5794 research outputs found
Sort by
A Deep Learning Multi-feature Based Fusion Model for Predicting The State of Health of Lithium-ion Batteries
Get PDFLithium-ion batteries have become the preferred energy storage method with applications ranging from consumer
electronics to electric vehicles. Utilization of the battery will eventually lead to degradation and capacity
fade. Accurately predicting the state of health (SOH) of the cells holds significant importance in terms of reliability
and safety of the cell during its operation. The battery degradation mechanism is strongly non-linear and
the physics-based model have their inherent disadvantages. The machine learning method has become popular
for estimating SOH due to its superior non-linear mapping, adaptive, and self-learning capabilities, made possible
by advances in deep learning technologies. In this study parallel hybrid neural network is formulated for predicting
the state of health of lithium-ion cell. Firstly, the factors that have an effect on the cell state were analysed.
These factors are cell voltage, charging & discharging time and incremental capacity curve. The features
were then processed for use as input to the model. Spearman correlation coefficient analysis shows that all the
factors had a positive correlation with SOH. While charging time has a negative correlation with the other
features. Next the deep learning models namely convolution neural network (CNN), temporal convolution
network (TCN), long-short-term memory (LSTM) and bi-directional LSTM were used to make fusion models. The
number of layers in CNN and TCN were also varied. The hyperparameters used in the models were optimized
using Bayesian optimization algorithm. The models were validated through comparative experiments on the
University of Maryland battery degradation dataset. The prediction accuracy with CNN 3-layer LSTM was found
to be the best for the training and the test dataset. The overall R2 value, root mean squared error (RMSE) and
mean absolute percentage error (MAPE) with the model was found to be 0.999646, 0.003807 and 0.3, respectively.
The impact of the features on the model was also analysed by removing one feature and retraining the
model with the other features. The effect of discharging time and the peak of the discharge incremental capacity
curve was maximum. The analysis also reveals that either charging voltage or discharging voltage can be used.
Further, the proposed model was also compared with the other studies. The comparison shows that the R2, RMSE
and MAPE values of the proposed model was better
A Project-Based Learning Approach to Supply Chain Mapping Education
Get PDFAlthough recent disruptions have revealed the importance of supply chain mapping, there is a
lack of academic content in this domain. This is evident because supply chain management
textbooks and pedagogical articles offer limited practical guidance on developing supply chain
maps. Neither do Harvard Business Publishing and the Case Center cases. The main reason for this
scarcity is the challenge of integrating supply chain mapping into the course curriculum. To
address this and enrich academic content, we introduce a Supply Chain Mapping Project based on
a Project-Based Learning approach to instruct undergraduate business students in fundamental
mapping skills and raise awareness of the complexities involved in producing high-quality maps.
The project is implemented in two upper-level undergraduate courses. The project’s effectiveness
is assessed through the post-project survey responses. Results indicate that students were actively
engaged throughout the project. Similarly, survey results from one of the similar courses offered
in the subsequent semester validate the effectiveness of the project. Given the rising demand for
supply chain talent within the management domain, this project will enhance the management/
supply chain management curricula at business schools. The benefits and challenges of the proposed
approach are discussed in the paper
A Bioinspired Method for Optimal Task Scheduling in Fog-Cloud Environment
Get PDFDue to the intense data flow in expanding Internet ofThings (IoT) applications, a heavy processing cost
and workload on the fog-cloud side become inevitable. One of the most critical challenges is optimal task scheduling.
Since this is an NP-hard problem type, a metaheuristic approach can be a good option. This study introduces a
novel enhancement to the Artificial Rabbits Optimization (ARO) algorithm by integrating Chaotic maps and Levy
flight strategies (CLARO). This dual approach addresses the limitations of standard ARO in terms of population
diversity and convergence speed. It is designed for task scheduling in fog-cloud environments, optimizing energy
consumption, makespan, and execution time simultaneously three critical parameters often treated individually in
prior works. Unlike conventional single-objective methods, the proposed approach incorporates a multi-objective
fitness function that dynamically adjusts the weight of each parameter, resulting in better resource allocation and load
balancing. In analysis, a real-world dataset, the Open-source Google Cloud Jobs Dataset (GoCJ_Dataset), is used for
performancemeasurement, and analyses are performed on three considered parameters. Comparisons are applied with
well-known algorithms: GWO, SCSO, PSO,WOA, and ARO to indicate the reliability of the proposed method. In this
regard, performance evaluation is performed by assigning these tasks to VirtualMachines (VMs) in the resource pool.
Simulations are performed on 90 base cases and 30 scenarios for each evaluation parameter.The results indicated that
the proposed algorithm achieved the bestmakespan performance in 80% of cases, ranked first in execution time in 61%
of cases, and performed best in the final parameter in 69% of cases. In addition, according to the obtained results based
on the defined fitness function, the proposed method (CLARO) is 2.52% better than ARO, 3.95% better than SCSO,
5.06% better than GWO, 8.15% better than PSO, and 9.41% better thanWOA
Towards Better Sentiment Analysis in the Turkish Language: Dataset Improvements and Model Innovations
Get PDFSentiment analysis in the Turkish language has gained increasing attention due
to the growing availability of Turkish textual data across various domains. However,
existing datasets often suffer from limitations such as insufficient size, lack of diversity, and
annotation inconsistencies, which hinder the development of robust and accurate sentiment
analysis models. In this study, we present a novel enhanced dataset specifically designed
to address these challenges, providing a comprehensive and high-quality resource for
Turkish sentiment analysis. We perform a comparative evaluation of previously proposed
models using our dataset to assess their performance and limitations. Experimental findings
demonstrate the effectiveness of the presented dataset and trained models, offering valuable
insights for advancing sentiment analysis research in the Turkish language. These results
underscore the critical role of the enhanced dataset in bridging the gap between existing
datasets and the importance of training the modern sentiment analysis models on scalable,
balanced, and curated datasets. This can offer valuable insights for advancing sentiment
analysis research in the Turkish language. Furthermore, the experimental results represent
an important step in overcoming the challenges associated with Turkish sentiment analysis
and improving the performance of existing models
Sustainable Education and Degrowth: International Trends
No full textIn the twenty-first century, sustainability has become a critical concept in addressing economic, social, and environmental
challenges. Within this context, education plays a pivotal role in raising awareness and fostering action toward a more
sustainable future. However, mainstream approaches to sustainabilty have been criticized for perpetuating economic
growth paradigms, prompting the need for alternative perspectives. Degrowth, an emerging concept, seeks to redefine
sustainability by prioritizing ecological responsibility, social justice, and equity. This study employs a bibliometric analysis
of publications indexed in the Web of Science (WoS) database between 2012 and 2025 to examine how sustainability
and degrowth intersect within the academic discourse. The findings reveal dominant trends, thematic evolutions, and
research gaps in the literature, highlighting the necessity of interdisciplinary approaches to align educational policies
with degrowth principles. Moreover, this study underscores the importance of embedding degrowth-oriented values
into educational practices to promote a more equitable and ecologically conscious future
The theological aspect of modernist historicist thought: The example of Fazlurrahman ve Hasan Hanefi
No full textBatı'da kendine has tarihsel şartlarda ortaya çıkan tarihselcilik İslâm dünyasına aktarıldığında genel olarak, üzerinde ittifak edilmiş bazı dînî ahkâmın tarihsel olduğunu bu sebeple de modern dönemin şartlarına göre değiştirilmesi gerektiğini ön gören ve Kur'ân'ın tarihselci bir perspektif üzerinden okunması lüzumunu öne süren bir anlama metodu olarak amelî hükümlere dair değerlendirmeleriyle ön plana çıkmıştır. Bu yönüyle akademi dünyasında çoğunlukla tefsir kürsülerinde ele alınan bir düşünce olmuştur. Ancak kendi tutarlığı açısından tarihselci bir yaklaşımın, amelî sahada yapılmasını teklif ettiği büyük çaplı değişikliklerle sınırlı kalmaması dindeki bazı temel tasavvurların yeniden belirlenmesini de içeren teorik bir zemini inşâ etmesi akademik bir gereklilik olarak gözükmektedir. Bu gerekliliğe binaen tarihselci düşünceyi savunanlar içinde, yukarıda zikredilen amelî boyutun ötesine geçenler olmuştur. Onlar için tarihselci düşünce, muamelat alanına tealluk eden ahkâmın da ötesinde bir kapsayıcılığı haizdir. Bazısı için Kur'an, Hz. Peygamber'in sözü olarak telakki edilirken bir kısım temel mesajlar hariç tamamen tarihsel olarak görülmüş, diğer bir kısım tarihselciler de tarihsel olanın alanını Allah'ı ve sıfatlarını da içine alacak şekilde genişletmiştir. Ne var ki meselenin daha çok kelâm ilmini ilgilendiren bu boyutu yeterince ele alınmamıştır. Dinin inanç noktasındaki hassasiyeti ve temel dinamikleri göz önünde tutulduğunda, amelî boyuttan ziyade, bahsi geçen teorik boyutunun arz ettiği önem ve tartışılmasının gerekliliği izahtan varestedir. Dolayısıyla bu çalışmada tarihselci düşünce, Fazlurrahman ve Hasan Hanefî üzerinden ilâh tasavvuru ve peygamber tasavvuru gibi dinin temel meselelerindeki boyutuyla ortaya konmaya çalışılmıştır. Bu çerçevede tezde nitel yöntem kullanılarak kelâm ilmi ve tarihselcilik muhtelif yönleriyle tanıtılmış ve sonrasında nitel ve analitik yöntemler tatbik edilerek mezkûr düşünürlerin ilâh ve peygamber tasavvurları ve bu konudaki yaklaşımlarının tarihselcilikle ilişkisi ele alınarak bu ilişkinin metodolojik tutarlılığı değerlendirmeye tabi tutulmuştur. Son olarak İslâm dünyası için yeni bir fenomen olan tarihselcilik bağlamında bir kavramsallaştırma teklifi sunularak tez, bazı görüş ve önerilerin yer aldığı sonuç bölümü ile de nihayete erdirilmiştir.Historicism, which emerged in the West under its own historical conditions, has generally come to the fore with its evaluations of practical rulings when it was transferred to the İslâmic world, as a method of understanding that foresees that some religious provisions that are agreed upon are historical and therefore need to be changed according to the conditions of the modern period and that the Quran should be read from a historicist perspective. In this respect, it has been a thought mostly addressed in the tafsir chairs in the academic world. However, in terms of its own consistency, it seems to be an academic necessity for a historicist approach not to be limited to the large-scale changes it proposes to make in the practical field and to build a theoretical ground that includes the re-determination of some basic concepts in religion. Based on this necessity, there have been those who have gone beyond the practical dimension mentioned above among those who defend historicist thought. For them, historicist thought has a comprehensiveness beyond the provisions that concern the field of transactions. For some, the Quran is the life of Hz. While it was considered as the word of the Prophet, it was seen as completely historical except for some basic messages, while other historicists expanded the scope of the historical to include Allah and his attributes. However, this dimension of the issue, which mostly concerns the science of theology, has not been addressed sufficiently. When the sensitivity and basic dynamics of religion in terms of belief are taken into account, the importance and necessity of discussing the theoretical dimension in question, rather than the practical dimension, is beyond explanation. Therefore, in this study, historicist thought has been tried to be revealed with its dimension in the fundamental issues of religion such as the conception of god and the conception of prophet through Fazlurrahman and Hasan Hanafi. Within this framework, the thesis introduces historicism and the science of theology in various aspects by using the qualitative method, and then, by applying qualitative and analytical methods, the relationship between the concepts of god and prophet of the aforementioned thinkers and their approaches on this issue and historicism has been discussed and the methodological consistency of this relationship has been evaluated. Finally, a conceptualization proposal is presented in the context of historicism, a new phenomenon for the İslâmic world, and the thesis is concluded with a conclusion section that includes some views and suggestions
Multi-teacher Based Knowledge Distillation for Retinal Vessel Segmentation
No full textAccurate segmentation of retinal vessels is crucial for the early diagnosis and management of various ocular diseases.
Existing methods often struggle to segment thin vessels, leading to missed diagnoses and inaccurate treatment plans.
This study proposes a novel Multi-Teacher Based Knowledge Distillation (MTKD) method for Retinal Vessel Segmenta
tion (RVS) to address this challenge. Our approach utilizes the expertise of multiple teacher networks, each specialized
in learning different vessel characteristics. Specifically, we train three distinct teacher networks: one on the original
ground truth, one on a modified ground truth highlighting thin vessels, and another on a modified ground truth
emphasizing thick vessels. The student network is then trained to minimize the knowledge discrepancy between its
predictions and the soft predictions of all three teachers. By incorporating knowledge from these specialized teachers,
the student network effectively learns to segment both thin and thick vessels with improved accuracy. We evaluate
our method on two retinal fundus image datasets and two angiography datasets, demonstrating highly competitive
performance compared to state-of-the-art methods. The proposed method improves the baseline U-Net model by
up to 8.44 points in F1 and 10.42 points in IOU. Additionally, we introduce a penalization technique to the student
model’s loss function, further enhancing segmentation performance. Comprehensive ablation studies validate the
effectiveness of the multi-teacher approach, the choice of loss functions, and the impact of model complexity. Our
f
indings suggest that MTKD offers a promising approach for enhancing the robustness and accuracy of RVS. All source
code, datasets, and results are made publicly available to support reproducibility and further research
Behavior assessment of Beylerbeyi Palace timber roof connections
No full textBEYLERBEYİ SARAYI AHŞAP ÇATI SİSTEMİ BİRLEŞİM DAVRANIŞININ DEĞERLENDİRİLMESİ Tarihi yapıların ahşap çatı sistemleri ülkemizin ve dünyanın birçok ülkesinin kültürel mirasını oluşturan ögelerinden biridir. Bu çalışmada İstanbul'un önemli tarihi yapılarından Beylerbeyi Sarayı ahşap çatı sistemi yerinde yapılan gözlemlerle değerlendirilmiş ve çatı sisteminde kullanılan geleneksel birleşim tipleri için iyileştirme/destekleme, müdahale önerileri deneysel olarak araştırılmıştır. Bu amaçla Beylerbeyi Sarayı ahşap çatı sistemi ve birleşimlerinde yapılacak olan çalışmalar saha ve deneysel çalışmalar olarak iki aşamada gerçekleştirilmiştir. Çalışmanın ilk aşamasında gerçekleştirilen saha çalışmaları ile tarihi ahşap çatının özgün durum tespiti ve kullanılan yapı malzemeleri, eleman boyutları, birleşim tipleri ve birleştirme vasıtaları hakkında bilgi edinilmesinin yanı sıra yapısal güvenlik değerlendirmesi yapılmıştır. Çalışmanın ikinci aşamasında saha çalışmalarının yapıldığı Beylerbeyi Sarayı tarihi ahşap çatısında kullanılan geleneksel birleşim tiplerinden yarım geçmeli "T" birleşimi seçilerek davranışı deneylerle incelenmiştir. Daha sonra deneylerle yük aktarımında metal (çivi, plaka, metal mil vb.) bağlantı elemanlarının kullanıldığı mekanik birleşim tiplerinin davranışları araştırılmıştır. Bunun için 3 farklı bağlantı elemanının kullanılan 4 farklı ahşap birleşim tipi deneysel olarak incelenmiştir. Toplamda 12 adet test numunesi üzerinde deneyler gerçekleştirilmiştir. Deneysel çalışmalarla hem geleneksel hem de mekanik yöntemle oluşturulan ahşap birleşimlerin davranışının anlaşılması, taşıma kapasitelerinin belirlenmesi, hasar oluşum bölgelerinin incelenmesi amaçlanmıştır.BEHAVIOR ASSESSMENT OF BEYLERBEYI PALACE TIMBER ROOF CONNECTIONS Historical timber roofs constitute a significant part of our cultural heritage as well as many countries of the world. In this study, the timber roof system of Beylerbeyi Palace, one of the significant historical monuments of İstanbul, was evaluated through on-site observations and experimental investigations. In addition, improvement/support and intervention suggestions for traditional connection types used in the roof system were investigated experimentally. In the first stage, field studies were carried out to understand the original condition of the historical roof and gather information about materials, connection types and fasteners. In the second stage the traditional half lap "T" type connection used in the Beylerbeyi Palace timber roof was selected to understand its behavior with experiments. Then, the behaviors of 4 different dowel-type timber connections with 3 different (screw, plate, angles) fasteners were examined experimentally. A total of 12 test specimens were tested. The main objective of the experimental study was to understand the behavior of both traditional and mechanically fastened timber connections, determine their load-carrying capacities, and identify the damage zones
Alanlar-arası Arama İçin Popülasyona Dayalı Yerel Arama Algoritmaları
No full textPopulation-based local search is a meta-heuristic algorithm combining the principles of the population-based search and the local search. This study presents an extensive comparison of two population-based local search approaches, specifically, the steady state memetic algorithm (SSMA) and a population-based iterated local search (PILS). To the best of our knowledge, PILS is proposed first for cross-domain search. Both approaches are implemented in Hyper-heuristics Flexible Framework (HyFlex) which contains different operators for different problem domains. The operators used in PILS and SSMA are the ones defined in HyFlex and the operator selection is done using two heuristic selection methods, namely, Simple Random and Reinforcement Learning with Tournament selection. The performance of the proposed methods with the selection methods is assessed over nine problem domains in HyFlex. The results reveal the success of the presented approaches for the cross-domain search.Popülasyona dayalı yerel arama, popülasyona dayalı arama ve yerel aramanın ilkelerini birleştiren meta-sezgisel bir algoritmadır. Bu çalışma, iki farklı popülasyona dayalı yerel arama yaklaşımının kapsamlı bir karşılaştırmasını sunmaktadır: kararlı durum memetik algoritma (SSMA) ve popülasyona dayalı iteratif yerel arama (PILS). PILS, bildiğimiz kadarıyla, alanlar arası arama için ilk önerilen yöntemdir. Her iki yaklaşım da farklı problem alanları için farklı operatörler içeren Hyper-heuristics Flexible Framework (HyFlex) üzerinde uygulanmıştır. PILS ve SSMA'da kullanılan operatörler, HyFlex'te tanımlanan operatörlerdir ve bu operatörler arasından seçim yapmak için Basit Rastgele ve Turnuva seçimi ile Pekiştirmeli Öğrenme yöntemleri kullanılmaktadır. Önerilen yöntemlerin her iki seçim yöntemiyle performansı HyFlex' teki dokuz farklı problem üzerinden değerlendirilmiştir. Sonuçlar, alanlar arası arama için sunulan yaklaşımların başarılı olduğunu ortaya koymaktadır
Spatiotemporal Variability of Football Pitch Surface Properties Under Meteorological Influences: A Case Study of Kasımpaşa Stadium
No full textUnderstanding the effects of game traffic, field design, and meteorological variables on the hydrological and
mechanical parameters of sports field surfaces is essential for creating quality fields that minimize surface-related
injuries, and fulfill game requirements. In the presented study, it is aimed to assess six performance parameters
(surface temperature, hardness, surface traction, turf coverage, root length, and rootzone soil moisture)
measured in Kasımpasa Stadium, which is located in Istanbul and hosts Türkiye’s Super League matches, over a
15-month period (August 2021–October 2022). The relationships between the relevant parameters and meteorological
variables such as ambient temperature, total precipitation height, sunshine duration, and global solar
radiation were also examined. Significant temporal variations were observed, whereas spatial differences across
various points of the pitch were relatively minor. Surface temperature levels remained within acceptable ranges
to prevent skin burns and injuries. Surface hardness was classified as a hard surface only in June-22, as a soft
surface in April-22 and May-22 and was optimal during the remaining periods. A Spearman correlation analysis
was conducted to reveal the pairwise relationships between the variables. Meteorological parameters, particularly
ambient temperature, had a significant influence on surface temperature (r = 0.84), traction (r = 0.68), and
root length (r = 0.73). This study provides a comprehensive evaluation of performance and quality monitoring in
sports fields. Stadium location and design, especially sun exposure and its duration, are crucial for meeting the
mechanical and hydrological requirements of field surfaces, maintaining game standards, and ensuring player
safety