Advances and Challenges in Automated Drowning Detection and Prevention Systems
Abstract
:1. Introduction
- Categorization of existing approaches into two main groups; detection-based systems that focus solely on detecting drowning incidents to notify parents or lifeguards to perform manual rescue, and detection and prevention systems that integrate both detection and automated rescue mechanisms;
- Classification of detection methods into Computer Vision (CV)-based approaches that involve the use of overhead or underwater cameras and machine learning algorithms to analyze visual data for DD, and sensor-based approaches that rely on wearable sensors to monitor the swimmer’s physical parameters like heart rate, oxygen levels, and motion to detect potential drowning;
- Highlighting the limited research on automatic rescue systems, as most current approaches focus on detection but lack integrated rescue functionalities, which remain a key area for future development;
- Identifying key technical challenges in DD and DP systems;
- Exploring future research areas and opportunities to enhance DD and DP systems.
2. Search Methodology
2.1. Search Criteria
2.2. Inclusion and Exclusion Criteria
2.3. Results
3. Analysis of Existing Drowning Detection and Prevention Approaches
3.1. Drowning Detection Approaches
3.1.1. CV-Based Drowning Detection Approaches
- A.
- Body Parts Coordinates and DL
- B.
- IoT and Transfer Learning
- C.
- CV-ResNet
- D.
- Improved YOLOv5
- E.
- AquaYOLO
3.1.2. Sensor-Based Drowning Detection Approaches
- A.
- Multi-Sensor Device
- B.
- Heart Rate Pressure
- C.
- Ultrasonic Drowning Recognition System
- D.
- Swimmers Goggles
- E.
- Yarn-Based Strain Sensor
- F.
- Wrist Band
3.2. Drowning Detection and Prevention Approaches
- A.
- Gravity Force Elevator
- B.
- Gantry Robot
- C.
- AuFloat
- D.
- Cameras and Robotic Arm
- E.
- Sensors and Diaphragm Pump
4. Technical Challenges and Open Issues
5. Conclusions and Future Directions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- WHO. Drowning; WHO: Geneva, Switzerland, 2023. [Google Scholar]
- WHO. Global Report on Drowning: Preventing a Leading Killer; World Heath Organization: Geneva, Switzerland, 2014. [Google Scholar]
- PAHO. World Drowning Prevention Day; Pan American Health Organization: Washington, DC, USA, 2023. [Google Scholar]
- Mohtasham-Amiri, Z. Traumatic injuries in drowning. J. Inj. Violence Res. 2022, 14, 6. [Google Scholar]
- Zaara, M.; Belhaj, A.; Naceur, Y.; Makni, C.; Gharbaoui, M.; Bellali, M.; Zhioua, M.; Allouche, M. Patterns of unintentional fatal drowning among children in North Tunisia: A 10-year study. Rev. D’épidémiol. Santé Publique 2022, 70, 31–37. [Google Scholar] [CrossRef] [PubMed]
- Crawford, G.; D’Orazio, N.; Gray, C.; Royce, B.; Maher, T.; Della Bona, M.; Leavy, J.E. Public health interventions to prevent children drowning: An updated systematic review. J. Public Health 2024, 1–22. [Google Scholar] [CrossRef]
- Ali, I.; Peden, A.E. The burden, risk factors and prevention strategies for drowning in Türkiye: A systematic literature review. BMC Public Health 2024, 24, 528. [Google Scholar]
- Jalalifar, S.; Belford, A.; Erfani, E.; Razmjou, A.; Abbassi, R.; Mohseni-Dargah, M.; Asadnia, M. Enhancing water safety: Exploring recent technological approaches for drowning detection. Sensors 2024, 24, 331. [Google Scholar] [CrossRef]
- Alharbi, N. Exploring advance approaches for drowning detection: A review. Eng. Technol. Appl. Sci. Res. 2024, 14, 16032–16039. [Google Scholar] [CrossRef]
- Kao, W.-C.; Fan, Y.-L.; Hsu, F.-R.; Shen, C.-Y.; Liao, L.-D. Next-Generation Swimming Pool Drowning Prevention Strategy Integrating AI and IoT Technologies. Heliyon 2024, 10, e35484. [Google Scholar] [CrossRef]
- Du, S.; Chen, S. Salient object detection via random forest. IEEE Signal Process. Lett. 2013, 21, 51–54. [Google Scholar] [CrossRef]
- Avola, D.; Cinque, L.; Foresti, G.L.; Mercuri, C.; Pannone, D. A practical framework for the development of augmented reality applications by using ArUco markers. In Proceedings of the International Conference on Pattern Recognition Applications and Methods, Rome, Italy, 24–26 February 2016. [Google Scholar]
- Avola, D.; Foresti, G.L.; Cinque, L.; Massaroni, C.; Vitale, G.; Lombardi, L. A multipurpose autonomous robot for target recognition in unknown environments. In Proceedings of the IEEE 14th International Conference on Industrial Informatics (INDIN), Poitiers, France, 18–20 July 2016. [Google Scholar]
- Cao, X.; Yang, L.; Guo, X. Total variation regularized RPCA for irregularly moving object detection under dynamic background. IEEE Trans. Cybern. 2015, 46, 1014–1027. [Google Scholar] [CrossRef]
- Avola, D.; Cinque, L.; Foresti, G.L.; Marini, M.R.; Pannone, D. A Rover-based System for Searching Encrypted Targets in Unknown Environments. In Proceedings of the International Conference on Pattern Recognition Applications and Methods, Funchal, Portugal, 16–18 January 2018; pp. 254–261. [Google Scholar]
- Lei, S.; Zhang, B.; Wang, Y.; Dong, B.; Li, X.; Xiao, F. Object recognition using non-negative matrix factorization with sparseness constraint and neural network. Information 2019, 10, 37. [Google Scholar] [CrossRef]
- Bakheet, S.; Al-Hamadi, A. A discriminative framework for action recognition using f-HOL Features. Information 2016, 7, 68. [Google Scholar] [CrossRef]
- Avola, D.; Bernardi, M.; Foresti, G.L. Fusing depth and colour information for human action recognition. Multimed. Tools Appl. 2019, 78, 5919–5939. [Google Scholar] [CrossRef]
- Tu, Z.; Li, H.; Zhang, D.; Dauwels, J.; Li, B.; Yuan, J. Action-stage emphasized spatiotemporal VLAD for video action recognition. IEEE Trans. Image Process. 2019, 28, 2799–2812. [Google Scholar] [CrossRef] [PubMed]
- Avola, D.; Cascio, M.; Cinque, L.; Foresti, G.L.; Massaroni, C.; Rodolà, E. 2-D skeleton-based action recognition via two-branch stacked LSTM-RNNs. IEEE Trans. Multimed. 2019, 22, 2481–2496. [Google Scholar] [CrossRef]
- Song, W. A new method for refined recognition for heart disease diagnosis based on deep learning. Information 2020, 11, 556. [Google Scholar] [CrossRef]
- Avola, D.; Cinque, L.; Fagioli, A.; Foresti, G.; Mecca, A. Ultrasound medical imaging techniques: A survey. ACM Comput. Surv. (CSUR) 2021, 54, 1–38. [Google Scholar] [CrossRef]
- Yu, B.; Zhou, L.; Wang, L.; Yang, W.; Yang, M.; Bourgeat, P.; Fripp, J. SA-LuT-Nets: Learning sample-adaptive intensity lookup tables for brain tumor segmentation. IEEE Trans. Med. Imaging 2021, 40, 1417–1427. [Google Scholar] [CrossRef]
- Avola, D.; Cinque, L.; Fagioli, A.; Filetti, S.; Grani, G.; Rodolà, E. Multimodal feature fusion and knowledge-driven learning via experts consult for thyroid nodule classification. IEEE Trans. Circuits Syst. Video Technol. 2021, 32, 2527–2534. [Google Scholar] [CrossRef]
- Avola, D.; Cinque, L.; Fagioli, A.; Foresti, G.L.; Massaroni, C. Deep temporal analysis for non-acted body affect recognition. IEEE Trans. Affect. Comput. 2020, 13, 1366–1377. [Google Scholar] [CrossRef]
- Avola, D.; Cascio, M.; Cinque, L.; Fagioli, A.; Foresti, G.L. LieToMe: An ensemble approach for deception detection from facial cues. Int. J. Neural Syst. 2021, 31, 2050068. [Google Scholar] [CrossRef]
- Khan, W.; Crockett, K.; O’Shea, J.; Hussain, A.; Khan, B.M. Deception in the eyes of deceiver: A computer vision and machine learning based automated deception detection. Expert Syst. Appl. 2021, 169, 114341. [Google Scholar] [CrossRef]
- Faisal, T.; Negassi, I.; Goitom, G.; Yassin, M.; Bashir, A.; Awawdeh, M. Systematic development of real-time driver drowsiness detection system using deep learning. IAES Int. J. Artif. Intell. 2022, 11, 148. [Google Scholar] [CrossRef]
- Shatnawi, M.; Albreiki, F.; Alkhoori, A.; Alhebshi, M. Deep Learning and Vision-Based Early Drowning Detection. Information 2023, 14, 52. [Google Scholar] [CrossRef]
- Ko, B.C. A brief review of facial emotion recognition based on visual information. Sensors 2018, 18, 401. [Google Scholar] [CrossRef]
- Alhadhrami, N.; Abobakr, A.; Alhammadi, A.; Shatnawi, M. Multiple Classification of Date Fruit using Transfer Learning. In Proceedings of the 2023 Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates, 20–23 February 2023. [Google Scholar]
- Alhanaee, K.; Alhammadi, M.; Almenhali, N.; Shatnawi, M. Face recognition smart attendance system using deep transfer learning. Procedia Comput. Sci. 2021, 192, 4093–4102. [Google Scholar] [CrossRef]
- Shatnawi, M.; Almenhali, N.; Alhammadi, M.; Alhanaee, K. Deep learning approach for masked face identification. Int. J. Adv. Comput. Sci. Appl. 2022, 13, 296–305. [Google Scholar] [CrossRef]
- Khan, A.R. Facial Emotion Recognition Using Conventional Machine Learning and Deep Learning Methods: Current Achievements, Analysis and Remaining Challenges. Information 2022, 13, 268. [Google Scholar] [CrossRef]
- Siddique, M.F.; Ahmad, Z.; Kim, J.-M. Pipeline leak diagnosis based on leak-augmented scalograms and deep learning. Eng. Appl. Comput. Fluid Mech. 2023, 17, 2225577. [Google Scholar] [CrossRef]
- Siddique, M.F.; Ahmad, Z.; Ullah, N.; Ullah, S.; Kim, J.-M. Pipeline Leak Detection: A Comprehensive Deep Learning Model Using CWT Image Analysis and an Optimized DBN-GA-LSSVM Framework. Sensors 2024, 24, 4009. [Google Scholar] [CrossRef]
- Alzubaidi, L.; Zhang, J.; Humaidi, A.; Al-Dujaili, A.; Duan, Y.; Al-Shamma, O.; Santamaría, J.; Fadhel, M.; Al-Amidie, M.; Farhan, L. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J. Big Data 2021, 8, 53. [Google Scholar] [CrossRef]
- Jiao, J.; Zhao, M.; Lin, J.; Liang, K. A comprehensive review on convolutional neural network in machine fault diagnosis. Neurocomputing 2020, 417, 36–63. [Google Scholar] [CrossRef]
- Fok, W.W.T. Artificial Intelligence for Drowning Detection and Swimmer Performance Analysis System; KE Newsletter: Hong Kong, China, 2020. [Google Scholar]
- Alotaibi, A. Automated and Intelligent System for Monitoring Swimming Pool Safety Based on the IoT and Transfer Learning. Electronics 2020, 9, 2082. [Google Scholar] [CrossRef]
- Yang, R.; Wang, K.; Yang, L. An Improved YOLOv5 Algorithm for Drowning Detection in the Indoor Swimming Pool. Appl. Sci. 2024, 14, 200. [Google Scholar] [CrossRef]
- Xue, W.; Zhang, Y. Marine drowning detection method based on improved YOLOv5. In Proceedings of the 4th International Conference on Internet of Things and Smart City (IoTSC 2024), Edinburgh, UK, 16–19 September 2024. [Google Scholar]
- Formica, D.; Schena, E. Smart Sensors for Healthcare and Medical Applications. Sensors 2021, 21, 543. [Google Scholar] [CrossRef] [PubMed]
- Zheng, W.; Yang, Y.; Liu, C.; Zhou, W. Recent Advancements in Sensor Technologies for Healthcare and Biomedical Applications. Sensors 2023, 23, 3218. [Google Scholar] [CrossRef]
- Jalalifar, S.; Kashizadeh, A.; Mahmood, I.; Belford, A.; Drake, N.; Razmjou, A.; Asadnia, M. A Smart Multi-Sensor Device to Detect Distress in Swimmers. Sensors 2022, 22, 1059. [Google Scholar] [CrossRef]
- John, S.N.; Ukpabio, I.G.; Omoruyi, O.; Onyiagha, G.; Noma-Osaghae, E.; Okokpujie, K.O. Design of a drowning rescue alert system. Int. J. Mech. Eng. Technol. 2019, 10, 1987–1995. [Google Scholar]
- Liu, H.; Frej, M.B.H.; Wen, B. A Novel Method for Recognition, Localization, and Alarming to Prevent Swimmers from Drowning. In Proceedings of the 2019 IEEE Cloud Summit, Washington, DC, USA, 8–10 August 2019. [Google Scholar]
- Roy, A.; Srinivasan, K. A novel drowning detection method for safety of swimmers. In Proceedings of the 2018 20th National Power Systems Conference (NPSC), Tiruchirappalli, India, 14–16 December 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 1–6. [Google Scholar]
- Lu, D.; Wang, Q.; Zhang, X.; Liao, S.; Cai, Y.; Wei, Q. Highly durable yarn-based strain sensor with enhanced underwater monitoring capabilities and rapid drowning detection for safety applications. Chem. Eng. J. 2024, 498, 155485. [Google Scholar] [CrossRef]
- Ramani, J.G.; Gayathri, J.; Aswanth, R.; Gunasekaran, M. Automatic prevention of drowning by inflatable wrist band system. In Proceedings of the 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), Coimbatore, India, 15–16 March 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 346–349. [Google Scholar]
- Laxman, P.; Jain, A. Drown Alerting, Preventing And Autonomous Rescue System using Ardiuno, Tacticle switche (weight sensors) and Artificial Intelligence. Int. J. Adv. Trends Comput. Sci. Eng. 2021, 10, 762–766. [Google Scholar]
- Jose, A.; Udupa, G. Gantry robot system for preventing drowning accidents in swimming pools. Mater. Today Proc. 2021, 46, 4975–4981. [Google Scholar] [CrossRef]
- Ilham, A.; Della, S.P.; Buana, B.M.; Syai’in, M.; Munadhif, I.; Endrasmono, J.; Jami’in, M.A.; Subiyanto, L.; Soelistijono, R.T.; Wahidin, A.; et al. AuFloat (Autonomous Float) Based-on Artificial Inteligent and LORA (Long Range) Using Haar Cascade Method for Rescuing of Water Accident Victims. In Proceedings of the 2019 International Symposium on Electronics and Smart Devices (ISESD), Badung, Indonesia, 8–9 October 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 1–4. [Google Scholar]
- MHayat, A.; Yang, G.; Iqbal, A.; Saleem, A.; Mateen, M. Comprehensive and comparative study of drowning person detection and rescue systems. In Proceedings of the 2019 8th International Conference on Information and Communication Technologies (ICICT), Karachi, Pakistan, 16–17 November 2019. [Google Scholar]
- Ghute, M.; Katole, T.; Hadge, A.; Walke, A.; Gabhane, G. Design of Drowning Rescue Alert System. In Proceedings of the 2024 8th International Conference on Inventive Systems and Control (ICISC), Coimbatore, India, 29–30 July 2024. [Google Scholar]
- Shatnawi, M.; Zaki, N. Prediction of inter-domain linker regions in protein sequences: A survey. In Proceedings of the 2013 9th International Conference on Innovations in Information Technology (IIT), Al Ain, United Arab Emirates, 17–19 March 2013. [Google Scholar]
- Shatnawi, M.; Alhanaee, K.; Alhammadi, M.; Almenhali, N. Advancements in Machine Learning-Based Face Mask Detection: A Review of Methods and Challenges. Int. J. Electr. Electron. Res. 2023, 11, 844–850. [Google Scholar] [CrossRef]
- Peden, A.E.; Scarr, J.; Doan Minh, T.; Latif, R.; Le Thi Anh, D.; Chong, T.L.; Fong, D.; Mei, G.C.; Suvanprakorn, A.; Suwanrit, S.; et al. Drowning prevention challenges and opportunities: An exploratory study of perspectives of delegates from ASEAN nations. PLoS ONE 2024, 19, e0304138. [Google Scholar] [CrossRef] [PubMed]
- Shatnawi, M.; Zaki, N.; Yoo, P.D. Protein inter-domain linker prediction using Random Forest and amino acid physiochemical properties. BMC Bioinform. 2014, 15, S8. [Google Scholar] [CrossRef] [PubMed]
- Shatnawi, M. Novel Tree-Based Proximity Search with SMOTE and Compositional Indexing Techniques for Protein Domain Identification. In Proceedings of the 2016 27th International Workshop on Database and Expert Systems Applications (DEXA), Porto, Portugal, 5–8 September 2016. [Google Scholar]
- Cosoli, G.; Antognoli, L.; Veroli, V.; Scalise, L. Accuracy and Precision of Wearable Devices for Real-Time Monitoring of Swimming Athletes. Sensors 2022, 22, 4726. [Google Scholar] [CrossRef]
- Alessandri, A.; Awawdeh, M. Moving-horizon estimation with guaranteed robustness for discrete-time linear systems and measurements subject to outliers. Automatica 2016, 67, 85–93. [Google Scholar] [CrossRef]
- Awawdeh, M.J.; Faisal, T.; Bashir, A.; Alshbatat, A.I.N.; Momani, R.T. Moving-horizon estimation approach for nonlinear systems with measurement contaminated by outliers. Telecommun. Comput. Electron. Control. 2024, 22, 219–231. [Google Scholar] [CrossRef]
- Awawdeh, M.; Ibrahim, T.F.; Bashir, A.; Queen, F.M. Study of positioning estimation with user position affected by outlier: A case study of moving-horizon estimation filter. Telecommun. Comput. Electron. Control. 2022, 20, 426–436. [Google Scholar] [CrossRef]
- Awan, K.M.; Shah, P.A.; Iqbal, K.; Gillani, S.; Ahmad, W.; Nam, Y. Underwater wireless sensor networks: A review of recent issues and challenges. Wirel. Commun. Mob. Comput. 2019, 2019, 6470359. [Google Scholar] [CrossRef]
- Khan, Z.U.; Gang, Q.; Muhammad, A.; Muzzammil, M.; Khan, S.U.; Affendi, M.E.; Ali, G.; Ullah, I.; Khan, J. A comprehensive survey of energy-efficient MAC and routing protocols for underwater wireless sensor networks. Electronics 2022, 11, 3015. [Google Scholar] [CrossRef]
- Fattah, S.; Gani, A.; Ahmedy, I.; Idris, M.Y.I.; Hashem, I.A.T. A survey on underwater wireless sensor networks: Requirements, taxonomy, recent advances, and open research challenges. Sensors 2020, 20, 5393. [Google Scholar] [CrossRef]
- Aman, M.; Gang, Q.; Shang, Z.; Khan, Z.U.; Khan, M.S.; Ullah, I. Realization of RSSI Based, Three Major Components (Hx, Hy, Hz) of Magnetic Flux Created around the MI-TD Coil. In Proceedings of the 2023 IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE), Changchun, China, 29–31 December 2023. [Google Scholar]
- Khan, S.U.; Khan, Z.U.; Alkhowaiter, M.; Khan, J.; Ullah, S. Energy-efficient routing protocols for UWSNs: A comprehensive review of taxonomy, challenges, opportunities, future research directions, and machine learning perspectives. J. King Saud Univ.-Comput. Inf. Sci. 2024, 36, 102128. [Google Scholar]
- Gang, Q.; Muhammad, A.; Khan, Z.U.; Khan, M.S.; Ahmed, F.; Ahmad, J. Machine learning-based prediction of node localization accuracy in IIoT-based MI-UWSNs and design of a TD coil for omnidirectional communication. Sustainability 2022, 14, 9683. [Google Scholar] [CrossRef]
- Star, K. Physical Symptoms of Panic Disorder and Anxiety. 2023. Available online: https://www.verywellmind.com/physical-symptoms-of-panic-and-anxiety-2584248 (accessed on 15 June 2024).
- Talukder, M.A.; Islam, M.M.; Uddin, M.A.; Hasan, K.F.; Sharmin, S.; Alyami, S.A.; Moni, M.A. Machine learning-based network intrusion detection for big and imbalanced data using oversampling, stacking feature embedding and feature extraction. J. Big Data 2024, 11, 33. [Google Scholar] [CrossRef]
- Araf, I.; Idri, A.; Chairi, I. Cost-sensitive learning for imbalanced medical data: A review. Artif. Intell. Rev. 2024, 574, 80. [Google Scholar] [CrossRef]
- Aish, M.A.; Ghafoor, A.A.; Nasim, F.; Ali, K.I.; Akhter, S.; Azeem, S. Improving Stroke Prediction Accuracy through Machine Learning and Synthetic Minority Over-sampling. J. Comput. Biomed. Inform. 2024, 7, 2. [Google Scholar]
- Hossain, M.S.; Hossain, M.S.; Klüttermann, S.; Müller, E. Evaluating Anomaly Detection Algorithms: A Multi-Metric Analysis Across Variable Class Imbalances. In Proceedings of the 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan, 30 June–5 July 2024. [Google Scholar]
- Zakariah, M.; AlQahtani, S.A.; Al-Rakhami, M.S. Machine learning-based adaptive synthetic sampling technique for intrusion detection. Appl. Sci. 2023, 13, 6504. [Google Scholar] [CrossRef]
- Fayaz, S.; Ahmad Shah, S.Z.; Uddin, N.M.; Gul, N.; Assad, A. Advancements in Data Augmentation and Transfer Learning: A Comprehensive Survey to Address Data Scarcity Challenges. Recent Adv. Comput. Sci. Commun. 2024, 17, 14–35. [Google Scholar] [CrossRef]
- Alobeidli, K.; Shatnawi, M.; Almansoori, B. Image Classification for Toxic and Non-Toxic Plants in UAE. In Proceedings of the 2023 Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates, 20–23 February 2023. [Google Scholar]
- Kumar, T.; Brennan, R.; Mileo, A.; Bendechache, M. Image data augmentation approaches: A comprehensive survey and future directions. IEEE Access 2024. [Google Scholar] [CrossRef]
- Cheung, T.-H.; Yeung, D.-Y. A survey of automated data augmentation for image classification: Learning to compose, mix, and generate. IEEE Trans. Neural Netw. Learn. Syst. 2024, 35, 13185–13205. [Google Scholar] [CrossRef]
Reference | Key Contribution | Scope | Limitations |
---|---|---|---|
[6] | Public health-focused drowning prevention strategies for children. | Policy, education, and community-based prevention. | Lacks technological coverage. |
[7] | Regional drowning prevention strategies, focusing on Turkey. | Public health interventions in Turkey. | Limited to one country, lacks technological insights. |
[8] | Overview of image processing and sensor-based DD methods. | Sensor-based and image-based technologies. | Focuses on technology, but lacks integration with automated rescue systems. |
[9] | Review of ML and DL algorithms for DD. | Machine Learning and Deep Learning applications. | Limited discussion on real-world implementation and rescue system integration. |
[10] | AI, IoT, and embedded systems for DD in enclosed environments. | Technology for enclosed environments (e.g., pools). | Limited focus on open water bodies or outdoor swimming environments. |
Approach | System Description | Tools Used | Advantages | Limitations |
---|---|---|---|---|
Body Parts Coordinates and DL [39] | In total, 16 underwater cameras are used to capture key body parts during swimming, which are fed into a deep learning system for DD. | -Cameras. -DL system. -Arduino alarm. | -Can identify key body parts and movements specific to drowning. | -Many cameras are used to cover the whole pool which increases the total cost. -Not a full replacement for human lifeguards. |
IoT and Transfer Learning [40] | Combines IoT, deep learning, and motion sensors. Images are captured upon motion detection and classified using deep learning. The system sends alerts through a mobile application. | -Cameras. -IoT network. -Wi-Fi. -Raspberry Pi 3. -TensorFlow. -Keras. | -High classification accuracy of 99%. -IoT-based for real-time alerts. -Low complexity. | -Uses mobile alerts that may be unnoticeable. -Reliant on Wi-Fi, which can disconnect. |
CV-ResNet [29] | Uses 5 CNN models to analyze drowning and non-drowning behaviors from internet-sourced images. | -ResNet50. -SqueezeNet. -GoogleNet. -AlexNet. -ShuffleNet. | -Achieves 100% accuracy in validation and testing. -Adaptable to different swimming pool environments like schools and gyms. | -Limited dataset. -Not integrated to rescue mechanism. |
Improved YOLOv5 [41] | Custom dataset of 8572 images created using drones to simulate drowning in swimming pools. Enhanced YOLOv5 with ICA and BiFPN modules to improve detection. | -YOLOv5. -ICA. -BiFPN. | -High accuracy rate. -Efficient in water behavior analysis. | -Limited dataset. -Drone-related challenges (battery, regulations). -Not fully tested in real-world environments. |
AquaYOLO [42] | Enhanced YOLOv5 for open water DD, using video footage from drones. | -YOLOv5. -Drones. | -Adapted to complex open water environments. -Handles diverse weather and lighting scenarios. | -High false positives due to water variability (lighting, reflections). -Difficult to generalize across all marine settings. |
Approach | System Description | Tools Used | Advantages | Limitations |
---|---|---|---|---|
Multi-Sensor Device [45] | Waterproof wearable system with heart rate, oxygen saturation, water depth/pressure, and acceleration sensors. Alerts when thresholds are exceeded. | -Microcontroller. -Wi-Fi. -Multiple sensors. -Alert. | -Can detect a wide range of drowning scenarios. -Continuous monitoring. | -Requires continuous Wi-Fi connection. |
Heart Rate Pressure [46] | Wristband that tracks heart rate and pressure and alerts lifeguards when the heart rate exceeds preset limits. Uses an RF module for alerts. | -Heart rate sensor. -Microcontroller. -RF module. | -Directly alerts lifeguards. -Constant heart rate monitoring. | -Relies solely on heart rate. -Does not guarantee rescue if the lifeguard misses the alert. |
Ultrasonic Drowning System [47] | Uses ultrasonic transmitters/receivers to track swimmer depth and location, alerting based on movement analysis. | -Ultrasonic sensors. -Hydraulic pressure detectors. -Wireless transmitter/receiver. -Alarm. | -Cost-effective. -Energy-efficient. -3D location detection. | -Requires manual intervention by lifeguards. -May miss alarms in real-time. |
Swimmers Goggles [48] | Goggles with DD sensors that monitor irregular water motion around the swimmer, sending alerts to lifeguards. | -Googles. -Sensors. -Microcontroller. -Resistive circuit. | -Simple design. -Low-cost. -Unobtrusive for swimmers. | -Low efficiency. -Sensor placement is crucial. -Depends on lifeguard alertness. |
Yarn-Based Strain Sensor [49] | Strain sensor integrated into fabric, detecting underwater motion with high durability and fast response time. | -Yarn-based strain sensor. -PDMS layer. | -Durable. -Flexible. -Works well in aquatic environments. -Rapid response. | -Limited field testing. -Needs further investigation into turbulent waters or multi-user scenarios. |
Wrist Band [50] | Heartbeat sensor worn on the head or hand, alerts lifeguard with LED and buzzer when heart rate deviates from normal. | -Heartbeat sensor. -GSM. -LED. -Alarm. | -Cost-effective. -Expands with GSM to send alerts to lifeguard and family. -Inclusion of buzzer and light indication system. | Only effective if the lifeguard is nearby; depends on immediate response. |
Approach | System Description | Tools Used | Advantages | Limitations |
---|---|---|---|---|
Gravity Force Elevator [51] | AI-based system with a responsive elevator assembly that raises victims from the pool bottom using weight-detecting switches and mechanical jacks. | -Arduino. -Tactical switches. -Mechanical jacks. -Loudspeakers. -Drainage motor. | -Covers the entire pool. -Automatically raises the victim in emergencies. | -Requires heavy-duty structures and hard-wired logic. -Not tested in real-life pools. |
Gantry Robot [52] | Uses an overhead camera for DD and coordinates with a robot to throw a ring buoy to the victim and pull them to safety. | -Overhead camera. -Gantry robot with chains. -Load cell. -LED display and alarm. | -Automatic rescue. -No lifeguard needed. | -Not effective for children as it relies on the victim pulling themselves up with the buoy. |
AuFloat [53] | Autonomous floating buoy system, remotely operated via smartphone, equipped with GPS and a camera to assist in open-water rescues. | -GPS. -Camera. -Smartphone app. -Electrical pump. -Compass module. -Battery. | -Can be operated remotely up to 700 m. -Effective in low-light conditions. | -Limited detection range (up to 4 m) -Requires manual oversight. |
Cameras and Robotic Arm [54] | Pool surveillance system with multiple cameras and a robotic arm for rescue. Cameras track drowning movements and send data to the arm for rescue. | -Overhead cameras. -Cam-shift algorithm. -Kalman filter. -Robotic arm. -Motor and motor drive circuit. | -Covers the entire pool area with automated tracking and rescue. | -Expensive to scale for larger pools due to the need for more cameras. |
Sensors and Diaphragm Pump [55] | Wearable sensor system that monitors vital signs like heart rate and underwater movements, triggering a diaphragm pump to keep the swimmer afloat. | -SPO2 sensor. -Accelerometer. -Gyroscope. -Diaphragm pump. -Microcontroller. -RF module. | -Real-time monitoring of vital signs. -Automatic rescue initiation with location tracking. | -Relies on the swimmer wearing the device -Sensors may be less accurate in turbulent or chlorinated water. |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Shatnawi, M.; Albreiki, F.; Alkhoori, A.; Alhebshi, M.; Shatnawi, A. Advances and Challenges in Automated Drowning Detection and Prevention Systems. Information 2024, 15, 721. https://doi.org/10.3390/info15110721
Shatnawi M, Albreiki F, Alkhoori A, Alhebshi M, Shatnawi A. Advances and Challenges in Automated Drowning Detection and Prevention Systems. Information. 2024; 15(11):721. https://doi.org/10.3390/info15110721
Chicago/Turabian StyleShatnawi, Maad, Frdoos Albreiki, Ashwaq Alkhoori, Mariam Alhebshi, and Anas Shatnawi. 2024. "Advances and Challenges in Automated Drowning Detection and Prevention Systems" Information 15, no. 11: 721. https://doi.org/10.3390/info15110721
APA StyleShatnawi, M., Albreiki, F., Alkhoori, A., Alhebshi, M., & Shatnawi, A. (2024). Advances and Challenges in Automated Drowning Detection and Prevention Systems. Information, 15(11), 721. https://doi.org/10.3390/info15110721