Distributed application execution in fog computing: A taxonomy, challenges and future directions

Ashraf, Maria; Shiraz, Mumhammad; Abbasi, Almas; Albahli, Saleh

doi:10.1016/j.jksuci.2022.05.002

Cited by 9 publications

(9 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The variability in recognition performance can be attributed to biases in the training data and the labeling methodologies used [12]. In prior research that attempted to generate datasets with emotion labels using ChatGPT, Koptyra et al [3] reported variability in the number of generated labels.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Interactive Task Encoding System for Learning-from-Observation

Wake¹,

Kanehira²,

Sasabuchi³

et al. 2023

2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

View full text Add to dashboard Cite

This technical report explores the ability of Chat-GPT in recognizing emotions from text, which can be the basis of various applications like interactive chatbots, data annotation, and mental health analysis. While prior research has shown ChatGPT's basic ability in sentiment analysis, its performance in more nuanced emotion recognition is not yet explored. Here, we conducted experiments to evaluate its performance of emotion recognition across different datasets and emotion labels. Our findings indicate a reasonable level of reproducibility in its performance, with noticeable improvement through fine-tuning. However, the performance varies with different emotion labels and datasets, highlighting an inherent instability and possible bias. The choice of dataset and emotion labels significantly impacts ChatGPT's emotion recognition performance. This paper sheds light on the importance of dataset and label selection, and the potential of fine-tuning in enhancing ChatGPT's emotion recognition capabilities, providing a groundwork for better integration of emotion analysis in applications using ChatGPT.

show abstract

Section: Discussionmentioning

confidence: 99%

“…However, one of the caveats associated with LLMs is their tendency to exhibit biases in the generated outputs. These biases often have roots in the non-uniformity of their training data and the labeling methodologies employed [12]. Consequently, it is likely that potential biases manifest in the nuances of emotional recognition.…”

Section: Introductionmentioning

confidence: 99%

Interactive Task Encoding System for Learning-from-Observation

Wake¹,

Kanehira²,

Sasabuchi³

et al. 2023

2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

View full text Add to dashboard Cite

show abstract

“…Transformer architecture was developed to help reduce limitations of earlier sequence‐to‐sequence models for natural language processing (e.g., recurrent neural networks) and uses a stack of 13 transformer blocks: each block has 12 attention heads with 768 hidden units (Ray 2023, pp. 212, 124; Sohail et al, 2023, p. 3). The tokenizer ‘divides raw text into smaller units called tokens for easier processing’.…”

Section: Introductionmentioning

confidence: 98%

“…ChatGPT has emerged from the subfield of natural language processing (NLP), a mix of computer science, linguistics, and, increasingly, AI. Developed by the San Francisco‐based OpenAI company, the chatbot is a large language model (LLM) engineered for text generation, language translation, text summarization, and data analysis (Sohail et al, 2023, pp. 2–3, 11, table 2).…”

Section: Introductionmentioning

confidence: 99%

“…The tokenizer ‘divides raw text into smaller units called tokens for easier processing’. (Sohail et al, 2023, p. 3) A sequence of embedded tokens is inputted into the model where they are supplied to the transformer blocks, hidden representations are produced, and are decoded into an output sequence (Ray 2023, pp. 124–125, figure 3, workflow chart).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating ChatGPT as a viable research tool for typological investigations of cultural heritage artefacts—Roman clay oil lamps

Lapp,

Lapp

2024

Archaeometry

View full text Add to dashboard Cite

This study evaluates the current viability of ChatGPT as a research tool in lychnology, a discipline of archaeology focusing on the study of light use and lamps in antiquity. Prompts applicable to a common cultural heritage artifact group—the Roman clay oil lamp—were entered in ChatGPT to test its capabilities in compiling, categorizing, describing, and identifying lamp types, and to assess how accurate, detailed, and knowledgeable its responses would be.

show abstract

Fog Computing Complete Review: Concepts, Trends, Architectures, Technologies, Simulators, Security Issues, Applications, and Open Research Fields

Ahammad

2023

SN COMPUT. SCI.

View full text Add to dashboard Cite

Distributed application execution in fog computing: A taxonomy, challenges and future directions

Cited by 9 publications

References 79 publications

Interactive Task Encoding System for Learning-from-Observation

Interactive Task Encoding System for Learning-from-Observation

Evaluating ChatGPT as a viable research tool for typological investigations of cultural heritage artefacts—Roman clay oil lamps

Fog Computing Complete Review: Concepts, Trends, Architectures, Technologies, Simulators, Security Issues, Applications, and Open Research Fields

Contact Info

Product

Resources

About