with 360° scanning
of the area. 20 different areas were calculated both by making a single-axis measurement and
with the help of the device. These calculations were compared with single-axis measurements
made with the help of civil engineers and error rates were obtained. As a result of the study, it
was observed that the device made measurements with an average error of 3.64%. The lowest
error rate was 1.50%, while the highest error rate was 6.04%. It is thought that better results will
be achieved by using different equipment and methods in the design of the device. It is believed
that it has the potential to pave the way for work to be done in many areas. |
| Solving Multidimensional Knapsack Problem with Bayesian Multiploid Genetic Algorithm | Author : Emrullah Gazioglu | Abstract | Full Text | Abstract :Solving optimization problems is still a big challenge in the area of optimization
algorithms. Many proposed algorithms in the literature don’t consider the relations
between the variables of the nature of the problem. However, a recently published
algorithm, called “Bayesian Multiploid Genetic Algorithm” exploits the relations
between the variables and then solves the given problem. It also uses more than one
genotype unlike the simple Genetic Algorithm (GA) and it acts like an implicit memory
in order to remember the old but good solutions. In this work, the well-known
Multidimensional Knapsack Problem (MKP) is solved by the Bayesian Multiploid
Genetic Algorithm. And the results show that exploiting relations between the variables
gets a huge advantage in solving the given problem. |
|
|