Search

This study focuses on the neural machine translation task for the TR-EN language pair, which is considered a low-resource language pair. We investigated fine-tuning strategies for pre-trained language models. Specifically, we explored the effectiveness of parameter-efficient adapter methods for fine-tuning multilingual pre-trained language models. Various combinations of LoRA and bottleneck adapters were experimented with. The combination of LoRA and bottleneck adapters demonstrated superior performance compared to other methods. This combination required only 5% of the pre-trained language model to be fine-tuned. The proposed method enhances parameter efficiency and reduces computational costs. Compared to the full fine-tuning of the multilingual pre-trained language model, it showed only a 3% difference in the BLEU score. Thus, nearly the same performance was achieved at a significantly lower cost. Additionally, models using only bottleneck adapters performed worse despite having a higher parameter count. Although adding LoRA to pre-trained language models alone did not yield sufficient performance, the proposed method improved machine translation. The results obtained are promising, particularly for low-resource language pairs. The proposed method requires less memory and computational load while maintaining translation quality. [ABSTRACT FROM AUTHOR]

As information systems become more widespread, data security becomes increasingly important. While traditional encryption methods provide effective protection against unauthorized access, they often struggle with multimedia data like images and videos. This necessitates specialized image encryption approaches. With the rise of mobile and Internet of Things (IoT) devices, lightweight image encryption algorithms are crucial for resource-constrained environments. These algorithms have applications in various domains, including medical imaging and surveillance systems. However, the biggest challenge of lightweight algorithms is balancing strong security with limited hardware resources. This work introduces a novel nonlinear matrix permutation approach applicable to both confusion and diffusion phases in lightweight image encryption. The proposed method utilizes three different chaotic maps in harmony, namely a 2D Zaslavsky map, 1D Chebyshev map, and 1D logistic map, to generate number sequences for permutation and diffusion. Evaluation using various metrics confirms the method's efficiency and its potential as a robust encryption framework. The proposed scheme was tested with 14 color images in the SIPI dataset. This approach achieves high performance by processing each image in just one iteration. The developed scheme offers a significant advantage over its alternatives, with an average NPCR of 99.6122, UACI of 33.4690, and information entropy of 7.9993 for 14 test images, with an average correlation value as low as 0.0006 and a vast key space of 2 800 . The evaluation results demonstrated that the proposed approach is a viable and effective alternative for lightweight image encryption. [ABSTRACT FROM AUTHOR]

Histopathology, vital in diagnosing medical conditions, especially in cancer research, relies on analyzing histopathology images (HIs). Nuclei segmentation, a key task, involves precisely identifying cell nuclei boundaries. Manual segmentation by pathologists is time‐consuming, prompting the need for robust automated methods. Challenges in segmentation arise from HI complexities, necessitating advanced techniques. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNNs), have transformed nuclei segmentation. This study emphasizes feature extraction, introducing the ConvNext Mixer‐based Encoder‐Decoder (CNM‐ED) model. Unlike traditional CNN based models, the proposed CNM‐ED model enables the extraction of spatial and long context features to address the inherent complexities of histopathology images. This method leverages a multi‐path strategy using a traditional CNN architecture as well as different paths focused on obtaining customized long context features using the ConvNext Mixer block structure that combines ConvMixer and ConvNext blocks. The fusion of these diverse features in the final segmentation output enables improved accuracy and performance, surpassing existing state‐of‐the‐art segmentation models. Moreover, our multi‐level feature extraction strategy is more effective than models using self‐attention mechanisms such as SwinUnet and TransUnet, which have been frequently used in recent years. Experimental studies were conducted using five different datasets (TNBC, MoNuSeg, CoNSeP, CPM17, and CryoNuSeg) to analyze the performance of the proposed CNM‐ED model. Comparisons were made with various CNN based models in the literature using evaluation metrics such as accuracy, AJI, macro F1 score, macro intersection over union, macro precision, and macro recall. It was observed that the proposed CNM‐ED model achieved highly successful results across all metrics. Through comparisons with state‐art‐of models from the literature, the proposed CNM‐ED model stands out as a promising advancement in nuclei segmentation, addressing the intricacies of histopathological images. The model demonstrates enhanced diagnostic capabilities and holds the potential for significant progress in medical research. [ABSTRACT FROM AUTHOR]

In recent years, many studies have been carried out in the field of artificial intelligence in the literature with the development of equipment. Face recognition algorithms have an important place among these developments. Among the face recognition algorithms, the most successful ones are usually deep learning approaches. Models such as SphereFace, CosFace, ArcFace, and MagFace are important deep learning models in the literature. Despite their success, deep learning models are often computationally costly. Therefore, advanced methods are needed to reduce the computational load for these models. One of the most valid methods for this is to choose the most valuable one among embedding features for face recognition. Thus, cost can be reduced, and accuracy values can be increased even more. In this study, the most valuable of the 512 embedded features in the MagFace model was tried to be obtained by using PSO, GA, SCA, and DE optimization algorithms. As a result, accuracy values of 99.83%, 98.57%, and 98.65% were reached for 193, 252, and 280 features selected in the LFW, CFP, and AGEDB datasets, respectively. [ABSTRACT FROM AUTHOR]

Retinal blood vessels are directly or indirectly associated with many diseases. The retinal blood vessels consist of artery and vein vessels. With the automatic correct identification of these vessels, many diseases can be prevented. In this paper, a method is proposed to separate between arteries and veins on retinal blood vessel images. In the proposed method, firstly, the image preprocessing step is applied. Then, image patches are obtained from pre-processed retinal fundus images. These patches are prepared as input to the deep learning network architecture. The proposed deep learning network architecture is presented as a new CNN architecture. This architecture decides whether the blood vessel pixels in the fundus image are arteries or veins. The proposed method was evaluated on publicly available given DRIVE, INSPIRE datasets, and the recently created LES-AV dataset. The performance of the proposed method was evaluated by using the most commonly used sensitivity, specificity, and accuracy performance measures. The accuracy measure for all vessel pixels is 0.9110 for DRIVE, 0.9654 for INSPIRE, and 0.9531 for LES-AV dataset. The proposed method is compared with other state-of-the-art artery/vein separation methods. The experimental results of the proposed method are promising. This method is suitable for automatic artery/vein separation. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Polytechnic is the property of Journal of Polytechnic and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Hyperspectral images (HSI) are 3-dimensional (3D) image cubes with two spatial and one spectral dimensions. The development of deep learning methods has had a significant impact on HSI classification. Especially convolutional neural network (CNN) based methods are getting more attention in this field. In this study, we make use of the deep learning architectures LeNet5, AlexNet, VGG16, GoogleNet and ResNet50, which are among the successful examples of CNN for the HSI classification problem. We use a 3D CNN-based hybrid approach when using these architectures. Because, using 3D CNN, spectral-spatial features are extracted simultaneously. In this case, the classification accuracy of HSIs is increased with the spectral-spatial-based deep learning architecture. However, in the proposed model, principal component analysis (PCA) is used as a preprocessing technique for optimal band extraction from HSIs. After applying PCA, 3D cubes are obtained by neighborhood extraction and given to the input of deep learning architectures. Indian pines, Salinas, Botswana and HyRANK-Loukia datasets were used to compare the classification performances of 3D CNN-based deep learning architectures. As a result of the applications, the best classification accuracy was obtained with VGG16 architectures in Indian pines dataset, ResNet50 in Botswana dataset, VGG16 in HyRANK-Loukia dataset, LeNet5 and VGG16 architectures in Salinas dataset. [ABSTRACT FROM AUTHOR]

English is accepted as an academic language in the world. This necessitates the use of English in their academic studies for speakers of other languages. Even when these researchers are competent in the use of the English language, some mistakes may occur while writing an academic article. To solve this problem, academicians tend to use automatic translation programs or get assistance from people with an advanced level of English. This study offers an expert system to enable assistance to the researchers throughout their academic article writing process. In this study, Turkish which is considered among low-resource languages is used as the source language. The proposed model combines the transformer encoder-decoder architecture model with the pre-trained Sci-BERT language model via the shallow fusion method. The model uses a Fully Attentional Network Layer instead of a Feed-Forward Network Layer in the known shallow fusion method. In this way, a higher success rate could be achieved by increasing the attention at the word level. Different metrics were used to evaluate the created model. The model created as a result of the experiments reached 45.1 BLEU and 73.2 METEOR scores. In addition, the proposed model achieved 20.12 and 20.56 scores, respectively, with the zero-shot translation method in the World Machine Translation (2017–2018) test datasets. The proposed method could inspire other low-resource languages to include the language model in the translation system. In this study, a corpus composed entirely of academic sentences is also introduced to be used in the translation system. The corpus consists of 1.2 million parallel sentences. The proposed model and corpus are made available to researchers on our GitHub page. [ABSTRACT FROM AUTHOR]

Copyright of Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Hyperspectral images (HSI) are contiguous band images commonly used in remote sensing. Deep learning (DL) is an effective method used in HSI classification. Convolutional neural networks (CNN) are one of the DL methods used in HSI classification. It provides automated approaches that can learn abstract features of HSIs from spectral-spatial fields. The high dimensionality of the HSIs increases the computational complexity. Therefore, most of the developed CNN models perform dimensionality reduction as a preprocessing step. Another problem in HSI classification is that spectral-spatial features must be considered in order to obtain accurate results. Because, HSI classification performance is highly dependent on spectralspatial information. In this study, a new 3D CNN model is proposed for HSI classification. The proposed method provides an effective method to simultaneously extract spectral-spatial features in HSIs. The network uses the 3D hyperspectral cube at the input. Principal component analysis is used to eliminate the dimensional redundancy in the hyperspectral cube. Then, using neighborhood extraction, spectral-spatial features are extracted effectively. The proposed method has been tested with 4 datasets. The application results were compared with 7 different DL-based methods and it was seen that our 4CF-Net method showed better classification performance. [ABSTRACT FROM AUTHOR]

In recent years, the diabetes-related retinal disease has become one of the leading causes of blindness. In order to prevent this disease, the retinal network structure needs to be segmented correctly. Computer-aided diagnostic systems are required for accurate and fast segmentation of the retinal network structure. In this paper, a method is proposed to segments retinal vessels automatically in the color retinal fundus image. A method based on morphological procedures to segmentation of vessels has been applied on retinal images. Three different thresholding methods were applied to the fundus image obtained as a result of morphological processes. These thresholding methods are; Multiple Thresholding, Maximum Entropy Based Thresholding and Fuzzy Cluster Based Thresholding methods. As a result of thresholding, segmented vessel images were obtained. The aim of this paper is to show the performance comparison of different thresholding algorithms on the same images. The method applied has been validated on the retinal image data set that is publicly available. The experimental results show that the proposed method can accurately detect. The accuracy ratio of the thresholding algorithms on the data set consisting of 40 images was calculated as 0.952 for Fuzzy Logic Based Threshold, 0.950 for Maximum Entopy Based Threshold and 0.925 for Multiple Threshold. [ABSTRACT FROM AUTHOR]

Copyright of Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Author Profiling is a text set analysis to reveal various characteristics of the author by examining the style and content of a text. These features include factors such as age, gender, personality traits and even profession. Gender identification is one of the subfields of author profile creation. Gender identification is very important in the investigation of marketing (advertising), sociological and psychological events, as well as forensic events such as spreading fake news, especially cybercrime. In addition, identifying the gender of the communication partner can help prevent fraud and abuse through social media such as e-mail, blogs, forums. Identifying the gender of short posts for the Turkish language is an area that has not been studied much compared to other languages. In this study, it was attempted to determine gender from Turkish Twitter posts. Twitter posts are widely used for gender identification, although they may include ungrammatical structures, abbreviated words and meaningless sentence structures. The problem is handled as a classification task. In the study, machine learning methods (TF-IDF + SVM), deep learning methods (LSTM, CNN) and pre-trained language models for Turkish (BERT, DistilBert, Electra) were used. As a result of the experiments, Bert model with the word size of 128k provided the highest success (80.1%). This study also features as a detailed study for other text classification tasks. [ABSTRACT FROM AUTHOR]

Image processing-based fire/flame detection has become popular in recent years. In this paper, a novel fire/flame detection system based on a new conversion matrix and artificial bee colony algorithm was presented. Flame and non-flame image pixel values were combined to have a new feature matrix. A conversion matrix was generated randomly. The conversion matrix was multiplied by the feature matrix. The error of this multiplication result was calculated using the K-means clustering algorithm. The conversion matrix was updated until getting desired performance using artificial bee colony algorithm. At the end of the updating process, updated conversion matrix was multiplied with all images in the dataset to move all images to new color space. The final images were converted into binary images. Otsu method was used to get binary images. These binary images were compared with the corresponding ground truth images in the dataset. The aim of this comparison is to calculate the similarity ratio of the two images. This ratio shows the extent to which the original image features are preserved. A forest fire dataset was used which has 500 forest fire images. It is publicly available and called as Corsican Fire Database. Jaccard and Dice similarity measure parameters were used to evaluate the proposed system performance and compared with other similar study such as particle swarm optimization. Evaluated mean Jaccard index value was 0.76, and mean Dice index value was 0.85. This evaluation was made for 500 images. These results provide that this system can be used in fire/flame detection systems. [ABSTRACT FROM AUTHOR]

To date, different approaches have been used to be correctly identified of plant species. Leaves are the most important approaches as part of the plants which provide many features with advantages such as shape, color and vein texture. In this study, a new approach based on the geometrical properties of the leaf has been proposed. This method called Edge Step (ES), consists of features such as angle, center-edge length and edge distance by using edge points in the shape boundary curve. In addition, Shearlet Transform method, which has features such as good sensitivity to tissue identification, rapid calculation and directional independence, is used. In addition to these methods, Color features and Gray-Level Co-Occurrence Matrix (GLCM) method to extract color and texture properties from leaf images have been applied. Attributes derived from all these methods were tested with the Extreme Learning Machine (ELM) classifier method as separately and combination. The proposed study has been tested by using four different plant leaf datasets such as Flavia, Swedish, ICL and Foliage. Using these datasets, studies based on texture, shape and color characteristics have been compared with the performance of the proposed approach. As a result, the proposed method is identified to be more successful than the other methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Polytechnic is the property of Journal of Polytechnic and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Human deaths caused by brain tumors are increasing nowadays. The brain tumor can grow very fast and can get twice of it is usual size. Therefore, physician have to analysis the Magnetic Resonance (MR) images quickly. This step is vital for the diagnosis of cancer, for treatment planning and for evaluation of the treatment outcome. If the patient who has the tumor in his brain is not treated correctly and quickly, the patient's chance of survival may decrease and resulted in death. In this article, we were developed a computer-assisted automated tumor detection system that can assist the physician in detecting and locating the tumor easily from brain MR images. The developed system is based on Regional based Convolutional Neural Networks (RCNN), which is one of the deep learning architectures. Besides RCNN is a structure that uses the architecture of the Convolutional Neural Networks (CNN), it can be considered as a structure in which the interested region is given as input in addition to the input images. In the proposed method, different RCNN architectures were designed and tested on Benchmark, Rembredant and Harvard datasets. The highest accuracy was obtained from the RCNN4 architecture on Benchmark data set is 99.10%. The highest average accuracy was calculated as 98.66% with RCNN4 architecture. Also, the success of the proposed method was compared with some of the methods exist in the literature. These comparisons showed that the proposed method is more successful and effective. [ABSTRACT FROM AUTHOR]

The timely and accurate diagnosis of plant diseases plays an important role in preventing the loss of productivity and loss or reduced quantity of agricultural products. In order to solve such problems, methods based on machine learning can be used. In recent years, deep learning, which is especially widely used in image processing, offers many new applications related to precision agriculture. In this study, we evaluated the performance results using different approaches of nine powerful architectures of deep neural networks for plant disease detection. Transfer learning and deep feature extraction methods are used, which adapt these deep learning models to the problem at hand. The utilized pretrained deep models are considered in the presented work for feature extraction and for further fine-tuning. The obtained features using deep feature extraction are then classified by support vector machine (SVM), extreme learning machine (ELM), and K-nearest neighbor (KNN) methods. The experiments are carried out using data consisting of real disease and pest images from Turkey. The accuracy, sensitivity, specificity, and F1-score are all calculated for performance evaluation. The evaluation results show that deep feature extraction and SVM/ELM classification produced better results than transfer learning. In addition, the fc6 layers of the AlexNet, VGG16, and VGG19 models produced better accuracy scores when compared to the other layers. [ABSTRACT FROM AUTHOR]

Human deaths caused by brain tumors are increasing nowadays. The brain tumor can grow very fast and can get twice of it is usual size. Therefore, physician have to analysis the Magnetic Resonance (MR) images quickly. This step is vital for the diagnosis of cancer, for treatment planning and for evaluation of the treatment outcome. If the patient who has the tumor in his brain is not treated correctly and quickly, the patient's chance of survival may decrease and resulted in death. In this article, we were developed a computer-assisted automated tumor detection system that can assist the physician in detecting and locating the tumor easily from brain MR images. The developed system is based on Regional based Convolutional Neural Networks (RCNN), which is one of the deep learning architectures. Besides RCNN is a structure that uses the architecture of the Convolutional Neural Networks (CNN), it can be considered as a structure in which the interested region is given as input in addition to the input images. In the proposed method, different RCNN architectures were designed and tested on Benchmark, Rembredant and Harvard datasets. The highest accuracy was obtained from the RCNN4 architecture on Benchmark data set is 99.10%. The highest average accuracy was calculated as 98.66% with RCNN4 architecture. Also, the success of the proposed method was compared with some of the methods exist in the literature. These comparisons showed that the proposed method is more successful and effective. [ABSTRACT FROM AUTHOR]

The brain cancer treatment process depends on the physician's experience and knowledge. For this reason, using an automated tumor detection system is extremely important to aid radiologists and physicians to detect brain tumors. The proposed method has three stages, which are preprocessing, the extreme learning machine local receptive fields (ELM-LRF) based tumor classification, and image processing based tumor region extraction. At first, nonlocal means and local smoothing methods were used to remove possible noises. In the second stage, cranial magnetic resonance (MR) images were classified as benign or malignant by using ELM-LRF. In the third stage, the tumors were segmented. The purpose of the study was using only cranial MR images, which have a mass, in order to save the physician's time. In the experimental studies the classification accuracy of cranial MR images is 97.18%. Evaluated results showed that the proposed method's performance was better than the other recent studies in the literature. Experimental results also proved that the proposed method is effective and can be used in computer aided brain tumor detection. [ABSTRACT FROM AUTHOR]