Browsing by Author "Shroff, Mickey"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Design and Implementation of a Profile-based Protocol for Remote Industrial Automation Control
    (2010) Shroff, Mickey; Tuominen, Pasi; Informaatio- ja luonnontieteiden tiedekunta; Perustieteiden korkeakoulu; School of Science; Aura, Tuomas
    In today's automation scene remote management is a hot topic. New business models are built around remote access. A protocol is needed which enables remote access over TCP/IP networks to the automation boundary in efficient manner. The main objective of this thesis is to design and implement a profile-based protocol for industrial automation remote control. The protocol should support transferring of field bus data and common data exchange mechanisms. In addition, the implementation must be easily extensible and platform dependent. This thesis also studies field buses and automation environments in general, as well as the levels of automation, starting from the bit and the device level and ending with the process and plant levels. Furthermore, Internet readiness of field buses is reviewed. Protocol security is also considered. Work objectives were successfully achieved. The protocol design and implementation produced expected results. Also the literature study was conducted successfully. The protocol could he developed further by opening its specification to the public for wider review. The protocol specification could be published first to the Internet community as Internet draft.
  • Thumbnail Image
    Item
    Utilization of local large language models for business applications
    (2024-03-11) Haaralahti, Elias; Shroff, Mickey; Perustieteiden korkeakoulu; Laaksonen, Jorma
    Large Language Models (LLMs) have gained popularity in various use cases due to their capabilities. Currently third party services are commonly used, but these solutions contain drawbacks, such as data privacy concerns. Due to this, the interest for local solutions has increased causing international companies to release their own models, which are comparable to closed solutions. This thesis explores how local large language models can be utilized for business applications. The goal of this thesis is to form a comprehensive view of the state of LLMs, including their capabilities and limitations by researching them from various sources. Additionally, experiments are conducted to analyze the inference requirements, assess the impact of quantization on them, evaluate the language capabilities of the models and determine their capability to follow instructions and generate coherent output. The experiments include applying Retrieval Augmented Generation (RAG) using internal company data and fine-tuning a model to improve language capabilities with limited computational resources. As a part of research, a customized method was created and is used to evaluate the effectiveness of retrieval augmented generation. This is done by automatically creating a question-answer dataset with over a thousand entries. The dataset can be used by an LLM to evaluate the factuality and relevance of the context or the model output. The result of the thesis is a comprehensive study of current LLMs, tools and methods, which can be applied as a foundation to build new products in the future. The results indicate that LLMs are suitable for many use cases, although they do have limitations.