Browsing by Subject "Machine learning"

Now showing 1 - 20 of 86

Embargo
A decomposable branch-and-price formulation for optimal classification trees
(2024-07) Yöner, Elif Rana
Construction of Optimal Classification Trees (OCTs) using mixed-integer programs, is a promising approach as it returns a tree with minimum classification error. Yet solving integer programs to optimality is known to be computationally costly, especially as the size of the instance and the depth of the tree grow, calling for efficient solution methods. Our research presents a new, decomposable model which lends itself to efficient solution algorithms such as Branch-and-Price. We model the classification tree using a “patternbased” formulation, deciding which feature should be used to split data at each branching node of each leaf. Our results are promising, illustrating the potential of decomposition in the domain of binary OCTs.
Embargo
A machine learning approach for the estimation of photocatalytic activity of ALD ZnO thin films on fabric substrates
(Elsevier, 2024-02-01) Akyıldız, Halil I.; Yiğit, E.; Arat, A. B.; Islam, S.
Research in the field of photocatalytic wastewater treatment is striving to enhance catalyst materials to achieve high-performance systems. A promising approach to this goal has been immobilizing photocatalytic materials on fibrous substrates via atomic layer deposition (ALD). Nevertheless, both the ALD process and the assessment of photocatalytic performance involve a multitude of parameters necessitating thorough investigation. In this study, we employ popular machine-learning algorithms, including Support Vector Regression (SVR) and Artificial Neural Networks (ANN), to predict the photocatalytic activity of ALD-coated textiles. The photocatalytic activity is evaluated through methylene blue and methyl orange degradation tests. Machine learning algorithms are tested and trained using the k-fold cross-validation technique. The findings demonstrate that the ANN and SVR methods utilized in this research can predict catalytic activity with mean absolute percentage errors (MAPE) of 2.35 and 3.25, respectively. This study illuminates that, within the defined range of process parameters, the photocatalytic activity of ALD-coated textiles can be precisely estimated with suitable machine-learning algorithms.
Open Access
Activity recognition invariant to sensor orientation with wearable motion sensors
(MDPI AG, 2017) Yurtman, A.; Barshan, B.
Most activity recognition studies that employ wearable sensors assume that the sensors are attached at pre-determined positions and orientations that do not change over time. Since this is not the case in practice, it is of interest to develop wearable systems that operate invariantly to sensor position and orientation. We focus on invariance to sensor orientation and develop two alternative transformations to remove the effect of absolute sensor orientation from the raw sensor data. We test the proposed methodology in activity recognition with four state-of-the-art classifiers using five publicly available datasets containing various types of human activities acquired by different sensor configurations. While the ordinary activity recognition system cannot handle incorrectly oriented sensors, the proposed transformations allow the sensors to be worn at any orientation at a given position on the body, and achieve nearly the same activity recognition performance as the ordinary system for which the sensor units are not rotatable. The proposed techniques can be applied to existing wearable systems without much effort, by simply transforming the time-domain sensor data at the pre-processing stage. © 2017 by the authors. Licensee MDPI, Basel, Switzerland.
Open Access
Adaptive ensemble learning with confidence bounds for personalized diagnosis
(AAAI Press, 2016) Tekin, Cem; Yoon, J.; Van Der Schaar, M.
With the advances in the field of medical informatics, automated clinical decision support systems are becoming the de facto standard in personalized diagnosis. In order to establish high accuracy and confidence in personalized diagnosis, massive amounts of distributed, heterogeneous, correlated and high-dimensional patient data from different sources such as wearable sensors, mobile applications, Electronic Health Record (EHR) databases etc. need to be processed. This requires learning both locally and globally due to privacy constraints and/or distributed nature of the multimodal medical data. In the last decade, a large number of meta-learning techniques have been proposed in which local learners make online predictions based on their locally-collected data instances, and feed these predictions to an ensemble learner, which fuses them and issues a global prediction. However, most of these works do not provide performance guarantees or, when they do, these guarantees are asymptotic. None of these existing works provide confidence estimates about the issued predictions or rate of learning guarantees for the ensemble learner. In this paper, we provide a systematic ensemble learning method called Hedged Bandits, which comes with both long run (asymptotic) and short run (rate of learning) performance guarantees. Moreover, we show that our proposed method outperforms all existing ensemble learning techniques, even in the presence of concept drift.
Open Access
ANN-based estimation of MEMS diaphragm response: An application for three leaf clover diaphragm based Fabry-Perot interferometer
(Elsevier BV, 2022-06-23) Yigit, E.; Hayber, Ş. E.; Aydemir, Umut
In this study, an artificial neural network (ANN) based model is developed for MEMS diaphragm analysis, which does not require difficult and time-consuming FEM processes. ANN-based estimator is generated for static pressure response (d) and dynamic pressure response (f) analysis of TLC (three leaf clover) diaphragms for Fabry-Perot interferometers as an example. TLC is one of the unsealed MEMS design diaphragms formed by three leaves of equal angles. The diaphragms used to train ANNs are designed with SOLIDWORKS and analyzed with ANSYS. A total of 1680 TLC diaphragms are simulated with eight diaphragm parameters (3 for SiO2 material, 4 for geometry, and 1 for pressure) to create a data pool for ANN’s training, validation, and testing processes. 80% of the data is used for training, 15% for validation, and the remaining for testing. Only four geometric parameters are used as input in the ANN estimator, and the material parameters are added to the model with an analytical multiplier. Thus, network models that estimate d and f values for all kinds of diaphragm materials are proposed, with a material-independently trained ANN structure. The performance of the ANN model is compared with the empirical equation suggested in the literature, and its superiority is demonstrated. In addition, the d and f parameters of TLC diaphragms designed with five different materials (Si, In2Se3, Ag, EPDM, Graphene) are estimated to be very close to the real ones. By using the proposed method, analyses of TLC diaphragms are quickly performed without the need for time-consuming and costly design and analysis programs.
Open Access
Anomaly detection in diverse sensor networks using machine learning
(2022-01) Akyol, Ali Alp
Earthquake precursor detection is one of the oldest research areas that has the potential of saving human lives. Recent studies have enlightened the fact that strong seismic activities and earthquakes affect the electron distribution of the ionosphere. These effects are clearly observable on the ionospheric Total Electron Content (TEC) that shall be measured by using the satellite position data of the Global Navigation Satellite System (GNSS). In this dissertation, several earthquake precursor detection techniques are proposed and their precursor detection performances are investigated on TEC data obtained from different sensor networks. First, a model based earthquake precursor detection technique is proposed to detect precursors of the earthquakes with magnitudes greater than 5 in the vicinity of Turkey. Precursor detection and TEC reliability signals are generated by using ionospheric TEC variations. These signals are thresholded to obtain earthquake precursor decisions. Earthquake precursor detections are made by using Particle Swarm Optimization (PSO) technique on these precursor decisions. Performance evaluations show that the proposed technique is able to detect 14 out of 23 earthquake precursors of magnitude larger than 5 in Richter scale while generating 8 false precursor decisions. Second, a machine learning based earthquake precursor detection technique, EQ-PD is proposed to detect precursors of the earthquakes with magnitudes greater than 4 in the vicinity of Italy. Spatial and spatio-temporal anomaly detection thresholds are obtained by using the statistics of TEC variation during seismically active times and applied on TEC variation based anomaly detection signal to form precursor decisions. Resulting spatial and spatio-temporal anomaly decisions are fed to a Support Vector Machine (SVM) classifier to generate earthquake precursor detections. When the precursor detection performance of the EQ-PD is investigated, it is observed that the technique is able to detect 22 out of 24 earthquake precursors while generating 13 false precursor decisions during 147 days of no-seismic activity. Last, a deep learning based earthquake precursor detection technique, DLPD is proposed to detect precursors of the earthquakes with magnitudes greater than 5.4 in the vicinity Anatolia region. The DL-PD technique utilizes a deep neural network with spatio-temporal Global Ionospheric Map (GIM)-TEC data estimation capabilities. GIM-TEC anomaly score is obtained by comparing GIMTEC estimates with GIM-TEC recordings. Earthquake precursor detections are generated by thresholding the GIM-TEC anomaly scores. Precursor detection performance evaluations show that DL-PD shall detect 5 out of 7 earthquake precursors while generating 1 false precursor decision during 416 days of noseismic activity.
Open Access
Application of the RIMARC algorithm to a large data set of action potentials and clinical parameters for risk prediction of atrial fibrillation
(Springer, 2015) Ravens, U.; Katircioglu-Öztürk, D.; Wettwer, E.; Christ, T.; Dobrev, D.; Voigt, N.; Poulet, C.; Loose, S.; Simon, J.; Stein, A.; Matschke, K.; Knaut, M.; Oto, E.; Oto, A.; Güvenir, H. A.
Ex vivo recorded action potentials (APs) in human right atrial tissue from patients in sinus rhythm (SR) or atrial fibrillation (AF) display a characteristic spike-and-dome or triangular shape, respectively, but variability is huge within each rhythm group. The aim of our study was to apply the machine-learning algorithm ranking instances by maximizing the area under the ROC curve (RIMARC) to a large data set of 480 APs combined with retrospectively collected general clinical parameters and to test whether the rules learned by the RIMARC algorithm can be used for accurately classifying the preoperative rhythm status. APs were included from 221 SR and 158 AF patients. During a learning phase, the RIMARC algorithm established a ranking order of 62 features by predictive value for SR or AF. The model was then challenged with an additional test set of features from 28 patients in whom rhythm status was blinded. The accuracy of the risk prediction for AF by the model was very good (0.93) when all features were used. Without the seven AP features, accuracy still reached 0.71. In conclusion, we have shown that training the machine-learning algorithm RIMARC with an experimental and clinical data set allows predicting a classification in a test data set with high accuracy. In a clinical setting, this approach may prove useful for finding hypothesis-generating associations between different parameters.
Open Access
An approach based on sound classification to predict soundscape perception through machine learning
(2021-06) Acun, Volkan
A growing amount of literature and a series of ISO standards focus on concept, data collection, and data analysis methods of soundscapes. Yet, this field of research still lacks predictive models. We hypothesize that machine learning methods can be used to develop a predictive model by identifying the audio content of soundscapes and correlating it with individuals’ perceived affective response to the soundscapes. Therefore, this research aims to identify machine learning-based sound classification methods for analyzing the audio content of soundscapes and using its output in a second model for evaluating the association between the audio content and perception of the soundscape. We focused on museum soundscapes to conduct our research. The methodology of this thesis is divided into two parts. For the first part, we used Convolutional Neural Networks for classifying the audio content of the soundscape. Due to their limitations, we used a different approach rather than the typical environmental sound classification methods. We used musical instruments for the training dataset and optimized the neural network for this type of task. The convolutional neural network classified the audio content of the soundscapes based on their similarities to the musical instruments of the dataset. We conducted an online soundscape perception survey to measure participants' affective responses to different museum soundscapes for the second part. To predict individuals’ perception of soundscapes, we developed a feedforward neural network model. This model used the audio content output from the sound classification model and the soundscape survey data to predict the perceived affective quality of soundscapes. We concluded the thesis by conducting statistical analyses to explore the association between the variable used in the predictive model.
Open Access
Artificial intelligence-based hybrid anomaly detection and clinical decision support techniques for automated detection of cardiovascular diseases and Covid-19
(2023-10) Terzi, Merve Begüm
Coronary artery diseases are the leading cause of death worldwide, and early diagnosis is crucial for timely treatment. To address this, we present a novel automated arti cial intelligence-based hybrid anomaly detection technique com posed of various signal processing, feature extraction, supervised, and unsuper vised machine learning methods. By jointly and simultaneously analyzing 12-lead electrocardiogram (ECG) and cardiac sympathetic nerve activity (CSNA) data, the automated arti cial intelligence-based hybrid anomaly detection technique performs fast, early, and accurate diagnosis of coronary artery diseases. To develop and evaluate the proposed automated arti cial intelligence-based hybrid anomaly detection technique, we utilized the fully labeled STAFF III and PTBD databases, which contain 12-lead wideband raw recordings non invasively acquired from 260 subjects. Using the wideband raw recordings in these databases, we developed a signal processing technique that simultaneously detects the 12-lead ECG and CSNA signals of all subjects. Subsequently, using the pre-processed 12-lead ECG and CSNA signals, we developed a time-domain feature extraction technique that extracts the statistical CSNA and ECG features critical for the reliable diagnosis of coronary artery diseases. Using the extracted discriminative features, we developed a supervised classi cation technique based on arti cial neural networks that simultaneously detects anomalies in the 12-lead ECG and CSNA data. Furthermore, we developed an unsupervised clustering technique based on the Gaussian mixture model and Neyman-Pearson criterion that performs robust detection of the outliers corresponding to coronary artery diseases. By using the automated arti cial intelligence-based hybrid anomaly detection technique, we have demonstrated a signi cant association between the increase in the amplitude of CSNA signal and anomalies in ECG signal during coronary artery diseases. The automated arti cial intelligence-based hybrid anomaly de tection technique performed highly reliable detection of coronary artery diseases with a sensitivity of 98.48%, speci city of 97.73%, accuracy of 98.11%, positive predictive value (PPV) of 97.74%, negative predictive value (NPV) of 98.47%, and F1-score of 98.11%. Hence, the arti cial intelligence-based hybrid anomaly detection technique has superior performance compared to the gold standard diagnostic test ECG in diagnosing coronary artery diseases. Additionally, it out performed other techniques developed in this study that separately utilize either only CSNA data or only ECG data. Therefore, it signi cantly increases the detec tion performance of coronary artery diseases by taking advantage of the diversity in di erent data types and leveraging their strengths. Furthermore, its perfor mance is comparatively better than that of most previously proposed machine and deep learning methods that exclusively used ECG data to diagnose or clas sify coronary artery diseases. It also has a very short implementation time, which is highly desirable for real-time detection of coronary artery diseases in clinical practice. The proposed automated arti cial intelligence-based hybrid anomaly detection technique may serve as an e cient decision-support system to increase physicians' success in achieving fast, early, and accurate diagnosis of coronary artery diseases. It may be highly bene cial and valuable, particularly for asymptomatic coronary artery disease patients, for whom the diagnostic information provided by ECG alone is not su cient to reliably diagnose the disease. Hence, it may signi cantly improve patient outcomes, enable timely treatments, and reduce the mortality associated with cardiovascular diseases. Secondly, we propose a new automated arti cial intelligence-based hybrid clinical decision support technique that jointly analyzes reverse transcriptase polymerase chain reaction (RT-PCR) curves, thorax computed tomography im ages, and laboratory data to perform fast and accurate diagnosis of Coronavirus disease 2019 (COVID-19). For this purpose, we retrospectively created the fully labeled Ankara University Faculty of Medicine COVID-19 (AUFM-CoV) database, which contains a wide variety of medical data, including RT-PCR curves, thorax computed tomogra phy images, and laboratory data. The AUFM-CoV is the most comprehensive database that includes thorax computed tomography images of COVID-19 pneu monia (CVP), other viral and bacterial pneumonias (VBP), and parenchymal lung diseases (PLD), all of which present signi cant challenges for di erential diagnosis. We developed a new automated arti cial intelligence-based hybrid clinical de cision support technique, which is an ensemble learning technique consisting of two preprocessing methods, long short-term memory network-based deep learning method, convolutional neural network-based deep learning method, and arti cial neural network-based machine learning method. By jointly analyzing RT-PCR curves, thorax computed tomography images, and laboratory data, the proposed automated arti cial intelligence-based hybrid clinical decision support technique bene ts from the diversity in di erent data types that are critical for the reliable detection of COVID-19 and leverages their strengths. The multi-class classi cation performance results of the proposed convolu tional neural network-based deep learning method on the AUFM-CoV database showed that it achieved highly reliable detection of COVID-19 with a sensitivity of 91.9%, speci city of 92.5%, precision of 80.4%, and F1-score of 86%. There fore, it outperformed thorax computed tomography in terms of the speci city of COVID-19 diagnosis. Moreover, the convolutional neural network-based deep learning method has been shown to very successfully distinguish COVID-19 pneumonia (CVP) from other viral and bacterial pneumonias (VBP) and parenchymal lung diseases (PLD), which exhibit very similar radiological ndings. Therefore, it has great potential to be successfully used in the di erential diagnosis of pulmonary dis eases containing ground-glass opacities. The binary classi cation performance results of the proposed convolutional neural network-based deep learning method showed that it achieved a sensitivity of 91.5%, speci city of 94.8%, precision of 85.6%, and F1-score of 88.4% in diagnosing COVID-19. Hence, it has compara ble sensitivity to thorax computed tomography in diagnosing COVID-19. Additionally, the binary classi cation performance results of the proposed long short-term memory network-based deep learning method on the AUFM-CoV database showed that it performed highly reliable detection of COVID-19 with a sensitivity of 96.6%, speci city of 99.2%, precision of 98.1%, and F1-score of 97.3%. Thus, it outperformed the gold standard RT-PCR test in terms of the sensitivity of COVID-19 diagnosis Furthermore, the multi-class classi cation performance results of the proposed automated arti cial intelligence-based hybrid clinical decision support technique on the AUFM-CoV database showed that it diagnosed COVID-19 with a sen sitivity of 66.3%, speci city of 94.9%, precision of 80%, and F1-score of 73%. Hence, it has been shown to very successfully perform the di erential diagnosis of COVID-19 pneumonia (CVP) and other pneumonias. The binary classi cation performance results of the automated arti cial intelligence-based hybrid clinical decision support technique revealed that it diagnosed COVID-19 with a sensi tivity of 90%, speci city of 92.8%, precision of 91.8%, and F1-score of 90.9%. Therefore, it exhibits superior sensitivity and speci city compared to laboratory data in COVID-19 diagnosis. The performance results of the proposed automated arti cial intelligence-based hybrid clinical decision support technique on the AUFM-CoV database demon strate its ability to provide highly reliable diagnosis of COVID-19 by jointly ana lyzing RT-PCR data, thorax computed tomography images, and laboratory data. Consequently, it may signi cantly increase the success of physicians in diagnosing COVID-19, assist them in rapidly isolating and treating COVID-19 patients, and reduce their workload in daily clinical practice.
Open Access
Assessment and correction of errors in DNA sequencing technologies
(2017-12) Fırtına, Can
Next Generation Sequencing technologies differ by several parameters where the choice to use whether short or long read sequencing platforms often leads to trade-offs between accuracy and read length. In this thesis, I first demonstrate the problems in reproducibility in analyses using short reads. Our comprehensive analysis on the reproducibility of computational characterization of genomic variants using high throughput sequencing data shows that repeats might be prone to ambiguous mapping. Short reads are more vulnerable to repeats and, thus, may cause reproducibility problems. Next, I introduce a novel algorithm Hercules, the first machine learning-based long read error correction algorithm. Several studies require long and accurate reads including de novo assembly, fusion and structural variation detection. In such cases researchers often combine both technologies and the more erroneous long reads are corrected using the short reads. Current approaches rely on various graph based alignment techniques and do not take the error profile of the underlying technology into account. Memory- and time- efficient machine learning algorithms that address these shortcomings have the potential to achieve better and more accurate integration of these two technologies. Our algorithm models every long read as a profile Hidden Markov Model with respect to the underlying platform's error profile. The algorithm learns a posterior transition/ emission probability distribution for each long read and uses this to correct errors in these reads. Using datasets from two DNA-seq BAC clones (CH17-157L1 and CH17-227A2), and human brain cerebellum polyA RNA-seq, we show that Hercules-corrected reads have the highest mapping rate among all competing algorithms and highest accuracy when most of the basepairs of a long read are covered with short reads.
Open Access
Automatic method for generation of sememe knowledge bases from machine readable dictionaries
(2023-09) Battal, Ömer Musa
The minimal semantic units of natural languages are defined as sememes. Sememe Knowledge Bases (SKBs) are organized word collections annotated with appro-priate sememes. As external knowledge bases, SKBs have successful applications in multiple high-level language processing tasks. However, the construction of mainstream SKBs is performed by linguistic experts over extended periods, which restricts their prevalent usage. We present MRD4SKB as an automatic SKB generation method from readily available Machine Readable Dictionaries (MRDs). Construction of MRDs is more straightforward than SKBs, and many prominent MRDs are present in various forms. Consequently, the presented MRD4SKB is viable as a fast, flexible, and extendable method for SKB construction. Several variants of MRD4SKB, based on matrix factorization and topic modeling, are proposed to generate SKBs automatically. The performance of the automatically generated SKBs is evaluated and compared with that of other SKBs, which are constructed manually or semi-manually.
Open Access
Automatic selection of compiler optimizations by machine learning
(IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Peker, Melih; Öztürk, Özcan; Yıldırım, S.; Uluyağmur Öztürk, M.
Many widely used telecommunications applications have extremely long run times. Therefore, faster and more efficient execution of these codes on the same hardware is important in critical telecommunication applications such as base stations. Compilers greatly affect the properties of the executable program to be created. It is possible to change properties such as compilation speed, execution time, power consumption and code size using compiler flags. This study aims to find the set of flags that will provide the shortest run time among hundreds of compiler flag combinations in GCC using code flow analysis, loop analysis and machine learning methods without running the program.
Open Access
Bilişsel algılamaya doğru: çok görevli öğrenme ile radar fonksiyon sınıflandırma
(IEEE, 2019-04) Altıparmak, Fatih; Akyön, Fatih Çağatay; Özmen, E.; Çoğun, Fuat; Bayri, A.
Elektronik Harp (EH) sistemleri için ortamda yayın yapan bir radarın tespiti ve ilgili radarın fonksiyonunun belirlenmesi, sistemin en önemli görevlerinden biridir. Bu çalışmada, EH sistemleri tarafından ölçülen radar parametreleri kullanılarak radarların Elektronik Karşı Tedbir (EKT) kullanım konseptine uygun olarak fonksiyonlarının belirlenmesi hedeflenmiştir. Çok Görevli Öğrenme ve Tek Görevli Öğrenme sinirağları probleme uyarlanmıştır. Sınıflandırıcı öncesinde aşırı örnekleme, aralık değerleri için nicemleme ve sınıf değerleri için gruplama ön işlemleri yapılmıştır. Çok Görevli Öğrenme tekniğinin performansının Tek Görevli Öğrenme tekniğininkinden daha iyi olduğu gözlenmiştir. Sınıflandırıcı öncesinde uygulanan aşırı örnekleme algoritmasının, ön işlemler neticesinde elde edilen verisetinin ve gruplandırılmış sınıfların bir veya daha fazlasının kullanımıyla her iki metodun performanslarının arttığı gözlenmiştir.
Embargo
Can investors’ informed trading predict cryptocurrency returns? Evidence from machine learning
(Elsevier Inc., 2022-05-24) Wang, Y.; Wang, C.; Şensoy, Ahmet; Yao, S.; Cheng, F.
As an emerging asset, cryptocurrencies have attracted more and more attention from investors and researchers in recent years. With the gradual convergence of the investors in cryptocurrency and traditional financial markets, the research on investor trading behavior from the perspective of microstructure has become increasingly important in cryptocurrency market. In this paper, we study whether investors’ informed trading behavior can significantly predict cryptocurrency returns. We use various machine learning algorithms to verify the contribution of informed trading to the predictability of cryptocurrency returns. The results show that informed trading plays a role in the prediction of some individual cryptocurrency returns, but it cannot significantly improve the prediction accuracy in an average sense of the whole market. The lack of market supervision of cryptocurrency market may be the main factor for relatively low efficiency of this market, and policymakers need to pay attention to it.
Open Access
Chat mining: predicting user and message attributes in computer-mediated communication
(Elsevier Ltd, 2008-07) Kucukyilmaz T.; Cambazoglu, B. B.; Aykanat, Cevdet; Can, F.
The focus of this paper is to investigate the possibility of predicting several user and message attributes in text-based, real-time, online messaging services. For this purpose, a large collection of chat messages is examined. The applicability of various supervised classification techniques for extracting information from the chat messages is evaluated. Two competing models are used for defining the chat mining problem. A term-based approach is used to investigate the user and message attributes in the context of vocabulary use while a style-based approach is used to examine the chat messages according to the variations in the authors' writing styles. Among 100 authors, the identity of an author is correctly predicted with 99.7% accuracy. Moreover, the reverse problem is exploited, and the effect of author attributes on computer-mediated communications is discussed. © 2008 Elsevier Ltd. All rights reserved.
Open Access
A comparative study on prediction of the indoor soundscape in museums via machine learning
(Institute of Noise Control Engineering(INCE), 2019-06) Yılmazer, Semiha; Yılmazer, Cengiz; Acun, Volkan
This paper presents the preliminary findings of a soundscape research, which uses machine learning to make a prediction about human perception for indoor auditory environments. Museums of Çengelhan Rahmi Koc and Erim Tan are selected as the case study settings for data collection. The survey questionnaire basically consisted of three parts which are concerned with identifying the socio-cultural status, the personal tendencies, and evaluation of the physical and auditory environment. Before constructing of grounding the predictive model, data went through analyses to normalize and to eliminate the irrelevant items. Preliminary findings demonstrated how an indoor auditory environment would be perceived based on the individuals’ socio-cultural status, tendencies, preference and expectation from the space and physical elements of the space with together constructing a preliminary grounding model to use Machine / Deep learning algorithm.
Open Access
Control and system identification of legged locomotion with recurrent neural networks
(2022-06) Çatalbaş, Bahadır
In recent years, robotic systems have gained massive popularity in the industry, military, and daily use for various purposes, thanks to advancements in artificial intelligence and control theory. As an exciting sub-branch of robotics with their differences and opportunities, legged robots have the potential to diversify and spread the use of robotic systems to new fields. Especially, legged locomotion is a desirable ability for mechanical systems where agile mobility and a wide range of motions are required to fulfill the designated task. On the other hand, unlike wheeled robots, legged robot platforms have a hybrid dynamical structure consisting of the flight and contact phases of the legs. Since the hybrid dynamical structure and nonlinear dynamics in the robot model make it challenging to apply control and perform system identification for them, various methods are proposed to solve these problems in the literature. This thesis focuses on developing new neural network-based techniques to apply control and system identification to legged locomotion so that robotic platforms can be designed to move efficiently as animal counterparts do in nature. In the first part of this thesis, we present our works on neural network-based controller development and evaluation studies for bipedal locomotion. In detail, neural controllers, in which long short-term memory (LSTM) type of neuron models are employed at recurrent layers, are utilized in the feedback and feedforward paths. Supervised learning data sets are produced using a biped robot platform controlled by a central pattern generator to train these neural networks. Then, the ability of the neural networks to perform stable gait by controlling the robot platform is assessed under various ground conditions in the simulation environment. After that, the stable walking generation capacity of the neural networks and the central pattern generators are compared with each other. It is shown that the proposed neural networks are more successful gait controllers than the central pattern generator, which is employed to generate data sets used in training. In the second part, we present our studies on the end-to-end usage of neural networks in system identification for bipedal locomotion. To this end, supervised learning data sets are produced using a biped robot model controlled by a central pattern generator. After that, neural networks are trained under series-parallel and parallel system identification schemes to approximate the input-output relations of the biped robot model. In detail, different neural models and neural network architectures are trained and tested in an end-to-end manner. Among neuron models, LeakyReLU and LSTM are found as the most suitable feedforward and recurrent neuron types for system identification, respectively. Moreover, neural network architecture consisting of recurrent and feedforward layers is found to be efficient in terms of learnable parameter numbers for system identification of the biped robot model. The last part discusses the results obtained in the control and system identification studies using neural networks. In the light of acquired results, neural networks with recurrent layers can apply control and systems identification in an end-to-end manner. Finally, the thesis is completed by discussing possible future research directions with the obtained results.
Open Access
Data mining experiments on the Angiotensin II-Antagonist in Paroxysmal Atrial Fibrillation (ANTIPAF-AFNET 2) trial: ‘exposing the invisible’
(Oxford University Press, 2016) Okutucu, S.; Katircioglu-Öztürk, D.; Oto, E.; Güvenir, H. A.; Karaagaoglu, E.; Oto, A.; Meinertz, T.; Goette, A.
Aims: The aims of this study include (i) pursuing data-mining experiments on the Angiotensin II-Antagonist in Paroxysmal Atrial Fibrillation (ANTIPAF-AFNET 2) trial dataset containing atrial fibrillation (AF) burden scores of patients with many clinical parameters and (ii) revealing possible correlations between the estimated risk factors of AF and other clinical findings or measurements provided in the dataset. Methods: Ranking Instances by Maximizing the Area under a Receiver Operating Characteristics (ROC) Curve (RIMARC) is used to determine the predictive weights (Pw) of baseline variables on the primary endpoint. Chi-square automatic interaction detector algorithm is performed for comparing the results of RIMARC. The primary endpoint of the ANTIPAF-AFNET 2 trial was the percentage of days with documented episodes of paroxysmal AF or with suspected persistent AF. Results: By means of the RIMARC analysis algorithm, baseline SF-12 mental component score (Pw = 0.3597), age (Pw = 0.2865), blood urea nitrogen (BUN) (Pw = 0.2719), systolic blood pressure (Pw = 0.2240), and creatinine level (Pw = 0.1570) of the patients were found to be predictors of AF burden. Atrial fibrillation burden increases as baseline SF-12 mental component score gets lower; systolic blood pressure, BUN and creatinine levels become higher; and the patient gets older. The AF burden increased significantly at age >76. Conclusions: With the ANTIPAF-AFNET 2 dataset, the present data-mining analyses suggest that a baseline SF-12 mental component score, age, systolic blood pressure, BUN, and creatinine level of the patients are predictors of AF burden. Additional studies are necessary to understand the distinct kidney-specific pathophysiological pathways that contribute to AF burden. Published on behalf of the European Society of Cardiology.
Open Access
Deep learning in electronic warfare systems: automatic pulse detection and intra-pulse modulation recognition
(2020-12) Akyon, Fatih Cagatay
Detection and classification of radar systems based on modulation analysis on pulses they transmit is an important application in electronic warfare systems. Many of the present works focus on classifying modulations assuming signal detection is done beforehand without providing any detection method. In this work, we propose two novel deep-learning based techniques for automatic pulse detection and intra-pulse modulation recognition of radar signals. As the first nechnique, an LSTM based multi-task learning model is proposed for end-to-end pulse detection and modulation classification. As the second technique, re-assigned spectrogram of measured radar signal and detected outliers of its instantaneous phases filtered by a special function are used for training multiple convolutional neural networks. Automatically extracted features from the networks are fused to distinguish frequency and phase modulated signals. Another major issue on this area is the training and evaluation of supervised neural network based models. To overcome this issue we have developed an Intentional Modulation on Pulse (IMOP) measurement simulator which can generate over 15 main phase and frequency modulations with realistic pulses and noises. Simulation results show that the proposed FFCNN and MODNET techniques outperform the current stateof-the-art alternatives and is easily scalable among broad range of modulation types.
Open Access
Deep reinforcement learning for urban modeling: morphogenesis simulation of self-organized settlements
(2023-07) H'sain, Houssame Eddine
Self-organized modes of urban growth could result in high-quality urban space and have notable benefits such as providing affordable housing and wider access to economic opportunities within cities. Modeling this non-linear, complex, and dynamic sequential urban aggregation process requires adaptive sequential decision-making. In this study, a deep reinforcement learning (DRL) approach is proposed to automatically learn these adaptive decision policies to generate self-organized settlements that maximize a certain performance objective. A framework to formulate the self-organized settlement morphogenesis problem as single-agent reinforcement learning (RL) environment is presented. This framework is then verified by developing three environments based on two cellular automata urban growth models and training RL agents using the Deep Q-learning (DQN) and Proximal Policy Optimization (PPO) algorithms to learn sequential urban aggregation policies that maximize performance metrics within those environments. The agents consistently learn to sequentially grow the settlements while adapting their morphology to maximize performance, maintain right-of-way, and adapt to topographic constraints. The method proposed in this study can be used not only to model self-organized settlement growth based on preset performance objectives but also could be generalized to solve various single-agent sequential decision-making generative design problems.