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 15 of 15 for “"Vector Search"”.
-
EFFICIENT LARGE-SCALE VECTOR SEARCH
Vector retrieval is foundational to a wide range of applications—including recommendation systems, data mining, and information retrieval—especially as the volume and complexity of data on the internet continue to grow. Addressing the challenges of constructing efficient, scalable, and robust …
-
IVF Singular Search: Agent-Based Implementation of Vector Search on GPU
Vector search plays a crucial role in large-scale similarity search applications, with IVF (Inverted File Index) being a widely used indexing method due to its balance between accuracy and efficiency. However, traditional vector search algorithms that used IVF as an indexing method, such as IVF …
-
Single and multi-frame video quality enhancement
… that uses temporal redundancy to improve motion-vector search by choosing bias vectors from the previous frame and adaptively penalizes deviations from the bias vectors. This increases the robustness of the motion-vector search. The spatial correlation is more reliable because temporal …
-
TeleRAG: Optimizing Retrieval for Retrieval-Augmented Generation
… a critical challenge: large language models and vector datastores compete for limited GPU memory, often forcing datastores to the CPU and leading to slow CPU-based retrieval latency. This thesis introduces TeleRAG, a system that resolves this bottleneck through lookahead retrieval, a technique …
-
H.263 Based Facial Image Compression For Low Bit Rate Communications
… can improve the encoding speed. Since the motion vector search, DCT transform and bit rate control are the heart of the H.263 video encoding, the method presented in this thesis focuses on each of the encoding components to improve the computational efficiency. After applying proposed methods of …
-
Cohesive Autonomous Navigation System: Image Processing and Data Management
… monitoring systems, natural disaster search and rescue robots, civil construction monitoring systems, robotic satellite servicing, and many more. An architecture that is conducive to Simultaneous Localization and Mapping (SLAM), path planning, and mission planning is a critical element …
-
NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance
… demand for extending existing DBMSs with vector indices to become unified systems that can support modern predictive applications, which require joint querying of vector embeddings and structured properties and connections of objects. We present NaviX, a Native vector indeX for graph DBMSs …
-
Flux-Based Dynamic Subspace Model Predictive Control of Dual-Three Phase Permanent Magnet Synchronous Motors
… field-programmable gate arrays (FPGA), many researchers are investigating whether finite-control set model predictive control (FCS-MPC) can be a suitable alternative. FCS-MPC is simple to implement and can achieve a better dynamic performance when compared to other controllers. Furthermore, the …
-
Numerical methods for discontinuous remote sensing coverage analysis
… coverage of Earth. Evolutionary algorithms can search the trade space intelligently but they require many simulation evaluations to approximate the typically multi-objective pareto front. We have developed an efficient semi-analytic routine, to compute the access events of Earth-based targets …
-
Retrieval-Augmented Generation for Sustainable Material Data Handling in Automotive Value Chain
… data, (2) retrieves relevant chunks via dense vector search, and (3) generates source-grounded responses. The work investigates whether a RAG model that explicitly integrates both domains can outperform a baseline tuned for unstructured text and explores which tabular serialization format …
-
Albebraic, geometric and complexity aspects of quantum search algorithms
Quantum search algorithm determines k marked items in an otherwise unstructured set (database), of size N by performing Order(SQRT(N/k)) trials. Hence a quadratic reduction of search complexity is achieved compared to Order(N/k) trials required by any classical algorithm. The quantum algorithm …
-
Near duplicate image search
… the information overload, the major challenge in search algorithm design is to ensure that useful information can be found both accurately and efficiently from large databases.To address this challenge, different indexing and retrieval methods had been proposed for different types of data, namely …
-
Near Memory Accelerators for Approximate Nearest Neighbor Search
Approximate Nearest Neighbor (ANN) search has become a critical component in modern retrieval systems, supporting applications such as recommendation engines, semantic search, and large language models. Despite the effectiveness of embedding-based methods, performing ANN search over billion-scale, …