Sökning: "Analytics system"

Visar resultat 1 - 5 av 155 uppsatser innehållade orden Analytics system.

1. 1. A type-driven approach for sensitivity checking with branching

   Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

   Författare :Daniel Freiermuth; [2023-10-24]
   Nyckelord :Computer; science; computer science; thesis; differential privacy; type system; sensitivity; branching;

   Sammanfattning : Differential Privacy (DP) is a promising approach to allow privacy preserving statistics over large datasets of sensitive data. It works by adding random noise to the result of the analytics. Understanding the sensitivity of a query is key to add the right amount of noise capable of protecting privacy of individuals in the dataset. LÄS MER

3. 2. Circular economy of spare parts and data-driven analytics - “Unlocking Sustainable Value: Analyzing Buyback Policy Circularity Performance in Volvo Group’s Reverse Supply Chain - A Renault Trucks Case Study”

   Master-uppsats, Göteborgs universitet/Graduate School

   Författare :Vladyslav Zahladko; [2023-07-20]
   Nyckelord :closed-loop supply chain; reverse logistics; buyback policy; circular economy; performance measurement; supply chain analytics;

   Sammanfattning : To address the current environmental challenges, companies are steadily shifting from a linear to a circular model in their daily operations. This process implies supplementing the traditional forward logistics with a reverse flow, enabling the reuse, remanufacturing, and recycling of existing products. LÄS MER

4. 3. MetaStackVis: Visually-Assisted Performance Evaluation of Metamodels in Stacking Ensemble Learning

   Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

   Författare :Ilya Ploshchik; [2023]
   Nyckelord :Visualization; interaction; metamodels; validation metrics; predicted probabilities; stacking; stacked generalization; ensemble learning; machine learning;

   Sammanfattning : Stacking, also known as stacked generalization, is a method of ensemble learning where multiple base models are trained on the same dataset, and their predictions are used as input for one or more metamodels in an extra layer. This technique can lead to improved performance compared to single layer ensembles, but often requires a time-consuming trial-and-error process. LÄS MER

5. 4. Wi-Fi fingerprinting as a mean to measure building occupancy : A case study in an office environment

   Master-uppsats, KTH/Transportplanering

   Författare :Johan Bexhorn; Karl Kvarnefalk; [2023]
   Nyckelord :Wi-Fi tracking systems; Wi-Fi fingerprinting; footfall analytics;

   Sammanfattning : The task of collecting visitor data in an indoor environment and therein determining the occupancy of a building is an extensive task. Conventional methods are expensive, time-consuming, and often lack the ability to produce data in longer time series. Further, they often require disruption of the studied area as equipment must be deployed. LÄS MER

7. 5. Vem eller vad kan hållas straffrättsligt ansvarig för ett självkörande fordon? : En analys av gällande rätt och föreslagen lagstiftning i Sverige

   Uppsats för yrkesexamina på avancerad nivå, Stockholms universitet/Juridiska institutionen

   Författare :Petri Dahlström; [2023]
   Nyckelord :Self-driving; autonomous; automated; automatic; AV; vehicles; cars; artificial intelligence; AI; machine learning; electronic person; criminal liability; Självkörande; autonoma; automatiserade; artificiell intelligens; AI; maskininlärning; elektronisk person; fordon; bilar; straffrättsligt ansvar; ansvarsbedömning;

   Sammanfattning : The last decade has seen a rapid advancement in the fields of artificial intelligence (AI) and automation, with terms such as machine learning, deep learning and algorithms finding their way into everyday conversations. The usage of AI is evergrowing and present in many areas of life such as health care, financial services, and social media interactions. LÄS MER