Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090235
Utku Kose, P. Vasant
As a result of unstoppable rise of Artificial Intelligence, there has been a remarkable focus on the question of “Will intelligent systems be safe for humankind of the future?” Because of that, many researchers have started to direct their works on dealing with problems that may cause problems on enabling Artificial Intelligence systems to behave out of control or take positions dangerous for humans. Such research works are currently included under the literature of Artificial Intelligence Safety and / or Future of Artificial Intelligence. In the context of the explanations, this research paper proposes a theory on achieving safe intelligent systems by considering life-time of an Artificial Intelligence based system according to some operational variables and eliminate – terminate an intelligent system, which is ‘old enough' to operate for giving chance to new generations of systems, which seem safer. The paper makes a brief introduction to the theory and opens doors widely for further research on it.
{"title":"Fading intelligence theory: A theory on keeping artificial intelligence safety for the future","authors":"Utku Kose, P. Vasant","doi":"10.1109/IDAP.2017.8090235","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090235","url":null,"abstract":"As a result of unstoppable rise of Artificial Intelligence, there has been a remarkable focus on the question of “Will intelligent systems be safe for humankind of the future?” Because of that, many researchers have started to direct their works on dealing with problems that may cause problems on enabling Artificial Intelligence systems to behave out of control or take positions dangerous for humans. Such research works are currently included under the literature of Artificial Intelligence Safety and / or Future of Artificial Intelligence. In the context of the explanations, this research paper proposes a theory on achieving safe intelligent systems by considering life-time of an Artificial Intelligence based system according to some operational variables and eliminate – terminate an intelligent system, which is ‘old enough' to operate for giving chance to new generations of systems, which seem safer. The paper makes a brief introduction to the theory and opens doors widely for further research on it.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126789476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090304
Ismail Karadogan, Resul Das, A. Karcı
In this paper, two different packet timing and IP ID based network steganography approaches have been proposed to provide confidential transmission of information. In the proposed packet timing approach, it is seen that the bandwidth is higher than the previous methods. The proposed IP ID field based approach has been found to be more effective than previous methods in ensuring the uniqueness of the ID field and is suitable for sending confidential data over the Internet. In addition, comprehensive information on this study was presented by examining methods of information hiding, hidden channels and secret data transmission in the network environment.
{"title":"Novel network steganography approaches for confidential transmission of information","authors":"Ismail Karadogan, Resul Das, A. Karcı","doi":"10.1109/IDAP.2017.8090304","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090304","url":null,"abstract":"In this paper, two different packet timing and IP ID based network steganography approaches have been proposed to provide confidential transmission of information. In the proposed packet timing approach, it is seen that the bandwidth is higher than the previous methods. The proposed IP ID field based approach has been found to be more effective than previous methods in ensuring the uniqueness of the ID field and is suitable for sending confidential data over the Internet. In addition, comprehensive information on this study was presented by examining methods of information hiding, hidden channels and secret data transmission in the network environment.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124248663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090166
M. Altun, İbrahim Karteri, M. Güneş
Following the rapid development of technology, various electrical and electronic devices have been a great part of life day by day due to make human life easier and comfortable. However, they emit electromagnetic radiations causing the electromagnetic pollution. Depending on this role, electromagnetic pollution becomes a crucial problem for humanity, environment, and negatively effected the performance of electronic devices because of the electromagnetic interference. In order to prevent the unwanted signals, we have produced a graphene based polymer composites (light weight, strong, flexible), graphene/wood-plastic (G/WP), as a shielding material and investigated its electromagnetic interference shielding effectiveness (EMI SE). Four combination of G/WP is observed with different (% 0, % 3, % 6, % 9 wt) graphene rates in 8-9 GHz frequency range. As a result, the shielding success has been attributed to the graphene increase in composite. The results claim that G/WP composites can efficiently take place in electronics technology and electronic protection.
{"title":"A study on EMI shielding effectiveness of graphene based structures","authors":"M. Altun, İbrahim Karteri, M. Güneş","doi":"10.1109/IDAP.2017.8090166","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090166","url":null,"abstract":"Following the rapid development of technology, various electrical and electronic devices have been a great part of life day by day due to make human life easier and comfortable. However, they emit electromagnetic radiations causing the electromagnetic pollution. Depending on this role, electromagnetic pollution becomes a crucial problem for humanity, environment, and negatively effected the performance of electronic devices because of the electromagnetic interference. In order to prevent the unwanted signals, we have produced a graphene based polymer composites (light weight, strong, flexible), graphene/wood-plastic (G/WP), as a shielding material and investigated its electromagnetic interference shielding effectiveness (EMI SE). Four combination of G/WP is observed with different (% 0, % 3, % 6, % 9 wt) graphene rates in 8-9 GHz frequency range. As a result, the shielding success has been attributed to the graphene increase in composite. The results claim that G/WP composites can efficiently take place in electronics technology and electronic protection.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121303717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090224
Bircan Kamislioglu, Ayhan Akbal
In next generation communication systems high data rate, and higher transmission capacity through wireless channel are important for researchers. Filter bank based multicarrier (FBMC) modulation with offset quadrature amplitude modulation (OQAM) makes researchers interested due to its advantages over orthogonal frequency division multiplexing (OFDM). The paper indicates that OFDM, FBMC-QAM, multiple-input multiple output (MIMO) transmission layouts and channel estimation layouts study same logic. Also MIMO receiver design is realized for FBMC such as ZF, MMSE, ML techniques. Finally, FBMC-QAM and OFDM is compared about magnitude response, amplitude of subcarriers in frequency and BER performance and MIMO receiver techniques are compared about SER to SNR.
{"title":"ZF and MMSE application for FBMC-QAM","authors":"Bircan Kamislioglu, Ayhan Akbal","doi":"10.1109/IDAP.2017.8090224","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090224","url":null,"abstract":"In next generation communication systems high data rate, and higher transmission capacity through wireless channel are important for researchers. Filter bank based multicarrier (FBMC) modulation with offset quadrature amplitude modulation (OQAM) makes researchers interested due to its advantages over orthogonal frequency division multiplexing (OFDM). The paper indicates that OFDM, FBMC-QAM, multiple-input multiple output (MIMO) transmission layouts and channel estimation layouts study same logic. Also MIMO receiver design is realized for FBMC such as ZF, MMSE, ML techniques. Finally, FBMC-QAM and OFDM is compared about magnitude response, amplitude of subcarriers in frequency and BER performance and MIMO receiver techniques are compared about SER to SNR.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"80 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116257968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090200
Muhammet Üsame Öziç, Seral Özşen, A. Ekmekci
Examining of progress of diseases that occur in brain using numerical methods is one of the topics of neuroscience researches. One of the developing numerical methods for examinig local and global changes that occur in brain is Voxel Based Morphometry. For examining intragroup and intergroup differences via Voxel Based Morphometry is required to use some preprocessing methods together with statistical tools. In this study, Voxel Based Morphometry method have been examined using labeled Normal Control and Alzheimer Disease. Magnetic Resonanse images were taken from Open Access Series of Imaging Studies database. After examining volumetric differences as statistical that occur in the brain between two groups via Voxel Based Morphometry, it has been mapped on the template atlases.
用数值方法研究脑内疾病的进展是神经科学研究的热点之一。基于体素的形态测量法是研究大脑局部和全局变化的一种发展中的数值方法。基于体素的形态测量法检测组内和组间差异需要使用一些预处理方法和统计工具。在这项研究中,基于体素的形态测量方法已经检查了标记正常对照和阿尔茨海默病。磁共振图像取自开放获取系列成像研究数据库。在通过基于体素的形态测量法(Voxel Based Morphometry)对两组大脑中的体积差异进行统计分析后,它被映射到模板地图集上。
{"title":"Voxel based morphometric analysis on MR images","authors":"Muhammet Üsame Öziç, Seral Özşen, A. Ekmekci","doi":"10.1109/IDAP.2017.8090200","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090200","url":null,"abstract":"Examining of progress of diseases that occur in brain using numerical methods is one of the topics of neuroscience researches. One of the developing numerical methods for examinig local and global changes that occur in brain is Voxel Based Morphometry. For examining intragroup and intergroup differences via Voxel Based Morphometry is required to use some preprocessing methods together with statistical tools. In this study, Voxel Based Morphometry method have been examined using labeled Normal Control and Alzheimer Disease. Magnetic Resonanse images were taken from Open Access Series of Imaging Studies database. After examining volumetric differences as statistical that occur in the brain between two groups via Voxel Based Morphometry, it has been mapped on the template atlases.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121653013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090179
M. Ünalir, Özgü Can, Emine Sezer, Okan Bursa, Handan Ak
The convergence of IoT, cloud computing and big data creates new opportunities for diabetes management. There are many research projects on diabetes management in the literature. They are generally based on web application architectures and rely on traditional data management systems. This paper firstly describes the big data characteristics and then discusses the perspectives of healthcare systems should have. After briefing the requirements of diabetes management in big data era, big data awareness matrix for diabetes management is presented. Existing solutions are revisited in the light of the matrix and a general review of diabetes management is concluded with the convergent technologies.
{"title":"Big data aware diabetes management: Requirements, solutions and reviews","authors":"M. Ünalir, Özgü Can, Emine Sezer, Okan Bursa, Handan Ak","doi":"10.1109/IDAP.2017.8090179","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090179","url":null,"abstract":"The convergence of IoT, cloud computing and big data creates new opportunities for diabetes management. There are many research projects on diabetes management in the literature. They are generally based on web application architectures and rely on traditional data management systems. This paper firstly describes the big data characteristics and then discusses the perspectives of healthcare systems should have. After briefing the requirements of diabetes management in big data era, big data awareness matrix for diabetes management is presented. Existing solutions are revisited in the light of the matrix and a general review of diabetes management is concluded with the convergent technologies.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121964654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090314
N. Nwulu
In this work, an artificial neural network is designed for predicting the heating and cooling loads for buildings. The paper develops two neural models that make use of a dataset with 8 input attributes with the output as a numeric value of the heating and cooling loads of the buildings. The predictive abilities of the neural nets are compared with linear regression under conventional validation, 5-fold validation and 10-fold validation. Obtained results show that both neural models obtain encouraging results and can be dependably deployed in building loads determination.
{"title":"An artificial neural network model for predicting building heating and cooling loads","authors":"N. Nwulu","doi":"10.1109/IDAP.2017.8090314","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090314","url":null,"abstract":"In this work, an artificial neural network is designed for predicting the heating and cooling loads for buildings. The paper develops two neural models that make use of a dataset with 8 input attributes with the output as a numeric value of the heating and cooling loads of the buildings. The predictive abilities of the neural nets are compared with linear regression under conventional validation, 5-fold validation and 10-fold validation. Obtained results show that both neural models obtain encouraging results and can be dependably deployed in building loads determination.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131940903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090170
Korhan Cengiz
Spatial Modulation (SM) which provides to map a block of information bits to a constellation point in the signal domain and a constellation point in the spatial domain is a novel communication technology. It is aimed to use in 5G networks and it becomes popular for researchers each passing day. In this paper, at first, the evolution of SM technology is presented. The promoter technologies for SM are indicated and the fundamental architecture of SM is explained. Finally, the novel studies related with SM are also presented and discussed.
{"title":"Evolution of spatial modulation and reviewing of novel studies","authors":"Korhan Cengiz","doi":"10.1109/IDAP.2017.8090170","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090170","url":null,"abstract":"Spatial Modulation (SM) which provides to map a block of information bits to a constellation point in the signal domain and a constellation point in the spatial domain is a novel communication technology. It is aimed to use in 5G networks and it becomes popular for researchers each passing day. In this paper, at first, the evolution of SM technology is presented. The promoter technologies for SM are indicated and the fundamental architecture of SM is explained. Finally, the novel studies related with SM are also presented and discussed.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130006500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090299
Ersan Yazan, M. F. Talu
The stochastic gradual descent method (SGD) is a popular optimization technique based on updating each θk parameter in the ∂J(θ)/∂θk direction to minimize / maximize the J(θ) cost function. This technique is frequently used in current artificial learning methods such as convolutional learning and automatic encoders. In this study, five different approaches (Momentum, Adagrad, Adadelta, Rmsprop ve Adam) based on SDA used in updating the θ parameters were investigated. By selecting specific test functions, the advantages and disadvantages of each approach are compared with each other in terms of the number of oscillations, the parameter update rate and the minimum cost reached. The comparison results are shown graphically.
{"title":"Comparison of the stochastic gradient descent based optimization techniques","authors":"Ersan Yazan, M. F. Talu","doi":"10.1109/IDAP.2017.8090299","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090299","url":null,"abstract":"The stochastic gradual descent method (SGD) is a popular optimization technique based on updating each θk parameter in the ∂J(θ)/∂θk direction to minimize / maximize the J(θ) cost function. This technique is frequently used in current artificial learning methods such as convolutional learning and automatic encoders. In this study, five different approaches (Momentum, Adagrad, Adadelta, Rmsprop ve Adam) based on SDA used in updating the θ parameters were investigated. By selecting specific test functions, the advantages and disadvantages of each approach are compared with each other in terms of the number of oscillations, the parameter update rate and the minimum cost reached. The comparison results are shown graphically.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134194298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090203
Mehmet Sönmez
The light emitted diode (LED) technology can be used for both data transmission and lighting in Visible Light Communication (VLC) systems. This work presents a new modulator architecture for Overlapping Pulse Position Modulation (OPPM) to provide data transmission by using LEDs. The parameter of OPPM can be changed in modulation process hence the OPPM scheme has an adjustable structure. Additionally, the proposed scheme is implemented on Field Programmable Gate Arrays (FPGA) board. The accuracy of the proposed architecture is shown by observing experimental and simulation results.
{"title":"Overlapping PPM scheme with adjustable parameters for visible light communication systems","authors":"Mehmet Sönmez","doi":"10.1109/IDAP.2017.8090203","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090203","url":null,"abstract":"The light emitted diode (LED) technology can be used for both data transmission and lighting in Visible Light Communication (VLC) systems. This work presents a new modulator architecture for Overlapping Pulse Position Modulation (OPPM) to provide data transmission by using LEDs. The parameter of OPPM can be changed in modulation process hence the OPPM scheme has an adjustable structure. Additionally, the proposed scheme is implemented on Field Programmable Gate Arrays (FPGA) board. The accuracy of the proposed architecture is shown by observing experimental and simulation results.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131648928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}