Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 19 of 19 for “"AGGREGATION ALGORITHMS"”.

  1. Federated and Multi-Task Learning for Privacy-Preserving Short-Term Electric Load Forecasting

    … weights instead of data. Using multiple server aggregation algorithms, we implement several fine-tuning optimizers to improve the local load forecasting accuracy compared to non-personalized FL. We also propose training a Temporal Fusion Transformer (TFT), which improved load forecasting …

    carleton Repository record for Federated and Multi-Task Learning for Privacy-Preserving Short-Term Electric Load Forecasting (opens in a new tab)

  2. Aggregation operations by spatiotemporal databases

    The efficient evaluation of aggregation queries is key to the success of relational database systems and Geographic Information Systems. However, the aggregation queries for spatiotemporal databases that represent a set of moving point objects is a relatively new area. In this dissertation, we …

    nebraska Repository record for Aggregation operations by spatiotemporal databases (opens in a new tab)

  3. Energy efficient security and privacy management in sensor clouds

    … code have to be attained by way of lightweight algorithms. In this work, we first present two data aggregation algorithms, one based on an Elliptic Curve Cryptosystem (ECC) and the other based on symmetric key system, which provide confidentiality and integrity of data against an outside …

    must-thes Repository record for Energy efficient security and privacy management in sensor clouds (opens in a new tab)

  4. The security properties of in-network aggregation

    In-netvork aggregation is an important paradigm for current and future networked systems, enabling efficient cooperate processing of aggregate information, while providing sub-linear scalability properties. However, security of this important class of algorithms has to date not been sufficiently …

    reykjavik Repository record for The security properties of in-network aggregation (opens in a new tab)

  5. Federated Learning on Knowledge Graphs via Contrastive Alignment

    … the performance of traditional FL global aggregation algorithms is significantly challenged by the non-identical distribution of data across clients’ knowledge graphs. To tackle this issue, we introduce AlignNet, a novel supervised contrastive learning (CL) approach that helps align both …

    brock Repository record for Federated Learning on Knowledge Graphs via Contrastive Alignment (opens in a new tab)

  6. Robust distributed data aggregation

    Distributed aggregation algorithms are an important building block of modern large scale systems, as it allows the determination of meaningful system-wide properties (e.g., network size, total storage capacity, average load, or majorities) which are required to direct the execution of distributed …

    minho-thes Repository record for Robust distributed data aggregation (opens in a new tab)

  7. Malicious & Cooperative Client Behavior Under Federated Learning with Score-Based Aggregation and Cluster Elimination

    … model is distributed among the clients. Various aggregation methods have been published for increasing the global model's accuracy performance after aggregation. However, those new aggregation algorithms must be thoroughly investigated under malicious and collaborative environments. A malicious …

    ottawa-retro Repository record for Malicious & Cooperative Client Behavior Under Federated Learning with Score-Based Aggregation and Cluster Elimination (opens in a new tab)

  8. Morphology Extraction and Analysis of Primary Soot Particles and Aggregates and Aggregates in Soot TEM Images Using Machine Learning

    … The synthetic images, created using validated aggregation algorithms, mimic real TEM images and allow large-scale model pretraining without extensive manual labeling, while fine-tuning on real TEM images refines the model’s ability to accurately segment actual primary particles. Additional …

    marquette Repository record for Morphology Extraction and Analysis of Primary Soot Particles and Aggregates and Aggregates in Soot TEM Images Using Machine Learning (opens in a new tab)

  9. Enhancing Internet of Things Security: Practical Solutions using Federated Learning and One-Class Classifiers

    … investigating aspects such as the comparison of aggregation algorithms, the impact of the number of server rounds, the effects data heterogeneity, client availability, and partial local training. Finally, FL is compared against centralized and distributed learning. Before any attacks or …

    sask Repository record for Enhancing Internet of Things Security: Practical Solutions using Federated Learning and One-Class Classifiers (opens in a new tab)

  10. Harnessing the Power of Distributed Computing: Advancements in Scientific Applications, Homomorphic Encryption, and Federated Learning Security

    … the concept of parallel caching of secure aggregation to mitigate the performance overhead incurred by the HE module in outsourced databases. The key idea of this optimization approach is caching selected radix-ciphertexts in parallel without violating existing security guarantees of the …

    unr Repository record for Harnessing the Power of Distributed Computing: Advancements in Scientific Applications, Homomorphic Encryption, and Federated Learning Security (opens in a new tab)

  11. Forecast Aggregation and Binned Sequential Testing in a Streaming Environment

    … 2015 by IARPA to develop improved group forecast aggregation algorithms. Each team had at least ten algorithms under continuous development and evaluation over the four year project. The mean Brier score was used to rank the algorithms on approximately 130 questions concerning categorical …

    rice Repository record for Forecast Aggregation and Binned Sequential Testing in a Streaming Environment (opens in a new tab)

  12. Network Optimizations for Literature-based Discovery

    … graph data structure has been improved; (2) new algorithms have been developed for improved calculation speed, especially for longer metapaths; (3) ULARA, a flawed rank aggregation system, has been replaced with new aggregation algorithms. SemNet version 2, with the new changes implemented, was …

    gatech Repository record for Network Optimizations for Literature-based Discovery (opens in a new tab)

  13. Adoption of Deep Learning Models and its Applications in Dementia Research

    … in healthcare through privacy-preserving aggregation algorithms and human-centered evaluations of transparency in clinical decision support systems. In particular, this dissertation explores advanced methodologies in Federated Learning (FL) for improving collaborative learning, data …

    concordia Download PDF for Adoption of Deep Learning Models and its Applications in Dementia Research (opens in a new tab)

  14. On the efficiency of data collection and aggregation for the combination of multiple classifiers

    … in the existing literature. On the one hand, aggregation algorithms are numerous but are mostly designed for predictive accuracy alone. Achieving state-of-the-art accuracy in a computationally efficient way is currently an open question. On the other hand, empirical studies show that the …

    soton Download PDF for On the efficiency of data collection and aggregation for the combination of multiple classifiers (opens in a new tab)

  15. Optimized federated learning framework for Open Radio Access Networks (O-RAN)

    … Through its foundational characteristics of disaggregation, standardized open interfaces enabling genuine multi-vendor interoperability, and embedded intelligence via RAN Intelligent Controllers (RICs), O-RAN enables unprecedented network capabilities. The programmable nature of O-RAN, …

    ets-quebec Download PDF for Optimized federated learning framework for Open Radio Access Networks (O-RAN) (opens in a new tab)

  16. Radiogenomics machine learning analyses for treatment personalization of locally advanced head and neck squamous cell carcinoma

    … be then be leveraged alongside machine learning algorithms for modelling of various endpoints. The present thesis was dedicated not only towards establishing prognostic models within locally-advanced HNSCC but also towards a radiogenomic study of the relationship and interplay between image-level …

    qucosa-diss

  17. Demonstrativní nástroj pro výpočet komponent elektrické energie

    Diplomová práce se soustředí na problematiku komponent v elektrických sítích a jejich vyhodnocení v rámci analyzátorů sítě a to zejména ve specifických provozních stavech, jako jsou obousměrné toky energie, nesmetrie nebo rychlé změny odběru výkonu. V rámci práce byl vyvinut nástroj v jazyce …

    brno-tech Repository record for Demonstrativní nástroj pro výpočet komponent elektrické energie (opens in a new tab)

  18. Um novo algoritmo agregação temporal para resolver processos de decisão markovianos com custo médio

    … and proves the convergence of a new class of algorithms based on time aggregation to solve Markov decision problems with average cost. The new algorithms use a new partitioning scheme that divides the state space into multiple subsets comprised of frontier states and interior states. The …

    brazil-uerj Repository record for Um novo algoritmo agregação temporal para resolver processos de decisão markovianos com custo médio (opens in a new tab)

  19. ΔΙΑΣΠΑΣΗ ΕΡΓΑΣΙΩΝ ΣΕ ΣΥΣΤΗΜΑΤΑ ΚΑΤΑΝΕΜΗΜΕΝΗΣ ΕΠΙΛΥΣΗΣ ΠΡΟΒΛΗΜΑΤΟΣ

    DISTRIBUTED PROBLEM SOLVING (DPS) IS DEFINED AS THE COOPERATIVE SOLUTION OF PROBLEMS BY A DECENTRALISED AND LOOSELY COUPLED COLLECTION OF PROBLEM SOLVERS (AGENTS), EACH OF THEM KNOWING HOW TO EXECUTE ONLY SOME OF THE NECESSARY TASKS. THIS APPROACH CONSIDERS THE PROBLEM SOLVING PROCESS AS OCCURING …

    greece Repository record for ΔΙΑΣΠΑΣΗ ΕΡΓΑΣΙΩΝ ΣΕ ΣΥΣΤΗΜΑΤΑ ΚΑΤΑΝΕΜΗΜΕΝΗΣ ΕΠΙΛΥΣΗΣ ΠΡΟΒΛΗΜΑΤΟΣ (opens in a new tab)