WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7150

Browse

Filters

2021 - 20223

Settings

Access Right: Embargoed AccessSubject: search.filters.subject.Machine learning

Search Results

Now showing 1 - 3 of 3
  • Article
    Citation - WoS: 17
    Citation - Scopus: 19
    Prediction of Aspergillus Parasiticus Inhibition and Aflatoxin Mitigation in Red Pepper Flakes Treated by Pulsed Electric Field Treatment Using Machine Learning and Neural Networks
    (Elsevier, 2022) Akdemir Evrendilek, Gülsün; Bulut, Nurullah; Atmaca, Bahar; Uzuner, Sibel
    Presence of aflatoxins in agricultural products is a worldwide problem. Because of their high heat stability and resistance to most of the food processing technologies, aflatoxin degradation is still a big challenge. Thus, efficacy of pulsed electric fields (PEF) by energies ranging from 0.97 to 17.28 J was tested to determine changes in quality properties in red pepper flakes, mitigation of aflatoxins, inactivation of aflatoxin producing Aspergillus parasiticus, reduction in aflatoxin mutagenity, and modelling of A. parasiticus inactivation in addition to aflatoxin mitigation. Maximum inactivation rate of 64.37 % with 17.28 J was encountered on the mean initial A. parasiticus count. A 99.88, 99.47, 97.75, and 99.58 % reductions were obtained on the mean initial AfG1, AfG2, AfB1, and AfB2 concentrations. PEF treated samples by 0.97, 1.36, 5.76, and 17.28 J at 1 μg/plate, 0.97, 1.92, 7.78, 10.80 J at 10 μg/plate, and 0.97, 1.92, 2.92, 4.08, 5.76, 4.86, 6.80, 9.60, 10.80, and 10.89 J at 100 μg/plate were not mutagenic. Modelling with gradient boosting regression tree (GBRT), random forest regression (RFR), and artificial neural network (ANN) provided the lowest RMSE and highest R2 value for GBRT model for the predicted inactivation of A. parasiticus, whereas ANN model provided the lowest RMSE and highest R2 for predicted mitigation of AfG1, AfB1, and AfB2. PEF treatment possess a viable alternative for aflatoxin degradation with reduced mutagenity and without adverse effect on quality properties of red pepper flakes.
  • Article
    Performance and Accuracy Predictions of Approximation Methods for Shortest-Path Algorithms on Gpus
    (Elsevier, 2022) Aktılav, Busenur; Öz, Işıl
    Approximate computing techniques, where less-than-perfect solutions are acceptable, present performance-accuracy trade-offs by performing inexact computations. Moreover, heterogeneous architectures, a combination of miscellaneous compute units, offer high performance as well as energy efficiency. Graph algorithms utilize the parallel computation units of heterogeneous GPU architectures as well as performance improvements offered by approximation methods. Since different approximations yield different speedup and accuracy loss for the target execution, it becomes impractical to test all methods with various parameters. In this work, we perform approximate computations for the three shortest-path graph algorithms and propose a machine learning framework to predict the impact of the approximations on program performance and output accuracy. We evaluate random predictions for both synthetic and real road-network graphs, and predictions of the large graph cases from small graph instances. We achieve less than 5% prediction error rates for speedup and inaccuracy values.
  • Article
    Citation - WoS: 3
    Citation - Scopus: 4
    Quasi-Supervised Strategies for Compound-Protein Interaction Prediction [article]
    (Wiley-VCH Verlag, 2021) Çakı, Onur; Karaçalı, Bilge
    In-silico compound-protein interaction prediction addresses prioritization of drug candidates for experimental biochemical validation because the wet-lab experiments are time-consuming, laborious and costly. Most machine learning methods proposed to that end approach this problem with supervised learning strategies in which known interactions are labeled as positive and the rest are labeled as negative. However, treating all unknown interactions as negative instances may lead to inaccuracies in real practice since some of the unknown interactions are bound to be positive interactions waiting to be identified as such. In this study, we propose to address this problem using the Quasi-Supervised Learning (QSL) algorithm. In this framework, potential interactions are predicted by estimating the overlap between a true positive dataset of compound-protein pairs with known interactions and an unknown dataset of all the remaining compound-protein pairs. The potential interactions are then identified as those in the unknown dataset that overlap with the interacting pairs in the true positive dataset in terms of the associated similarity structure. We also address the class-imbalance problem by modifying the conventional cost function of the QSL algorithm. Experimental results on GPCR and Nuclear Receptor datasets show that the proposed method can identify actual interactions from all possible combinations.