Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Publication
- Publication Type
Articles 1 - 10 of 10
Full-Text Articles in Computer Engineering
Signer-Independent Sign Language Recognition With Feature Disentanglement, İnci̇ Meli̇ha Baytaş, İpek Erdoğan
Signer-Independent Sign Language Recognition With Feature Disentanglement, İnci̇ Meli̇ha Baytaş, İpek Erdoğan
Turkish Journal of Electrical Engineering and Computer Sciences
Learning a robust and invariant representation of various unwanted factors in sign language recognition (SLR) applications is essential. One of the factors that might degrade the sign recognition performance is the lack of signer diversity in the training datasets, causing a dependence on the singer’s identity during representation learning. Consequently, capturing signer-specific features hinders the generalizability of SLR systems. This study proposes a feature disentanglement framework comprising a convolutional neural network (CNN) and a long short-term memory (LSTM) network based on adversarial training to learn a signer-independent sign language representation that might enhance the recognition of signs. We aim to …
Uncovering And Mitigating Spurious Features In Domain Generalization, Saeed Karimi, Hamdi̇ Di̇bekli̇oğlu
Uncovering And Mitigating Spurious Features In Domain Generalization, Saeed Karimi, Hamdi̇ Di̇bekli̇oğlu
Turkish Journal of Electrical Engineering and Computer Sciences
Domain generalization (DG) techniques strive to attain the ability to generalize to an unfamiliar target domain solely based on training data originating from the source domains. Despite the increasing attention given to learning from multiple training domains through the application of various forms of invariance across those domains, the enhancements observed in comparison to ERM are nearly insignificant under specified evaluation rules. In this paper, we demonstrate that the disentanglement of spurious and invariant features is a challenging task in conventional training since ERM simply minimizes the loss and does not exploit invariance among domains. To address this issue, we …
Dynamic Deep Neural Network Inference Via Adaptive Channel Skipping, Meixia Zou, Xiuwen Li, Jinzheng Fang, Hong Wen, Weiwei Fang
Dynamic Deep Neural Network Inference Via Adaptive Channel Skipping, Meixia Zou, Xiuwen Li, Jinzheng Fang, Hong Wen, Weiwei Fang
Turkish Journal of Electrical Engineering and Computer Sciences
Deep neural networks have recently made remarkable achievements in computer vision applications. However, the high computational requirements needed to achieve accurate inference results can be a significant barrier to deploying DNNs on resource-constrained computing devices, such as those found in the Internet-of-things. In this work, we propose a fresh approach called adaptive channel skipping (ACS) that prioritizes the identification of the most suitable channels for skipping and implements an efficient skipping mechanism during inference. We begin with the development of a new gating network model, ACS-GN, which employs fine-grained channel-wise skipping to enable input-dependent inference and achieve a desirable balance …
Uibee: An Improved Deep Instance Segmentation And Classification Of Ui Elements In Wireframes, Cahi̇t Berkay Kazangi̇rler, Caner Özcan, Buse Yaren Teki̇n
Uibee: An Improved Deep Instance Segmentation And Classification Of Ui Elements In Wireframes, Cahi̇t Berkay Kazangi̇rler, Caner Özcan, Buse Yaren Teki̇n
Turkish Journal of Electrical Engineering and Computer Sciences
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 …
An Exploratory Study On The Effect Of Applying Various Artificial Neural Networks To The Classification Of Lower Limb Injury, Rachel Yun, May Salama, Lamiaa Elrefaei
An Exploratory Study On The Effect Of Applying Various Artificial Neural Networks To The Classification Of Lower Limb Injury, Rachel Yun, May Salama, Lamiaa Elrefaei
Turkish Journal of Electrical Engineering and Computer Sciences
This paper explores the application of a deep neural network (DNN) framework to human gait analysis for injury classification. The paper aims to identify whether a subject is healthy or has an injury of the ankle, knee, hip, or heel solely based on ground reaction force plate measurements. We consider how three DNNs-the multi-layer perceptron (MLP), fully convolutional network (FCN), and residual network (ResNet)-can be applied to gait analysis when the number of trainable network parameters far exceeds the number of training samples, and benchmark their performance in this context against that of shallow neural networks. The DNN architectures outperformed …
Dynamic Planning Networks, Norman Tasfi, Miriam A M Capretz
Dynamic Planning Networks, Norman Tasfi, Miriam A M Capretz
Electrical and Computer Engineering Publications
We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. DPN learns to efficiently form plans by expanding a single action conditional state transition at a time instead of exhaustively evaluating each action, reducing the number of state-transitions used during planning. We observe emergent planning patterns in our agent, including classical search methods such as breadth-first and depth-first search. DPN shows improved …
Determination Of Pneumonia In X-Ray Chest Images By Using Convolutionalneural Network, Özlem Polat, Zümray Ölmez, Tamer Ölmez
Determination Of Pneumonia In X-Ray Chest Images By Using Convolutionalneural Network, Özlem Polat, Zümray Ölmez, Tamer Ölmez
Turkish Journal of Electrical Engineering and Computer Sciences
Pneumonia is one of the major diseases that cause a lot of deaths all over the world. Determining pneumonia from chest X-ray (CXR) images is an extremely difficult and important image processing problem. The discrimination of whether pneumonia is of bacterium or virus origin has also become more important during the pandemic. Automatic determination of the presence and origin of pneumonia is crucial for speeding up the treatment process and increasing the patient's survival rate. In this study, a convolutional neural network (CNN) framework is proposed for detection of pneumonia from CXR images. Two different binary CNNs and a triple …
Deep Neural Network For Load Forecasting Centred On Architecture Evolution, Santiago Gomez-Rosero, Miriam A M Capretz, London Hydro
Deep Neural Network For Load Forecasting Centred On Architecture Evolution, Santiago Gomez-Rosero, Miriam A M Capretz, London Hydro
Electrical and Computer Engineering Publications
Nowadays, electricity demand forecasting is critical for electric utility companies. Accurate residential load forecasting plays an essential role as an individual component for integrated areas such as neighborhood load consumption. Short-term load forecasting can help electric utility companies reduce waste because electric power is expensive to store. This paper proposes a novel method to evolve deep neural networks for time series forecasting applied to residential load forecasting. The approach centres its efforts on the neural network architecture during the evolution. Then, the model weights are adjusted using an evolutionary optimization technique to tune the model performance automatically. Experimental results on …
Sketic: A Machine Learning-Based Digital Circuit Recognition Platform, Mohamamd Abdel Majeed, Tasneem Almousa, Maysaa Alsalman, Abeer Yosef
Sketic: A Machine Learning-Based Digital Circuit Recognition Platform, Mohamamd Abdel Majeed, Tasneem Almousa, Maysaa Alsalman, Abeer Yosef
Turkish Journal of Electrical Engineering and Computer Sciences
In digital system design, digital logic circuit diagrams are built using interconnects and symbolic representations of the basic logic gates. Constructing such diagrams using free sketches is the first step in the design process. After that the circuit schematic or code has to be generated before being able to simulate the design. While most of the mentioned steps are automated using design automation tools, drafting the schematic circuit and then converting it into a valid format that can be simulated are still done manually due to the lack of robust tools that can recognize the free sketches and incorporate them …
Turkish Entity Discovery With Word Embeddings, Murat Kalender, Emi̇n Erkan Korkmaz
Turkish Entity Discovery With Word Embeddings, Murat Kalender, Emi̇n Erkan Korkmaz
Turkish Journal of Electrical Engineering and Computer Sciences
Entity-linking systems link noun phrase mentions in a text to their corresponding knowledge base entities in order to enrich a text with metadata. Wikipedia is a popular and comprehensive knowledge base that is widely used in entity-linking systems. However, long-tail entities are not popular enough to have their own Wikipedia articles. Therefore, a knowledge base created by using Wikipedia entities would be limited to only popular entities. In order to overcome the knowledge base coverage limitation of Wikipedia-based entity-linking systems, this paper presents an entity-discovery system that can detect semantic types of entities that are not defined in Wikipedia. The …