Silent hypoxia is a complication that can lead to severe respiratory disorders at a time when people feel well, especially in Covid-19, and lung destruction if not intervened early. In this paper, a wearable device and a mobile application synchronized with the device were developed to measure people’s vitals and reduce the risk of silent hypoxia. The device consists of 2 parts: a wristband and a finger-clip, and includes a micro-controller, a bluetooth module, a Li-Po battery and various sensors to measure body temperature, pulse and SpO2 values. It can measure body temperature, pulse and SpO2 instantly or at certain programmable intervals like a holter device through the mobile app. These measured values can be recorded and various analyzes can be performed on them. Also the measurement results can be sent via an e-mail. When the vitals reach or exceed the predefined risk levels, a notification can be generated. The proposed device was evaluated in various performance tests and compared to a commercial pulse oximeter as well as alternatives in the literature. It was tested for connectivity and transmission, battery endurance and field testing. In the comparison test, error values of 1.8

There have been numerous studies on the control of quadcopters. These studies mainly aim to control the flight behavior of quadcopters. To achieve this, researchers have been developing new tools and testing new methods. One of the developed tools is the 3-DOF Hover system, which enables researchers to analyze the flight behaviors of quadcopters, such as roll, pitch, and yaw, even in a physically limited area or only in a computer environment. The control method applied in the control of the 3-DOF Hover system has been determined by the manufacturer as Linear-Quadratic Regulator (LQR). LQR has control parameters that are complex to calculate. This complex calculation process creates an optimization problem. Beyond controlling the 3-DOF Hover system using LQR, this study focuses on calculating the complex control parameters of LQR using optimization algorithms when controlling a dynamic system with LQR. This study includes well-known algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA), as well as an innovative approach known Gray Wolf Optimization (GWO). These algorithms were selected due to their proven effectiveness in various studies. Based on the results obtained from these algorithms, a hybrid algorithm incorporating SA and GWO is proposed. The aim of this hybrid algorithm is to combine the advantages of different methods and achieve a more effective and efficient optimization process. The mentioned hybrid algorithm, obtained by combining SA and GWO, is named hSA-GWO. This hSA-GWO is compared with traditional algorithms, and the comparison results show that the proposed hybrid algorithm can be used as an alternative and competitive method for controlling the flight behaviors of quadcopters.

Çok seviyeli görüntü eşikleme, görüntüyü ileri düzeyde anlamlı özelliklere ayırmak için kullanılan önemli bir görüntü işleme tekniğidir. Bu teknik, metasezgisel optimizasyon algoritmaları ile birlikte kullanılarak hesaplama süresi açısından başarılı sonuçlar elde edilebilmektedir. Bu çalışmada, çok seviyeli görüntü eşikleme problemini çözmek için GWO-HS olarak isimlendirilen hibrit bir algoritma önerilmiştir. Önerilen algoritma gri kurt optimizasyon (GWO) ve harmoni arama (HS) algoritmaları hibritlenerek elde edilmiştir. GWO-HS algoritmasının performansı beş diğer algoritmanın performansları ile karşılaştırılmıştır. Karşılaştırmalarda Otsu ve Kapur entropi tabanlı eşikleme yöntemleri kullanılmıştır. Deneylerde, görüntü işleme çalışmalarında iyi bilinen ve yaygın olarak kullanılan altı görüntü tercih edilmiştir. Her bir görüntü üzerinde 2’den 10’a kadar değişen seviyeler için eşikleme işlemi uygulanmıştır. Sonuçlar, önerilen GWO-HS algoritmasının, diğer algoritmalara kıyasla özellikle yüksek eşik seviyeleri için daha üstün bir performansa sahip olduğunu göstermiştir.

The traveling salesman problem (TSP) is one of the most popular combinatorial optimization problems today. It is a problem that is easy to identify but hard to solve. Therefore, it belongs to the class of NP-hard optimization problems, and it is a problem of high time complexity. The TSP can be used to solve various real-world problems. Therefore, researchers use it as a standard test bench for performance evaluation of new algorithms. In this study, a new simulated annealing algorithm with crossover operator was proposed, and it was called LBSA-CO. The LBSA-CO is a population-based metaheuristic method. In this method, a list-based temperature cooling schedule, which can adapt to the topology of the solution space of the problem, was used. The solutions in the population were improved with the inversion, insertion and 2-opt local search operators. The order crossover (OX1) and genetic edge recombination crossover (ER) operators were applied to the improved solutions to accelerate the convergence. In addition, the Taguchi method was used to tune the parameters of the LBSA-CO. The proposed method was tested on 65 well-known TSP instances. The results indicated that this method performs better than the state-of-the-art methods on many instances.

This work focuses on the capacitated vehicle routing problem. In this work, a real-time application is developed using online real-world data for mobile devices have IOS and Android operating systems. The fuzzy c-means clustering algorithm is used to group the demand points and the ant colony optimization algorithm is employed to determine the best route within each group. The customer demand points and distances between these points are obtained via Google Places and Google Directions APIs. The deviations in the route that result from the environmental and road conditions are identified immediately with the help of global positioning system technology allowing the route suggestions to be made. The developed application was evaluated on two datasets for testing. The test results showed that this real-time application can be used to find the optimum route for the capacitated vehicle routing problem and follow the route optimally.

In this study, a novel hybrid Simulated Annealing-Genetic Algorithm (hSA-GA) is proposed. In the hSA-GA, population-based SA is used and each solution in the population is improved using the local search operator. The information exchange between the improved solutions is provided by the crossover operator. A new selection operator is used to ensure the balance between intensification and diversification. The hSA-GA is tested first on nine benchmark functions. Then it is used for tuning proportional-integral-derivative (PID) parameters for automatic generation control (AGC) of multi-area interconnected power systems. Firstly, PID parameters are determined with hSA-GA on a two-area interconnected non-reheating thermal system (System-1) in two different generator time constants. Secondly, to demonstrate the effect of supplementary control in AGC systems, the system is simulated with hSA-GA tuned PID controller and without controller. Additionally, the performance of the proposed hSA-GA is observed on AGC system of two area thermal power system with governor dead-band (GDB) nonlinearity (System-2). Transient responses of delta f(1), delta f(2) and delta P-tie obtained for both System-1 and System-2 are compared with studies on the same systems in the literature and it is seen that hSA-GA exhibits better control performance on power systems than compared studies. The proposed algorithm shows the best performance in System-1 (when T-g = 0.08). Accordingly, settling times of delta f(1), delta f(2) and delta P-tie are reduced to 2.33 s, 3.783 s and 3.11 s, respectively. Finally, the non-linear two area thermal power system is tested with a load varying between +/- 50% for 180 s to validation of proposed algorithm and results are compared relevant studies. (C) 2022 Elsevier B.V. All rights reserved.

The capacitated vehicle routing problem (CVRP) is one of the commonly studied issues today. It belongs to the class of NP-hard problems and has a high time complexity. Therefore, the solution of the CVRP was focused in this study. An improved simulated annealing algorithm with crossover operator, called ISA-CO, was proposed. A population based simulated annealing algorithm was used in the proposed algorithm. The solutions in the popu-lation were developed through the local search operators, including swap, scramble, insertion, and reversion. The improved 2-opt algorithm was used to develop the routes making up the solution. The partially mapped crossover (PMX) and the order crossover (OX) operators were applied to the solutions in the population to accelerate the convergence. A mix selection method was used to ensure the balance between exploitation and exploration. The ISA-CO was tested on 91 well-known benchmark instances. The results indicated that the method has a better performance compared to other state-of-the-art methods on many instances.

Image processing is one of the current research topics widely used in different engineering fields. Therefore, it is taught as a lesson under different names in various engineering departments. In-class applications are usually done through programs that depend on desktop platforms such as Windows, Linux or MacOS. These platforms, which self or its camera are fixed, can only take real time images with limited mobility. It is difficult to apply image processing algorithms for real time images and make comparisons. In this study, a cross-platform test tool for image processing was developed. This tool can work on desktop platforms such as Windows and MacOS, as well as mobile platforms such as Android and IOS. Thanks to mobile platform support, the real time images can be taken anytime and anywhere. The basic image processing operations can be performed on recorded or real time images. The resulting images can be recorded. Thus, a test environment is provided to apply and compare different methods and algorithms.

The Vehicle Routing Problem (VRP) is one of the most discussed and researched topics nowadays. The VRP is briefly defined as the problem of identifying the best route to reduce distribution costs and improve the quality of service provided to customers. The Capacitated VRP (CVRP) is one of the most commonly researched among the VRP types. Therefore, the CVRP was studied in this paper and a new population based simulated annealing algorithm was proposed. In the algorithm, three different route development operators were used, which are exchange, insertion and reversion operators. It was tested on 63 well-known benchmark instances in the literature. The results showed that the optimum routes could be determined for the 23 instances.

In present study, an automatic blood pressure measurement device was developed to perform measurement on the arm.The developed blood pressure measurement device was also used as display and control device.On this device, the curve fitting method, which is a very common numerical analysis method, was used to predict blood pressure.Resistor-Capacitor (RC) and digital filters were preferred to process and filter signal.Various tests were conducted on 21 individuals under the supervision of specialist.The obtained results showed that a prediction accuracy of 94.67%, 92.51% and 97.68% could be achieved for systolic and diastolic blood pressure and heart rate values, respectively.

The development and improvement of control techniques has attracted many researchers for many years. Especially in the controller design of complex and nonlinear systems, various methods have been proposed to determine the ideal control parameters. One of the most common and effective of these methods is determining the controller parameters with optimization algorithms.In this study, LQR controller design was implemented for position control of the double inverted pendulum system on a cart. First of all, the equations of motion of the inverted pendulum system were obtained by using Lagrange formulation. These equations were linearized by Taylor series expansion around the equilibrium position to obtain the state-space model of the system. The LQR controller parameters required to control the inverted pendulum system were determined by using a trial and error method. The determined parameters were optimized by using five different configurations of three different optimization algorithms (GA, PSO, and ABC). The LQR controller parameters obtained as a result of the optimization study with five different configurations of each algorithm were applied to the system and the obtained results were compared with each other. In addition, the configurations that yielded the best control results for each algorithm were compared with each other and the control results were evaluated in terms of response speed and response smoothness.

Background and Objective: In this study, a wireless blood pressure holter that can be used with smart mobile devices was developed. The developed blood pressure holter consists of two parts, which are a smart mobile device and a cuff. The smart mobile device is used as a recording, control and display device through a developed interface, while the cuff was designed to take measurements from the arm.& para;& para;Methods: Resistor-Capacitor (RC) and digital filters were used on the cuff that communicates with the smart mobile device via Bluetooth. The blood pressure was estimated using the Simple Hill Climbing Algorithm (HCA). It is possible to measure instantaneous or programmable blood pressure and heart rate values at certain intervals using this holter.& para;& para;Results: The test was conducted with 30 individuals at different ages with the guidance of a specialist health personnel. The results showed that an accuracy at 93.89% and 91.95% rates could be obtained for systolic and diastolic pressure values, respectively, when compared with those obtained using a traditional sphygmomanometer. The accuracy level for the heart rate was measured as 97.66%. Furthermore, this device was tested day and night in the holter mode in terms of working time, the continuity of the Bluetooth connection and the reliability of the measurement results.& para;& para;Conclusions: The test results were evaluated separately in terms of measurement accuracy, working time, the continuity of the Bluetooth connection and the reliability of the measurement results. The measurement accuracy for systolic, diastolic blood pressure and heart rate values was obtained as 93.89%, 91.95% and 97.66%, respectively. The maximum number of measurements which can be conducted with four 1000 mA alkaline batteries at 20 min intervals was found approximately 79 (little more than 24 h). In addition, it was determined that the continuity of the Bluetooth connection and the reliability of the measurement results were automatically achieved through the features in the interface developed for the smart mobile device. These different evaluations showed that the smart blood pressure holter can meet the requirements of a classical holter device. (C) 2017 Elsevier B.V. All rights reserved.

Nowadays, the Traveling Salesman Problem (TSP) is one of the most studied combinational optimization problems that researchers study. Although it is easy to define, its solution is hard. Therefore, it is one of the NP-hard problems in the research literature. It can be used to solve real-life problems such as route planning and scheduling, and transportation and logistics applications. In this study, for TSP, an interface that can run on mobile devices using Android and IOS operating systems is developed. Real-world data are used online by the interface. Locations, and the distance between them, are obtained instantly by Google Maps APIs. Genetic (GA) and ant colony optimization (ACO) algorithms are used to solve the TSP. Furthermore, users have also been allowed to conduct trials for different parameter values. The application developed has been tested on two different datasets. The test results show that for the determination of the optimum route, the ACO algorithm is better than the GA. However, when considering the run times, GA works much faster than ACO.

Optimization can be defined as the operation of finding the best solution for a problem. This operation is performed by changing the initial parameters using existing data. There are various optimization algorithms to solve these kinds of problems; however, it cannot be expected that all optimization algorithms offer a proper and effective solution to all optimization problems. Therefore, it is necessary to select the proper algorithm by using similar benchmark functions to the problem, and to determine the best parameter values for the selected algorithm. In this study, a test tool that can run on the devices using the Windows, OS X, Android, and IOS operating systems was developed for eight different optimization algorithms: genetic, artificial immune, differential evolution, particle swarm optimization, simulated annealing, tabu search, artificial bee colony, and ant colony optimization algorithms. Six Hump Camel Back, Rastrigin, Shubert, Schwefel, and Drop Wave were the preferred benchmark functions. Special user defined special functions were also permitted. The developed test tool was tested for all the optimization algorithms in different platforms. In spite of the small differences in the running times, the results show that the tool can easily be used in Windows, OS X, Android, and IOS devices. © 2016 Wiley Periodicals, Inc. Comput Appl Eng Educ 24:744–754, 2016; View this article online at wileyonlinelibrary.com/journal/cae; DOI 10.1002/cae.21747

Today, smart mobile devices (telephones and tablets) are very commonly used due to their powerful hardware and useful features. According to an eMarketer report, in 2014 there were 1.76 billion smartphone users (excluding users of tablets) in the world; it is predicted that this number will rise by 15.9% to 2.04 billion in 2015. It is thought that these devices can be used successfully in biomedical applications. A wireless blood pressure measuring device used together with a smart mobile device was developed in this study. By means of an interface developed for smart mobile devices with Android and iOS operating systems, a smart mobile device was used both as an indicator and as a control device. The cuff communicating with this device through Bluetooth was designed to measure blood pressure via the arm. A digital filter was used on the cuff instead of the traditional analog signal processing and filtering circuit. The newly developed blood pressure measuring device was tested on 18 patients and 20 healthy individuals of different ages under a physician's supervision. When the test results were compared with the measurements made using a sphygmomanometer, it was shown that an average 93.52% accuracy in sick individuals and 94.53% accuracy in healthy individuals could be achieved with the new device.

Researchers should select a suitable subgroup that includes all SNPs and represents the rest of the SNPs with little error for very large-scale association studies. The SNPs included in the subgroup are tag SNPs or haplotype tag SNPs (htSNPs). When selecting the tag SNPs, it is critical to accurately predict and identify the smallest number of tag SNPs with minimum error. This study used the Clonal Selection Algorithm (CLONALG) to decide on the tag SNPs to be included in the subgroup. In addition, the study proposed a new method called CSMV, which used the Majority Voting (MV) method to predict the rest of the SNPs. This method was compared with the BPSO method and the CLONTagger with parameter optimisation method using datasets of different sizes. According to the experimental results of the study, the CSMV method could determine the tag SNPs with significantly higher accuracy than the other two methods.

Following students’ attendance is a challenging and time-taking process for the instructor. At colleges, attendance is taken by passing around the attendance list which the students sign and write their ID numbers. This decreases the efficiency of the course and causes time loss. Taking university students’ attendance is an important activity for instructors and student alike and for increasing efficiency. In this study, using Near Field Communication (NFC) technology for smart phones, student attendance application was designed. The students swipe contactless NFC labels in which their numbers are defined through the mobile device and their attendance is taken in this way. At the end of the term, attendance information saved in the mobile device can be transferred to the host computer and statistics and reports by student can be obtained. Keywords-Attendance system, Sensors, NFC (Near Field Communication), Mobile device

Travelling Salesman Problem (TSP) are among the most studied optimization problems we have today. Although it is easy to define, its solution is rather difficult. Therefore, it is shown among NP-hard problems. In this study, an interface that can run on mobile devices has been developed. The interface developed uses real world data online. Locations and the distances between them are instantly obtained via Google Maps APIs. Ant Colony Optimization (ACO) algorithm is used to solve TSP. Deviations in the routes due to environmental and road conditions are immediately determined with the help of Global Positioning System (GPS) technology and new route suggestions can be presented instantly. The application developed is tested on three different real world datasets of various sizes. Test results have shown that this application can be used real time to follow the route created in an optimal way. Keywords— Ant Colony Optimization, Google Maps API, Mobile Device, Travelling Salesman Problem.

Protein-protein interactions hold very important roles in biological processes. Prediction of PPIs is important for understanding these processes. In this context, substantive representations of proteins are needed during the process of interaction prediction in order to achieve higher prediction accuracy. In this paper, a new feature representation method, based on the concept of Chou's pseudo amino acid composition, was introduced. It is composed of the weighted amino acid composition information and the correlation factors of the protein. Finally, an SVM classification model was constructed for predicting PPIs. Experimental results exhibit that our method precedes those previously published in the literature.