Biologically-inspired object recognition system for recognizing natural scene categories

Alameer, Ali; Degenaar, Patrick; Nazarpour, Kianoush

doi:10.1109/icsae.2016.7810174

Cited by 6 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All images were collected via the Internet from the SUN and Places 365 databases (Xiao et al, 2010; Zhou et al, 2014). All images were classified into one of 13 natural scene categories identified as important in previous studies: offices, kitchens, living rooms, bedrooms, industrial scenes, tall buildings, city scenes, streets, highways, coasts, open country, mountains, and forests (Oliva & Torralba, 2001; Lazebnik et al, 2006; Alameer et al, 2016).…”

Section: Methodsmentioning

confidence: 99%

Spatiotemporal cortical dynamics for rapid scene recognition as revealed by EEG decoding

Orima

Motoyoshi

2023

Preprint

View full text Add to dashboard Cite

The human visual system rapidly recognizes the categories and global properties of complex natural scenes. The present study investigated the spatiotemporal dynamics of neural signals involved in ultra-rapid scene recognition using electroencephalography (EEG) decoding. We recorded visual evoked potentials from 11 human observers for 232 natural scenes, each of which belonged to one of 13 natural scene categories (e.g., a bedroom or open country) and had three global properties (naturalness, openness, and roughness). We trained a deep convolutional classification model of the natural scene categories and global properties using EEGNet. Having confirmed that the model successfully classified natural scene categories and the three global properties, we applied Grad-CAM to the EEGNet model to visualize the EEG channels and time points that contributed to the classification. The analysis showed that EEG signals in the occipital lobes at short latencies (~88 ms) contributed to the classifications other than roughness, whereas those in the frontal lobes at relatively long latencies (~250 ms) contributed to the classification of naturalness and the individual scene category. These results suggest that different global properties are encoded in different cortical areas and with different timings, and that the encoding of scene categories shifts from the occipital to the frontal lobe over time.

show abstract

Section: Methodsmentioning

confidence: 99%

Spatiotemporal cortical dynamics for rapid scene recognition as revealed by EEG decoding

Orima

Motoyoshi

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, AI techniques may be prone to overgeneralization since deep learning models depend largely on training data. This causes the risk of overgeneralizing the patterns, further reinforcing the biases in the algorithmic biases [90]. For instance, if historical successful hires have been predominantly male, the model may favor male candidates in future predictions.…”

Section: Limitations Of Ai In Eliminating Biasmentioning

confidence: 99%

A Comprehensive Review of AI Techniques for Addressing Algorithmic Bias in Job Hiring

Albaroudi,

Mansouri,

Alameer

2024

Self Cite

View full text Add to dashboard Cite

The study comprehensively reviews artificial intelligence (AI) techniques for addressing algorithmic bias in job hiring. More businesses are using AI in curriculum vitae (CV) screening. While the move improves efficiency in the recruitment process, it is vulnerable to biases, which have adverse effects on organizations and the broader society. This research aims to analyze case studies on AI hiring to demonstrate both successful implementations and instances of bias. It also seeks to evaluate the impact of algorithmic bias and the strategies to mitigate it. The basic design of the study entails undertaking a systematic review of existing literature and research studies that focus on artificial intelligence techniques employed to mitigate bias in hiring. The results demonstrate that the correction of the vector space and data augmentation are effective natural language processing (NLP) and deep learning techniques for mitigating algorithmic bias in hiring. The findings underscore the potential of artificial intelligence techniques in promoting fairness and diversity in the hiring process with the application of artificial intelligence techniques. The study contributes to human resource practice by enhancing hiring algorithms’ fairness. It recommends the need for collaboration between machines and humans to enhance the fairness of the hiring process. The results can help AI developers make algorithmic changes needed to enhance fairness in AI-driven tools. This will enable the development of ethical hiring tools, contributing to fairness in society.

show abstract

“…We assumed these natural images were taken with the gamma of 2.0, and loaded with the gamma of 0.5. All images were classified into one of 13 natural scene categories identified as important in previous studies: offices, kitchens, living rooms, bedrooms, industrial scenes, tall buildings, city scenes, streets, highways, coasts, open country, mountains, and forests (Oliva and Torralba, 2001;Lazebnik et al, 2006;Alameer et al, 2016).…”

Section: Stimulimentioning

confidence: 99%

Spatiotemporal cortical dynamics for visual scene processing as revealed by EEG decoding

Orima,

Motoyoshi

2023

Front. Neurosci.

View full text Add to dashboard Cite

The human visual system rapidly recognizes the categories and global properties of complex natural scenes. The present study investigated the spatiotemporal dynamics of neural signals involved in visual scene processing using electroencephalography (EEG) decoding. We recorded visual evoked potentials from 11 human observers for 232 natural scenes, each of which belonged to one of 13 natural scene categories (e.g., a bedroom or open country) and had three global properties (naturalness, openness, and roughness). We trained a deep convolutional classification model of the natural scene categories and global properties using EEGNet. Having confirmed that the model successfully classified natural scene categories and the three global properties, we applied Grad-CAM to the EEGNet model to visualize the EEG channels and time points that contributed to the classification. The analysis showed that EEG signals in the occipital electrodes at short latencies (approximately 80 ~ ms) contributed to the classifications, whereas those in the frontal electrodes at relatively long latencies (200 ~ ms) contributed to the classification of naturalness and the individual scene category. These results suggest that different global properties are encoded in different cortical areas and with different timings, and that the combination of the EEGNet model and Grad-CAM can be a tool to investigate both temporal and spatial distribution of natural scene processing in the human brain.

show abstract

Biologically-inspired object recognition system for recognizing natural scene categories

Abstract: Newcastle University ePrints -eprint.ncl.ac.uk Alameer A, Degenaar P, Nazarpour K. Biologically-inspired object recognition system for recognizing natural scene categories.

Cited by 6 publications

References 24 publications

Spatiotemporal cortical dynamics for rapid scene recognition as revealed by EEG decoding

Spatiotemporal cortical dynamics for rapid scene recognition as revealed by EEG decoding

A Comprehensive Review of AI Techniques for Addressing Algorithmic Bias in Job Hiring

Spatiotemporal cortical dynamics for visual scene processing as revealed by EEG decoding

Contact Info

Product

Resources

About