Sefer kurnaz | Altınbaş University (original) (raw)

Papers by Sefer kurnaz

Research paper thumbnail of Deep Learning Based COVID-19 Detection via Hard Voting Ensemble Method

Wireless Personal Communications

Healthcare systems throughout the world are under a great deal of strain because to the continuin... more Healthcare systems throughout the world are under a great deal of strain because to the continuing COVID-19 epidemic, making early and precise diagnosis critical for limiting the virus's propagation and efficiently treating victims. The utilization of medical imaging methods like X-rays can help to speed up the diagnosis procedure. Which can offer valuable insights into the virus's existence in the lungs. We present a unique ensemble approach to identify COVID-19 using X-ray pictures (X-ray-PIC) in this paper. The suggested approach, based on hard voting, combines the confidence scores of three classic deep learning models: CNN, VGG16, and DenseNet. We also apply transfer learning to enhance performance on small medical image datasets. Experiments indicate that the suggested strategy outperforms current techniques with a 97% accuracy, a 96% precision, a 100% recall, and a 98% F1-score.These results demonstrate the effectiveness of using ensemble approaches and COVID-19 transfer-learning diagnosis using X-ray-PIC, which could greatly aid in early detection and reducing the burden on global health systems.

Research paper thumbnail of Regional Cooperation in Space Science and Technology for Sustainable Development

2007 3rd International Conference on Recent Advances in Space Technologies, 2007

A joining to the EuASA of other countries of the Caspian - Black - Mediterranean seas region can ... more A joining to the EuASA of other countries of the Caspian - Black - Mediterranean seas region can be highly encouraged. There is the signed "Memorandum of Understanding between Romanian Space Agency and Azerbaijan National Aerospace Agency" for cooperation in the exploration and use of outer space for peaceful purposes. This issue is the positive aspect for establishment cooperative relationships

Research paper thumbnail of RETRACTED ARTICLE: Novel method for diagnosis diseases using advanced high-performance machine learning system

Research paper thumbnail of Binary Error and a three-level division multiplexing Dispersion analysis of a rat optical fibre communication system

2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

Research paper thumbnail of Detecting and Classifying Drug Interaction using Data mining Techniques

2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Oct 20, 2022

Research paper thumbnail of Study for Buildings with IoT System for Energy Management

2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

Research paper thumbnail of Fusing network traffic features with host traffic features for an improved 5G network intrusion detection system

Research paper thumbnail of Lise Öğrencilerinin Akademik Başarıya Ulaşma Davranışlarının Veri Madenciliği Yöntemleri ile İncelenmesi

Istanbul University - DergiPark, Jun 30, 2020

This research presents an applied study of the field of knowledge discovery of educational data u... more This research presents an applied study of the field of knowledge discovery of educational data using data mining techniques, focusing on the development of teaching and learning, by discovering the main patterns of testing the data of the academic student of the intermediate level (baccalaureate) in Baghdad-Iraq, from 2010 to 2019 to get results on the Academic Performance Index. In this study, we discover some major patterns data, Some of this patterns association exists between student changed summation and the student gain level for some subjects, also the relation between summation degrees with degree gained from some subject. This research attempts to read this result and interpretation, supply and verification level and its type to supply to the ministry decision-maker. We choose data mining technique because it's better to use the benefit of quantity data; we use a different way from data mining technique to support discovery result clusters using (k-means) and classification use a decision tree, after first pre-processing data for database and restriction like logical data warehouse shape, we use k-means algorithm of clusters technique and (J48) algorithm of the classification technique of the decision tree, this different way and algorithms application through WEKA tool, which supports more algorithms and way of data mining Last deductive abstract and suggests some recommendation which interest for the decision-maker. Results from this research built a logical data warehouse & applying the algorithm of data mining's algorithm, besides the difficulties of some subjects which may form its tough words or other disqualification planning

Research paper thumbnail of Object oriented programming in the computer science curriculum (panel session)

ACM SIGCSE Bulletin, 1990

As object-oriented programming becomes a mainstream technology, instructors are wrestling with ho... more As object-oriented programming becomes a mainstream technology, instructors are wrestling with how to incorporate it into the Computer Science curriculum. In what ways does teaching object-oriented techniques differ from teaching procedural programming? What are the barriers for both professors and students encountering object-oriented programming for the first time? Where does object-oriented programming belong in the Computer Science curriculum? This panel will address these questions from the perspective of two panelists who have been working with and teaching object-oriented programming for many years and two panelists who have begun working with object-oriented techniques quite recently. The panelists are: .

Research paper thumbnail of A Framework for Reactive Motion and Sensing Planning: A Critical Events-Based Approach

Lecture Notes in Computer Science, 2005

We propose a framework for reactive motion and sensing planning based on critical events. A criti... more We propose a framework for reactive motion and sensing planning based on critical events. A critical event amounts to crossing a critical curve, which divides the environment. We have applied our approach to two different problems: i) object finding and ii) pursuit-evasion. We claim that the proposed framework is in general useful for reactive motion planning based on information provided by sensors. We generalize and formalize the approach and suggest other possible applications.

Research paper thumbnail of Monitoring of the linear infrastructure: Environmental and social impacts

International Conference on Recent Advances in Space Technologies, 2009

The use of advanced technologies is available to enhance planning, design, management, operation ... more The use of advanced technologies is available to enhance planning, design, management, operation and maintenance of the linear infrastructure. Aerial and satellite data based on the remote sensing methods with further integration to GIS technologies represent the area of rapid responds and developments which can be leveraged to assist the linear systems risk assessment to assure the safety of linear

Research paper thumbnail of Internet of Things: Security Threats and Proposed Solutions

2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)

Research paper thumbnail of Establishing Point to Point Connections Among IoT Devices Over the Internet

The rapid growth in the number of devices connected to the internet, other than computers, has pr... more The rapid growth in the number of devices connected to the internet, other than computers, has proposed the Internet of Things (IoT) era. These devices make use of the high availability of internet connection to interchange data that enables them of achieving their tasks. However, as these devices usually belong to private networks, with private Internet Protocol (IP) addresses, it is not possible to reach these devices from outside their networks. To overcome this limitation, relay servers are used with public IP address to act like a midpoint in the communications among the IoT devices. This approach increases the path that the data travels through, from one IoT device to another, which increases the time required to reach the destination device and the power consumption at these devices, in addition to the security threat the extension of the path poses to the communications. In this study, a new approach is proposed to establish a direct connection between any two IoT device, us...

Research paper thumbnail of Creating and Applying a Model for Human Resources Candidate Selection System by Using a Fuzzy Database and Fuzzy Queries

Journal of Aeronautics and Space Technologies, 2011

Retreieving the desired data accurately and quickly is as important as keeping it in an orderly m... more Retreieving the desired data accurately and quickly is as important as keeping it in an orderly manner. In database systems, data can be accessed by crisp queries. However, by nature, the user does not always use crisp queries. This leads to retrieval of redundant data for the queries. In nature, not everything is built upon exact values and thus needs flexibility. The subjective change of the data from one individual to another makes the query process harder. Thus, there is always a need for flexible query systems. Fuzzy queries and fuzzy databases give us the required flexibility. In this study, a human resources evaluation system was developed into a more flexible one by applying fuzzy databases and fuzzy queries. This is a hard subject to resolve by using crisp data. The data entered into the knowledge base was evaluated through the rule bases that were created and reporting with desired flexibity was achieved.

Research paper thumbnail of Unmanned Ground Vehicle Navigation with Sectoral Grid Based Axising Method and Genetic Algorithms

Journal of Aeronautics and Space Technologies, 2009

In this study, autonomous navigation of an Unmanned Ground Vehicle moving in an unknown environme... more In this study, autonomous navigation of an Unmanned Ground Vehicle moving in an unknown environment is realized with Genetic Algorithms using Sectoral Grid Based Axising Method. For the algorithm, three dimensional environment is reduced to two dimensional numerical matrix. Terrain structure as well as obstacles are mapped one to oneon to the matrix. Coding is based upon modularity for integrating real sensing and localization inputs into the matrix including error rates. Mathematical formulization is build over Cartesian Coordinate System for computational simplicity. Simulations are made in intense obstacle and severe terrain conditions. The algorithm?s performance is tested and the results are discussed.

Research paper thumbnail of Hybrid Datamining Approaches to Predict Success of Bank Telemarketing

Telemarketing is a kind of straightforward marketing in which salesman requests the consumer eith... more Telemarketing is a kind of straightforward marketing in which salesman requests the consumer either face to face or telephone request and influence him to purchase the product. Telemarketing achieves most prevalence in the 20th century and still increasing it. Now, the phone has been broadly accepted. It is valued efficient and holds the consumers up to date. In the Banking area, marketing is the backbone to exchange its goods or service. Business promotion and marketing is frequently based on an exhaustive understanding of actual information about the market and the real client demands for the productive bank manner. We recommend a data mining (DM) method to foretell the achievement of telemarketing requests for contracting long-term bank deposits. A local Portuguese bank was labeled, with data gathered from 2011 to 2016, thus involving the effects of the current economic crisis. We examined a comprehensive set of 11 features associated with bank consumer, goods and social-economic...

Research paper thumbnail of Energy Efficient Routing Protocol for IoT Networks Using Ns2 Simulation

Journal of Communications

Limited power, poor memory, and low computing capabilities make the Internet of Things (IoT) devi... more Limited power, poor memory, and low computing capabilities make the Internet of Things (IoT) devices resource restricted. Extending the network lifetime is one of the critical objectives in IoT. When it comes to preserving energy in a smart city, routing is one of the most critical factors. Designing an energy-efficient routing protocol boosts energy utilization to a significant extent. Networks with Reduced Power and Loss, the Energy Aware Routing Protocol for the IoT, decreases network traffic and extends network lifespan. As a result, routing variables such as load, remaining energy, and predicted transmission count identify the optimum parent for data transfer. The data traffic is dispersed throughout the network because it considers the load routing measure during route construction. As a result, it enhances network lifetime and achieves a high packet delivery ratio.

Research paper thumbnail of Advances of Space Technology in Geotechnical Studies

Geographical Information Systems (GIS) is the technology where geospatial data can be represented... more Geographical Information Systems (GIS) is the technology where geospatial data can be represented in the graphic form integrated into the geotechnical, geologic and hydrologic information routinely used by geotechnical engineers. A GIS makes available a wide of forms of spatial data to be integrated, selected and sorted with any number of physical, chemical or any possible environmental factors.

Research paper thumbnail of Real Estate Price Range Prediction Using Artificial Neural Network And Grey Wolf Optimizer

2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

Real estate market price prediction is less popular than the stock market prediction and other br... more Real estate market price prediction is less popular than the stock market prediction and other branches of sales markets, however, there’s evidence that the real-estate market is growing substantially out of proportions, and this lack of knowledge is a setback to understanding the elements that effect the real-estate market behaviors, and the relationship between these elements and the market prices. In this paper we propose a Deep learning scheme for predicting the housing market prices by using an artificial neural network and a grey wolf optimizer, we use data collected from 1.2 million leased property listing recorded over the course of two months, and we train our hybrid ANN-GWO algorithm to analyze the data through a generalized linear regression and predict the market prices, then we evaluate our method by using the MSE and Accuracy indexes and find that our method have a 98.7951% accuracy rate with very low MSE, we also find that the accuracy of our model can be increased by increasing the number of neurons.

Research paper thumbnail of Robot Localization and Trajectory Planning Using ANN

2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)

Research paper thumbnail of Deep Learning Based COVID-19 Detection via Hard Voting Ensemble Method

Wireless Personal Communications

Healthcare systems throughout the world are under a great deal of strain because to the continuin... more Healthcare systems throughout the world are under a great deal of strain because to the continuing COVID-19 epidemic, making early and precise diagnosis critical for limiting the virus's propagation and efficiently treating victims. The utilization of medical imaging methods like X-rays can help to speed up the diagnosis procedure. Which can offer valuable insights into the virus's existence in the lungs. We present a unique ensemble approach to identify COVID-19 using X-ray pictures (X-ray-PIC) in this paper. The suggested approach, based on hard voting, combines the confidence scores of three classic deep learning models: CNN, VGG16, and DenseNet. We also apply transfer learning to enhance performance on small medical image datasets. Experiments indicate that the suggested strategy outperforms current techniques with a 97% accuracy, a 96% precision, a 100% recall, and a 98% F1-score.These results demonstrate the effectiveness of using ensemble approaches and COVID-19 transfer-learning diagnosis using X-ray-PIC, which could greatly aid in early detection and reducing the burden on global health systems.

Research paper thumbnail of Regional Cooperation in Space Science and Technology for Sustainable Development

2007 3rd International Conference on Recent Advances in Space Technologies, 2007

A joining to the EuASA of other countries of the Caspian - Black - Mediterranean seas region can ... more A joining to the EuASA of other countries of the Caspian - Black - Mediterranean seas region can be highly encouraged. There is the signed "Memorandum of Understanding between Romanian Space Agency and Azerbaijan National Aerospace Agency" for cooperation in the exploration and use of outer space for peaceful purposes. This issue is the positive aspect for establishment cooperative relationships

Research paper thumbnail of RETRACTED ARTICLE: Novel method for diagnosis diseases using advanced high-performance machine learning system

Research paper thumbnail of Binary Error and a three-level division multiplexing Dispersion analysis of a rat optical fibre communication system

2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

Research paper thumbnail of Detecting and Classifying Drug Interaction using Data mining Techniques

2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Oct 20, 2022

Research paper thumbnail of Study for Buildings with IoT System for Energy Management

2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

Research paper thumbnail of Fusing network traffic features with host traffic features for an improved 5G network intrusion detection system

Research paper thumbnail of Lise Öğrencilerinin Akademik Başarıya Ulaşma Davranışlarının Veri Madenciliği Yöntemleri ile İncelenmesi

Istanbul University - DergiPark, Jun 30, 2020

This research presents an applied study of the field of knowledge discovery of educational data u... more This research presents an applied study of the field of knowledge discovery of educational data using data mining techniques, focusing on the development of teaching and learning, by discovering the main patterns of testing the data of the academic student of the intermediate level (baccalaureate) in Baghdad-Iraq, from 2010 to 2019 to get results on the Academic Performance Index. In this study, we discover some major patterns data, Some of this patterns association exists between student changed summation and the student gain level for some subjects, also the relation between summation degrees with degree gained from some subject. This research attempts to read this result and interpretation, supply and verification level and its type to supply to the ministry decision-maker. We choose data mining technique because it's better to use the benefit of quantity data; we use a different way from data mining technique to support discovery result clusters using (k-means) and classification use a decision tree, after first pre-processing data for database and restriction like logical data warehouse shape, we use k-means algorithm of clusters technique and (J48) algorithm of the classification technique of the decision tree, this different way and algorithms application through WEKA tool, which supports more algorithms and way of data mining Last deductive abstract and suggests some recommendation which interest for the decision-maker. Results from this research built a logical data warehouse & applying the algorithm of data mining's algorithm, besides the difficulties of some subjects which may form its tough words or other disqualification planning

Research paper thumbnail of Object oriented programming in the computer science curriculum (panel session)

ACM SIGCSE Bulletin, 1990

As object-oriented programming becomes a mainstream technology, instructors are wrestling with ho... more As object-oriented programming becomes a mainstream technology, instructors are wrestling with how to incorporate it into the Computer Science curriculum. In what ways does teaching object-oriented techniques differ from teaching procedural programming? What are the barriers for both professors and students encountering object-oriented programming for the first time? Where does object-oriented programming belong in the Computer Science curriculum? This panel will address these questions from the perspective of two panelists who have been working with and teaching object-oriented programming for many years and two panelists who have begun working with object-oriented techniques quite recently. The panelists are: .

Research paper thumbnail of A Framework for Reactive Motion and Sensing Planning: A Critical Events-Based Approach

Lecture Notes in Computer Science, 2005

We propose a framework for reactive motion and sensing planning based on critical events. A criti... more We propose a framework for reactive motion and sensing planning based on critical events. A critical event amounts to crossing a critical curve, which divides the environment. We have applied our approach to two different problems: i) object finding and ii) pursuit-evasion. We claim that the proposed framework is in general useful for reactive motion planning based on information provided by sensors. We generalize and formalize the approach and suggest other possible applications.

Research paper thumbnail of Monitoring of the linear infrastructure: Environmental and social impacts

International Conference on Recent Advances in Space Technologies, 2009

The use of advanced technologies is available to enhance planning, design, management, operation ... more The use of advanced technologies is available to enhance planning, design, management, operation and maintenance of the linear infrastructure. Aerial and satellite data based on the remote sensing methods with further integration to GIS technologies represent the area of rapid responds and developments which can be leveraged to assist the linear systems risk assessment to assure the safety of linear

Research paper thumbnail of Internet of Things: Security Threats and Proposed Solutions

2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)

Research paper thumbnail of Establishing Point to Point Connections Among IoT Devices Over the Internet

The rapid growth in the number of devices connected to the internet, other than computers, has pr... more The rapid growth in the number of devices connected to the internet, other than computers, has proposed the Internet of Things (IoT) era. These devices make use of the high availability of internet connection to interchange data that enables them of achieving their tasks. However, as these devices usually belong to private networks, with private Internet Protocol (IP) addresses, it is not possible to reach these devices from outside their networks. To overcome this limitation, relay servers are used with public IP address to act like a midpoint in the communications among the IoT devices. This approach increases the path that the data travels through, from one IoT device to another, which increases the time required to reach the destination device and the power consumption at these devices, in addition to the security threat the extension of the path poses to the communications. In this study, a new approach is proposed to establish a direct connection between any two IoT device, us...

Research paper thumbnail of Creating and Applying a Model for Human Resources Candidate Selection System by Using a Fuzzy Database and Fuzzy Queries

Journal of Aeronautics and Space Technologies, 2011

Retreieving the desired data accurately and quickly is as important as keeping it in an orderly m... more Retreieving the desired data accurately and quickly is as important as keeping it in an orderly manner. In database systems, data can be accessed by crisp queries. However, by nature, the user does not always use crisp queries. This leads to retrieval of redundant data for the queries. In nature, not everything is built upon exact values and thus needs flexibility. The subjective change of the data from one individual to another makes the query process harder. Thus, there is always a need for flexible query systems. Fuzzy queries and fuzzy databases give us the required flexibility. In this study, a human resources evaluation system was developed into a more flexible one by applying fuzzy databases and fuzzy queries. This is a hard subject to resolve by using crisp data. The data entered into the knowledge base was evaluated through the rule bases that were created and reporting with desired flexibity was achieved.

Research paper thumbnail of Unmanned Ground Vehicle Navigation with Sectoral Grid Based Axising Method and Genetic Algorithms

Journal of Aeronautics and Space Technologies, 2009

In this study, autonomous navigation of an Unmanned Ground Vehicle moving in an unknown environme... more In this study, autonomous navigation of an Unmanned Ground Vehicle moving in an unknown environment is realized with Genetic Algorithms using Sectoral Grid Based Axising Method. For the algorithm, three dimensional environment is reduced to two dimensional numerical matrix. Terrain structure as well as obstacles are mapped one to oneon to the matrix. Coding is based upon modularity for integrating real sensing and localization inputs into the matrix including error rates. Mathematical formulization is build over Cartesian Coordinate System for computational simplicity. Simulations are made in intense obstacle and severe terrain conditions. The algorithm?s performance is tested and the results are discussed.

Research paper thumbnail of Hybrid Datamining Approaches to Predict Success of Bank Telemarketing

Telemarketing is a kind of straightforward marketing in which salesman requests the consumer eith... more Telemarketing is a kind of straightforward marketing in which salesman requests the consumer either face to face or telephone request and influence him to purchase the product. Telemarketing achieves most prevalence in the 20th century and still increasing it. Now, the phone has been broadly accepted. It is valued efficient and holds the consumers up to date. In the Banking area, marketing is the backbone to exchange its goods or service. Business promotion and marketing is frequently based on an exhaustive understanding of actual information about the market and the real client demands for the productive bank manner. We recommend a data mining (DM) method to foretell the achievement of telemarketing requests for contracting long-term bank deposits. A local Portuguese bank was labeled, with data gathered from 2011 to 2016, thus involving the effects of the current economic crisis. We examined a comprehensive set of 11 features associated with bank consumer, goods and social-economic...

Research paper thumbnail of Energy Efficient Routing Protocol for IoT Networks Using Ns2 Simulation

Journal of Communications

Limited power, poor memory, and low computing capabilities make the Internet of Things (IoT) devi... more Limited power, poor memory, and low computing capabilities make the Internet of Things (IoT) devices resource restricted. Extending the network lifetime is one of the critical objectives in IoT. When it comes to preserving energy in a smart city, routing is one of the most critical factors. Designing an energy-efficient routing protocol boosts energy utilization to a significant extent. Networks with Reduced Power and Loss, the Energy Aware Routing Protocol for the IoT, decreases network traffic and extends network lifespan. As a result, routing variables such as load, remaining energy, and predicted transmission count identify the optimum parent for data transfer. The data traffic is dispersed throughout the network because it considers the load routing measure during route construction. As a result, it enhances network lifetime and achieves a high packet delivery ratio.

Research paper thumbnail of Advances of Space Technology in Geotechnical Studies

Geographical Information Systems (GIS) is the technology where geospatial data can be represented... more Geographical Information Systems (GIS) is the technology where geospatial data can be represented in the graphic form integrated into the geotechnical, geologic and hydrologic information routinely used by geotechnical engineers. A GIS makes available a wide of forms of spatial data to be integrated, selected and sorted with any number of physical, chemical or any possible environmental factors.

Research paper thumbnail of Real Estate Price Range Prediction Using Artificial Neural Network And Grey Wolf Optimizer

2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

Real estate market price prediction is less popular than the stock market prediction and other br... more Real estate market price prediction is less popular than the stock market prediction and other branches of sales markets, however, there’s evidence that the real-estate market is growing substantially out of proportions, and this lack of knowledge is a setback to understanding the elements that effect the real-estate market behaviors, and the relationship between these elements and the market prices. In this paper we propose a Deep learning scheme for predicting the housing market prices by using an artificial neural network and a grey wolf optimizer, we use data collected from 1.2 million leased property listing recorded over the course of two months, and we train our hybrid ANN-GWO algorithm to analyze the data through a generalized linear regression and predict the market prices, then we evaluate our method by using the MSE and Accuracy indexes and find that our method have a 98.7951% accuracy rate with very low MSE, we also find that the accuracy of our model can be increased by increasing the number of neurons.

Research paper thumbnail of Robot Localization and Trajectory Planning Using ANN

2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)