Search Results (20)

The stable operation of electrical equipment is critical for industrial safety, yet traditional anomaly detection methods often suffer from limitations, such as high resource demands, dependency on expert knowledge, and lack of real-world capabilities. To address these challenges, this article proposes an unsupervised anomaly detection method for electrical equipment, utilizing audio latent representation and a parallel attention mechanism. The framework employs an autoencoder to extract low-dimensional features from audio signals and introduces a phase-aware parallel attention block to dynamically weight these features for an improved anomaly sensitivity. With adversarial training and a dual-encoding mechanism, the proposed method demonstrates robust performance in complex scenarios. Using public datasets (MIMII and ToyADMOS) and our collected real-world wind turbine data, it achieves high AUC scores, surpassing the best baselines, which demonstrates our framework design is suitable for industrial applications. Full article

Introduction: Widespread adoption of AI for medical decision-making is still hindered due to ethical and safety-related concerns. For AI-based decision support systems in healthcare settings, it is paramount to be reliable and trustworthy. Common deep learning approaches, however, have the tendency towards overconfidence when faced with unfamiliar or changing conditions. Inappropriate extrapolation beyond well-supported scenarios may have dire consequences highlighting the importance of the reliable estimation of local knowledge uncertainty and its communication to the end user. Materials and Methods: While neural network ensembles (ENNs) have been heralded as a potential solution to these issues for many years, deep learning methods, specifically modeling the amount of knowledge, promise more principled and reliable behavior. This study compares their reliability in clinical applications. We centered our analysis on experiments with low-dimensional toy datasets and the exemplary case study of mortality prediction for intensive care unit hospitalizations using Electronic Health Records (EHRs) from the MIMIC3 study. For predictions on the EHR time series, Encoder-Only Transformer models were employed. Knowledge uncertainty estimation is achieved with both ensemble and Spectral Normalized Neural Gaussian Process (SNGP) variants of the common Transformer model. We designed two datasets to test their reliability in detecting token level and more subtle discrepancies both for toy datasets and an EHR dataset. Results: While both SNGP and ENN model variants achieve similar prediction performance (AUROC: $\approx 0.85$, AUPRC: $\approx 0.52$ for in-hospital mortality prediction from a selected MIMIC3 benchmark), the former demonstrates improved capabilities to quantify knowledge uncertainty for individual samples/patients. Discussion/Conclusions: Methods including a knowledge model, such as SNGP, offer superior uncertainty estimation compared to traditional stochastic deep learning, leading to more trustworthy and safe clinical decision support. Full article

The primary objective of this research investigation is to examine object detection within the specific environment of a nursery. The nursery environment presents a complex scene with a multitude of objects, varying in size and background. To simulate real-world conditions, we gathered data from a nursery. Our study is centered around the detection of small objects, particularly in nursery settings where objects that include stationery, toys, and small accessories are commonly present. These objects are of significant importance in facilitating cognition of the activities and interactions taking place within the confines of the room. Due to their small size and the possibility of occlusion by other objects or children, precisely detecting these objects is regrettably fraught with inherent challenges. This study introduces YOLOv8s-NE in an effort to enhance the detection of small objects found in the nursery. We improve the standard YOLOv8 by incorporating an extra detection head to effectively for small objects. We replace the C2f module with C2f_DCN to further improve the model’s ability to detect objects of varying sizes that can be deformed or occluded within the image. Furthermore, we introduce NAM attention to focus on the important features and ignore less informative ones, thereby improving the accuracy of our proposed model. We used the five-fold cross-validation approach to split the dataset in order to evaluate the performance of YOLOv8s-NE, thereby facilitating a more comprehensive model evaluation. Our model achieves $34.1\%$ of AP_s, $45.1\%$ of mAP_50:90, and $76.7\%$ of mAP₅₀ detection accuracy at 37.55 FPS on the nursery dataset. In terms of AP_s, mAP_50:90, and mAP₅₀ metrics, our proposed YOLOv8s-NE model outperforms the standard YOLOv8s model, with improvements of $4.6\%$, $4.7\%$, and $3.9\%$, respectively. We apply our proposed YOLOv8s-NE model as a safety system by developing an algorithm to detect objects on top of cabinets that could be potentially risky to children. Full article

Poly(vinyl chloride) (PVC) is widely used to produce various consumer goods, including food packaging, toys for children, building materials, and cosmetic products. However, despite their widespread use, phthalate plasticizers have been identified as endocrine disruptors, which cause adverse health effects, thus leading to increasing concerns regarding their migration from PVC products to the environment. This study proposed a method for rapidly measuring the migration of phthalates, particularly di(2-ethylhexyl) phthalate (DEHP), from PVC products to commonly encountered liquids. The release of DEHP under various conditions, including exposure to aqueous and organic solvents, different temperatures, and household microwaves, was investigated. The amount of DEHP released from both laboratory-produced PVC films and commercially available PVC products was measured to elucidate the potential risks associated with its real-world applications. Furthermore, tests were performed to evaluate cytotoxicity using estrogen-dependent and -independent cancer cell lines. The results revealed a dose-dependent impact on estrogen-dependent cells, thus emphasizing the potential health implications of phthalate release. This comprehensive study provides valuable insights into the migration patterns of DEHP from PVC products and forms a basis for further research on the safety of PVC and plasticizers. Full article

Standard limits for harmful chemicals in consumer goods are important for consumer safety and the development of relevant industries. This paper proposes a method for determining content limits of chemicals in consumer goods by extending the “as low as reasonably practicable” (ALARP) principle by adding the impact of price and cost changes. While giving due consideration to the price and cost factors of consumer goods, this method derives such limits by measuring “acceptable consumer risk level” on the demand side and “industrial tolerance to chemical limits” on the supply side to obtain the ALARP area. Through a combination of functional relations between different factors and chemical limits, including consumer welfare, producer welfare, and external cost, a general chemical limit decision model can be created for the determination of the general limits of chemicals. This research provides a new methodology for studying decisions on chemical limits by considering consumer and industry affordability. In the final part of this paper, the feasibility and effectiveness of the proposed method are verified based on data of Bisphenol A used in the production of polycarbonate (PC) toys; the data were obtained from enterprise surveys and consumer questionnaires. Through our method, in this paper, a more suitable determination of harmful chemical substances can be obtained. Full article

The playground is perhaps the one area where school children feel like they can roam free, and public playgrounds provide many learning opportunities through different types of play. A cross-sectional descriptive study is presented with the objective of studying playground safety and the play behavior of primary school children at a park in Nakhon Si Thammarat Province, Thailand. The total number of playground equipment pieces was 22, the sample group of children was 362 children, and the data were collected using a playground safety survey and an observation form on playground play behavior. Data were collected from 2017 to 2018 and were analyzed using descriptive statistics including frequency, average, and standard deviation. The research showed that: (1) the most common defects of playground equipment included the material selection, the distance of the stair steps, and the height of the playground equipment; (2) the lack of awareness of children in terms of using the playground equipment safely; and (3) the three top risks in the play behavior of children were not checking equipment or toys before play, playing on the equipment over-adventurously, and playing on the equipment carelessly with friends. Related government agencies should provide support and management for playground areas and playground equipment by continuously implementing equipment checks, improvements, and repairs. Full article

As the number of vehicles increases, road accidents are on the rise every day. According to the World Health Organization (WHO) survey, 1.4 million people have died, and 50 million people have been injured worldwide every year. The key cause of death is the unavailability of medical care at the accident site or the high response time in the rescue operation. A cognitive agent-based collision detection smart accident alert and rescue system will help us to minimize delays in a rescue operation that could save many lives. With the growing popularity of smart cities, intelligent transportation systems (ITS) are drawing major interest in academia and business, and are considered as a means to improve road safety in smart cities. This article proposed an intelligent accident detection and rescue system which mimics the cognitive functions of the human mind using the Internet of Things (IoTs) and the Artificial Intelligence system (AI). An IoT kit is developed that detects the accident and collects all accident-related information, such as position, pressure, gravitational force, speed, etc., and sends it to the cloud. In the cloud, once the accident is detected, a deep learning (DL) model is used to validate the output of the IoT module and activate the rescue module. Once the accident is detected by the DL module, all the closest emergency services such as the hospital, police station, mechanics, etc., are notified. Ensemble transfer learning with dynamic weights is used to minimize the false detection rate. Due to the dataset’s unavailability, a personalized dataset is generated from the various videos available on the Internet. The proposed method is validated by a comparative analysis of ResNet and InceptionResnetV2. The experiment results show that InceptionResnetV2 provides a better performance compared to ResNet with training, validation, and a test accuracy of 98%, respectively. To measure the performance of the proposed approach in the real world, it is validated on the toy car. Full article

Ferrets (Mustela putorius furo) are kept and used in multiple sectors of society, but little is known about how they are housed and what environmental enrichment (EE) they may benefit from. We aimed to help guide caretakers about what housing and EE can be provided for ferrets. Through an online questionnaire of ferret caretakers, including pet, laboratory, zoological collection, rescue and working animal sectors internationally, we described ferret housing, opportunities for exploration, EE provision and caretaker opinions on ferrets’ preferred EE types, and problematic EE. In total, 754 valid responses from 17 countries were analysed, with most (82.4%) coming from pet owners. Most ferrets were housed socially, with housing varying across sectors from single-level cages to free-range housing in a room or outdoor enclosure; pet owners mostly used multi-level cages. The most commonly reported EE included hammocks, tunnels and tactile interaction with caretakers. Respondents reported that ferrets particularly enjoyed digging substrates, tunnels, human interaction and exploration. The most frequently reported problems were that ingestion of unsuitable chew toys and rubber items could cause internal blockages, narrow tunnels could trap ferrets, and certain fabrics that could catch claws. This suggests a need for increased awareness of the risks of these EE types and for more commercially available safety-tested ferret EE. Scent trails were relatively rarely provided but were reported to be enjoyed and harmless, so we recommend that these should be provided more commonly. Our results suggest that there is scope to improve ferret housing and EE provision to benefit ferret welfare across all sectors. Full article

In this work, we present an eye-image acquisition device that can be used as an image acquisition front-end application in compact, low-cost, and easy-to-integrate products for smart-city access control applications, based on iris recognition. We present the advantages and disadvantages of iris recognition compared to fingerprint- or face recognition. We also present the main drawbacks of the existing commercial solutions and propose a concept device design for door-mounted access control systems based on iris recognition technology. Our eye-image acquisition device was built around a low-cost camera module. An integrated infrared distance measurement was used for active image focusing. FPGA image processing was used for raw-RGB to grayscale demosaicing and passive image focusing. The integrated visible light illumination meets the IEC62471 photobiological safety standard. According to our results, we present the operation of the distance-measurement subsystem, the operation of the image-focusing subsystem, examples of acquired images of an artificial toy eye under different illumination conditions, and the calculation of illumination exposure hazards. We managed to acquire a sharp image of an artificial toy eye sized 22 mm in diameter from an approximate distance of 10 cm, with 400 pixels over the iris diameter, an average acquisition time of 1 s, and illumination below hazardous exposure levels. Full article

Traffic calming is introduced to minimise the negative results of motor vehicle use, for example, low safety level or quality of life, high noise and pollution. It can be implemented through the introduction of road infrastructure reducing the velocity and the traffic volume. In this paper, we studied how traffic-calming influences the traffic assignment. For the research, a traffic-calming measure of speed cushions on the Stachiewicza street in Krakow was taken. A method of extracting trajectories from aerial footage was shown, and it was used to build a model. For a given example, through driving characteristics research and microscopic modelling, volume–delay BPR functions were estimated—for a street with and without traffic calming. Later, a toy network of two roads of the same length, connecting the same origin and destination, was simulated using an equilibrium traffic assignment method. Simulations were conducted both with the use of PTV Vissim and Visum software and through individual calculations. According to the results of this paper, there was a difference in traffic volume according to the equilibrium traffic assignment in the aforementioned toy network as a function of total network traffic volume. Full article

Children spend most of their daily time indoors. Many of the items used indoors, such as furniture, electronics, textile, and children toys, are treated with chemicals to provide longevity and fulfil the safety standards. However, many chemicals added to these products are released into the environment during leaching out from the treated products. Many studies have reported brominated flame retardants (BFRs) in indoor environments; however, few have focused on environments specified for young children. In this study, paired air (PM₁₀) and dust samples were collected from the rooms (n = 30) of Saudi children. These samples were analyzed for different congeners of polybrominated diphenyl ethers (PBDEs) and three important alternative flame retardants using gas chromatography-mass spectrometry. Decabromodiphenyl ether (BDE 209) was the most important analyzed BFR in dust and PM₁₀ samples with a median value of 3150 ng/g of dust and 75 pg/m³. This indicates the wider application of BDE 209 has implications for its occurrence, although its use has been regulated for specified uses since 2014. Among alternative BFRs, 2-Ethylhexyl-2,3,4,5-tetrabromobenzoate (TBB), Bis(2-ethylhexyl)-3,4,5,6-tetrabromophthalate (TBPH), and 1,2-Bis(2,4,6-tribromophenoxy)ethane (BTBPE) were found with a median levels of 10, 15 and 8 ng/g of dust, respectively. However, alternative BFRs were present in <50% of the PM₁₀ samples. The calculated long term and daily exposures via indoor dust and PM₁₀ of Saudi children from their rooms were well below the respective reference dose (RfD) values. Nonetheless, the study highlights BDE 209 at higher levels than previously reported from household dust in Saudi Arabia. The study warrants further extensive research to estimate the different classes of chemical exposure to children from their rooms. Full article

Unmanned air vehicles (UAVs) or drones have gained popularity in recent years. However, the US Federal Aviation Administration (FAA) is still hesitant to open up the national air space (NAS) to UAVs due to safety concerns because UAVs have several orders of magnitude of more accidents than manned aircraft. To limit the scope in this paper, we focus on large, heavy, and expensive UAVs that can be used for cargo transfer and search and rescue operations, not small radio-controlled toy drones. We first present a general architecture for enhancing the safety of UAVs. We then illustrate how signal processing technologies can help enhance the safety of UAVs. In particular, we provide a bird’s eye view of the application of signal processing algorithms on condition-based maintenance, structural health monitoring, fault diagnostics, and fault mitigation, which all play critical roles in UAV safety. Some practical applications are used to illustrate the importance of the various algorithms. Full article

A high proportion of dogs and cats are fearful during veterinary visits, which in some cases may escalate into aggression. Here, we discuss factors that contribute to negative emotions in a veterinary setting and how these can be addressed. We briefly summarise the available evidence for the interventions discussed. The set-up of the waiting area (e.g., spatial dividers; elevated places for cat carriers), tailoring the examination and the treatment to the individual, considerate handling (minimal restraint when possible, avoiding leaning over or cornering animals) and offering high-value food or toys throughout the visit can promote security and, ideally, positive associations. Desensitisation and counterconditioning are highly recommended, both to prevent and address existing negative emotions. Short-term pain from injections can be minimised by using tactile and cognitive distractions and topical analgesics, which are also indicated for painful procedures such as ear cleanings. Recommendations for handling fearful animals to minimise aggressive responses are discussed. However, anxiolytics or sedation should be used whenever there is a risk of traumatising an animal or for safety reasons. Stress-reducing measures can decrease fear and stress in patients and consequently their owners, thus strengthening the relationship with the clients as well as increasing the professional satisfaction of veterinary staff. Full article

According to the asymptotic safety conjecture, gravity is a renormalizable quantum field theory whose continuum limit is defined by an interacting fixed point of the renormalization group flow. In these proceedings, we review some implications of the existence of this nontrivial fixed point in cosmological contexts. Specifically, we discuss a toy model exemplifying how the departure from the fixed-point regime can explain the approximate scale-invariance of the power spectrum of temperature fluctuations in the cosmic microwave background. Full article

For consumer protection across borders, the European Union has established the rapid alert system for dangerous non-food products (RAPEX), with the overarching goal of preventing or limiting the sale and use of non-food products that present a serious risk for the health and safety of consumers. In our study, we comprehensively analyzed RAPEX notifications associated with products posing a microbiological risk from 2005 through 2017. Additional information was retrieved from national laboratory reports. A total of 243 microbiologically harmful consumer products triggered notifications in 23 out of 31 participating countries. About half of the products were reported by Spain, Germany, and Italy. Notifications mainly included contaminated toys, cosmetics, and chemical products. Depending on the notifying country, measures taken to prevent the spread of dangerous products were predominantly ordered either by public authorities or economic operators. The interval between microbiological diagnosis and the date of RAPEX notifications considerably varied between RAPEX member states, ranging between a few days and 82 weeks. The nature and extent of RAPEX usage substantially differed among member states, calling for harmonization and optimization. Slight modifications to RAPEX could help to systematically record microbiological hazards, which may improve the assessment of potential health risks due to contaminated non-food products. Full article