This study aims to detect human face images generated by artificial intelligence. A balanced dataset containing real and artificial intelligence-based human face images was created. Thirty thousand images were used to train an EfficientNet-B0 model through transfer learning. The performance was evaluated using a Leave-One-Domain-Out analysis. This analysis was performed to evaluate the model’s generalization performance across unseen data domains. Experimental results demonstrate that the model achieved a promising accuracy across different data sources. The proposed model achieved an average accuracy of 0.82 and an F1-score of approximately 0.85 in the K-fold cross-validation setting based on out of fold predictions. This research contributes to the literature by providing a practical deep learning-based approach for detecting artificial intelligence-generated synthetic human faces.

The aim of maritime surveillance is to support maritime security by protecting national and international rights and interests through reliable monitoring systems, thereby increasing situational awareness. As threats continue to grow, ranging from piracy and illegal fishing to environmental hazards like oil spills the critical importance of surveillance to ensure security and support sustainable use of the ocean becomes increasingly evident. However, relying solely on single-sensor data for detection and identification purposes is often inadequate. To increase the likelihood of successful detection and identification of vessels, it is critical that heterogeneous (i.e., varying types of) data from several different sensors (i.e., radar, optical systems, Automatic Identification System (AIS), and Synthetic Aperture Radar (SAR)) be integrated to eliminate the limitations of individual sensors and create a more comprehensive view of the maritime domain. The focus of this review is to provide a systematic overview of various approaches to multi-sensor fusion with emphasis on artificial intelligence (AI)-based methodologies. The article provides a structured literature review of literature related to the ship detection, recognition, tracking, and anomaly detection using fusion processes and presents and discusses most recent and successful practices, some of the technical challenges that exist today, and potential areas of future research. The evaluation includes both traditional and contemporary AI-based techniques (i.e., machine learning and deep learning) as well as the complexities that exist when attempting to handle large volumes of data, process data in real-time, and account for variability in the environment and potential cyber threats. In summary, the ultimate goal of this study is to provide an informative reference, for the purpose of enhancing maritime situational awareness.

Savunma teknolojilerinde kullanılan termal optik sistemler, görüntüleme sırasında çeşitli sorunlarla karşılaşırlar ve bu sorunlar, görüntülerin üzerinde farklı türlerde bulanıklık kusuru olarak ortaya çıkarlar. Bulanıklığın türünü belirlemek, görüntüyü iyileştirmenin ilk adımıdır. Bu çalışmada, çeşitli bulanıklık türleri (odaksızlık bulanıklığı, atmosferik türbülans bulanıklığı, görüntü titreme bulanıklığı, Gaussian bulanıklığı ve hareket bulanıklığı) modellenmiş ve 15000 FLIR termal görüntü içeren bir veri seti üzerinde Python programlama dili aracılığıyla rastgele değerlerle bulanıklıklar uygulanarak bir veri seti oluşturulmuştur. Daha sonra, ResNet50, InceptionV3, DenseNet201, VGG16 ve EfficientNetB0 gibi farklı Evrişimsel Sinir Ağları bu termal görüntüleri sınıflandırmak için kullanılmıştır. Elde edilen sonuçlara göre en yüksek performans %98 doğruluk ile EfficientNetB0 mimarisi tarafından sağlanmıştır. Bu çalışma ile termal görüntülerdeki bulanıklık türlerini sınıflandırmada derin öğrenme yaklaşımının etkileri incelenmiş ve gelecekteki uygulamalar için umut verici sonuçlar elde edilmiştir.

Developments in technology have significantly affected the marketing activities of businesses. With the integration of technology into marketing activities, sales increased and the attention of target markets began to be drawn more. Thanks to the opportunities brought by technology, businesses have had the chance to understand the personal needs and expectations of consumers more easily. Thus, personalization in marketing has begun to take place at the center of marketing. However, developments in recent years have brought the issue of hyper-personalization, which is one step beyond personalization of businesses, to the agenda. The effects of artificial intelligence, machine learning, internet of things have an important impact great in this. In this paper, gait-based gender recognition problem, which is an important example for hyper-personalized marketing activities, was attempted to solve with Convolutional Neural Networks (CNNs). Various networks underwent evaluation for this task, with one chosen as a foundation. Subsequent modifications were applied to this base network through experimentation with architectural choices and hyperparameters. Despite exhibiting promising performance akin to prior research, the experimental findings shed light on the impact of network structure and hyperparameters on performance. The experiments employed gait silhouette, a feature descriptor, as input. The resultant overall accuracy reached 97.45% with the proposed CNN architecture. This outcome offers valuable insights into utilizing gait feature descriptions for classification within the problem domain.

Visual place recognition is vital in enhancing destination marketing by helping service providers present offerings more effectively and enabling consumers to form stronger connections with locations. Integrating artificial intelligence into this process allows for smarter and more targeted marketing strategies through visual data analysis, content recommendations, and user behavior tracking. However, there are many challenges in visual place recognition due to the numerous image samples for processing, complex visual structures, and noise from non-recognizable images. This study explores the use of zero-shot learning (ZSL) for visual place recognition to address these challenges, particularly the issue of limited sample availability. We compared ZSL with traditional learning methods and evaluated multiple configurations, including city-, country-, and continent-level classification, as well as generalized zero-shot learning and label-based classification. Feature comparisons using 3D color histograms and gist descriptors were also conducted at test time. Our findings indicate that ZSL can effectively handle visual place recognition tasks, especially when proper class splits and configurations are applied. While the generalized ZSL approach, which includes seen classes during testing, often achieves higher success rates depending on the target set size, some ZSL configurations show performance comparable to traditional methods. These results highlight ZSL’s potential in real-world applications of visual place recognition and destination marketing.

An image processing pipeline is proposed in this paper to determine electrochemical drilling (ECD) process parameters that yield better response values, such as hmax, hideal, and surface roughness. To achieve this, images of the drilled holes obtained via electrochemical drilling were processed using image processing techniques within the developed decision support system (DSS). Furthermore, the DSS was structured to provide processing parameter values for other non-traditional manufacturing processes (NTMPs) in the future by uploading process-specific photographs to the DSS database. Finally, the DSS was developed using the Python language, and its usability was demonstrated through an application study.

Alzheimer’s disease is a progressive neurodegenerative disorder marked by cognitive decline, memory loss, and behavioral changes. Early diagnosis, particularly identifying Early Mild Cognitive Impairment (EMCI), is vital for managing the disease and improving patient outcomes. Detecting EMCI is challenging due to the subtle structural changes in the brain, making precise slice selection from MRI scans essential for accurate diagnosis. In this context, the careful selection of specific MRI slices that provide distinct anatomical details significantly enhances the ability to identify these early changes. The chief novelty of the study is that instead of selecting all slices, an approach for identifying the important slices is developed. The ADNI-3 dataset was used as the dataset when running the models for early detection of Alzheimer’s disease. Satisfactory results have been obtained by classifying with deep learning models, vision transformers (ViT) and by adding new structures to them, together with the model proposal. In the results obtained, while an accuracy of 99.45% was achieved with EfficientNetB2 + FPN in AD vs. LMCI classification from the slices selected with SSIM, an accuracy of 99.19% was achieved in AD vs. EMCI classification, in fact, the study significantly advances early detection by demonstrating improved diagnostic accuracy of the disease at the EMCI stage. The results obtained with these methods emphasize the importance of developing deep learning models with slice selection integrated with the Vision Transformers architecture. Focusing on accurate slice selection enables early detection of Alzheimer’s at the EMCI stage, allowing for timely interventions and preventive measures before the disease progresses to more advanced stages. This approach not only facilitates early and accurate diagnosis, but also lays the groundwork for timely intervention and treatment, offering hope for better patient outcomes in Alzheimer’s disease. The study is finally evaluated by a statistical significance test.

PURPOSE:The primary aim of this study is to develop an effective and reliable diagnostic system for neurodegenerative diseases by utilizing gait data transformed into QR codes and classified using convolutional neural networks (CNNs). The objective of this method is to enhance the precision of diagnosing neurodegenerative diseases, including amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), and Huntington's disease (HD), through the introduction of a novel approach to analyze gait patterns. METHODS:The research evaluates the CNN-based classification approach using QR-represented gait data to address the diagnostic challenges associated with neurodegenerative diseases. The gait data of subjects were converted into QR codes, which were then classified using a CNN deep learning model. The dataset includes recordings from patients with Parkinson's disease (n = 15), Huntington's disease (n = 20), and amyotrophic lateral sclerosis (n = 13), and from 16 healthy controls. RESULTS:The accuracy rates obtained through 10-fold cross-validation were as follows: 94.86% for NDD versus control, 95.81% for PD versus control, 93.56% for HD versus control, 97.65% for ALS versus control, and 84.65% for PD versus HD versus ALS versus control. These results demonstrate the potential of the proposed system in distinguishing between different neurodegenerative diseases and control groups. CONCLUSION:The results indicate that the designed system may serve as a complementary tool for the diagnosis of neurodegenerative diseases, particularly in individuals who already present with varying degrees of motor impairment. Further validation and research are needed to establish its wider applicability.

Sign language functions as an indispensable interaction method for a certain portion of people in society, offering a unique way of communication. A significant challenge in advancing towards this objective is the difficulty in obtaining suitable training data for each sign in supervised learning. This challenge comes from the complex process of labeling signs and the limited number of skilled people available to do this job. This work introduces a new approach to the problem of Zero-Shot Sign Language Recognition (ZSSLR). We basically utilize and model hand and landmark data streams extracted from the body of the signer. Based on these extracted and modeled features, we employ a data grading approach to facilitate visual embedding with the self-attention mechanism. We utilize textual sign description features along with visual embedding in the Zero-Shot Learning (ZSL) settings. We assess the efficacy of our methodology in two of the suggested ZSL benchmarks.

Cognitive problems like Dementia and Alzheimer's are usually challenging to diagnose but can be noticed by some signs of their symptoms. The most common symptoms are confu-sion, trouble finding the right word, memory loss, and difficulty concentrating. This study aims to design a cognitive activity detection and tracing system that contains games and an-alyzes users' performances then displays detailed statistics to the users. The proposed Cogni-tive Activity Detection and Tracing System (CADTS) is software that contains different kinds of games from different categories inside its body that aims to measure cognitive activity by utilizing formulations in the context of the games and give feedback to users concerning the performance analyses done. The purpose of these analyses is to catch the signs of symptoms. An insight into a possible scoring system is provided, and as our results, several descriptive statistics are shared based on the tests conducted.

Early diagnosis is crucial in Alzheimer's disease both clinically and for preventing the rapid progression of the disease. Early diagnosis with awareness studies of the disease is of great importance in terms of controlling the disease at an early stage. Additionally, early detection can reduce treatment costs associated with the disease. A study has been carried out on this subject to have the great importance of detecting Alzheimer's disease at a mild stage and being able to grade the disease correctly. This study's dataset consisting of MRI images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) was split into training and testing sets, and deep learning -based approaches were used to obtain results. The dataset consists of three classes: Alzheimer's disease (AD), Cognitive Normal (CN), and Mild Cognitive Impairment (MCI). The achieved results showed an accuracy of 98.94% for CN vs AD in the one vs one (1 vs 1) classification with the EfficientNetB0 model and 99.58% for AD vs CNMCI in the one vs All (1 vs All) classification with AlexNet model. In addition, in the study, an accuracy of 98.42% was obtained with the EfficientNet121 model in MCI vs CN classification. These results indicate the significant potential for mild stage Alzheimer's disease detection of Alzheimer's disease. Early detection of the disease in the mild stage is a critical factor in preventing the progression of Alzheimer's disease. In addition, a variant of the non -parametric statistical McNemar's Test was applied to determine the statistical significance of the results obtained in the study. Statistical significance of 1 vs 1 and 1 vs all classifications were obtained for EfficientNetB0, DenseNet, and AlexNet models.

Teknolojideki gelişmeler, işletmelerin pazarlama faaliyetlerini önemli ölçüde etkilemiştir. Teknolojinin pazarlama faaliyetlerine entegre edilmesi ile birlikte satışlar artmış ve hedef pazarlarda daha fazla dikkat çekilmeye başlanmıştır. İşletmeler, teknolojinin getirdiği fırsatlar sayesinde, tüketicilerin kişisel ihtiyaçlarını ve beklentilerini daha kolay anlama imkânına sahip olmuştur. Böylelikle, pazarlamada kişiselleştirme, pazarlamanın merkezinde yer almaya başlamıştır. Ancak son yıllarda yaşanan gelişmeler, işletmelerin kişiselleştirilmesinin bir adım ötesinde olan hiper kişiselleştirme konusunu gündeme getirmiştir. Bunda yapay zekânın, makine öğrenmesinin ve nesnelerin internetinin büyük ve önemli bir etkisi vardır. Bu makalede, hiper kişiselleştirilmiş pazarlama faaliyetleri için önemli bir örnek olan yürüyüş biçimi tabanlı cinsiyet tanıma sorununa, Evrişimsel Sinir Ağları ile çözüm getirilmeye çalışılmıştır. Bu amaçla farklı ağlar değerlendirilmiş ve bir temel ağ seçilmiştir. Mimari seçenekler ve üst değişkenler üzerinde deneyler yapılarak temel ağ üzerinde ek ayarlamalar yapılmıştır. Sonuçlar mevcut çalışmalarla karşılaştırıldığında umut verici bir performans göstermekte olup deneysel sonuçlar, ağ yapısının ve üst değişkenlerin performansı nasıl etkilediğine dair bir içgörü sağlamaktadır. Deneyler, girdi olarak bir öznitelik tanımlayıcısı olan yürüyüş biçimi silüeti kullanılarak gerçekleştirilmiştir. Önerilen ESA mimarisi kullanıldığında, genel doğruluk düzeyinin %97,45 olduğu hesaplanmıştır. Bu dikkate alındığında, elde edilen sonuç, sorun alanımız olan yürüyüş biçimi öznitelik tanımlamasının sınıflandırma amacıyla kullanılması konusunda bir anlayış kazanmaya imkân tanımaktadır.

Recently, convolutional neural network-based methods have been used extensively for roof type classification on images taken from space. The most important problem with classification processes using these methods is that it requires a large amount of training data. Usually, one or a few images are enough for a human to recognise an object. The one-shot learning approach, like the human brain, aims to effect learning about object categories with just one or a few training examples per class, rather than using huge amounts of data. In this study, roof-type classification was carried out with a few training examples using the one-time learning approach and the so-called Siamese neural network method. The images used for training were artificially produced due to the difficulty of finding roof data. A data set consisting of real roof images was used for the test. The test and training data set consisted of three different types: flat, gable and hip. Finally, a convolutional neural network-based model and a Siamese neural network model were trained with the same data set and the test results were compared with each other. When testing the Siamese neural network model, which was trained with artificially produced images, with real roof images, an average classification success of 66% was achieved.

Three-dimensional magnetic resonance imaging has been proved to detect and predict the severity of progressive neurodegenerative disorders such as Parkinson's disease. The application of pre-processing with neuroimaging methods plays a vital role in post-processing for these problems. The development of technology over the years has enabled the use of deep learning methods such as convolutional neural networks (CNN) on magnetic resonance imaging (MRI) . In this study, the detection of Parkinson's disease and the prediction of disease severity were studied with 2D and 3D CNN using T1-weighted MRIs that were pre-processed with FLIRT image registration and BET non-brain tissue scraper. For 2D CNN, the median slices of the MR images in the sagittal, coronal, and axial planes were used separately and in combination. In addition, the whole brain for 3D CNN has been downsized. Considering the performance of the proposed methods, the highest results achieved for detecting Parkinson's disease were measured as 0.9620, 0.9452, 0.9407, and 0.9536 for Accuracy, F1 score, precision, and Recall, respectively. The highest result achieved for estimating the severity of Parkinson's disease was that 3D CNN was fed three times with a downsized whole MRI, which were measured for R, and R2 as 0.9150 and 0.8372, respectively. When the results obtained with the methods suggested within the scope of the study were examined, it was observed that the applied methods yielded promising performance.

Detection of neurodegenerative diseases such as Parkinson's disease, Huntington's disease, Amyotrophic Lateral Sclerosis, and grading of these diseases' severity have high clinical significance. These tasks based on walking analysis stand out compared to other methods due to their simplicity and non-invasiveness. This study has emerged to realize an artificial intelligence-based disease detection and severity prediction system for neurodegenerative diseases using gait features obtained from gait signals. For the detection of the disease, the problem is divided into parts which are subgroups of 4 classes consisting of Parkinson's, Huntington's, Amyotrophic Lateral Sclerosis diseases, and the control group. In addition, the disease vs. control subgroup where all diseases are collected under a single label, the subgroups where each disease is separately against the control group. For disease severity grading, each disease was divided into subgroups and a solution was sought for the prediction problem mentioned by various machine and deep learning methods separately for each group. In this context, the resulting detection performance was measured by the metrics of Accuracy, F1 Score, Precision, and Recall while the resulting prediction performance was measured by the metrics such as R, R2, MAE, MedAE, MSE, and RMSE.

Today, there are challenges in terms of eye care, including the treatment and prevention of visual impairment and vision rehabilitation services. Since the eye is an organ that gives information about other diseases due to its structure, examinations have an important role. This study, it is aimed to classify eye diseases with the EfficientNetB0, VGG-16, and VGG-19 models, which are deep learning-based approaches, over the dataset consisting of four classes of visual impairment from retinal images. In this way, it is aimed to reduce the visual impairment of patients with early diagnosis by identifying the people with the possibility of visual impairment, and determining which class they belong to. In this way, significant increases in the patient's quality of life can be observed. The results showed that, the best accuracy rate of 98.47% was obtained with the EfficientNetB0 model.

Digital steganography is the science of establishing hidden communication on electronics; the aim is to transmit a secret message to a particular recipient using unsuspicious carriers such as digital images, documents, and audio files with the help of specific hiding methods. This article proposes a novel steganography method that can hide plaintext payloads on digital halftone images. The proposed method distributes the secret message over multiple output copies and scatters parts of the message randomly within each output copy for increased security. A payload extraction algorithm, where plain carrier is not required, is implemented and presented as well. Results gained from conducted objective and subjective tests prove that the proposed steganography method is secure and can hide large payloads.

Neurodegenerative diseases occur because of degeneration in brain cells but can manifest as impairment of motor functions. One of the side effects of this impairment is an abnormality in walking. With the development of sensor technologies and artificial intelligence applications in recent years, the disease severity of patients can be estimated using their gait data. In this way, decision support applications for grading the severity of the disease that the patient suffers in the clinic can be developed. Thus, patients can have treatment methods more suitable for the severity of the disease. The presented research proposes a deep learning-based approach using gait data represented by a Quick Response code to develop an effective and reliable disease severity grading system for neurodegenerative diseases such as amyotrophic lateral sclerosis, Huntington's disease, and Parkinson's disease. The two-dimensional Quick Response data set was created by converting each one-dimensional gait data of the subjects with a novel representation approach to a Quick Response code. This data set was regressed with the convolutional neural network deep learning method, and a solution was sought for the problem of grading disease severity. Further, to demonstrate the success of the results obtained with the novel approach, native machine learning approaches such as Multilayer Perceptron, Random Forest, Extremely Randomized Trees, and K-Nearest Neighbours, and ensemble machine learning methods, such as voting and stacking, were applied on one-dimensional data. Finally, the results obtained on the prediction of disease severity by testing one-dimensional gait data with a convolutional neural network architecture that operates on one-dimensional data were included. The results showed that, in most cases, the two-dimensional convolutional neural network approach performed the best among all methods.

Along with the differences in customer preferences, a strong competition has emerged among the companies. Marketing managers have begun to design their marketing plans according to the target markets' needs and expectations. At this point, value-oriented marketing activities have become even more important. Personalized marketing is one of the most effective way of creating value to consumers. It is one of the best ways to establish relationships with target markets. Personalized marketing aims at delivering individualized messages to customers. By this means, personalized marketing activities attract more consumer attention relatively. It is a fact that it can also have positive impacts on the sales of the business. In this paper, a conceptual framework on personalized advertising is proposed. In this context, a hypothetical smart billboard system is designed at a shopping mall's entrance. The camera mounted system detects the car license plates via an image segmentation-based approach, which is composed of color space conversion, noise removal, edge analysis, geometric correction and connected component analysis. For license plate recognition, a 3-step image processing method, which comprises morphological dilation, character cropping and template matching is applied. A database is associating the detected license plates with the customers. When any match is found, the screen shows relevant advertisement to the customer. The study's major contribution is to propose a smart billboard system for shopping malls that presents personalized advertisements to customers based on their previous shopping experiences.

Steganography is the common name of methods that aim secret communication. In this conference proceeding, a novel steganography algorithm that hides plaintext payload in halftone images and a payload extraction algorithm that is suitable for messages hidden using this steganography method is presented. Our steganography algorithm uses a modified pattern-based halftone image generation procedure and distributes the payload into multiple output images. The proposed method has proven to be secure and able to hide large payloads. According to the objective and subjective evaluations made, it was seen that the proposed method produces promising results.