1,721,025 research outputs found
On the performance, availability and energy consumption modelling of clustered IoT systems
Full text linkWireless sensor networks (WSNs) form a large part of the ecosystem of the Internet of Things (IoT), hence they have numerous application domains with varying performance and availability requirements. Limited resources that include processing capability, queue capacity, and available energy in addition to frequent node and link failures degrade the performance and availability of these networks. In an attempt to efficiently utilise the limited resources and to maintain the reliable network with efficient data transmission; it is common to select a clustering approach, where a cluster head is selected among the diverse IoT devices. This study presents the stochastic performance as well as the energy evaluation model for WSNs that have both node and link failures. The model developed considers an integrated performance and availability approach. Various duty cycling schemes within the medium-access control of the WSNs are also considered to incorporate the impact of sleeping/idle states that are presented using analytical modeling. The results presented using the proposed analytical models show the effects of factors such as failures, various queue capacities and system scalability. The analytical results presented are in very good agreement with simulation results and also present an important fact that the proposed models are very useful for identification of thresholds between WSN system characteristics
A4WSN: an architecture-driven modelling platform for analysing and developing WSNs
Full text linkThis paper proposes A4WSN, an architecture-driven modelling platform for the development and the analysis of wireless sensor networks (WSNs). A WSN consists of spatially distributed sensor nodes that cooperate in order to accomplish a specific task. Sensor nodes are cheap, small, and battery-powered devices with limited processing capabilities and memory. WSNs are mostly developed directly on the top of the operating system. They are tied to the hardware configuration of the sensor nodes, and their design and implementation can require cooperation with a myriad of system stakeholders with different backgrounds. The peculiarities of WSNs and current development practices bring a number of challenges, ranging from hardware and software coupling, limited reuse, and the late assessment of WSN quality properties. As a way to overcome a number of existing limitations, this study presents a multi-view modelling approach that supports the development and analysis of WSNs. The framework uses different models to describe the software architecture, hardware configuration, and physical deployment of a WSN. A4WSN allows engineers to perform analysis and code generation in earlier stages of the WSN development life cycle. The A4WSN platform can be extended with third-party plug-ins providing additional analysis or code generation engines. We provide evidence of the applicability of the proposed platform by developing PlaceLife, an A4WSN plug-in for estimating the WSN lifetime by taking various physical obstacles in the deployment environment into account. In turn, PlaceLife has been applied to a real-world case study in the health care domain as a running example
ELEKTRONİK SAĞLIK UYGULAMALARINDA HAFİF VE VERİMLİ İNSAN ETKİNLİĞİ TANIMA İÇİN GRAF VERİ YAPISININ VE GRAF SİNİR AĞLARININ KULLANIMI
No full textHuman activity recognition (HAR) plays a crucial role in applications like healthcare, and smart environments, aiming to improve health outcomes, and optimize daily living. Traditional HAR systems often rely on complex models unsuitable for edge computing due to high computational requirements. This thesis addresses the need for lightweight models that maintain high accuracy while being comptationally light. To achieve this, it proposes the use of graph neural networks (GNNs), a mechanism that has been extensively studied but is relatively underexplored for Human Activity Recognition (HAR) using various sensors, such as accelerometers, gyroscopes, and magnetometers. The proposed mechanism uses bidirectional Long Short-Term Memory (LSTM) layers for temporal feature extraction and GNNs for activity classification. The model’s performance is validated on a well known dataset through extensive experiments, demonstrating a detection accuracy of 93.19%, with significantly lower computational requirements compared to existing models. Sensor importance analysis highlights the critical role of gyroscope and accelerometer sensors in capturing detailed motion data.Insan aktivitesi tanıma (HAR), sağlık ve akıllı çevre uygulamalarinda, sağlık sonuçlarını iyileştirmeyi ve günlük yaşamı optimize etmeyi hedefleyerek önemli bir rol oynar. Geleneksel HAR sistemleri, yüksek hesaplama gereksinimleri nedeniyle uç bilişim için uygun olmayankarmaşık modellere dayanır. Bu tez, yüksek doğruluğu korurken hafif modellerin gelistirilmesini ele almaktadır. Bu amacı gerçekleştirmek için, literatürde geniş çapta araştırılmamış bir mekanizma olan graf sinir ağları (GNN’ler) önermektedir. Bu model, ivmeölçerler, jiroskoplar ve manyetometreler gibi çeşitli sensörleri kullanmaktadır. Önerilen mekanizma, zamansal özellik çıkarımı için çift yönlü Uzun Kısa Süreli Bellek (LSTM) katmanlarını ve aktivite sınıflandırması için GNN’leri kullanmaktadır. Modelin performansı, iyi bilinen bir veri kümesi üzerinde kapsamlı deneylerle doğrulanmış ve mevcut modellere kıyasla önemli ölçüde daha düşük hesaplama gereksinimleri ile %93.19 tespit doğruluğu göstermiştir. Sensör önemi analizi, jiroskop ve ivmeölçer sensörlerinin detaylı hareket verilerini yakalamadaki kritik rolünü vurgulamaktadır.M.S. - Master of Scienc
Colour coding based novel data representation and lightweight convolutional neural network architecture for hierarchical anomaly detection on ehealth applications
Full text linkeHealth is on its way to become an essential industry due to the advancements in information technology. Human activity recognition (HAR) is one of the most popular areas within the scope of eHealth, particularly with applications in anomaly detection. Although there are various studies on HAR, most of them propose complex models that are not compatible with portable devices and wearables due to their restricted computing capabilities. In this thesis, new data representation is presented along with a lightweight convolutional neural network (CNN) for this purpose. An anomaly detection framework is presented, which uses ECG data for heart effort prediction of daily life activities. The novel data representation approach and the proposed deep learning model are tested on the MHEALTH dataset with two different validation techniques for accuracy and three different complexity metrics. The results show that the proposed approaches can achieve up to 96.92% and 97.06% accuracy for HAR, and heart effort level with five fold cross validation. In addition, the models proposed for inertial data based and ECG based predictions have sizes of 0.89 MB and 1.97 MB and have a complexity of 0.06 and 1.04 Giga FLOPS, respectively.M.S. - Master of Scienc
Network Experience Scheduling and Routing Approach for Big Data Transmission in the Internet of Things
Full text linkThe recent developments in the Internet of Things related technologies have caused a shift towards smart applications such as smart cities, smart homes, smart education systems, e-health, and online applications to run businesses. These, in turn, have introduced significant additional loads to the existing network infrastructures. In addition, these applications use big data and require relatively short response times. In this paper, we are introducing a new scheduling and routing approach to enhance the end user experience, and utilize the network resources by providing improved transmission speed for the big data applications. The approach considers the source and destination requirements in terms of data size, expected delay, link load, and link capacity. Extensive simulations are performed, and the results obtained show the efficiency of our approach against other competitive approaches in terms of in-network delay, network throughput, and dropped packets
Erken Orman Yangını Algılamanın Geliştirilmesi: Kablosuz Sensör Ağlarını (WSN'ler), İnsansız Hava Araçlarını (İHA'lar) ve Yapay Zekayı (AI) Bütünleştiren Kapsamlı Bir Çerçeve
No full textForest fires pose significant environmental, ecological, economic, and social threats globally, necessitating rapid and accurate detection systems for timely intervention. Traditional detection methods, such as watchtowers, manual patrols, and satellite imagery, face challenges including limited coverage, delays, and accuracy constraints. In response, this thesis introduces a three-tier edge-centric framework integrating wireless sensor networks (WSNs), wireless multimedia sensor networks (WMSNs), unmanned aerial vehicles (UAVs), and lightweight artificial intelligence (AI) models for efficient early detection of forest fires.
Our proposed architecture improves accuracy, energy efficiency, and communication reliability by integrating scalar sensors for initial detection, smart sensors with a machine learning model for intermediate verification (achieving a 94% F1-score with a minimal subset, comparable to the 95% of state-of-the-art methods), and UAVs equipped with a lightweight convolutional neural network (CNN) for final confirmation. The CNN model achieves 100% accuracy and F1-score on the FireMan-UAV-RGBT dataset and 99.57% accuracy with a 99.5% F1-score on the UAV-FFDBs dataset. Despite its strong performance, the model remains compact at 1.6 MB, significantly smaller than the 98 MB state-of-the-art using the FireMan-UAV-RGBT dataset, and delivers an inference speed of 157 ms per image on edge devices, validating its practical deployment.
Extensive simulations reveal that the proposed framework significantly reduces end-to-end delay to 813.59 ms compared to traditional WSN-only methods (865.84 ms) and WSN combined with machine learning approaches (1066.18 ms). Additionally, it achieves a 100% packet delivery ratio and increased throughput (7.05 kbps versus 3.80 kbps and 3.06 kbps, respectively) against these methods. Real-world WSN testbed experiments further confirm these findings, showing a packet delivery ratio of 97%, latency of 144.39 ms (lower than simulation latency of 258.37 ms), and energy consumption of 0.0559 J/s compared to simulation results of 0.0442 J/s, closely aligning and validating the framework’s feasibility and effectiveness for real-time forest fire monitoring and rapid response.Orman yangınları küresel olarak önemli çevresel, ekolojik, ekonomik ve sosyal tehditler oluşturur ve zamanında müdahale için hızlı ve doğru tespit sistemleri gerektirir. Gözetleme kuleleri, manuel devriyeler ve uydu görüntüleri gibi geleneksel tespit yöntemleri sınırlı kapsama, gecikmeler ve doğruluk kısıtlamaları gibi zorluklarla karşı karşıyadır. Buna karşılık, bu tez orman yangınlarının etkili erken tespiti için kablosuz sensör ağları (WSN'ler), kablosuz multimedya sensör ağları (WMSN'ler), insansız hava araçları (İHA'lar) ve hafif yapay zeka (AI) modellerini entegre eden üç katmanlı bir kenar merkezli çerçeve sunmaktadır.
Önerdiğimiz mimari, ilk tespit için skaler sensörleri, ara doğrulama için makine öğrenimi modeliyle akıllı sensörleri (en son teknoloji yöntemlerinin %95'ine kıyasla minimal bir alt kümeyle %94 F1 puanı elde ederek) ve son onay için hafif bir evrişimsel sinir ağı (CNN) ile donatılmış İHA'ları entegre ederek doğruluğu, enerji verimliliğini ve iletişim güvenilirliğini artırır. CNN modeli, FireMan-UAV-RGBT veri setinde %100 doğruluk ve F1 puanı ve UAV-FFDBs veri setinde %99,57 doğruluk ve %99,5 F1 puanı elde eder. Güçlü performansına rağmen, model 1,6 MB'de kompakt kalır ve FireMan-UAV-RGBT veri setini kullanan 98 MB'lik en son teknolojiden önemli ölçüde daha küçüktür ve uç cihazlarda görüntü başına 157 ms çıkarım hızı sunarak pratik dağıtımını doğrular.
Kapsamlı simülasyonlar, önerilen çerçevenin uçtan uca gecikmeyi geleneksel WSN-yalnızca yöntemlerine (865,84 ms) ve makine öğrenimi yaklaşımlarıyla birleştirilmiş WSN'ye (1066,18 ms) kıyasla önemli ölçüde 813,59 ms'ye düşürdüğünü ortaya koymaktadır. Ek olarak, bu yöntemlere karşı %100 paket teslim oranı ve artan verim (sırasıyla 3,80 kbps ve 3,06 kbps'ye kıyasla 7,05 kbps) elde etmektedir. Gerçek dünya WSN test yatağı deneyleri bu bulguları daha da doğrulayarak %97 paket teslim oranı, 144,39 ms gecikme (258,37 ms'lik simülasyon gecikmesinden daha düşük) ve 0,0442 J/s'lik simülasyon sonuçlarına kıyasla 0,0559 J/s enerji tüketimi göstererek çerçevenin gerçek zamanlı orman yangını izleme ve hızlı müdahale için uygulanabilirliğini ve etkinliğini yakından hizalamakta ve doğrulamaktadır.M.S. - Master of Scienc
Does the Assumption of Exponential Arrival Distributions in Wireless Sensor Networks Hold?
Full text linkWireless sensor networks (WSNs) have seen a tremendous growth in various application areas despite prominent performance and availability challenges. Although researchers continue to address these challenges, the type of distributions for arrivals at the cluster head and intermediary routing nodes is still an interesting area of investigation. The general practice in published works is to compare an empirical exponential arrival distribution of WSNs with a theoretical exponential distribution in a Q-Q plot diagram. In this paper, we show that such comparisons based on simple eye checks are not sufficient since, in many cases, incorrect conclusions may be drawn from such plots. After estimating the maximum likelihood parameters of empirical distributions, we generate theoretical distributions based on the estimated parameters. By conducting Kolmogorov-Smirnov test statistics for each generated inter-arrival time distributions, we find out, if it is possible to represent the traffic into the cluster head by using theoretical distribution. Empirical exponential arrival distribution assumption of WSNs holds only for a few cases. The work is further extended to understand the effect of delay on inter-arrival time distributions based on the type of medium access control (MAC) used in WSNs
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
An analytical approach for modelling unmanned aerial vehicles and base station interaction for disaster recovery scenarios
Full text linkFunding Information: Open access funding provided by the Scientific and Technological Research Council of Türkiye (TÜBİTAK). No funding was provided for this study. Publisher Copyright: © The Author(s) 2024.Unmanned Aerial Vehicles (UAVs) are an emerging technology with the potential to be used in various sectors for various applications and services. In wireless networking, UAVs can be used as a vital part of the supplementary infrastructure to improve coverage, principally during public safety emergencies. Because of their affordability and potential for widespread deployment, there has been a growing interest in exploring the ways in which UAVs can enhance the services offered to isolated ground devices. Large areas may lose cellular coverage following a public safety emergency that impacts critical communication infrastructure. This prompts the need for the employment of D2D communication frameworks as a complement. In such critical conditions, timely response and network connectivity are essential factors for reliable communication. This study focuses on the mathematical models of UAV-based wireless communication in the context of disaster recovery. Particularly, we aim to model a queuing framework comprising UAVs as mobile relay nodes between the stranded user devices and neighbouring operational base stations. We present an iterative solution with a novel method for generating initial conditions for the two-stage queuing model. The approximate approach presented is validated for its accuracy using discrete-event simulation. The effects of various factors on performance measures are also analysed in detail. The validation results show that the discrepancy between the analytical approach and the simulation is less than 5%, which is the confidence interval of the simulation.publishersversionpublishe
- …
