: In image classification, there are no labeled training instances for some classes, which are therefore called unseen classes or test classes. To classify these classes, zero-shot learning (ZSL) was developed, which typically attempts to learn a mapping from the (visual) feature space to the semantic space in which the classes are represented by a list of semantically meaningful attributes. However, the fact that this mapping is learned without using instances of the test classes affects the performance of ZSL, which is known as the domain shift problem. In this study, we propose to apply the learning vector quantization (LVQ) algorithm in the semantic space once the mapping is determined. First and foremost, this allows us to refine the prototypes of the test classes with respect to the learned mapping, which reduces the effects of the domain shift problem. Secondly, the LVQ algorithm increases the margin of the 1-NN classifier used in ZSL, resulting in better classification. Moreover, for this work, we consider a range of LVQ algorithms, from initial to advanced variants, and applied them to a number of state-of-the-art ZSL methods, then obtained their LVQ extensions. The experiments based on five ZSL benchmark datasets showed that the LVQ-empowered extensions of the ZSL methods are superior to their original counterparts in almost all settings.
{"title":"LVQ Treatment for Zero-Shot Learning","authors":"Firat Ismailoglu","doi":"10.2139/ssrn.4025907","DOIUrl":"https://doi.org/10.2139/ssrn.4025907","url":null,"abstract":": In image classification, there are no labeled training instances for some classes, which are therefore called unseen classes or test classes. To classify these classes, zero-shot learning (ZSL) was developed, which typically attempts to learn a mapping from the (visual) feature space to the semantic space in which the classes are represented by a list of semantically meaningful attributes. However, the fact that this mapping is learned without using instances of the test classes affects the performance of ZSL, which is known as the domain shift problem. In this study, we propose to apply the learning vector quantization (LVQ) algorithm in the semantic space once the mapping is determined. First and foremost, this allows us to refine the prototypes of the test classes with respect to the learned mapping, which reduces the effects of the domain shift problem. Secondly, the LVQ algorithm increases the margin of the 1-NN classifier used in ZSL, resulting in better classification. Moreover, for this work, we consider a range of LVQ algorithms, from initial to advanced variants, and applied them to a number of state-of-the-art ZSL methods, then obtained their LVQ extensions. The experiments based on five ZSL benchmark datasets showed that the LVQ-empowered extensions of the ZSL methods are superior to their original counterparts in almost all settings.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"13 1","pages":"216-237"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80954173","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}
: Retail companies monitor inventory stock levels regularly and manage them based on forecasted sales to sustain their market position. Inventory accuracy, defined as the difference between the warehouse stock records and the actual inventory, is critical for preventing stockouts and shortages. The root causes of inventory inaccuracy are the employee or customer theft, product damage or spoilage, and wrong shipments. In this paper, we aim at detecting inaccurate stocks of one of Turkey’s largest supermarket chain using the variational autoencoder (VAE), which is an unsupervised learning method. Based on the findings, we showed that VAE is able to model the underlying probability distribution of data, regenerate the pattern from time series data, and detect anomalies. Hence, it reduces time and effort to manually label the inaccuracy in data. Since the distribution of inventory data depends on selected product/product categories, we had to use a parametric approach to handle potential differences. For individual products, we built univariate time series, whereas for product categories we built multivariate time series. The experimental results show that the proposed approaches can detect anomalies both in the low and high inventory quantities.
{"title":"Variational autoencoder-based anomaly detection in time series data for inventory record inaccuracy","authors":"Hali̇l Arğun, S. Alptekin","doi":"10.55730/1300-0632.3977","DOIUrl":"https://doi.org/10.55730/1300-0632.3977","url":null,"abstract":": Retail companies monitor inventory stock levels regularly and manage them based on forecasted sales to sustain their market position. Inventory accuracy, defined as the difference between the warehouse stock records and the actual inventory, is critical for preventing stockouts and shortages. The root causes of inventory inaccuracy are the employee or customer theft, product damage or spoilage, and wrong shipments. In this paper, we aim at detecting inaccurate stocks of one of Turkey’s largest supermarket chain using the variational autoencoder (VAE), which is an unsupervised learning method. Based on the findings, we showed that VAE is able to model the underlying probability distribution of data, regenerate the pattern from time series data, and detect anomalies. Hence, it reduces time and effort to manually label the inaccuracy in data. Since the distribution of inventory data depends on selected product/product categories, we had to use a parametric approach to handle potential differences. For individual products, we built univariate time series, whereas for product categories we built multivariate time series. The experimental results show that the proposed approaches can detect anomalies both in the low and high inventory quantities.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"114 1","pages":"163-179"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79343121","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}
: This study performed a deep learning-based classification of chaotic systems over their phase portraits. To the best of the authors’ knowledge, such classification studies over phase portraits have not been conducted in the literature. To that end, a dataset consisting of the phase portraits of the most known two chaotic systems, namely Lorenz and Chen, is generated for different values of the parameters, initial conditions, step size, and time length. Then, a classification with high accuracy is carried out employing transfer learning methods. The transfer learning methods used in the study are SqueezeNet, VGG-19, AlexNet, ResNet50, ResNet101, DenseNet201, ShuffleNet, and GoogLeNet deep learning models. As a result of the study, classification accuracy between 97.4% and 100% for 2-ways classifier and between 83.68% and 99.82% for 3-ways classifier is achieved depending on the problem. Thanks to this, random signals obtained in real life can be associated with a mathematical model.
{"title":"Deep learning-based classification of chaotic systems over phase portraits","authors":"S. Kaçar, Süleyman Uzun, B. Arıcıoğlu","doi":"10.55730/1300-0632.3969","DOIUrl":"https://doi.org/10.55730/1300-0632.3969","url":null,"abstract":": This study performed a deep learning-based classification of chaotic systems over their phase portraits. To the best of the authors’ knowledge, such classification studies over phase portraits have not been conducted in the literature. To that end, a dataset consisting of the phase portraits of the most known two chaotic systems, namely Lorenz and Chen, is generated for different values of the parameters, initial conditions, step size, and time length. Then, a classification with high accuracy is carried out employing transfer learning methods. The transfer learning methods used in the study are SqueezeNet, VGG-19, AlexNet, ResNet50, ResNet101, DenseNet201, ShuffleNet, and GoogLeNet deep learning models. As a result of the study, classification accuracy between 97.4% and 100% for 2-ways classifier and between 83.68% and 99.82% for 3-ways classifier is achieved depending on the problem. Thanks to this, random signals obtained in real life can be associated with a mathematical model.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"212 1","pages":"17-38"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90371305","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}
: Object reidentification (ReID) in cluttered rigid scenes is a challenging problem especially when same-looking objects coexist in the scene. ReID is accepted to be one of the most powerful tools for matching the correct identities to each individual object when issues such as occlusion, missed detections, multiple same-looking objects coexisting in the same scene, and disappearance of objects from the view and/or revisiting the same region arise. We propose a novel framework towards more efficient object ReID, improved object reidentification (IO-ReID), to perform object ReID in challenging scenes with real-time processing in mind. The proposed approach achieves distinctive and efficient object embedding via training with the triplet loss, with input from both the foreground/background split by bounding box, and the full input image. With extensive experiments on two datasets serving for Object ReID, we demonstrate that the proposed method, IO-ReID, obtains a higher ReID accuracy and runs faster compared to the state-of-the-art methods on object ReID.
{"title":"Improved Object Re-Identification via More Efficient Embeddings","authors":"Ertugrul Bayraktar","doi":"10.55730/1300-0632.3984","DOIUrl":"https://doi.org/10.55730/1300-0632.3984","url":null,"abstract":": Object reidentification (ReID) in cluttered rigid scenes is a challenging problem especially when same-looking objects coexist in the scene. ReID is accepted to be one of the most powerful tools for matching the correct identities to each individual object when issues such as occlusion, missed detections, multiple same-looking objects coexisting in the same scene, and disappearance of objects from the view and/or revisiting the same region arise. We propose a novel framework towards more efficient object ReID, improved object reidentification (IO-ReID), to perform object ReID in challenging scenes with real-time processing in mind. The proposed approach achieves distinctive and efficient object embedding via training with the triplet loss, with input from both the foreground/background split by bounding box, and the full input image. With extensive experiments on two datasets serving for Object ReID, we demonstrate that the proposed method, IO-ReID, obtains a higher ReID accuracy and runs faster compared to the state-of-the-art methods on object ReID.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"1 1","pages":"282-294"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90715321","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}
Cahit Berkay Kazangirler, Caner Özcan, Buse Yaren Tekin
: User Interface (UI) is a basic concept in which individuals interact with any computer program or technological device to create a graphical design. In the initial stages of app development, UI prototype is a must. An automatic analysis system for the basic execution of UI designs will considerably speed up the development of designs according to old-fashioned methods. In this approach, it is aimed at saving cost and time by automating the process. For the aforesaid objective, we present a new approach rather than the traditional methods. For this reason, a high amount of elements in wireframes are detected and segmented. Furthermore, with the state-of-the-art methods, one of the machine learning classifiers is expected to give lower performance than deep learning for comparison purposes. In this study, the detection and segmentation of elements, which is the first stage which will eliminate time loss, redundant time, cost, and labor in the communication between designers and front-end developers. To test the classification task of the Mask R-CNN, was designed using transfer learning supported neural networks to compare with other algorithms. As a result, the precision reached 93.15% and the mAP (@IOU > 0.5) reached 96.50%. Then, we improved the algorithm by replacing the convolution blocks in the graphs, adding them, and changing the input units, and the accuracy increased to 98.49%.
{"title":"UIBee: An improved deep instance segmentation and classification of UI elements in wireframes","authors":"Cahit Berkay Kazangirler, Caner Özcan, Buse Yaren Tekin","doi":"10.55730/1300-0632.3999","DOIUrl":"https://doi.org/10.55730/1300-0632.3999","url":null,"abstract":": User Interface (UI) is a basic concept in which individuals interact with any computer program or technological device to create a graphical design. In the initial stages of app development, UI prototype is a must. An automatic analysis system for the basic execution of UI designs will considerably speed up the development of designs according to old-fashioned methods. In this approach, it is aimed at saving cost and time by automating the process. For the aforesaid objective, we present a new approach rather than the traditional methods. For this reason, a high amount of elements in wireframes are detected and segmented. Furthermore, with the state-of-the-art methods, one of the machine learning classifiers is expected to give lower performance than deep learning for comparison purposes. In this study, the detection and segmentation of elements, which is the first stage which will eliminate time loss, redundant time, cost, and labor in the communication between designers and front-end developers. To test the classification task of the Mask R-CNN, was designed using transfer learning supported neural networks to compare with other algorithms. As a result, the precision reached 93.15% and the mAP (@IOU > 0.5) reached 96.50%. Then, we improved the algorithm by replacing the convolution blocks in the graphs, adding them, and changing the input units, and the accuracy increased to 98.49%.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"46 1","pages":"516-532"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90774841","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}
Sajad Ghabeli Sani, M. Banaei, Seyed Hossein Hosseini
: This paper proposes an innovative structure for DC-DC converters with high buck gain by using a lower number of elements. The converter provides highly efficient output power and an extended output voltage range. In addition, the distribution of output current between two inductors and the soft-switching capability of the power switches have made the converter suitable for applications that require high output current. All power switches accomplish the ZVZCS (zero-voltage and zero-current switching) condition with the aid of a small auxiliary inductor (Lx), which charges and discharges parallel capacitors of main switches to provide soft-switching conditions. Thus, the switching losses associated with power switches are considerably reduced. Additionally, the output voltage ratio of the proposed converter can be changed by varying the switching frequency and duty cycle. In addition, the variation range of output voltage has been expanded compared to other topologies, allowing for a wider output voltage range. A coupled inductor is utilized to establish a relationship between the output gain and the turn ratios, resulting in a wider output voltage gain range. Eventually, a theoretical analysis is conducted and a 200-watt experimental prototype has been implemented to illustrate the proposed converter’s efficacy. It converts a voltage input (300 V) to a voltage output (10 V).
{"title":"Analysis and implementation of a new high-buck DC-DC converter with interleaved output inductors and soft switching capability","authors":"Sajad Ghabeli Sani, M. Banaei, Seyed Hossein Hosseini","doi":"10.55730/1300-0632.4000","DOIUrl":"https://doi.org/10.55730/1300-0632.4000","url":null,"abstract":": This paper proposes an innovative structure for DC-DC converters with high buck gain by using a lower number of elements. The converter provides highly efficient output power and an extended output voltage range. In addition, the distribution of output current between two inductors and the soft-switching capability of the power switches have made the converter suitable for applications that require high output current. All power switches accomplish the ZVZCS (zero-voltage and zero-current switching) condition with the aid of a small auxiliary inductor (Lx), which charges and discharges parallel capacitors of main switches to provide soft-switching conditions. Thus, the switching losses associated with power switches are considerably reduced. Additionally, the output voltage ratio of the proposed converter can be changed by varying the switching frequency and duty cycle. In addition, the variation range of output voltage has been expanded compared to other topologies, allowing for a wider output voltage range. A coupled inductor is utilized to establish a relationship between the output gain and the turn ratios, resulting in a wider output voltage gain range. Eventually, a theoretical analysis is conducted and a 200-watt experimental prototype has been implemented to illustrate the proposed converter’s efficacy. It converts a voltage input (300 V) to a voltage output (10 V).","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"17 1","pages":"533-549"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78906096","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}
: Latent fingerprints are ubiquitously used as forensic evidence by law enforcement agencies in solving crimes. However, due to deformations and artifacts within latent fingerprint images, performance of the automated latent recognition systems are far from desired levels. A basic matcher specifically designed for clean fingerprints using a minutiae-based matching algorithm can have high speed and accuracy in a sensor-to-sensor matching task, but low accuracy in matching latent prints, due to scale, rotation and quality differences between latent and sensor images. In this study, we propose a unique multistep fusion matcher (FM) on top of a base matcher that would utilize scale, rotation, and quality attributes of minutiae with speed, memory, and accuracy trade options in the latent recognition process. FM match characteristics are analyzed by using a private dataset consisting of 5560 latent and 1M slap/rolled fingerprint images. In addition, 292 domain expert selected latents are used to compare the nationwide performance of the proposed method. FM’s with multiresolution fusion (MRF) option have achieved competitive accuracy rates when searching 292 latent against 1 million background and projecting predictions for 69 million background. On the NIST SD302 public dataset, FM6 (FM option prioritizing accuracy for latent-to-sensor search) with MRF correctly recognizes 911 latent in rank-1, while the COTS system referenced in the NIST SD302 documentation recognizes only 790 from a gallery composed of 5950 latent and 100K rolled background database. FM6 MRF rank-1 count for 10K latent of NIST SD302 is 1415, whereas NIST’s referenced matcher rank-1 count is 880 for the same dataset. In addition, NIST SD302 rank-1 latents are used to construct 722 latent pairs to evaluate latent-to-latent matching performance. FM8 (FM option prioritizing accuracy for latent-to-latent search) with MRF has 46.1% rank-1 identification rate for latent-to-latent search against 10K latent background. Moreover, on a private 1457 latent palmprint versus 2296 sensor palmprint background, a palm matcher designed by dividing latent and palm images into 512x512 pixel segments produces 85.45% rank-1 accuracy by using FM6.
{"title":"A Multistep Fusion Matcher Approach for Large Scale Latent Fingerprint/Palmprint Recognition","authors":"Ismail Kilinç, Y. Artan, E. Baseski","doi":"10.55730/1300-0632.3992","DOIUrl":"https://doi.org/10.55730/1300-0632.3992","url":null,"abstract":": Latent fingerprints are ubiquitously used as forensic evidence by law enforcement agencies in solving crimes. However, due to deformations and artifacts within latent fingerprint images, performance of the automated latent recognition systems are far from desired levels. A basic matcher specifically designed for clean fingerprints using a minutiae-based matching algorithm can have high speed and accuracy in a sensor-to-sensor matching task, but low accuracy in matching latent prints, due to scale, rotation and quality differences between latent and sensor images. In this study, we propose a unique multistep fusion matcher (FM) on top of a base matcher that would utilize scale, rotation, and quality attributes of minutiae with speed, memory, and accuracy trade options in the latent recognition process. FM match characteristics are analyzed by using a private dataset consisting of 5560 latent and 1M slap/rolled fingerprint images. In addition, 292 domain expert selected latents are used to compare the nationwide performance of the proposed method. FM’s with multiresolution fusion (MRF) option have achieved competitive accuracy rates when searching 292 latent against 1 million background and projecting predictions for 69 million background. On the NIST SD302 public dataset, FM6 (FM option prioritizing accuracy for latent-to-sensor search) with MRF correctly recognizes 911 latent in rank-1, while the COTS system referenced in the NIST SD302 documentation recognizes only 790 from a gallery composed of 5950 latent and 100K rolled background database. FM6 MRF rank-1 count for 10K latent of NIST SD302 is 1415, whereas NIST’s referenced matcher rank-1 count is 880 for the same dataset. In addition, NIST SD302 rank-1 latents are used to construct 722 latent pairs to evaluate latent-to-latent matching performance. FM8 (FM option prioritizing accuracy for latent-to-latent search) with MRF has 46.1% rank-1 identification rate for latent-to-latent search against 10K latent background. Moreover, on a private 1457 latent palmprint versus 2296 sensor palmprint background, a palm matcher designed by dividing latent and palm images into 512x512 pixel segments produces 85.45% rank-1 accuracy by using FM6.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"63 1","pages":"412-430"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87027054","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}
Melih Aslan, Kaan Şik, İzzet Güzelkara, İ. Özdür, V. Kılıç
: In this paper a study of a helical antenna resonating at high-frequency (HF) band with a very compact structure is reported. The designed antenna’s S11 parameter magnitude change with frequency was calculated for different geometrical parameters. For each case, first, only a single parameter was changed. Then for a fair comparison, multiple parameters were changed simultaneously while the total wire length was set to be constant. Also, shifts in resonance frequencies and variations in –10 dB bandwidths were investigated. Our results show that resonance behaviour changes distinctively with the geometrical parameters and it allows shortening of the antenna wire length. For the designed antenna, the resonances shift to lower frequencies and –10 dB bandwidths around the resonances decrease as the winding wire thickness, number of turns, and turn radius increase. Whereas as the turn spacing increases the resonances shift to higher frequencies and –10 dB bandwidths widen, although the total wire length of the antenna increases. To verify the simulation results, the designed antenna was fabricated with an exclusive manufacturing process and characterized. The measurement results are in good agreement with the simulation results. It demonstrates the feasibility of the proposed manufacturing technique, which is new in the literature and enables accurate and rigid antenna fabrication with simple and low-cost steps.
{"title":"Study of Helical Antenna Endowing Short Wire Length and Compact Structure for High-Frequency Operations and Its Exclusive Manufacturing Process","authors":"Melih Aslan, Kaan Şik, İzzet Güzelkara, İ. Özdür, V. Kılıç","doi":"10.55730/1300-0632.3991","DOIUrl":"https://doi.org/10.55730/1300-0632.3991","url":null,"abstract":": In this paper a study of a helical antenna resonating at high-frequency (HF) band with a very compact structure is reported. The designed antenna’s S11 parameter magnitude change with frequency was calculated for different geometrical parameters. For each case, first, only a single parameter was changed. Then for a fair comparison, multiple parameters were changed simultaneously while the total wire length was set to be constant. Also, shifts in resonance frequencies and variations in –10 dB bandwidths were investigated. Our results show that resonance behaviour changes distinctively with the geometrical parameters and it allows shortening of the antenna wire length. For the designed antenna, the resonances shift to lower frequencies and –10 dB bandwidths around the resonances decrease as the winding wire thickness, number of turns, and turn radius increase. Whereas as the turn spacing increases the resonances shift to higher frequencies and –10 dB bandwidths widen, although the total wire length of the antenna increases. To verify the simulation results, the designed antenna was fabricated with an exclusive manufacturing process and characterized. The measurement results are in good agreement with the simulation results. It demonstrates the feasibility of the proposed manufacturing technique, which is new in the literature and enables accurate and rigid antenna fabrication with simple and low-cost steps.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"85 1","pages":"396-411"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80979796","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}
A. Shaheen, Ragab. A. Elsehiemy, M. Kharrich, S. Kamel
: Transmission network planning problem (TNPP) is one of the pertinent issues of the planning activities in power systems. It aims to optimally pick out the routs, types, and number of the new installed lines to confront the expected future loading conditions. In this line, this study proposes a new economic model to the TNPP. The aim of the model is to find the optimal transmission routes at least investment and operating costs. Three recent algorithms called grey wolf optimization algorithm (GWOA), spotted hyena optimization algorithm (SHOA) and whale optimization algorithm (WOA) are developed to solve the TNPP. The concept of these algorithms is based on encircling prey operation. The competitive methods are investigated to find the optimal TNPP solution for two realistic Egyptian networks. The first tested network is the 66 kV West Delta Region (WDR) system while the second one is the extra high voltage (EHV) 500 kV system. Their demand forecasting is extracted forward to 2030 dependent upon the adaptive neuro-fuzzy inference system (ANFIS). Tremendous technical and economic advantages through application of the encircling prey-based algorithms to handle the TNPP.
{"title":"Transmission network planning for realistic Egyptian systems via encircling prey based algorithms","authors":"A. Shaheen, Ragab. A. Elsehiemy, M. Kharrich, S. Kamel","doi":"10.3906/elk-2010-82","DOIUrl":"https://doi.org/10.3906/elk-2010-82","url":null,"abstract":": Transmission network planning problem (TNPP) is one of the pertinent issues of the planning activities in power systems. It aims to optimally pick out the routs, types, and number of the new installed lines to confront the expected future loading conditions. In this line, this study proposes a new economic model to the TNPP. The aim of the model is to find the optimal transmission routes at least investment and operating costs. Three recent algorithms called grey wolf optimization algorithm (GWOA), spotted hyena optimization algorithm (SHOA) and whale optimization algorithm (WOA) are developed to solve the TNPP. The concept of these algorithms is based on encircling prey operation. The competitive methods are investigated to find the optimal TNPP solution for two realistic Egyptian networks. The first tested network is the 66 kV West Delta Region (WDR) system while the second one is the extra high voltage (EHV) 500 kV system. Their demand forecasting is extracted forward to 2030 dependent upon the adaptive neuro-fuzzy inference system (ANFIS). Tremendous technical and economic advantages through application of the encircling prey-based algorithms to handle the TNPP.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"25 1","pages":"77-96"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79628432","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}
: It is well known that classifiers trained using imbalanced datasets usually have a bias toward the majority class. In this context, classification models can present a high classification performance overall and for the majority class, even when the performance for the minority class is significantly lower. This paper presents a genetic programming (GP) model with a crossover-based oversampling technique for oversampling the imbalanced dataset for binary text classification. The aim of this study is to apply an oversampling technique to solve the imbalanced issue and improve the performance of the GP model that employed the proposed technique. The proposed technique employs a crossover operator for generating new samples for the minority class in an imbalanced text dataset. By using a combination of this crossover-based oversampling technique with GP, the performance was improved. It is shown that the proposed combination outperforms all GP applications that use the original dataset without resampling. Moreover, the performance of the proposed system surpassed GP approaches using the synthetic minority oversampling technique (SMOTE) and random oversampling. Further comparison with the state-of-the-art on five imbalanced text datasets in terms of F1-score shows the superior performance of the proposed approach.
{"title":"Binary text classification using genetic programming with crossover-based oversampling for imbalanced datasets","authors":"Mona Khalifa A. Aljero, Nazife Dimililer","doi":"10.55730/1300-0632.3978","DOIUrl":"https://doi.org/10.55730/1300-0632.3978","url":null,"abstract":": It is well known that classifiers trained using imbalanced datasets usually have a bias toward the majority class. In this context, classification models can present a high classification performance overall and for the majority class, even when the performance for the minority class is significantly lower. This paper presents a genetic programming (GP) model with a crossover-based oversampling technique for oversampling the imbalanced dataset for binary text classification. The aim of this study is to apply an oversampling technique to solve the imbalanced issue and improve the performance of the GP model that employed the proposed technique. The proposed technique employs a crossover operator for generating new samples for the minority class in an imbalanced text dataset. By using a combination of this crossover-based oversampling technique with GP, the performance was improved. It is shown that the proposed combination outperforms all GP applications that use the original dataset without resampling. Moreover, the performance of the proposed system surpassed GP approaches using the synthetic minority oversampling technique (SMOTE) and random oversampling. Further comparison with the state-of-the-art on five imbalanced text datasets in terms of F1-score shows the superior performance of the proposed approach.","PeriodicalId":23352,"journal":{"name":"Turkish J. Electr. Eng. Comput. Sci.","volume":"250 1","pages":"180-192"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82916276","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：