Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
9 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.Conference Object Cash Flow Forecasting by Using Time Series Methods in Geothermal District Heating Systems: Balcova - Narlidere Case(National Technical University of Athens, 2006) Erdoğmuş, Abdullah Berkan; Özerdem, BarışCash flow forecasting is one of the difficult and important tasks in an economic evaluation of a geothermal investment. Geothermal district heating systems are characterized by a high capital cost. In addition, relatively low operation and maintenance costs occur throughout their life. The aim of this research is to estimate the potential cash flows for Balcova - Narlidere Geothermal District Heating System by using historical data accumulated over a period of time and several forecasting methods: moving average, exponential smoothing, adjusted exponential smoothing and curve fitting functions. Mean absolute percentage deviation (MAPD) which is the most common approach to select the appropriate method to a particular time series is used in the selection of the most suitable model. Alternative methods are compared with each other regarding to their MAPD values. It is found that the models represented by exponential curve fitting functions have smaller MAPD values and give better results in cash flow forecasting of investment investigated.Article Citation - WoS: 560Citation - Scopus: 607A Community Effort To Assess and Improve Drug Sensitivity Prediction Algorithms(Nature Publishing Group, 2014) Costello, James C.; Heiser, Laura M.; Georgii, Elisabeth; Gönen, Mehmet; Menden, Michael P.; Wang, Nicholas J.; Bansal, Mukesh; Ammad-ud-din, Muhammad; Hintsanen, Petteri; Khan, Suleiman A.; Mpindi, John-Patrick; Kallioniemi, Olli; Honkela, Antti; Aittokallio, Tero; Wennerberg, Krister; NCI-DREAM Community; Karaçalı, Bilge; Collins, James J.; Gallahan, Dan; Singer, Dinah; Saez-Rodriguez, Julio; Kaski, Samuel; Gray, Joe W.; Stolovitzky, GustavoPredicting the best treatment strategy from genomic information is a core goal of precision medicine. Here we focus on predicting drug response based on a cohort of genomic, epigenomic and proteomic profiling data sets measured in human breast cancer cell lines. Through a collaborative effort between the National Cancer Institute (NCI) and the Dialogue on Reverse Engineering Assessment and Methods (DREAM) project, we analyzed a total of 44 drug sensitivity prediction algorithms. The top-performing approaches modeled nonlinear relationships and incorporated biological pathway information. We found that gene expression microarrays consistently provided the best predictive power of the individual profiling data sets; however, performance was increased by including multiple, independent data sets. We discuss the innovations underlying the top-performing methodology, Bayesian multitask MKL, and we provide detailed descriptions of all methods. This study establishes benchmarks for drug sensitivity prediction and identifies approaches that can be leveraged for the development of new methods.Article Citation - WoS: 240Citation - Scopus: 264A Community Computational Challenge To Predict the Activity of Pairs of Compounds(Nature Publishing Group, 2014) Bansal, Mukesh; Yang, Jichen; Karan, Charles; Menden, Michael P.; Costello, James C.; Tang, Hao; Xiao, Guanghua; Li, Yajuan; Allen, Jeffrey; Zhong, Rui; Chen, Beibei; Kim, Minsoo; Wang, Tao; Heiser, Laura M.; Realubit, Ronald; Mattioli, Michela; Alvarez, Mariano J.; Shen, Yao; NCI-DREAM Community; Karaçalı, Bilge; Gallahan, Daniel; Singer, Dinah; Saez-Rodriguez, Julio; Xie, Yang; Stolovitzky, Gustavo; Califano, AndreaRecent therapeutic successes have renewed interest in drug combinations, but experimental screening approaches are costly and often identify only small numbers of synergistic combinations. The DREAM consortium launched an open challenge to foster the development of in silico methods to computationally rank 91 compound pairs, from the most synergistic to the most antagonistic, based on gene-expression profiles of human B cells treated with individual compounds at multiple time points and concentrations. Using scoring metrics based on experimental dose-response curves, we assessed 32 methods (31 community-generated approaches and SynGen), four of which performed significantly better than random guessing. We highlight similarities between the methods. Although the accuracy of predictions was not optimal, we find that computational prediction of compound-pair activity is possible, and that community challenges can be useful to advance the field of in silico compound-synergy prediction.Conference Object Citation - WoS: 1Citation - Scopus: 2Fisher's Linear Discriminant Analysis Based Prediction Using Transient Features of Seismic Events in Coal Mines(Institute of Electrical and Electronics Engineers Inc., 2016) Köktürk Güzel, Başak Esin; Karaçalı, BilgeIdentification of seismic activity levels in coal mines is important to avoid accidents such as rockburst. Creating an early warning system that can save lives requires an automated way of predicting. This study proposes a prediction algorithm for the AAIA'16 Data Mining Challenge: Predicting Dangerous Seismic Events in Active Coal Mines that is based on transient activity features along with average indicators evaluated by a Fisher's linear discriminant analysis. Performance evaluation experiments on the training datasets revealed an accuracy level of around 0.9438 while the performance on the test dataset was at a level of 0.9297. These results suggest that the proposed approach achieves high accuracy in predicting danger seismic events while maintaining low complexity.Article Citation - WoS: 3Citation - Scopus: 4Hierarchical Motif Vectors for Prediction of Functional Sites in Amino Acid Sequences Using Quasi-Supervised Learning(Institute of Electrical and Electronics Engineers Inc., 2012) Karaçalı, BilgeWe propose hierarchical motif vectors to represent local amino acid sequence configurations for predicting the functional attributes of amino acid sites on a global scale in a quasi-supervised learning framework. The motif vectors are constructed via wavelet decomposition on the variations of physico-chemical amino acid properties along the sequences. We then formulate a prediction scheme for the functional attributes of amino acid sites in terms of the respective motif vectors using the quasi-supervised learning algorithm that carries out predictions for all sites in consideration using only the experimentally verified sites. We have carried out comparative performance evaluation of the proposed method on the prediction of N-glycosylation of 55,184 sites possessing the consensus N-glycosylation sequon identified over 15,104 human proteins, out of which only 1,939 were experimentally verified N-glycosylation sites. In the experiments, the proposed method achieved better predictive performance than the alternative strategies from the literature. In addition, the predicted N-glycosylation sites showed good agreement with existing potential annotations, while the novel predictions belonged to proteins known to be modified by glycosylation.Article Citation - WoS: 6Citation - Scopus: 10Determination of Volume of Alaska Pollock (theragra Chalcogramma) by Image Analysis(Taylor and Francis Ltd., 2011) Balaban, Murat Ömer; Chombeau, Melanie; Gümüş, Bahar; Cırban, DilşatThe objective of this study was to develop two methods to predict the volume of whole Alaska pollock and to compare the results with the experimentally measured volumes. One hundred fifty-five whole pollock, obtained from a Kodiak processor, were individually immersed in a graduated cylinder equipped with an outflow tube to catch the displaced water as a result of immersion. The weight of the water was recorded. Then the fish were placed in a light box equipped with a digital video camera, and the side view and top view recorded (2 images for each fish). A reference square of known surface area was placed by the fish. A cubic spline method to predict volume by integration of cross-sectional area slices based on the top and side views and an empirical equation using dimensional (length L, width W, depth D) measurements at three locations of the fish image were developed. The R 2 value for the correlation between the L × W × D versus measured volume was 0.987. The best R 2 for the correlation of the predicted volume by the cubic spline method versus the measured volume was 0.99. Image analysis can be used reliably to predict the volume of whole Alaska pollock. © Taylor & Francis Group, LLC.Article Citation - WoS: 46Citation - Scopus: 49Predicting and Forecasting Flow Discharge at Sites Receiving Significant Lateral Inflow(John Wiley and Sons Inc., 2007) Tayfur, Gökmen; Moramarco, Tommaso; Singh, Vijay P.Two models, one linear and one non-linear, were employed for the prediction of flow discharge hydrographs at sites receiving significant lateral inflow. The linear model is based on a rating curve and permits a quick estimation of flow at a downstream site. The non-linear model is based on a multilayer feed-forward back propagation (FFBP) artificial neural network (ANN) and uses flow-stage data measured at the upstream and downstream stations. ANN predicted the real-time storm hydrographs satisfactorily and better than did the linear model. The results of sensitivity analysis indicated that when the lateral inflow contribution to the channel reach was insignificant, ANN, using only the flow-stage data at the upstream station, satisfactorily predicted the hydrograph at the downstream station. The prediction error of ANN increases exponentially with the difference between the peak discharge used in training and that used in testing. ANN was also employed for flood forecasting and was compared with the modified Muskingum model (MMM). For a 4-h lead time, MMM forecasts the floods reliably but could not be applied to reaches for lead times greater than the wave travel time. Although ANN and MMM had comparable performances for an 8-h lead time, ANN is capable of forecasting floods with lead times longer than the wave travel time.Article Citation - WoS: 14Citation - Scopus: 22Forecasting Ambient Air So2 Concentrations Using Artificial Neural Networks(Taylor and Francis Ltd., 2006) Sofuoğlu, Sait Cemil; Sofuoğlu, Aysun; Birgili, Savaş; Tayfur, GökmenAn Artificial Neural Networks (ANNs) model is constructed to forecast SO 2 concentrations in Izmir air. The model uses meteorological variables (wind speed and temperature) and measured particulate matter concentrations as input variables. The correlation coefficient between observed and forecasted concentrations is 0.94 for the network that uses all three variables as input parameters. The root mean square error value of the model is 3.60 g/mt 3 . Considering the limited number of available input variables, model performances show that ANNs are a promising method of modeling to forecast ambient air SO 2 concentrations in Izmir.