Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Classification (10)
- Machine learning (10)
- Support vector machine (8)
- Feature selection (7)
- Genetic algorithm (7)
-
- Feature extraction (6)
- Optimization (6)
- Wireless sensor networks (6)
- Particle swarm optimization (5)
- Artificial neural network (4)
- Clustering (4)
- Convolutional neural networks (4)
- Deep learning (4)
- Anomaly detection (3)
- Artificial bee colony (3)
- DBSCAN (3)
- Decision tree (3)
- Distributed generation (3)
- Electric vehicle (3)
- Fuzzy logic (3)
- Fuzzy logic control (3)
- Gravitational search algorithm (3)
- Image processing (3)
- K-means (3)
- Low power (3)
- Sentiment analysis (3)
- Social media (3)
- Social networks (3)
- Voltage stability (3)
- Artificial neural networks (2)
Articles 331 - 335 of 335
Full-Text Articles in Physical Sciences and Mathematics
Performance Tuning For Machine Learning-Based Software Development Effort Prediction Models, Egemen Ertuğrul, Zaki̇r Baytar, Çağatay Çatal, Ömer Can Muratli
Performance Tuning For Machine Learning-Based Software Development Effort Prediction Models, Egemen Ertuğrul, Zaki̇r Baytar, Çağatay Çatal, Ömer Can Muratli
Turkish Journal of Electrical Engineering and Computer Sciences
Software development effort estimation is a critical activity of the project management process. In this study, machine learning algorithms were investigated in conjunction with feature transformation, feature selection, and parameter tuning techniques to estimate the development effort accurately and a new model was proposed as part of an expert system. We preferred the most general-purpose algorithms, applied parameter optimization technique (GridSearch), feature transformation techniques (binning and one-hot-encoding), and feature selection algorithm (principal component analysis). All the models were trained on the ISBSG datasets and implemented by using the scikit-learn package in the Python language. The proposed model uses a multilayer …
A Hybrid Model For The Prediction Of Aluminum Foil Output Thickness In Cold Rolling Process, Ali̇ Öztürk, Ri̇fat Şeherli̇
A Hybrid Model For The Prediction Of Aluminum Foil Output Thickness In Cold Rolling Process, Ali̇ Öztürk, Ri̇fat Şeherli̇
Turkish Journal of Electrical Engineering and Computer Sciences
This study proposes a hybrid model composed of multiple prediction algorithms and an autoregressive moving average (ARMA) module for the thickness prediction. In order to attain higher accuracy, the prediction algorithms were globally combined by simple voting to reduce the effect of the inductive bias imposed by each algorithm on the dataset. The global multiexpert combination (GMEC) system included the multilayer perceptron neural network (MLPNN), radial basis function network (RBFN), multiple linear regression (MLR), and support vector machines (SVM) algorithms. The proposed hybrid model extends the GMEC system by integrating an ARMA module for the output. On the test dataset, …
Dynamic Physarum Solver: A Bio-Inspired Shortest Path Method Of Dynamically Changing Graphs, Hi̇lal Arslan
Dynamic Physarum Solver: A Bio-Inspired Shortest Path Method Of Dynamically Changing Graphs, Hi̇lal Arslan
Turkish Journal of Electrical Engineering and Computer Sciences
In dynamic graphs, edge weights of the graph change with time and solving the shortest path problem in such graphs is an important real-world problem. The studies in the literature require excessive computational time for computing the dynamic shortest path since determining changing edge weights is difficult especially when the graph size becomes large. In this paper, we propose a dynamic bio-inspired algorithm for finding the dynamic shortest path for large graphs based on Physarum Solver, which is a shortest path algorithm for static graphs. The proposed method is evaluated using three different large graph models representing diverse real-life applications. …
An Approach To Improve The Performance Of Cooperative Unmanned Vehicle Team, Ömer Ci̇han Kivanç
An Approach To Improve The Performance Of Cooperative Unmanned Vehicle Team, Ömer Ci̇han Kivanç
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, a method based on optimal energy management is proposed in order to improve the operational and tactical abilities of collaborative unmanned vehicle teams. Collaborative unmanned systems are used in surveillance, tracking, and military operations. The optimal assignment of these tasks requires cooperation among the vehicles in order to generate a strategy that is efficient with respect to overall mission duration and satisfies all problem constraints. The key motivation behind this paper is to design an unmanned vehicle team that mitigates the disadvantages caused by the structures and characteristics of unmanned ground vehicles (UGVs) and unmanned aerial vehicles …
Hybix: A Novel Encoding Bitmap Index For Space- And Time-Efficient Query Processing, Naphat Keawpibal, Ladda Preechaveerakul, Sirirut Vanichayobon
Hybix: A Novel Encoding Bitmap Index For Space- And Time-Efficient Query Processing, Naphat Keawpibal, Ladda Preechaveerakul, Sirirut Vanichayobon
Turkish Journal of Electrical Engineering and Computer Sciences
A bitmap-based index is an effective and efficient indexing method for answering selective queries in a read-only environment. It offers improved query execution time by applying low-cost Boolean operators on the index directly, before accessing raw data. A drawback of the bitmap index is that index size increases with the cardinality of indexed attributes, which additionally has an impact on a query execution time. This impact is related to an increase of query execution time due to the scanning of bitmap vectors to answer the queries. In this paper, we propose a new encoding bitmap index, called the HyBiX bitmap …