AI-Based Workspace Safety Solutions

Harshita Nauhwar, Kriti Shrivastva, Varshith Sai Gali, Aishwarya Perukari

Literature Review:

In recent years, the domain of fall detection systems has experienced a surge in research activity, with
researchers worldwide engaging in diverse methodologies and innovations aimed at addressing the critical
challenge of fall detection. This section embarks on a journey through these studies, shedding light on their
contributions and illustrating the evolving landscape of fall detection technology.

A. Foundational Research and Wearable Technology

Our journey commences with foundational research conducted by Villaseñor and colleagues in
2019 [4]. They provided a significant resource in the form of a multimodal dataset, serving as the
cornerstone for subsequent studies. This dataset established a benchmark for evaluating the
effectiveness of various fall detection systems. Complementing this dataset, Trkov et al. (2015)
introduced a novel slip detection and prediction scheme employing wearable Inertial Measurement
Units (IMUs) and extended Kalman filters, emphasizing the pivotal role of wearable technology in
enhancing fall detection [6].

B. Vision-Based Approaches and Machine Learning

As we delve deeper into the research landscape, we encounter the work of Nooruddin et al. (2021),
who conducted a systematic review categorizing fall detection solutions into single and multiple
sensor-based systems [1]. Beddiar and colleagues (2021) take a prominent position with their
emphasis on video-based fall detection, leveraging machine learning and pose estimation
techniques for precise classification [2]. Inturi and co-authors (2022) introduce a vision-based
approach employing AlphaPose for key point detection, emphasizing its potential for in-home fall
detection [3]. Wu et al. (2023) present an innovative weakly supervised learning-based dual-modal
network, promising improved efficiency and accuracy in fall detection [5]. These studies
collectively reflect the persistent pursuit of enhanced detection algorithms and their potential for
real-world applications.

Transitioning to the second phase of our journey, we explore recent international contributions to the field
and broaden our perspective to encompass the broader implications of fall detection technology for safety
and health.

A. International Innovations in Machine Learning and Sensing

Phand and team (2023) have harnessed the capabilities of Convolutional Neural Networks (CNN)
for human fall detection through visual surveillance, illustrating the global adoption of advanced
machine learning techniques [7]. Liao et al. (2011) propose a method incorporating the Integrated
Spatiotemporal Energy (ISTE) map and Bayesian Belief Networks (BBN) for effective fall and slip
detection, emphasizing the importance of incorporating both spatial and temporal information in
detection algorithms [8]. Trkov and colleagues (2019) introduce an innovative inertial sensor-based
slip detection system for human walking, showcasing potential safety improvements [9]. Mobsite
et al. (2023) pioneer a camera-based system that respects privacy concerns by utilizing human
silhouettes, highlighting the importance of addressing ethical and privacy considerations in system
design [10].
 AI-Based Workspace Safety Solutions
Harshita Nauhwar, Kriti Shrivastva, Varshith Sai Gali, Aishwarya Perukari

B. Broader Safety and Health Implications

Our journey takes us to researchers who have developed an affordable motion-based method
utilizing pyroelectric infrared sensors (PIR) and Arduino technology for accurate fall detection
[11]. This work serves as a reminder of the necessity for cost-effective solutions that can be
deployed in resource-constrained settings. Shifting to a broader perspective on safety and health,
we explore the meta-analyses conducted by Burke et al. (2006) and Christian et al. (2009), which
emphasize the effectiveness of behavioral modeling, safety knowledge, and motivation in safety
performance [16,17]. These studies offer valuable insights into the human factors that complement
technological advancements in fall detection

C. Ethical Considerations and Future Outlook

Returning to the international stage, researchers employ artificial intelligence and computer vision
for accident rate reduction, addressing challenges posed by low lighting conditions. This work
extends the application of computer vision beyond fall detection, showcasing its potential for
broader safety improvements. Our journey culminates in a scoping review that underscores the
transformative potential of AI in occupational safety and health across high-risk industries. It also
acknowledges the surveillance concerns associated with certain AI applications, highlighting the
ethical considerations that must accompany technological advancements. In Europe, researchers
conduct a literature review and expert interviews, emphasizing the need for safe and transparent
Artificial Intelligence for Workplace Management (AIWM) systems to address occupational safety
and health risks. This perspective broadens our understanding of the role of AI in shaping the future
of workplace safety.

In conclusion, our journey through these research papers reveals a rich tapestry of innovation, collaboration,
and exploration. The field of fall detection systems is continuously evolving, with researchers from diverse
backgrounds contributing to its advancement. From wearable sensors to computer vision, from machine
learning to human factors, these studies collectively paint a picture of a field poised to make significant
strides in improving safety and health across the globe.
 AI-Based Workspace Safety Solutions
Harshita Nauhwar, Kriti Shrivastva, Varshith Sai Gali, Aishwarya Perukari

REFERENCES

[1] S. Nooruddin, Md. M. Islam, F. A. Sharna, H. Alhetari, and M. N. Kabir, “Sensor-based Fall Detection Systems:
A Review,” Journal of Ambient Intelligence and Humanized Computing, vol. 13, no. 5, pp. 2735–2751, 2021.
doi:10.1007/s12652-021-03248-z

[2]: Beddiar, Djamila Romaissa, et al. “Fall Detection Using Body Geometry and Human Pose Estimation in Video
Sequences.” Journal of Visual Communication and Image Representation, vol. 82, no. 10959076, Jan. 2022, p.
103407, https://doi.org/10.1016/j.jvcir.2021.103407.

[3]: A. R. Inturi, V. M. Manikandan, and V. Garrapally, “A novel vision-based fall detection scheme using keypoints
of human skeleton with long short-term Memory Network,” Arabian Journal for Science and Engineering, vol. 48, no.
2, pp. 1143–1155, Mar. 2022. doi:10.1007/s13369-022-06684-x

[4]: L. Martínez-Villaseñor, H. Ponce, J. Brieva, E. Moya-Albor, J. Núñez-Martínez, and C. Peñafort-Asturiano, "UP-

[5]: L. Wu et al., “Robust fall detection in video surveillance based on weakly supervised learning,” Neural Networks,
vol. 163, pp. 286–297, 2023. doi:10.1016/j.neunet.2023.03.042

[6] M. Trkov, K. Chen, J. Yi, and T. Liu, "Slip detection and prediction in human walking using only wearable
inertial measurement units (IMUs)," in 2015 IEEE International Conference on Advanced Intelligent Mechatronics
(AIM), Busan, Korea (South), 2015, pp. 854-859, doi: 10.1109/AIM.2015.7222645.

[7]: S. Phand, S. Pathare, S. Bhavsar, R. Andhare, and G. Bhandari, "Human Fall Detection using CNN Algorithm,"
in International Journal of Advanced Research in Science, Communication and Technology, 2023, pp. 125-129, doi:
10.48175/IJARSCT-7849.

[8]: Y. T. Liao, C. Huang, and S. Hsu, "Slip and fall event detection using Bayesian Belief Network," in Pattern
Recognition, vol. 45, no. 1, pp. 24-32, 2011, doi: 10.1016/j.patcog.2011.04.017.

[9]: M. Trkov, K. Chen, J. Yi, and T. Liu, "Inertial Sensor-Based Slip Detection in Human Walking," in IEEE
Transactions on Automation Science and Engineering, vol. 16, no. 3, pp. 1399-1411, July 2019, doi:
10.1109/TASE.2018.2884723.

[10]: S. Mobsite, N. Alaoui, M. Boulmalf, and M. Ghogho, “Semantic segmentation-based system for fall detection
and post-fall posture classification,” Engineering Applications of Artificial Intelligence, vol. 117, p. 105616, 2023.
doi:10.1016/j.engappai.2022.105616

[11] Ch. A. Hassan et al., “A cost-effective fall-detection framework for the elderly using sensor-based technologies,”
Sustainability, vol. 15, no. 5, p. 3982, Feb. 2023. doi:10.3390/su15053982

[12] J. C. E. Guerrero, E. M. España, M. M. Añasco, and J. E. P. Lopera, "Dataset for human fall recognition in an
uncontrolled environment," in Data in brief, vol. 45, pp. 108610, 2022, doi: https://doi.org/10.1016/j.dib.2022.108610

[13] S. Li, X. Song, S. Xu, H. Qi, and Y. Xue, "Dilated spatial–temporal convolutional auto-encoders for human fall
detection in surveillance videos," in ICT Express, 2022, DOI:10.1109/CVPR.2018.00678
 AI-Based Workspace Safety Solutions
Harshita Nauhwar, Kriti Shrivastva, Varshith Sai Gali, Aishwarya Perukari

[14] J. D. Cardenas, C. A. Gutierrez, and R. Aguilar-Ponce, “Deep Learning Multi-class approach for human fall
detection based on Doppler signatures,” International Journal of Environmental Research and Public Health, vol. 20,
no. 2, p. 1123, Jan. 2023. doi:10.3390/ijerph20021123

[15] A. Naser, A. Lotfi, M. D. Mwanje, and J. Zhong, “Privacy-preserving, thermal vision with human in the Loop
Fall Detection Alert System,” IEEE Transactions on Human-Machine Systems, vol. 53, no. 1, pp. 164–175, Feb. 2023.
doi:10.1109/thms.2022.3203021

[16] Burke, M. J., Sarpy, S. A., Smith-Crowe, K., Chan-Serafin, S., Salvador, R. O., & Islam, G. (2006). Relative
Effectiveness of Worker Safety and Health Training Methods. American Journal of Public Health, 96(2), 315-324.
https://doi.org/10.2105/AJPH.2004.059840

[17] Christian, M. S., Bradley, J. C., Wallace, J. C., & Burke, M. J. (2009). Workplace safety: A meta-analysis of
the roles of person and situation factors. Journal of Applied Psychology, 94(5), 1103–1127.
https://doi.org/10.1037/a0016172

[18] Amaan D. Attar , A. Rahim A. R. Gharade , Israr A. Khan , Owais A. Shekasan, 2022, Workplace Safety using
AI and ML, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume
11, Issue 01 (January 2022), DOI : 10.17577/IJERTV11IS010107

[19] Fisher E, Flynn MA, Pratap P, Vietas JA. Occupational Safety and Health Equity Impacts of Artificial
Intelligence: A Scoping Review. International Journal of Environmental Research and Public Health. 2023;
20(13):6221. https://doi.org/10.3390/ijerph20136221

[20] K. Reinhold, M. Järvis, A. Christenko, V. Jankauskaitė, A. Paliokaitė, and A. Riedmann, "Artificial intelligence
for worker management: implications for occupational safety and health," 2022, Europe, DOI: 10.2802/76354