40 results
Search Results
Now showing 1 - 10 of 40
Article Citation - WoS: 33Citation - Scopus: 41Visual and Auditory Data Fusion for Energy-Efficient and Improved Object Recognition in Wireless Multimedia Sensor Networks(Ieee-inst Electrical Electronics Engineers inc, 2019) Koyuncu, Murat; Yazici, Adnan; Civelek, Muhsin; Cosar, Ahmet; Sert, MustafaAutomatic threat classification without human intervention is a popular research topic in wireless multimedia sensor networks (WMSNs) especially within the context of surveillance applications. This paper explores the effect of fusing audio-visual multimedia and scalar data collected by the sensor nodes in a WMSN for the purpose of energy-efficient and accurate object detection and classification. In order to do that, we implemented a wireless multimedia sensor node with video and audio capturing and processing capabilities in addition to traditional/ordinary scalar sensors. The multimedia sensors are kept in sleep mode in order to save energy until they are activated by the scalar sensors which are always active. The object recognition results obtained from video and audio applications are fused to increase the object recognition performance of the sensor node. Final results are forwarded to the sink in text format, and this greatly reduces the size of data transmitted in network. Performance test results of the implemented prototype system show that the fusing audio data with visual data improves automatic object recognition capability of a sensor node significantly. Since auditory data requires less processing power compared to visual data, the overhead of processing the auditory data is not high, and it helps to extend network lifetime of WMSNs.Article A Model Proposal To Optimize Bandwidth Usage in Multi-Access Wireless Networks(Univ Osijek, Tech Fac, 2012) Koyuncu, Murat; Gercek, Mehmet Kazim; Information Systems EngineeringDistribution of load among multiple access points, and therefore, optimizing the total throughput is one of the problems of wireless local area networks when there is more than one access point available in the network. It is not easy to balance the load when wireless hosts associate with one access point by using only the Received Signal Strength Indicator (RSSI). In this study, a new model which increases total throughput in a wireless local area network is proposed. The proposed model is mainly based on the prediction of the loads of all the available access points checking both their wireless and Ethernet interfaces and the association to the least loaded one. It is a host-based model and does not require any changes on the network infrastructure. The tests performed on the real wireless local area networks prove the applicability of the proposed model.Review Citation - WoS: 7Citation - Scopus: 9A Survey of Covid-19 Diagnosis Using Routine Blood Tests With the Aid of Artificial Intelligence Techniques(Mdpi, 2023) Habashi, Soheila Abbasi; Koyuncu, Murat; Alizadehsani, RoohallahSevere Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), causing a disease called COVID-19, is a class of acute respiratory syndrome that has considerably affected the global economy and healthcare system. This virus is diagnosed using a traditional technique known as the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. However, RT-PCR customarily outputs a lot of false-negative and incorrect results. Current works indicate that COVID-19 can also be diagnosed using imaging resolutions, including CT scans, X-rays, and blood tests. Nevertheless, X-rays and CT scans cannot always be used for patient screening because of high costs, radiation doses, and an insufficient number of devices. Therefore, there is a requirement for a less expensive and faster diagnostic model to recognize the positive and negative cases of COVID-19. Blood tests are easily performed and cost less than RT-PCR and imaging tests. Since biochemical parameters in routine blood tests vary during the COVID-19 infection, they may supply physicians with exact information about the diagnosis of COVID-19. This study reviewed some newly emerging artificial intelligence (AI)-based methods to diagnose COVID-19 using routine blood tests. We gathered information about research resources and inspected 92 articles that were carefully chosen from a variety of publishers, such as IEEE, Springer, Elsevier, and MDPI. Then, these 92 studies are classified into two tables which contain articles that use machine Learning and deep Learning models to diagnose COVID-19 while using routine blood test datasets. In these studies, for diagnosing COVID-19, Random Forest and logistic regression are the most widely used machine learning methods and the most widely used performance metrics are accuracy, sensitivity, specificity, and AUC. Finally, we conclude by discussing and analyzing these studies which use machine learning and deep learning models and routine blood test datasets for COVID-19 detection. This survey can be the starting point for a novice-/beginner-level researcher to perform on COVID-19 classification.Article Citation - Scopus: 1Optimizing the Stochastic Deployment of Small Base Stations in an Interleave Division Multiple Access-Based Heterogeneous Cellular Networks(Wiley, 2022) Noma-Osaghae, Etinosa; Misra, Sanjay; Koyuncu, MuratThe use of small base stations (SBSs) to improve the throughput of cellular networks gave rise to the advent of heterogeneous cellular networks (HCNs). Still, the interleave division multiple access (IDMA) performance in sleep mode active HCNs has not been studied in the existing literature. This research examines the 24-h throughput, spectral efficiency (SE), and energy efficiency (EE) of an IDMA-based HCN and compares the result with orthogonal frequency division multiple access (OFDMA). An energy-spectral-efficiency (ESE) model of a two-tier HCN was developed. A weighted sum modified particle swarm optimization (PSO) algorithm simultaneously maximized the SE and EE of the IDMA-based HCN. The result obtained showed that the IDMA performs at least 68% better than the OFDMA on the throughput metric. The result also showed that the particle swarm optimization algorithm produced the Pareto optimal front at moderate traffic levels for all varied network parameters of SINR threshold, SBS density, and sleep mode technique. The IDMA-based HCN can improve the throughput, SE, and EE via sleep mode techniques. Still, the combination of network parameters that simultaneously maximize the SE and EE is interference limited. In sleep mode, the performance of the HCN is better if the SBSs can adapt to spatial and temporal variations in network traffic.Conference Object An Alternative Product Extraction Method for E-Commerce Applications(Ieee Computer Soc, 2007) Koyuncu, MuratCustomers generally like to see alternative products and compare their characteristics and prices before deciding on one of them. Therefore, proposing alternative products is one of the crucial issues for e-commerce applications to increase customer satisfaction. This paper proposes a fuzzy similarity-based approach to determine similar products recorded in a database and submit them intelligently to the customer in a ranked way as alternative products.Conference Object Citation - WoS: 5Fuzzy Querying in Intelligent Information Systems(Springer-verlag Berlin, 2009) Koyuncu, MuratMany new database applications require intelligent information management to satisfy different users' query demands. One way to convert conventional database systems to intelligent information systems is to enhance them with a rule-based system. On the other hand, fuzziness becomes unavoidable for some applications and therefore both the database and rule-based systems should handle fuzziness existing in data and queries. This study explains how a fuzzy rule-based system integrated to a fuzzy spatial, temporal or multimedia database improves the query capabilities of the database system intelligently. Fuzzy query types that can be supported by the rule-based system to improve querying power are discussed.Article Citation - WoS: 12Citation - Scopus: 12A Polarity Calculation Approach for Lexicon-Based Turkish Sentiment Analysis(Tubitak Scientific & Technological Research Council Turkey, 2019) Yurtalan, Gökhan; Koyuncu, Murat; Turhan, ÇiğdemSentiment analysis attempts to resolve the senses or emotions that a writer or speaker intends to send across tothe people about an object or event. It generally uses natural language processing and/or artificial intelligence techniquesfor processing electronic documents and mining the opinion specified in the content. In recent years, researchers haveconducted many successful sentiment analysis studies for the English language which consider many words and wordgroups that set emotion polarities arising from the English grammar structure, and then use datasets to test theirperformance. However, there are only a limited number of studies for the Turkish language, and these studies have lowerperformance results compared to those studies for English. The reasons for this can be incorrect translation of datasetsfrom English into Turkish and ignoring the special grammar structures in the latter. In this study, special Turkish wordsand linguistic constructs which affect the polarity of a sentence are determined with the aid of a Turkish linguist, and anappropriate lexicon-based polarity determination and calculation approach is introduced for this language. The proposedmethodology is tested using different datasets collected from Twitter, and the test results show that the proposed systemachieves better accuracy than the previously developed lexical-based sentiment analysis systems for Turkish. The authorsconclude that especially analysis of word groups increases the overall performance of the system significantly.Article Citation - WoS: 13Citation - Scopus: 14An Intelligent Multimedia Information System for Multimodal Content Extraction and Querying(Springer, 2018) Yazici, Adnan; Koyuncu, Murat; Yilmaz, Turgay; Sattari, Saeid; Sert, Mustafa; Gulen, ElvanThis paper introduces an intelligent multimedia information system, which exploits machine learning and database technologies. The system extracts semantic contents of videos automatically by using the visual, auditory and textual modalities, then, stores the extracted contents in an appropriate format to retrieve them efficiently in subsequent requests for information. The semantic contents are extracted from these three modalities of data separately. Afterwards, the outputs from these modalities are fused to increase the accuracy of the object extraction process. The semantic contents that are extracted using the information fusion are stored in an intelligent and fuzzy object-oriented database system. In order to answer user queries efficiently, a multidimensional indexing mechanism that combines the extracted high-level semantic information with the low-level video features is developed. The proposed multimedia information system is implemented as a prototype and its performance is evaluated using news video datasets for answering content and concept-based queries considering all these modalities and their fused data. The performance results show that the developed multimedia information system is robust and scalable for large scale multimedia applications.Conference Object Citation - WoS: 3Flexible Content Extraction and Querying for Videos(Springer-verlag Berlin, 2011) Demir, Utku; Koyuncu, Murat; Yazici, Adnan; Yilmaz, Turgay; Sert, MustafaIn this study, a multimedia database system which includes a semantic content extractor, a high-dimensional index structure and an intelligent fuzzy object-oriented database component is proposed. The proposed system is realized by following a component-oriented approach. It supports different flexible query capabilities for the requirements of video users, which is the main focus of this paper. The query performance of the system (including automatic semantic content extraction) is tested and analyzed in terms of speed and accuracy.Article Citation - WoS: 3Citation - Scopus: 5Particle Swarm Optimization of the Spectral and Energy Efficiency of an Scma-Based Heterogeneous Cellular Network(Wiley, 2022) Noma-Osaghae, Etinosa; Misra, Sanjay; Ahuja, Ravin; Koyuncu, MuratBackground The effect of stochastic small base station (SBS) deployment on the energy efficiency (EE) and spectral efficiency (SE) of sparse code multiple access (SCMA)-based heterogeneous cellular networks (HCNs) is still mostly unknown. Aim This research study seeks to provide insight into the interaction between SE and EE in SBS sleep-mode enabled SCMA-based HCNs. Methodology A model that characterizes the energy-spectral-efficiency (ESE) of a two-tier SBS sleep-mode enabled SCMA-based HCN was derived. A multiobjective optimization problem was formulated to maximize the SE and EE of the SCMA-based HCN simultaneously. The multiobjective optimization problem was solved using a proposed weighted sum modified particle swarm optimization algorithm (PSO). A comparison was made between the performance of the proposed weighted sum modified PSO algorithm and the genetic algorithm (GA) and the case where the SCMA-based HCN is unoptimized. Results The Pareto-optimal front generated showed a simultaneous maximization of the SE and EE of the SCMA-based HCN at high traffic levels and a convex front that allows network operators to select the SE-EE tradeoff at low traffic levels flexibly. The proposed PSO algorithm offers a higher SBS density, and a higher SBS transmit power at high traffic levels than at low traffic levels. The unoptimized SCMA-based HCN achieves an 80% lower SE and a 51% lower EE than the proposed PSO optimized SCMA-based HCN. The optimum SE and EE achieved by the SCMA-based HCN using the proposed PSO algorithm or the GA are comparable, but the proposed PSO uses a 51.85% lower SBS density and a 35.96% lower SBS transmit power to achieve the optimal SE and EE at moderate traffic levels. Conclusion In sleep-mode enabled SCMA-based HCNs, network engineers have to decide the balance of SBS density and SBS transmit power that helps achieve the desired SE and EE.
