1267 results
Search Results
Now showing 1 - 10 of 1267
Article Citation - WoS: 50Citation - Scopus: 70Deep Learning Based Fall Detection Using Smartwatches for Healthcare Applications(Elsevier Sci Ltd, 2022) Sengul, Gokhan; Karakaya, Murat; Misra, Sanjay; Abayomi-Alli, Olusola O.; Damasevicius, RobertasWe implement a smart watch-based system to predict fall detection. We differentiate fall detection from four common daily activities: sitting, squatting, running, and walking. Moreover, we separate falling into falling from a chair and falling from a standing position. We develop a mobile application that collects the acceleration and gyroscope sensor data and transfers them to the cloud. In the cloud, we implement a deep learning algorithm to classify the activity according to the given classes. To increase the number of data samples available for training, we use the Bica cubic Hermite interpolation, which allows us to improve the accuracy of the neural network. The 38 statistical data features were calculated using the rolling update approach and used as input to the classifier. For activity classification, we have adopted the bi-directional long short-term memory (BiLSTM) neural network. The results demonstrate that our system can detect falling with an accuracy of 99.59% (using leave-one-activityout cross-validation) and 97.35% (using leave-one-subject-out cross-validation) considering all activities. When considering only binary classification (falling vs. all other activities), perfect accuracy is achieved.Article Citation - WoS: 3Citation - Scopus: 5Comparison of the Performance of Structural Break Tests in Stationary and Nonstationary Series: a New Bootstrap Algorithm(Springer, 2024) Camalan, Ozge; Hasdemir, Esra; Omay, Tolga; Kucuker, Mustafa CanStructural breaks are considered as permanent changes in the series mainly because of shocks, policy changes, and global crises. Hence, making estimations by ignoring the presence of structural breaks may cause the biased parameter value. In this context, it is vital to identify the presence of the structural breaks and the break dates in the series to prevent misleading results. Accordingly, the first aim of this study is to compare the performance of unit root with structural break tests allowing a single break and multiple structural breaks. For this purpose, firstly, a Monte Carlo simulation study has been conducted through using a generated homoscedastic and stationary series in different sample sizes to evaluate the performances of these tests. As a result of the simulation study, Zivot and Andrews (J Bus Econ Stat 20(1):25-44, 1992) are the best-performing tests in capturing a single break. The most powerful tests for the multiple break setting are those developed by Kapetanios (J Time Ser Anal 26(1):123-133, 2005) and Perron (Palgrave Handb Econom 1:278-352, 2006). A new Bootstrap algorithm has been proposed along with the study's primary aim. This newly proposed Bootstrap algorithm calculates the optimal number of statistically significant structural breaks under more general assumptions. Therefore, it guarantees finding an accurate number of optimal breaks in real-world data. In the empirical part, structural breaks in the real interest rate data of the US and Australia resulting from policy changes have been examined. The results concluded that the bootstrap sequential break test is the best-performing approach due to the general assumption made to cover real-world data.Article Citation - WoS: 6Citation - Scopus: 8A Novel Deep Learning-Based Framework With Particle Swarm Optimisation for Intrusion Detection in Computer Networks(Public Library Science, 2025) Yilmaz, Abdullah AsimIntrusion detection plays a significant role in the provision of information security. The most critical element is the ability to precisely identify different types of intrusions into the network. However, the detection of intrusions poses a important challenge, as many new types of intrusion are now generated by cyber-attackers every day. A robust system is still elusive, despite the various strategies that have been proposed in recent years. Hence, a novel deep-learning-based architecture for detecting intrusions into a computer network is proposed in this paper. The aim is to construct a hybrid system that enhances the efficiency and accuracy of intrusion detection. The main contribution of our work is a novel deep learning-based hybrid architecture in which PSO is used for hyperparameter optimisation and three well-known pre-trained network models are combined in an optimised way. The suggested method involves six key stages: data gathering, pre-processing, deep neural network (DNN) architecture design, optimisation of hyperparameters, training, and evaluation of the trained DNN. To verify the superiority of the suggested method over alternative state-of-the-art schemes, it was evaluated on the KDDCUP'99, NSL-KDD and UNSW-NB15 datasets. Our empirical findings show that the proposed model successfully and correctly classifies different types of attacks with 82.44%, 90.42% and 93.55% accuracy values obtained on UNSW-B15, NSL-KDD and KDDCUP'99 datasets, respectively, and outperforms alternative schemes in the literature.Article Citation - WoS: 19Citation - Scopus: 17Further Discussion on Modified Multivalued Α*-ψ-contractive Type Mapping(Univ Nis, Fac Sci Math, 2015) Ali, Muhammad Usman; Kamran, Tayyab; Karapinar, ErdalIn this paper, we investigate the existence of a fixed point for modified multivalued alpha(*)-psi-contractive type mapping in the context of complete metric space. We also construct some examples to illustrate the main result. Our results extend, improve and generalize the results on the topic in the literature.Article Citation - WoS: 1Citation - Scopus: 1On the Rate of Convergence for the q-durrmeyer Polynomials in Complex Domains(Walter de Gruyter Gmbh, 2024) Gurel, Ovgu; Ostrovska, Sofiya; Turan, MehmetThe q-Durrmeyer polynomials are one of the popular q-versions of the classical operators of approximation theory. They have been studied from different points of view by a number of researchers. The aim of this work is to estimate the rate of convergence for the sequence of the q-Durrmeyer polynomials in the case 0 < q < 1. It is proved that for any compact set D subset of C, the rate of convergence is O(q(n)) as n -> infinity. The sharpness of the obtained result is demonstrated.Article Citation - WoS: 60Two-Dimensional Fluorinated Boron Sheets: Mechanical, Electronic, and Thermal Properties(Amer Chemical Soc, 2018) Pekoz, Rengin; Konuk, Mine; Kilic, M. Emin; Durgun, EnginThe synthesis of atomically thin boron sheets on a silver substrate opened a new area in the field of two-dimensional systems. Similar to hydrogenated and halogenated graphene, the uniform coating of borophene with fluorine atoms can lead to new derivatives of borophene with novel properties. In this respect, we explore the possible structures of fluorinated borophene for varying levels of coverage (BnF) by using first-principles methods. Following the structural optimizations, phonon spectrum analysis and ab initio molecular dynamics simulations are performed to reveal the stability of the obtained structures. Our results indicate that while fully fluorinated borophene (BF) cannot be obtained, stable configurations with lower coverage levels (B4F and B2F) can be attained. Unveiling the stable structures, we explore the mechanical, electronic, and thermal properties of (BnF). Fluorination significantly alters the mechanical properties of the system, and remarkable results, including direction-dependent variation of Young's modulus and a switch from a negative to positive Poisson's ratio, are obtained. However, the metallic character is preserved for low coverage levels, and metal to semiconductor transition is obtained for B2F. The heat capacity at a low temperature increases with an increasing F atom amount but converges to the same limiting value at high temperatures. The enhanced stability and unique properties of fluorinated borophene make it a promising material for various high-technology applications in reduced dimensions.Article Citation - WoS: 12Citation - Scopus: 14The Markov Discrete Time Δ-Shock Reliability Model and a Waiting Time Problem(Wiley, 2022) Chadjiconstantinidis, Stathis; Eryilmaz, Serkandelta-shock model is one of the widely studied shock models in reliability theory and applied probability. In this model, the system fails due to the arrivals of two consecutive shocks which are too close to each other. That is, the system breaks down when the time between two successive shocks falls below a fixed threshold delta. In the literature, the delta-shock model has been mostly studied by assuming that the time between shocks have continuous distribution. In the present paper, the discrete time version of the model is considered. In particular, a proper waiting time random variable is defined based on a sequence of two-state Markov dependent binary trials and the problem of finding the distribution of the system's lifetime is linked with the distribution of the waiting time random variable, and we study the joint as well as the marginal distributions of the lifetime, the number of shocks and the number of failures associated with these binary trials.Article Citation - Scopus: 45Determination of Key Performance Indicators for Measuring Airport Success: a Case Study in Libya(Elsevier Ltd, 2018) Eshtaiwi,M.; Badi,I.; Abdulshahed,A.; Erkan,T.E.Airports need to evaluate their performance and effectiveness periodically to determine whether objectives are being achieved and how their performance compares to similar best practices. The goals of this paper are twofold: First, to offer a list of essential airport key performance indicators (KPIs) that can provide decision makers in the Libyan airport industry a practical framework to measure and monitor performance over time. The second goal is to use the AHP technique to derive the weights of the KPIs and to select the best international airport in Libya based on the values of the KPIs at each airport according to the judgments of experts. However, the implementation steps of the AHP method will be simplified by using the Expert Choice software. The paper presents the importance weights of seventeen KPIs across five aspects of airport performance. As a result of this study, Libyan airports can benchmark their performance against others or through internal benchmarking. © 2017 Elsevier LtdArticle Citation - WoS: 13Citation - Scopus: 14Investigating Space Utilization in Skyscrapers Designed with Prismatic Form(Mdpi, 2024) Ilgin, Hueseyin Emre; Aslantamer, Ozlem NurThe enduring appeal of prismatic shapes, historically prevalent in office building designs, persists in contemporary skyscraper architecture, which is attributed particularly to their advantageous aspects concerning cost-efficiency and optimal space utilization. Space efficiency is a crucial factor in prismatic skyscraper design, carrying substantial implications for sustainability. However, the current academic literature lacks a complete exploration of space efficiency in supertall towers with prismatic forms, despite their widespread use. This paper seeks to address this significant gap by conducting a comprehensive analysis of data gathered from a carefully selected set of 35 case studies. The primary discoveries presented in this paper are outlined as follows: (i) average space efficiency stood at approximately 72%, covering a range that extended from 56% to 84%; (ii) average core to gross floor area ratio averaged around 24%, spanning a spectrum that ranged from 12% to 36%; (iii) the majority of prismatic skyscrapers utilized a central core approach, mainly customized for residential use; (iv) the dominant structural system observed in the analyzed cases was the outriggered frame system, with concrete being the commonly utilized material for the structural components; and (v) the impact of diverse structural systems on space efficiency showed no significant deviation, although differences in function led to variations in average space efficiency. The authors expect that these findings will provide valuable guidance, especially for architects, as they strive to enhance the sustainable planning of prismatic towers.Article Citation - WoS: 25Citation - Scopus: 42Network Intrusion Detection With a Hashing Based Apriori Algorithm Using Hadoop Mapreduce(Mdpi, 2019) Azeez, Nureni Ayofe; Ayemobola, Tolulope Jide; Misra, Sanjay; Maskeliunas, Rytis; Damasevicius, RobertasUbiquitous nature of Internet services across the globe has undoubtedly expanded the strategies and operational mode being used by cybercriminals to perpetrate their unlawful activities through intrusion on various networks. Network intrusion has led to many global financial loses and privacy problems for Internet users across the globe. In order to safeguard the network and to prevent Internet users from being the regular victims of cyber-criminal activities, new solutions are needed. This research proposes solution for intrusion detection by using the improved hashing-based Apriori algorithm implemented on Hadoop MapReduce framework; capable of using association rules in mining algorithm for identifying and detecting network intrusions. We used the KDD dataset to evaluate the effectiveness and reliability of the solution. Our results obtained show that this approach provides a reliable and effective means of detecting network intrusion.
