Textile wastewater has a complex composition characterized by high dye content and chemical oxygen demand. Therefore, textile wastewaters have serious environmental impacts, such as aesthetic degradation, and carcinogenic properties. Treatment and the recovery of textile wastewater are important due to their high volume and toxicity. The effects of peroxidase enzyme immobilized on magnetic chitosan-clay beads of synthetic textile wastewater were investigated in a batch reactor. System performance was determined by chemical oxygen demand (COD) and color. The batch reactor was operated in three different pH (5, 7, 10), temperatures (25, 35, 45 °C), and reaction times (0-5-10-20-30 min.) with synthetic textile wastewater. As a result, COD and color removal efficiencies were determined as 44% and 56%, respectively, corresponding effluent concentrations are 1442 mg/L, 450 Pt-Co. The results of this study show that using the enzyme immobilization process is an effective method to remove color and COD concentration from textile wastewater.
{"title":"THE EFFECT OF IMMOBILIZED ENZYME ON TEXTILE WASTEWATER","authors":"İrem Ayranpinar, M. Kozak, S. Göçer, Kevser Cirik","doi":"10.17780/ksujes.1387514","DOIUrl":"https://doi.org/10.17780/ksujes.1387514","url":null,"abstract":"Textile wastewater has a complex composition characterized by high dye content and chemical oxygen demand. Therefore, textile wastewaters have serious environmental impacts, such as aesthetic degradation, and carcinogenic properties. Treatment and the recovery of textile wastewater are important due to their high volume and toxicity. The effects of peroxidase enzyme immobilized on magnetic chitosan-clay beads of synthetic textile wastewater were investigated in a batch reactor. System performance was determined by chemical oxygen demand (COD) and color. The batch reactor was operated in three different pH (5, 7, 10), temperatures (25, 35, 45 °C), and reaction times (0-5-10-20-30 min.) with synthetic textile wastewater. As a result, COD and color removal efficiencies were determined as 44% and 56%, respectively, corresponding effluent concentrations are 1442 mg/L, 450 Pt-Co. The results of this study show that using the enzyme immobilization process is an effective method to remove color and COD concentration from textile wastewater.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140267317","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}
Age-related decline in sensory inputs in elderly people leads to postural instability that increases irregularity of postural sway. This study aimed to examine the effect of visual or somatosensory inputs on postural sway irregularity in the elderly by using machine learning (ML). The feature set was extracted from entropy measurements including sample, fuzzy, distribution, conditional, and permutation. Then, the variables were classified by ML including support vector machines (SVM), k-nearest neighbors (k-NN), and linear discriminant analysis (LDA) algorithms. Classification performances were compared with the confusion matrix. For the elderly, in the eyes closed condition on an unstable surface, the SVM algorithm achieved higher accuracy (77%), sensitivity (72%), specificity (85%), and precision (83%) for the cv dataset. For young, SVM also achieved high accuracy (86%), sensitivity (87%), specificity (84%), and precision (84%). For the elderly, under the eyes open on unstable surface conditions, the SVM exhibited an accuracy of 79%, sensitivity of 75%, specificity of 72%, and precision of 75%. However, for young, it did not reveal good results for both surfaces. In conclusion, the findings suggest that older people adapt their postural control mechanisms, relying more on somatosensory inputs. ML algorithms with entropy-based features can give insights into age-related differences in postural control.
{"title":"YAŞA BAĞLI DUYUSAL DEĞİŞİKLİKLERİN POSTURAL SALINIM DÜZENSİZLİĞİ ÜZERİNDEKİ ETKİSİNİN DEĞERLENDİRİLMESİ","authors":"Veysel Alcan","doi":"10.17780/ksujes.1338361","DOIUrl":"https://doi.org/10.17780/ksujes.1338361","url":null,"abstract":"Age-related decline in sensory inputs in elderly people leads to postural instability that increases irregularity of postural sway. This study aimed to examine the effect of visual or somatosensory inputs on postural sway irregularity in the elderly by using machine learning (ML). The feature set was extracted from entropy measurements including sample, fuzzy, distribution, conditional, and permutation. Then, the variables were classified by ML including support vector machines (SVM), k-nearest neighbors (k-NN), and linear discriminant analysis (LDA) algorithms. Classification performances were compared with the confusion matrix. For the elderly, in the eyes closed condition on an unstable surface, the SVM algorithm achieved higher accuracy (77%), sensitivity (72%), specificity (85%), and precision (83%) for the cv dataset. For young, SVM also achieved high accuracy (86%), sensitivity (87%), specificity (84%), and precision (84%). For the elderly, under the eyes open on unstable surface conditions, the SVM exhibited an accuracy of 79%, sensitivity of 75%, specificity of 72%, and precision of 75%. However, for young, it did not reveal good results for both surfaces. In conclusion, the findings suggest that older people adapt their postural control mechanisms, relying more on somatosensory inputs. ML algorithms with entropy-based features can give insights into age-related differences in postural control.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139182967","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}
The impulsive fractional delayed differential system with the Caputo derivative with respect to another function is considered. An explicit solution to the system in the light of the available studies on this subject is determined and its existence and uniqueness are debated. Lastly, the stability and controllability of the given system are investigated.
{"title":"RELATIVE CONTROLLABILITY OF THE φ-CAPUTO FRACTIONAL DELAYED SYSTEM WITH IMPULSES","authors":"Mustafa Aydin","doi":"10.17780/ksujes.1339354","DOIUrl":"https://doi.org/10.17780/ksujes.1339354","url":null,"abstract":"The impulsive fractional delayed differential system with the Caputo derivative with respect to another function is considered. An explicit solution to the system in the light of the available studies on this subject is determined and its existence and uniqueness are debated. Lastly, the stability and controllability of the given system are investigated.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"15 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139182388","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}
Çinko klorür, sodyum hidroksit, magnezyum oksit, kalsiyum oksit gibi maddeler kimyasal yapıları gereği kristalleri içerisine difüzyon/absorpsiyon gibi yollarla su tutarlar. Bu maddeler, higroskopik maddeler olarak adlandırılıp sıvı ve katılar maddelerden su uzaklaştırmak amacıyla kullanılmaktadır. Üretimleri amacıyla özel kapalı sistemler kullanılması gerekmekle birlikte ortama giren veya maddenin absorpladığı suyun ortamdan uzaklaştırılması ve kalsinasyon işlemleri için yüksek sıcaklıklarda tepkime odaları gerekmektedir. Higroskopik maddelerin tepkimesi sırasında ortaya çıkan gazların ortamdan uzaklaştırılması veya ürünün nemlenmesi önlemek için su buharının sistemden uzaklaştırılması gerekmektedir. Piyasada yer alan reaktörler incelendiğinde başta topaklanma, hantal yapıları, yüksek enerji gereksinimleri ve paketlenme süreçlerinde havayla temas gibi olumsuzluklar göstermektedirler. Bu çalışma ile kalsiyum oksit ve magnezyum oksit temel alınmak üzere, ilgili kimyasalların üretim prosesinde ve kimyasal tepkimelerinde kullanılmak amacıyla yeni bir pilot reaktör ünitesinin sınır şartlarının belirlenmesi ve 3B tasarımlarının yapılması amaçlanmıştır. Piyasada yaygın kullanımı olan reaktörler incelenerek sınır şartları belirlenmiştir. Belirlenen ihtiyaçlara göre 3 boyutlu tasarımları gerçekleştirilmiştir olup elde edilen verilere göre mevcut sistemlere göre %42 daha hafif, %50 daha küçük yeni bir sistem tasarlanmıştır. Çalışma ile en az %38 daha fazla ürün işleme kapasitesine sahip olup %25 oranında enerji kullanımını azaltan bileşenlerden oluşan yeni bir reaktörün tasarımı gerçekleşmiştir.
{"title":"ULTRASONIC PILOT REACTOR DESIGN: TEMPERATURE, PRESSURE AND ROTARY CONTROL CAN BE USED IN THE PRODUCTION OF HYGROSCOPIC MATERIALS","authors":"Sinan Köse, Fatma Ulusal, S. H. Yetgi̇n","doi":"10.17780/ksujes.1340725","DOIUrl":"https://doi.org/10.17780/ksujes.1340725","url":null,"abstract":"Çinko klorür, sodyum hidroksit, magnezyum oksit, kalsiyum oksit gibi maddeler kimyasal yapıları gereği kristalleri içerisine difüzyon/absorpsiyon gibi yollarla su tutarlar. Bu maddeler, higroskopik maddeler olarak adlandırılıp sıvı ve katılar maddelerden su uzaklaştırmak amacıyla kullanılmaktadır. Üretimleri amacıyla özel kapalı sistemler kullanılması gerekmekle birlikte ortama giren veya maddenin absorpladığı suyun ortamdan uzaklaştırılması ve kalsinasyon işlemleri için yüksek sıcaklıklarda tepkime odaları gerekmektedir. Higroskopik maddelerin tepkimesi sırasında ortaya çıkan gazların ortamdan uzaklaştırılması veya ürünün nemlenmesi önlemek için su buharının sistemden uzaklaştırılması gerekmektedir. Piyasada yer alan reaktörler incelendiğinde başta topaklanma, hantal yapıları, yüksek enerji gereksinimleri ve paketlenme süreçlerinde havayla temas gibi olumsuzluklar göstermektedirler. Bu çalışma ile kalsiyum oksit ve magnezyum oksit temel alınmak üzere, ilgili kimyasalların üretim prosesinde ve kimyasal tepkimelerinde kullanılmak amacıyla yeni bir pilot reaktör ünitesinin sınır şartlarının belirlenmesi ve 3B tasarımlarının yapılması amaçlanmıştır. Piyasada yaygın kullanımı olan reaktörler incelenerek sınır şartları belirlenmiştir. Belirlenen ihtiyaçlara göre 3 boyutlu tasarımları gerçekleştirilmiştir olup elde edilen verilere göre mevcut sistemlere göre %42 daha hafif, %50 daha küçük yeni bir sistem tasarlanmıştır. Çalışma ile en az %38 daha fazla ürün işleme kapasitesine sahip olup %25 oranında enerji kullanımını azaltan bileşenlerden oluşan yeni bir reaktörün tasarımı gerçekleşmiştir.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"266 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139182024","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 brain tumor is a dangerous neural illness produced by the strict growth of prison cells in the brain or head. The segmentation, analysis, and separation of unclean tumor parts from Magnetic Resonance Imaging (MRI) images are the main sources of anxiety. To report the segmented MRI images including tumor, the usage of computer-assisted methods is necessary. In this paper, a Convolutional Neural Network (CNN) approach is applied to identify brain cancers in MRI images. Two datasets are used in this study, namely Kaggle Brain MRI database and Figshare Brain MRI database. Models of deep CNN, consisting of VGG16, AlexNet, and ResNet, are utilized to extract deep features. The classification accuracies of the aforementioned Deep Learning (DL) networks are used to measure the efficiencies of the implemented systems. For the Kaggle database, AlexNet achieves 98% accuracy, VGG16 has 97% accuracy and ResNet has 66% accuracy. Among these networks, AlexNet has provided the highest level of accuracy. In the Figshare dataset, AlexNet and VGG16 both achieve 99% accuracy, and ResNet has 96% accuracy. In terms of accuracy, AlexNet and VGG16 outperform ResNet. These performances aid in the early detection of cancers before they cause physical harm such as paralysis and other complications.
{"title":"CLASSIFICATION OF BRAIN TUMORS ON MRI IMAGES USING DEEP LEARNING ARCHITECTURES","authors":"Samaneh Sarfarazi, Önsen Toygar","doi":"10.17780/ksujes.1339884","DOIUrl":"https://doi.org/10.17780/ksujes.1339884","url":null,"abstract":"A brain tumor is a dangerous neural illness produced by the strict growth of prison cells in the brain or head. The segmentation, analysis, and separation of unclean tumor parts from Magnetic Resonance Imaging (MRI) images are the main sources of anxiety. To report the segmented MRI images including tumor, the usage of computer-assisted methods is necessary. In this paper, a Convolutional Neural Network (CNN) approach is applied to identify brain cancers in MRI images. Two datasets are used in this study, namely Kaggle Brain MRI database and Figshare Brain MRI database. Models of deep CNN, consisting of VGG16, AlexNet, and ResNet, are utilized to extract deep features. The classification accuracies of the aforementioned Deep Learning (DL) networks are used to measure the efficiencies of the implemented systems. For the Kaggle database, AlexNet achieves 98% accuracy, VGG16 has 97% accuracy and ResNet has 66% accuracy. Among these networks, AlexNet has provided the highest level of accuracy. In the Figshare dataset, AlexNet and VGG16 both achieve 99% accuracy, and ResNet has 96% accuracy. In terms of accuracy, AlexNet and VGG16 outperform ResNet. These performances aid in the early detection of cancers before they cause physical harm such as paralysis and other complications.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"57 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139182969","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}
Son yıllarda teknolojinin hızla gelişmesi ve internet kullanımının artmasıyla birlikte online alışveriş sitelerine olan ilgi daha da artmaktadır. Artan bu tüketici ilgisi göz önüne alındığında, online alışveriş siteleri arasındaki rekabet de her geçen gün artmaktadır. Bu rekabet ortamında tüketicilerin ilgisini çeken ve tercih edilen bir platform olmak büyük önem taşımaktadır. Bu çalışmada Endüstri 4.0 temelinde online alışveriş sitelerinin tercih edilmesinde etkili olan kriterlerin değerlendirilme süreci ele alınmaktadır. Çalışmada dikkat edilecek kriterler; ürün bilgisi ve çeşitliliği, zamanında ve doğru teslimat, web sitesi tasarımı ve performansı, güvenilirlik/gizlilik ve müşteri memnuniyetidir. Bu kriterlerin ilişkilerinin ve önemlerinin belirlenmesinde Çok Kriterli Karar Verme (ÇKKV) yöntemlerinden DEMATEL yöntemi kullanılmıştır. Böylelikle online rekabet ortamında dikkate alınması gereken kriterlerin belirlenme süreci gösterilmiş ve buna katkı sağlayacağı varsayılan kriterler değerlendirilmiştir. Bu değerlendirmeler sonucunda, online alışveriş sitelerinin mevcut durumlarını, Endüstri 4.0 temelinde iyileştirmelerine yönelik öneriler sunulmuştur.
{"title":"EVALUATION OF THE CRITERIA TO BE CONSIDERED WHEN SELECTING ONLINE SHOPPING SITES BASED ON INDUSTRY 4.0 WITH DEMATEL METHOD","authors":"Zeynep Durmaz, E. Aksakal","doi":"10.17780/ksujes.1340294","DOIUrl":"https://doi.org/10.17780/ksujes.1340294","url":null,"abstract":"Son yıllarda teknolojinin hızla gelişmesi ve internet kullanımının artmasıyla birlikte online alışveriş sitelerine olan ilgi daha da artmaktadır. Artan bu tüketici ilgisi göz önüne alındığında, online alışveriş siteleri arasındaki rekabet de her geçen gün artmaktadır. Bu rekabet ortamında tüketicilerin ilgisini çeken ve tercih edilen bir platform olmak büyük önem taşımaktadır. Bu çalışmada Endüstri 4.0 temelinde online alışveriş sitelerinin tercih edilmesinde etkili olan kriterlerin değerlendirilme süreci ele alınmaktadır. Çalışmada dikkat edilecek kriterler; ürün bilgisi ve çeşitliliği, zamanında ve doğru teslimat, web sitesi tasarımı ve performansı, güvenilirlik/gizlilik ve müşteri memnuniyetidir. Bu kriterlerin ilişkilerinin ve önemlerinin belirlenmesinde Çok Kriterli Karar Verme (ÇKKV) yöntemlerinden DEMATEL yöntemi kullanılmıştır. Böylelikle online rekabet ortamında dikkate alınması gereken kriterlerin belirlenme süreci gösterilmiş ve buna katkı sağlayacağı varsayılan kriterler değerlendirilmiştir. Bu değerlendirmeler sonucunda, online alışveriş sitelerinin mevcut durumlarını, Endüstri 4.0 temelinde iyileştirmelerine yönelik öneriler sunulmuştur.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"150 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139182332","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}
In this study, the use of Al2O3 and TiO2 nano particles with a size of 12 nm and a purity of 99.9% as gasoline fuel additives was investigated. Fuel mixtures were prepared using a 3-level factorial design technique, and density and refractive index values were determined. Al2O3 nano particles, due to their high surface area, increased the density by 0.17% (3.5 ppm) and 1.22% (7 ppm), while TiO2 nano particles increased the density by 0.22% (3.5 ppm) and 1.26% (7 ppm). It was observed that the nano particle with a higher surface area had a less significant effect on density. The refractive index values decreased by 0.11% (3.5 ppm) and 0.14% (7 ppm) for Al2O3 nano particles, and by 0.21% (3.5 ppm) and 0.24% (7 ppm) for TiO2 nano particles. This study highlighted the importance of particle size, purity, and surface area in the selection of nano particles. Based on the evaluations and preliminary tests, nano particle levels above 15 ppm exhibited a tendency for agglomeration in the fuel. It is crucial to limit the total concentration to 15 ppm, especially for nano particles with a high surface area like Al2O3, to achieve homogeneous fuel.
{"title":"NANOPARTİKÜL İLAVESİNİN BENZİNİN KIRILMA İNDİSİ VE YOĞUNLUĞU ÜZERİNDEKİ ETKİSİNİN ARAŞTIRILMASI","authors":"M. Gökmen, Mehmet Fatih Parlak, Hasan Aydoğan","doi":"10.17780/ksujes.1340166","DOIUrl":"https://doi.org/10.17780/ksujes.1340166","url":null,"abstract":"In this study, the use of Al2O3 and TiO2 nano particles with a size of 12 nm and a purity of 99.9% as gasoline fuel additives was investigated. Fuel mixtures were prepared using a 3-level factorial design technique, and density and refractive index values were determined. Al2O3 nano particles, due to their high surface area, increased the density by 0.17% (3.5 ppm) and 1.22% (7 ppm), while TiO2 nano particles increased the density by 0.22% (3.5 ppm) and 1.26% (7 ppm). It was observed that the nano particle with a higher surface area had a less significant effect on density. The refractive index values decreased by 0.11% (3.5 ppm) and 0.14% (7 ppm) for Al2O3 nano particles, and by 0.21% (3.5 ppm) and 0.24% (7 ppm) for TiO2 nano particles. This study highlighted the importance of particle size, purity, and surface area in the selection of nano particles. Based on the evaluations and preliminary tests, nano particle levels above 15 ppm exhibited a tendency for agglomeration in the fuel. It is crucial to limit the total concentration to 15 ppm, especially for nano particles with a high surface area like Al2O3, to achieve homogeneous fuel.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"3 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139182806","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}
In this study, the face recognition task is applied on masked and unmasked faces using hand-crafted methods. Due to COVID-19 and masks, facial identification from unconstrained images became a hot topic. To avoid COVID-19, most people use masks outside. In many cases, typical facial recognition technology is useless. The majority of contemporary advanced face recognition methods are based on deep learning, which primarily relies on a huge number of training examples, however, masked face recognition may be investigated using hand-crafted approaches at a lower computing cost than using deep learning systems. A low-cost system is intended to be constructed for recognizing masked faces and compares its performance to that of face recognition systems that do not use masks. The proposed method fuses hand-crafted methods using feature-level fusion strategy. This study compares the performance of masked and unmasked face recognition systems. The experiments are undertaken on two publicly accessible datasets for masked face recognition: Masked Labeled Faces in the Wild (MLFW) and Cross-Age Labeled Faces in the Wild (CALFW). The best accuracy is achieved as 94.8% on MLFW dataset. The rest of the results on different train and test sets from CALFW and MLFW datasets are encouraging compared to the state-of-the-art models.
{"title":"MASKED AND UNMASKED FACE RECOGNITION ON UNCONSTRAINED FACIAL IMAGES USING HAND-CRAFTED METHODS","authors":"Ali Torbati, Önsen Toygar","doi":"10.17780/ksujes.1339868","DOIUrl":"https://doi.org/10.17780/ksujes.1339868","url":null,"abstract":"In this study, the face recognition task is applied on masked and unmasked faces using hand-crafted methods. Due to COVID-19 and masks, facial identification from unconstrained images became a hot topic. To avoid COVID-19, most people use masks outside. In many cases, typical facial recognition technology is useless. The majority of contemporary advanced face recognition methods are based on deep learning, which primarily relies on a huge number of training examples, however, masked face recognition may be investigated using hand-crafted approaches at a lower computing cost than using deep learning systems. A low-cost system is intended to be constructed for recognizing masked faces and compares its performance to that of face recognition systems that do not use masks. The proposed method fuses hand-crafted methods using feature-level fusion strategy. This study compares the performance of masked and unmasked face recognition systems. The experiments are undertaken on two publicly accessible datasets for masked face recognition: Masked Labeled Faces in the Wild (MLFW) and Cross-Age Labeled Faces in the Wild (CALFW). The best accuracy is achieved as 94.8% on MLFW dataset. The rest of the results on different train and test sets from CALFW and MLFW datasets are encouraging compared to the state-of-the-art models.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"269 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139183088","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}
Addressing traffic congestion holds paramount importance due to its severe economic and environmental repercussions. This study introduces an approach to address this pervasive issue by employing a wide-area control strategy for diverse road networks. The strategy leverages a dynamic offset control method and a multi-agent model to create a unique solution. In this framework, individual intersections function as distinct agents, engaging in negotiations, establishing connections, and forming a dynamic offset control zone resembling a tree structure. Within this structure, agents collaboratively manage green wave synchronization based on real-time traffic conditions at the network boundaries. To evaluate the effectiveness of this approach, comprehensive tests utilize both a simulated road network (Experiment 1) and an actual grid-like road network (Experiment 2). In Experiment 1, the proposed method consistently reduces lost time, resulting in an average reduction of 15% across all scenarios. Experiment 2 demonstrates a reduction in lost time across various intervals, with an impressive average reduction of 34% in lost time across all scenarios. These results demonstrate the strategy's ability to dynamically and adaptively establish green waves that significantly enhance traffic flow. In conclusion, this study demonstrates that the proposed method autonomously conducts offset control, effectively contributing to the smooth flow of vehicles.
{"title":"A STUDY ON OPTIMIZING TRAFFIC SIGNAL CONTROL FOR IMPROVED TRAFFIC FLOW","authors":"S. Ergün","doi":"10.17780/ksujes.1336288","DOIUrl":"https://doi.org/10.17780/ksujes.1336288","url":null,"abstract":"Addressing traffic congestion holds paramount importance due to its severe economic and environmental repercussions. This study introduces an approach to address this pervasive issue by employing a wide-area control strategy for diverse road networks. The strategy leverages a dynamic offset control method and a multi-agent model to create a unique solution. In this framework, individual intersections function as distinct agents, engaging in negotiations, establishing connections, and forming a dynamic offset control zone resembling a tree structure. Within this structure, agents collaboratively manage green wave synchronization based on real-time traffic conditions at the network boundaries. To evaluate the effectiveness of this approach, comprehensive tests utilize both a simulated road network (Experiment 1) and an actual grid-like road network (Experiment 2). In Experiment 1, the proposed method consistently reduces lost time, resulting in an average reduction of 15% across all scenarios. Experiment 2 demonstrates a reduction in lost time across various intervals, with an impressive average reduction of 34% in lost time across all scenarios. These results demonstrate the strategy's ability to dynamically and adaptively establish green waves that significantly enhance traffic flow. In conclusion, this study demonstrates that the proposed method autonomously conducts offset control, effectively contributing to the smooth flow of vehicles.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139181970","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}
Buğra Sarper, Döndü Nur Türk, Kayhan Dağidir, Orhan Aydin
In this numerical investigation, the impacts of complete and partial cylindrical fin configurations on the thermohydraulic performance of a minichannel heatsink are studied. ANSYS Fluent software is used to conduct numerical analyses for four distinct mass flow rates ranging from 0.00265 kg/s to 0.0045 kg/s and three distinct fin positions. The effects of various configurations on velocity and temperature fields, average Nusselt number, Nusselt number ratio, friction coefficient, and performance evaluation coefficient are analyzed. According to the study’s findings, using partial cylindrical fins has a substantial impact on both heat transfer and pressure drop. When evaluating heat transfer, MCHS-R2a produces the greatest results, but this configuration greatly raises flow resistance. MCHS-R2c was found to have substantial potential when evaluated in terms of thermohydraulic performance.
{"title":"TAM VE PARÇALI SİLİNDİRİK KANATÇIK KONFİGÜRASYONLARININ BİR MİNİKANALLI ISI ALICININ TERMOHİDROLİK PERFORMANSI ÜZERİNDEKİ ETKİLERİ","authors":"Buğra Sarper, Döndü Nur Türk, Kayhan Dağidir, Orhan Aydin","doi":"10.17780/ksujes.1340343","DOIUrl":"https://doi.org/10.17780/ksujes.1340343","url":null,"abstract":"In this numerical investigation, the impacts of complete and partial cylindrical fin configurations on the thermohydraulic performance of a minichannel heatsink are studied. ANSYS Fluent software is used to conduct numerical analyses for four distinct mass flow rates ranging from 0.00265 kg/s to 0.0045 kg/s and three distinct fin positions. The effects of various configurations on velocity and temperature fields, average Nusselt number, Nusselt number ratio, friction coefficient, and performance evaluation coefficient are analyzed. According to the study’s findings, using partial cylindrical fins has a substantial impact on both heat transfer and pressure drop. When evaluating heat transfer, MCHS-R2a produces the greatest results, but this configuration greatly raises flow resistance. MCHS-R2c was found to have substantial potential when evaluated in terms of thermohydraulic performance.","PeriodicalId":508025,"journal":{"name":"Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi","volume":"143 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139182342","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：