Article Highlights: An automated water recycle method for cleaning dust-fall in rooftop photovoltaic module is proposed.Both simulation and experimental models are developed to predict output power of the photovoltaic module.Proposed method can produce 24.40% more output power than a no-cleaning system with a mere water loss of 0.32%/cycle.
SETTING: Nationwide data from the Social Security Organisation (SOCSO) of Malaysia.
PARTICIPANTS: A stratified random sample of workers registered with the SOCSO of Malaysia with documentation of eye injury.
PRIMARY AND SECONDARY OUTCOME MEASURES: Characteristics of eye injuries and medical costs related to eye injury (primary) and return-to-work status (secondary).
RESULTS: A total of 884 from 8861 case files workplace accidents involving eye injury registered with Social Security Services (SOCSO) were identified. The mean age was 35±10 years and the highest incidence of work-related eye injury occurred in the age group 30-39 years and among Malay ethnics. Males are affected more than females' workers. The highest cause of eye injury was the impact from a moving object excluding falling objects (89.2%) and anterior segment injuries occurred more than posterior segment injuries. The total direct and Indirect medical cost was RM1 108 098.00 (US$316 599.40) and RM4 150 140.00 (US$1 185 754.20) for 884 cases.
CONCLUSION: The majority of workers suffered from the low level of eye injury. A significant relationship was found between the severity of eye injury and employee work status. The indirect cost of medical and vision rehabilitation was higher than the direct cost. Awareness and vision rehabilitation programmes at the workplace need to be addressed for better prevention and rehabilitative service.
METHODS: A cross-sectional study on sports vision screening was used to evaluate the visual skills of 214 elementary students (107 athletes, 107 non-athletes), aged between 13 and 16y. The visual screening assessed visual parameters such as ocular motor alignment, accommodation, and vergence functions.
RESULTS: Mean visual parameters were compared between age-group matched athletes (mean age 14.82±0.98y) and non-athletes (mean age 15.00±1.04y). The refractive errors of all participants were corrected to maximal attainable best corrected visual acuity of logMAR 0.0. Accommodation function assessment evaluated amplitude of accommodation and accommodation facility. Vergence functions measured the near point of convergence, vergence facility, and distance fusional vergence at break and recovery point. Ocular motor alignment was not statistically significant between both groups. Athletes had a statistically significant amplitude of accommodation for both the right eye (t=2.30, P=0.02) and the left eye (t=1.99, P=0.05). Conversely, non-athletes had better accommodation facility (t=-2.54, P=0.01) and near point of convergence (t=4.39, P<0.001) when compared to athletes. Vergence facility was found to be better among athletes (t=2.47, P=0.01). Nevertheless, non-athletes were significantly better for both distance negative and positive fusional vergence.
CONCLUSION: Although the findings are still inconclusive as to whether athletes had superior visual skills as compared to non-athletes, it remains important to identify and elucidate the key visual skills needed by athletes in order for them to achieve higher performance in their sports.
METHODS: Natural language processing (NLP) techniques were harnessed to preprocess the occupational injury narratives obtained from the US Occupational Safety and Health Administration (OSHA) from January 2015 to June 2023. The methodology involved meticulous preprocessing of textual narratives to standardize text and eliminate noise, followed by the innovative integration of Term Frequency-Inverse Document Frequency (TF-IDF) and Global Vector (GloVe) word embeddings for effective text representation. The proposed predictive model adopts a novel Bidirectional Long Short-Term Memory (Bi-LSTM) architecture and is further refined through model optimization, including random search hyperparameters and in-depth feature importance analysis. The optimized Bi-LSTM model has been compared and validated against other machine learning classifiers which are naïve Bayes, support vector machine, random forest, decision trees, and K-nearest neighbor.
RESULTS: The proposed optimized Bi-LSTM models' superior predictability, boasted an accuracy of 0.95 for hospitalization and 0.98 for amputation cases with faster model processing times. Interestingly, the feature importance analysis revealed predictive keywords related to the causal factors of occupational injuries thereby providing valuable insights to enhance model interpretability.
CONCLUSION: Our proposed optimized Bi-LSTM model offers safety and health practitioners an effective tool to empower workplace safety proactive measures, thereby contributing to business productivity and sustainability. This study lays the foundation for further exploration of predictive analytics in the occupational safety and health domain.