Safety Systems Research Articles

Design of smoke detection system using deep learning and sensor fusion with recursive feature elimination cross-validation

The fire safety system is an important component that controls material and immaterial losses. Fire disasters are generally indicated by the appearance of excess smoke and changes in temperature, pressure, and changes in other parameters in the environment. Conventional smoke sensors are limited in reading parameter changes around their environment, making them less effective in early fire detection. This study aims to design a smoke detection system as an early fire detection system, using sensor fusion based on deep learning using the recursive feature elimination method with cross-validation (RFECV) using a random forest classifier used to select optimal parameters from public datasets as the basis for determining the sensor to be used. Based on the RFECV optimal feature, a deep learning algorithm was performed and obtained an accuracy of 0.99, a precision of 0.99, a recall of 1.00, and an F1 score of 0.99, with a latency time of 34.02 μs, which is 71.76% times faster than the original model.

Implementation of Smart 24x7 Women Security App W-SAFE

Abstract: Physical assaults and other forms of violence against women have increased in recent years. The increasing number of women working in industries and other commercial sectors has made it necessary for them to travel at odd hours and visit remote and isolating places as part of their jobs. Defence is not the sole tactic that can be sufficient to stop this growing misuse. It is necessary to come up with a security strategy that gives women a means of safety. As a result, a more straightforward safety solution is required, one that may be triggered by merely pressing a button and that can immediately notify the victim's loved ones. Therefore, the project's main focus is on a safety system that is made for women so that they never feel helpless while facing a security threat it is specifically designed to give women protection and safetyso they never feel powerless in the face of such social issues. A machine learning algorithm is used to enhance the responsiveness of an android application that records women's live whereabouts and includes voice activation, crowd space rating, emergency hotline numbers, and safe route suggestions. Giving users access to current information about locations where other people have expressed safety concerns is the goal. The program wouldautomatically sound a warning when approaching such regions in order to increase user awareness and encouragea proactive approach to personal safety

Advanced Helmet and License Plate Recognition: A Breakthrough in Safety and Surveillance Systems

Abstract: Helmet detection and license plate recognition have emerged as crucial components in ensuring safety and security in various domains, particularly in transportation and law enforcement. This review paper presents a comprehensive survey and analysis of methodologies, techniques, and advancements in the field of helmet detection and license plate recognition using computer vision and deep learning approaches. The paper investigates diverse datasets, algorithms, and architectures utilized for accurate detection and recognition of helmets worn by individuals in critical settings and the identification of license plates on vehicles. Furthermore, it explores the challenges, limitations, and future directions within these domains. The paper also evaluates the performance metrics, technological advancements, and potential applications in real-world scenarios, emphasizing the importance of these technologies in enhancing safety measures, traffic regulation, and security enforcement systems. Through this review, we aim to provide a consolidated overview and critical analysis of existing methodologies while identifying opportunities for future research and development in helmet detection and license plate recognition.

An IOT Based Vehicle Theft Detection and Remote Engine Locking System

Abstract: An IoT based vehicle theft detection and remote engine locking system is GSM (Global System for Mobile Communication) technology that helps the users to identify the vehicle in the theft mode and allow you to use the controlling mechanism technique. These days, there are a ton of cars being stolen. It's a big problem because crime rates are going up, and it's making it harder to keep vehicles safe. Criminals are becoming smarter and have reached the stage of applications present against the vehicles safety system. Vehicle theft has become a considerable issue which should be traced and prevented. The new system solves many problems and is affordable. Also the proposed system reducing complications by making use of some high priced products like ignition key, microcontroller. In the proposed method, we include an additional feature where controlling mechanisms remotely lock the vehicle engine and prevent theft. In proposed technique, user can start/stop the vehicle either by using the ignition key, which tracks exact location of the vehicle using the application. This paper talks about a great anti-theft system for vehicles. It uses Global Positioning System(GPS),Global System for Mobile Communication(GSM),and Biometrics technologies(i.e fingerprint ) to find the vehicle and confirm the owner's identity. Fingerprint device captures the fingerprints and matches the distinctiveness of every print scan by the device and compares it to the one keeps in its module or native system database.

Novel Approach for Vehicle Accident Tracking using IoT

Abstract: In recent years, there has been significant interestin integrating Internet of Things (IoT) technology into vehicle safety systems to enhance emergency response capabilities and road safety. This paper introduces a comprehensive Vehicle Accident Tracking System (VATS) that utilizes IoT principles. The proposed system incorporates various sensors and communication devices installed within vehicles to monitor theirstatus and detect potential accidents in real-time. When anaccident is detected, the system automatically triggers an alert mechanism, notifying relevant stakeholders such as emergency services and fleet managers. Key components of the VATSinclude accelerometers, GPS modules, and onboard communication units, which work together to provide precise accident geospatial data and vehicle condition data. The systemutilizes cloud-based platforms for data storage and processing, ensuring seamless integration with existing infrastructure and scalability. By continuously monitoring and analyzing vehicle telemetry data, the VATS facilitates proactive accident prevention measures and post-accident analysis. Additionally, it offers benefits such as reduced emergency response times, improved accident documentation for insurance claims, and enhanced overall road safety. Privacy and security concerns areaddressed through encryption protocols and access control mechanisms to protect sensitive information. Overall, the Vehicle Accident Tracking System presented in this paper represents a significant advancement in leveraging IoT technology to mitigate the impact of accidents on roadways, thereby contributing to a safer and more efficient transportation ecosystem.

Research Paper on Women Safety System

Abstract: In latest years, Violence and physical assault Against Women have increased in recent years. The number of women working in industries and other commercial market sectors is increasing. It's getting more and more necessary for women to travel at an odd hours and lonely locations as a part of their work. There are other strategies besides defense that may be sufficient to stop this growing abuse. It is necessary to come up with a security strategy that gives women a means of safety. Therefore, a more straightforward safety solution that can be engaged with just a button push and that can immediately notify the victim's close relatives is required

Wake Up Safe in the USA & International Patient Safety.

Patient safety is the most important aspect of anesthetic care. For both healthcare professionals and patients, the ideal would be no significant morbidity or mortality under anesthesia. Lessons from harm during healthcare can be shared to reduce harm and to increase safety. Many nations and individual institutions have developed robust safety systems to improve the quality and safety of patient care. Large registries that collect rare events, analyze them, and share findings have been developed. The approach, the funding, the included population, support from institutions and government and the methods of each vary. Wake Up Safe (WUS) is a patient safety organization accredited by Agency for Healthcare Research and Quality. Wake Up Safe was established in the United States in 2008 by the Society for Pediatric Anesthesia. The initiative aims to gather data on adverse events, analyze these incidents to gain insights, and apply this knowledge to ultimately reduce their occurrence. The purpose of this review is to describe the patient safety approaches in the USA. Through a national patient safety database WUS. Similar approaches either through WUS international or independent safety approaches have been described in Australia-New Zealand, India, and Singapore. We examine the patient safety processes across the four countries, evaluating their incident review process and the distribution of acquired knowledge. Our focus is on assessing the potential benefits of a WUS collaboration, identifying existing barriers, and determining how such a collaboration would integrate with current incident review databases or systems.

Value of the three-dimensional visualization ablation planning system in ultrasound-guided percutaneous microwave ablation for malignant adrenal tumors: A clinical comparative study.

We aimed to assess the efficacy and safety of the three-dimensional visualization ablation planning system (3DVAPS) in ultrasound-guided percutaneous microwave ablation (US-PMWA) for malignant adrenal tumors (MATs). A retrospective analysis was conducted on a cohort of 62 unilateral MAT cases from March 2011 to November 2022. There were a total of 62 lesions, with a mean maximum diameter of 5.4 ± 2.7 cm (range, 1.4-15.7 cm). The patients were categorized into the following, based on the pre-operative planning method: 3D planning (n = 32) and 2D planning (n = 30) groups. A comparative analysis was performed on various parameters, including ablation techniques, tumor-related prognosis, and incidence of complications. This analysis encompassed indicators, such as overall survival (OS) rate and local tumor progression (LTP), among others. The median follow-up period was 30 months (range, 3-84 months). Notably, compared with the 2D planning group, the 3D planning group exhibited significant disparities in the number of punctures (P = 0.035) and incidence of complications (P = 0.029) and had no significant difference in the OS (P > 0.05) but had a significantly lower LTP rate (6.2% vs. 23.3%, P = 0.033). In the 3D planning group, the sub-group with a tumor diameter of < 5 cm exhibited a significantly less number of punctures (P = 0.039), lower input energy (P = 0.002), and a shorter ablation time (P = 0.001), compared with the sub-group with a tumor diameter of ≥ 5 cm, but there was no significant difference in the LTP and OS rates between the two sub-groups (P > 0.05). The use of 3DVAPS in US-PMWA of MATs was advantageous, especially in lesions with a diameter of ≥ 5 cm. It can help in developing more rational surgical plans, reducing the incidence of complications, and extending the local recurrence-free survival time of patients and can add a certain value for precise treatment and expand the indications for ablation.

The relationship between freight train length and the risk of derailment.

In recent years, longer and heavier trains have become more common, primarily driven by efficiency and cost-saving measures in the railroad industry. Regulation of train length is currently under consideration in the United States at both the federal and state levels, because of concerns that longer trains may have a higher risk of derailment, but the relationship between train length and risk of derailment is not yet well understood. In this study, we use data on freight train accidents during the 2013-2022 period from the Federal Railroad Administration (FRA) Rail Equipment Accident and Highway-Rail Grade Crossing Accident databases to estimate the relationship between freight train length and the risk of derailment. We determine that longer trains do have a greater risk of derailment. Based on our analysis, running 100-car trains is associated with 1.11 (95% confidence interval: 1.10-1.12) times the derailment odds of running 50-car trains (or a 11% increase), even accounting for the fact that only half as many 100-car trains would need to run. For 200-car trains, the odds increase by 24% (odds ratio 1.24, 95% confidence interval: 1.20-1.28), again accounting for the need for fewer trains. Understanding derailment risk is an important component for evaluating the overall safety of the rail system and for the future development and regulation of freight rail transportation. Given the limitations of the current data on freight train length, this study provides an important step toward such an understanding.

Review of ISO 45001:2018 Implementation as Prevention Effort from Fire Occurred in PT Pertamina (Persero) Refinery Unit VI Balongan

Abstract PT Pertamina Refinery Unit VI Balongan has made a significant contribution in providing good income for PT Pertamina and the state. A large number of petroleum processing products produced daily cause a high risk of fire. Fires and explosions at oil refineries are still common even though major oil companies have occupational safety and health systems in place. Monitoring errors and the absence of re-evaluation of established companies for a long time are the reasons why this can happen. This research uses a descriptive approach through literature studies to collect data and obtain the necessary information by studying various journals, conference proceedings, books, and written references. The results of the research were obtained by PT Pertamina Refinery Unit VI Balongan, which applies several rules regarding work safety from ISO 45001: 2018 based on technical and non-technical aspects. In the technical aspect, the rules include the installation of warning signs and signs, noise, temperature, lighting intensity and personal safety equipment. Meanwhile, the regulations include administration and licensing as Safe Work Permits in non-technical aspects. However, based on several parameters of the application of ISO 45001: 2018, aspects that do not meet the standards are found and can be a problem, resulting in the potential for fire. This study concluded that PT Pertamina Refinery Unit VI Balongan must be able to provide firmness in implementing work safety rules or procedures for its employees.

Pedestrian Abnormal Behavior Detection System Using Edge–Server Architecture for Large–Scale CCTVEnvironments

As the deployment of CCTV cameras for safety continues to increase, the monitoring workload has significantly exceeded the capacity of the current workforce. To overcome this problem, intelligent CCTV technologies and server-efficient deep learning analysis models are being developed. However, real-world applications exhibit performance degradation due to environmental changes and limited server processing capacity for multiple CCTVs. This study proposes a real-time pedestrian anomaly detection system with an edge–server structure that ensures efficiency and scalability. In the proposed system, the pedestrian abnormal behavior detection model analyzed by the edge uses a rule-based mechanism that can detect anomalies frequently, albeit less accurately, with high recall. The server uses a deep learning-based model with high precision because it analyzes only the sections detected by the edge. The proposed system was applied to an experimental environment using 20 video streams, 18 edge devices, and 3 servers equipped with 2 GPUs as a substitute for real CCTV. Pedestrian abnormal behavior was included in each video stream to conduct experiments in real-time processing and compare the abnormal behavior detection performance between the case with the edge and server alone and that with the edge and server in combination. Through these experiments, we verified that 20 video streams can be processed with 18 edges and 3 GPU servers, which confirms the scalability of the proposed system according to the number of events per hour and the event duration. We also demonstrate that the pedestrian anomaly detection model with the edge and server is more efficient and scalable than the models with these components alone. The linkage of the edge and server can reduce the false detection rate and provide a more accurate analysis. This research contributes to the development of control systems in urban safety and public security by proposing an efficient and scalable analysis system for large-scale CCTV environments.

A Review of Tailings Dam Safety Monitoring Guidelines and Systems

A Review of Tailings Dam Safety Monitoring Guidelines and Systems

What is diagnostic safety? A review of safety science paradigms and rethinking paths to improving diagnosis.

Diagnostic errors in health care are a global threat to patient safety. Researchers have traditionally focused diagnostic safety efforts on identifying errors and their causes with the goal of reducing diagnostic error rates. More recently, complementary approaches to diagnostic errors have focused on improving diagnostic performance drawn from the safety sciences. These approaches have beencalled Safety-II and Safety-III, which apply resilience engineering and system safety principles, respectively. This review explores the safety science paradigms andtheir implications for analyzing diagnostic errors, highlighting their distinct yet complementary perspectives. The integration of Safety-I, Safety-II, and Safety-III paradigms presents a promising pathway for improving diagnosis. Diagnostic researchers not yet familiar with the various approaches and potential paradigm shift in diagnostic safetyresearch may use this review as a starting point for considering Safety-I, Safety-II, and Safety-III in their efforts toboth reduce diagnostic errors and improve diagnostic performance.

The expanding scope of ship design practice

As the former International Chair of IMDC, the initiator of the continuing series of IMDC State of Art (SoA) Reports and the lead author of most IMDC SoA Reports on design methodology from 1997 to 2018, the author has both pioneered and observed an increasingly broader scope in the practice of the design of particularly complex vessels. The paper commences with reviewing some key publications, not just to recent IMDCs, that have tracked the manner in which “ship design” (in the broadest sense) has become more sophisticated – especially in the crucial early stages of design. The diversity of ship design practice, not just due to computer-based methods, is readily observable. Moreover, the impact of computer aided design in ship design has not just been to better analyse ship performance (e. g. in hydrodynamics, strength and ship infrastructure systems behaviour) but also in the increasing use of graphical tools and design methods to enable “better ship design”. In a growing number of, mainly, academic centres, but also in some government agencies and design consultancies, there is a clear desire to better understand how to design “ships” and to manage the ship design process, especially for the most complex and novel classes of vessels. In particular, the objectives being sought when conceptualising and synthesising a range of ship options (as part of the requirement elucidation approach) in an ever-increasing scoping of the relevant issues, amounts to developing a more holistic approach. This is not just due to an increasingly complex ship acquisition and ownership environment, but also due to environmental and socio-economic (especially system safety) concerns. Overlaying all this are the opportunities or the spectre of Artificial Intelligence (or perhaps more immediately those of Machine Learning) and its likely impact on engineering practice as well as those other professions in the “marine design enterprise”. The paper concludes by emphasising that while ship design has distinct differences, when compared with most other large scale engineering design practice, the lead ship design profession of the naval architect has somehow to deal with this expanding scope in the practice of “ship design”. This means the education and on the job development thrust must broaden if the ship design profession is not to be side-lined into acting as mere hull engineers. It is argued, such a specific role will be more vulnerable in an increasingly Machine Learning dominated future, than the holistic ship creating and systems architectural alternative. Finally an ambitious vision for future ship designers is given alongside a summary of the specific main contributions by the author to ship design methodology.

Advances and novel applications in systems reliability and safety engineering (selected papers of the International Conference of SRSE 2022)

Advances and novel applications in systems reliability and safety engineering (selected papers of the International Conference of SRSE 2022)

CNN-based defect detection and classification of PV cells by infrared thermography method

ABSTRACT As a crucial component of the photovoltaic (PV) power generation system, effective defect detection of PV cells can help to ensure the power generation efficiency and the system safety. The photo-thermal-radiation infrared thermography experimental system has been built, and the infrared images of normal and defective PV cells were collected by an IR camera. An effective convolutional neural network (CNN) based model with the residual architecture is designed here to detect and classify the defects. An offline date augmentation method is performed to overcome the insufficient image dataset in the step of dataset establishment, so as to improve the defects classification capability of the designed CNN model. The defects classification accuracy of the proposed model is obtained as 96.96% with 3-class. In order to verify the defect classification ability of the designed CNN model, other four models were adopted for comparative analysis. The results indicate that the proposed CNN model has advantages in defect classification of PV cells. The completed work can provide meaningful exploration in the industrial application of defect detection of PV cells.

BIKE RIDER SAFETY SYSTEM USING STM 32 MICROCONTROLLER

This study focuses on the development of an innovative safety jacket designed for horse riders, high-altitude workers, and particularly two- wheeler riders to mitigate the impact of accidents and enhance life-saving measures. Given the high incidence of road accidents in India, with 499,628 reported in 2010 leading to 134,513 fatalities and over 500,000 injuries, the need for improved safety mechanisms is critical. The proposed safety jacket integrates a micro controller-based system to detect falls and trigger an emergency response, inflating air cushions around the jacket to cushion impacts. Additionally, the system incorporates an alcohol sensor and a helmet detection sensor to ensure the bike starts only if the rider is sober and wearing a helmet. Visibility issues for riders are also addressed, with the jacket featuring turn indicators and other visibility enhancements to alert other road users. The jacket is designed to be water-resistant and washable, ensuring durability and ease of maintenance. The Bike Rider Safety System (BRSS) further enhances safety through real-time monitoring and adaptive response to potential hazards, using accelerometer, gyroscopes, and proximity sensors. The Arduino-based system comprises four main functionalities: helmet and alcohol detection, accident detection, airbag deployment, and live location transmission to authorities. In summary, the smart jacket aims to significantly reduce the risks faced by riders by incorporating advanced technology and a robust design to ensure their safety on the road.

Camera-Based Safety System for Optical Wireless Power Transmission Using Dynamic Safety-Distance

This paper introduces a new safety approach for Optical Wireless Power Transmission (OWPT), a technology that is integral to the new kinds of Wireless Power Transmission technology (WPT). It starts from the fundamental configuration of the current OWPT system, addressing the safety concerns related to lasers by involving laser irradiation hazards, laser exposure regulation and guidelines, and a comparison with other safety methods. A camera-based OWPT safety system focused on the emission control of the light source is proposed, and it utilizes a depth camera and finely tuned computer vision-based control program. Through meticulous system design and experiments, the proposed system can detect moving objects in a limited indoor environment and control the laser/LED light transmission according to the object’s velocity dynamically. Various functions and exclusive improvements towards OWPT operation are mentioned, and Dynamic Safety-Distance is proposed as the core mechanism of the safety system. Through on-site experiments, indoor safety control and system operation’s evaluation are discussed, acknowledging both the advantages and limitations of the proposed safety system. This paper concludes with suggestions for further developments in camera-based OWPT safety incorporating the concept of Automatic Emission Control.

Clinical performance and safety of a two-lead cardiac resynchronization therapy system with a floating atrial sensing dipole

Abstract Background The incidence of complications after implantable cardioverter-defibrillator (ICD) and cardiac resynchronisation therapy (CRT-D) implantations is dependent on the number of implanted leads. The majority of CRT-D patients have unimpaired sinus node function and do not require atrial pacing. A two-lead CRT-D system with a floating atrial sensing dipole mounted on the right ventricular lead ((CRT-DX) allows dual chamber tachyarrhythmia detection, and atrio-ventricular sequential pacing with a reduced amount of implanted material. Purpose This study investigated the clinical efficacy and safety of the CRT-DX system. Methods This multicentre, single-arm study observed patients after de novo implantation of a CRT-DX system for 12 months. Patients were eligible for the study when chronotropic competence was proven by heart rates ≥100 bpm during exercise, premature ventricular contractions rate of &amp;lt; 5%/h and absence of atrioventricular block ≥ II. Intraoperatively measured p-wave amplitude of ≥ 1 mV was recommended. The primary safety endpoint was the additional implantation of a right atrial (RA) lead after the initial implantation. As indicators of efficacy, we report the changes in left ventricular ejection fraction (LVEF) and New York Heart Association (NYHA) class over the follow-up period. Results Overall, 110 patients were implanted with the complete CRT-DX system. Mean age of study participants was 62 ± 12 years and 77 (70%) were male. The underlying heart disease was non-ischemic in 66 (60%) patients and 103 (93%) had a left bundle branch block. NYHA class was II in 60 (54.5%) and III in 50 (45.5%) patients. ICD placement was performed in 13 (11.8%) patients for the secondary prevention of sudden cardiac death. A total of 104 patients completed the follow-up, 2 patients died, 1 had the system explanted for infection, 2 withdrew consent and 1 was lost to follow-up. The primary endpoint of RA lead implantation was met in 2 (1.8%) participants (Figure 1). One patient required atrial pacing and one patient, who had shown a p-wave amplitude &amp;lt; 1 mV at implantation, lost atrial sensing. The mean RA sensing amplitude remained stable during follow-up (4.6 ± 1.8 mV, 4.9 ± 1.8 mV and 4.6 ± 1.8 mV at 1, 6 and 12 months, respectively; Figure 2). The LVEF improved by 14.7% ± 11.0%, from 26.3% ± 6.9% to 40.8% ± 10.7% (p &amp;lt; 0.00001). Changes in NYHA class were available in 87 patients with 35 (40.2%) improved by one class and 13 (14.9 %) by two classes. Thirty-four (39.1%) had no change and 5 (5.7%) worsened by one class (global p &amp;lt; 0.00001). Conclusion The two-lead CRT-DX system showed a low requirement of subsequent RA lead implantations (1.8%) and stable RA sensing amplitudes. Our results suggest a CRT response similar to that of conventional three-lead CRT-D systems. CRT-DX systems appear to be a feasible alternative for patients with chronotropic competence.Kaplan-Meier curve for primary endpointDaily mean RA sensing amplitude

Multimodal imbalanced‐data fault diagnosis method based on a dual‐branch interactive fusion network

AbstractBearing‐fault diagnosis in rotating machinery is essential for ensuring the safety and reliability of mechanical systems. However, under complicated working conditions, the number of normal mechanical equipment samples can far exceed the number of faulty ones. When the data are so imbalanced, data fault diagnosis cannot be easily conducted using conventional deep learning methods. This study proposes a fault diagnosis method based on a dual‐branch interactive fusion network, which improves the accuracy and stability of bearing‐fault diagnosis. First, a dual‐branch feature representation network comprising an iterative attention‐feature fusion residual neural network and a long short‐term memory network is designed for extracting different modal features. Meanwhile, intermodal fusion of the extracted features is performed through multilayer perception. Based on the cost‐sensitive regularization loss, a new joint loss function is then designed for network training. Finally, the effectiveness of the proposed method is verified through comparative experiments, visualization analyses, ablation experiments, and generalization performance experiments.