Detta arbete undersöker integreringen av artificiell intelligens (AI) och maskininlärning (ML) teknologier i prediktivt underhåll (PdM) vid Glada Hudikhem. De primära målen är att utvärdera effektiviteten hos olika AI/ML-modeller för att förutsäga fel på hushållsapparater och att förbättra transparensen och tillförlitligheten i dessa förutsägelser ...
This thesis investigates the integration of sentiment analysis from both text and audio data of financial earnings calls, an innovative approach situated at the intersection of Natural Language Processing (NLP), Speech Emotion Recognition (SER), and financial analysis. The core problem addressed is the limited accuracy and depth of sentiment analys...
In Aquaculture, the feed accounts for a major portion of the environmental impact and overall costs. Recently, attempts to develop intelligent feeding systems using image data have shown promising results. This work investigates an approach to detect different levels of feeding intensity in land-based fish farms, using a Convolutional Neural Networ...
This thesis aims to address the concurrent challenges of multi-person 2D pose estimation and object detection within a unified bottom-up framework. Our foundational solutions encompass a recently proposed pose estimation framework named OpenPifPaf, grounded in composite fields. OpenPifPaf employs the Composite Intensity Field (CIF) for precise join...
This study aimed to address a workflow challenge in the business sector by applied deep learning, Artificial Intelligence (AI) and automation. It focused on the detection and extraction of tabular data found in Annual General Meeting (AGM) minutes; official records summarizing relevant information gathered during annual firm meetings. The findings ...
This study explores the scalability of state-of-the-art reinforcement learning for imperfect information games with respect to how the degree of hidden information impacts learning efficiency and computational demands. We reproduce the student of games general learning algorithm and evaluate its performance across three variants of a custom poker g...
Titel: Redovisningsstudenter & generativ AI Nivå: Examensarbete på grundnivå (kandidatexamen) i ämnet företagsekonomi. Författare: Jennifer Roos och Josefine Olsson Handledare: Jan Svanberg Datum: 2024 – maj Syfte: Undersöka hur redovisningsstudenter med olika inlärningsstrategier (ytinlärning och djupinlärning) använder generativ AI i sina studie...
Real-time prediction of taxi demand in a discrete geographical space is useful as it can minimise service disequilibrium by informing idle drivers of the imbalance, incentivising them to reduce it. This, in turn, can lead to improved efficiency, more stimulating work conditions, and a better customer experience. This study aims to investigate the p...
Under produktionen av plåtdetaljer är det vanligt att defekta komponenter förekommer. I dagens samhälle är det viktigare än någonsin att sträva efter effektiva processer som leder till ekonomiska, ekologiska och sociala förbättringar. Detta beror på nya bestämmelser och krav som ställs på företag i samband med utveckling och hållbarhet. Genom att f...
Automated electrocardiogram (ECG) analysis using deep neural networks has seen promising results in recent years in various fields such as arrhythmia diagnosis and mortality prediction through age proxies. However, these deep learning models are susceptible to small indistinguishable perturbations that change the model prediction. These models also...
