WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7150
Browse
4 results
Search Results
Article Citation - WoS: 8Citation - Scopus: 14An End-To Trainable Feature Selection-Forecasting Architecture Targeted at the Internet of Things(IEEE, 2021) Nakıp, Mert; Karakayalı, Kubilay; Güzeliş, Cüneyt; Rodoplu, VolkanWe develop a novel end-to-end trainable feature selection-forecasting (FSF) architecture for predictive networks targeted at the Internet of Things (IoT). In contrast with the existing filter-based, wrapper-based and embedded feature selection methods, our architecture enables the automatic selection of features dynamically based on feature importance score calculation and gamma-gated feature selection units that are trained jointly and end-to-end with the forecaster. We compare the performance of our FSF architecture on the problem of forecasting IoT device traffic against the following existing (feature selection, forecasting) technique pairs: Autocorrelation Function (ACF), Analysis of Variance (ANOVA), Recurrent Feature Elimination (RFE) and Ridge Regression methods for feature selection, and Linear Regression, Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM), 1 Dimensional Convolutional Neural Network (1D CNN), Autoregressive Integrated Moving Average (ARIMA), and Logistic Regression for forecasting. We show that our FSF architecture achieves either the best or close to the best performance among all of the competing techniques by virtue of its dynamic, automatic feature selection capability. In addition, we demonstrate that both the training time and the execution time of FSF are reasonable for IoT applications. This work represents a milestone for the development of predictive networks for IoT in smart cities of the near future.Article Citation - WoS: 9A Fuzzy Logic Model for Benchmarking the Knowledge Management Performance of Construction Firms(NRC Research Press, 2011) Kale, Serdar; Karaman, Erkan A.Knowledge management is rapidly becoming a key organizational capability for creating competitive advantage in the construction industry. The emergence of knowledge management in this capacity poses enormous challenges to executives of construction firms. This paper proposes a model for benchmarking the knowledge management performance of construction firms that can guide and assist construction business executives in meeting these challenges. The proposed model incorporates benchmarking and knowledge management concepts with fuzzy set theory to adequately handle imprecision, vagueness, and uncertainty that prevail in this process. It uses the fuzzy-weighted average (FWA) algorithm to evaluate the knowledge management performance of construction firms. It is an internal reporting model that can provide powerful diagnostic information to executives of construction firms by evaluating their firm's knowledge management performance, identifying their firm's strengths and weaknesses with regard to each knowledge management practice, and setting priorities for managerial actions related to knowledge management practices that need improvement. A real-world case study is presented to illustrate the implementation and utility of the proposed model.Article Citation - WoS: 10Citation - Scopus: 26Mobile Join Operators for Restricted Sources(Hindawi Publishing Corporation, 2005) Özakar, Belgin; Morvan, Franck; Hameurlain, AbdelkaderWe consider the problem of query execution when there is limited access to the relations, i.e. when binding patterns require values to be specified in order to get data from the relation. This problem is common in virtual data integration systems where there are heterogeneous sources with various restricted access patterns and query capabilities. Another problem is the lack of the statistical information about the sources and occurrence of unpredictable events. We introduce two mobile join operators, MDJoin and SMDJoin which are designed for restricted sources and implemented using ‘mobile agents’ in order to benefit from their autonomous and reactive characteristics. Mobile operators of restricted sources are capable to deal with restricted sources and react to the variations between the compile-time estimations and run-time computations of data during query execution. The difference between the two new query operators lies in their level of adaptation ability to the execution environment. Performance results show that mobile agent-based approach at operator level can lead to a significant reduction in response time with restricted sources.Article Citation - WoS: 27Citation - Scopus: 28An Exergetic Performance Assessment of Three Different Food Driers(SAGE Publications Inc., 2010) Hepbaşlı, Arif; Erbay, Zafer; Çolak, Neslihan; Hancıoğlu, Ebru; İçier, FilizIn this study, plum slices were dried in three different driers (tray, fluid bed, and heat pump (HP) driers). Drying experiments were carried out at an air temperature range of 45-55 °C with an air velocity of 1.5 m/s. The performance of the driers along with their main components was evaluated and compared by using the exergy analysis method. The most important component for improving the system efficiency was determined to be the fan-heater combination for both the tray and fluid bed driers, and the motor-compressor assembly for the HP drier. The exergy loss and flow diagram (the so-called Grassmann diagram) of the driers was also presented to give quantitative information regarding the proportion of the exergy input dissipated in the various system components. Effects of the drying air temperature on the performance of the drying process were discussed. The highest exergetic efficiency values were obtained to range from 72.72 to 75.66 per cent for the HP drier, followed by the tray and fluid bed driers varying between 37.94 and 39.46 per cent, and between 22.83 and 24.07 per cent, respectively.