Explore the vast range of titles available.

Dense crossbar arrays of non-volatile memory (NVM) can potentially enable massively parallel and highly energy-efficient neuromorphic computing systems. The key requirements for the NVM elements are continuous (analog-like) conductance tuning capability and switching symmetry with acceptable noise levels. However, most NVM devices show non-linear and asymmetric switching behaviors. Such non-linear behaviors render separation of signal and noise extremely difficult with conventional characterization techniques. In this study, we establish a practical methodology based on Gaussian process regression to address this issue. The methodology is agnostic to switching mechanisms and applicable to various NVM devices. We show tradeoff between switching symmetry and signal-to-noise ratio for HfO 2 -based resistive random access memory. Then, we characterize 1000 phase-change memory devices based on Ge 2 Sb 2 Te 5 and separate total variability into device-to-device variability and inherent randomness from individual devices. These results highlight the usefulness of our methodology to realize ideal NVM devices for neuromorphic computing. The application of resistive and phase-change memories in neuromorphic computation will require efficient methods to quantify device-to-device and switching variability. Here, the authors assess the impact of a broad range of device switching mechanisms using machine learning regression techniques.

Incessant increases in vehicles and massive road networks lead to traffic-related problems and noise pollution. Road tunnels are considered a more feasible and effective solution for solving traffic problems. Compared to other traffic noise abatement strategies, road tunnels also offer enormous benefits to urban mass transit systems. However, the road tunnels that are non-complying with the design and safety standards negatively impact commuters’ health of being exposed to the high noise level inside the tunnel, particularly for road tunnels above 500 m in length. The study aims to evaluate the applicability of the ASJ RTN-Model 2013 by validating predicted data with the measurement data at the tunnel portal. The study also investigates the acoustic characteristics of noise inside the tunnel by analysing octave frequencies to inspect the correlation of noise spectrum for noise-induced hearing loss (NIHL) and discussed the possible health effect on the pedestrian and vehicle riders passing through the tunnel. The result shows that people are exposed to a high noise level inside the tunnel. The equivalent sound pressure levels at different locations inside the tunnel along the length observed between 78.9 to 86.5 dB(A), which exceeded the CPCB, recommended permissible limits for road traffic noise. The locations L1, L5, L6 and L7 found higher sound pressure levels at 4 kHz and relates to NIHL. The observed average difference between the measurement and predicted LAeq value at the tunnel portal was 2.8 dB(A) which is highly acceptable and confirms the ASJ RTN-2013 prediction model applicability for predicting tunnel portal noise in the Indian road conditions. The study recommends complete restriction of honking inside the tunnel. Considering the commuter’s safety perspective, the road tunnels above 500 m must have separate walk sides for pedestrians with a barrier.

Noise annoyance is recognized as an expression of physiological and psychological strain in acoustical environment. The studies on prediction of noise annoyance and parametric sensitivity analysis of factors affecting it have been rarely reported in India. A hybrid ConvLSTM technique was developed in the study to predict traffic-induced noise annoyance in 484 people based on ambient noise levels, as well as survey information. Ambient noise levels were obtained at different locations of Dhanbad city using sound level meter at varying intervals, viz. 09AM–12PM, 03PM–06PM, and 08PM–11PM. The proposed method was compared with some well-known neural network techniques such as K-nearest neighbors (KNN), artificial neural network (ANN), recurrent neural network (RNN), and long-short-term memory (LSTM). The experimental results indicate that the proposed method outperforms other techniques and can be a reliable approach for prediction of noise annoyance with an accuracy of 93.8%. It can be concluded from noise maps that the noise levels in all locations of the Dhanbad city were higher than 70 dB(A) and noise sensitivity is the most important input variable of traffic-induced noise annoyance, followed by honking noise, education, exposure hours, L Aeq , sleeping disorder, and chronic disease. The study shall facilitate in developing a decision support tool for prediction of noise annoyance and promoting implementation of suitable public policy in urban cities.

Excessive occupational exposure to noise results in a well-recognized occupational hearing loss which is prevalent in many workplaces and now it is taken as a global problem. Therefore, this study aims to assess the prevalence of noise-induced hearing loss and associated factors among workers in the Bishoftu Central Air Base in Ethiopia. An institutional-based cross-sectional study was conducted among 260 central air base workers through face-to-face interviews, an environment noise survey, and an audiometric test for data collection. Data were entered by Epi-data version 3.1 and SPSS was used to analyze the data. Finally, a statistical analysis such as descriptive and binary logistic regression analysis was applied. A P-value < 0.05 at 95% CI was considered statistically significant. The overall prevalence of noise-induced hearing loss and hearing impairments was 24.6 and 30.9%, respectively. The highest prevalence of noise-induced hearing loss was recorded for workers who were exposed to noise levels greater than 90 dBA. Out of 132 workers exposed to the average noise level of 75 dB A, only 5% of workers were affected with noise-induced hearing loss, while 128 workers exposed to an average noise level equal to or greater than 90 dB A, 19.6% of workers were identified with noise-induced hearing loss. Regarding sex, around 21.9% of male workers were identified with noise-induced hearing loss. Workers who were exposed to a high noise level workplace previously or before the Central Air Base workplace were five times (AOR = 5.0, 95% CI 1.74–14.36) more likely affected by noise-induced hearing loss than those workers not previously exposed. Those workers who were exposed to greater or equal to 90dBA noise level were 4.98 times (AOR = 4.98, 95% CI 2.59–9.58) more likely to be exposed to noise-induced levels than those who were exposed to less than 90dBA noise level. Moreover, male air base workers were 3.5 times more likely exposed to hearing impairment than female workers (AOR = 3.5, 95% CI 1.01–12.0). This study identified that the prevalence of noise-induced hearing loss and hearing impairments was significantly high. So implementation of a hearing conservation program, giving noise education, and supplying adequate hearing protective devices (HPDs) are essentials.

Background Occupational noise has been associated with numerous adverse health outcomes. However, limited evidence exists regarding its association with obesity. We aim to investigate the effect of occupational noise exposure on the risk of overweight/obesity among workers, providing scientific evidence for the prevention and management of overweight/obesity in the occupational population. Methods This study included 3427 participants from two factories in Guangzhou, China. Individual occupational noise exposure levels were assessed using cumulative noise exposure (CNE). Body mass index (BMI) data were obtained from physical examinations. Linear and logistic regression models, restricted cubic spline, as well as subgroup analyses, were used to explore the association. Results In continuous models, each 1 dB-year increase in CNE was significantly associated with a 0.03 (95% confidence interval (CI): 0.00, 0.05) kg/m² increase in BMI. In categorical models, higher CNE levels were significantly associated with BMI (β = 0.54, 95% CI: 0.16, 0.92) and overweight/obesity (odd ratio (OR) = 1.57, 95%CI: 1.21, 2.04). Restricted cubic splines (RCS) analysis demonstrated a linear dose-response relationship between CNE and overweight/obesity ( P for overall =0.013, P for non-linear =0.175). Additionally, shift and night work were identified as critical moderating factors, with a stronger association observed among workers engaged in shift and night work. Conclusion Occupational noise exposure is positively associated with overweight/obesity, particularly among those engaged in shift and night work. Thus, enhancing noise source management and promoting awareness among workers for prevention are imperative.

The effect of urban green spaces on traffic noise reduction has been extensively studied at the level of single vegetation, hedges, etc., but there is a lack of corresponding studies at the scale of spatial patterns of urban green spaces. Therefore, this study aims to analyze the relationship between the spatial pattern of urban green space and the change in green space’s noise reduction capacity. Through the morphology spatial pattern analysis method, this analysis divides the urban green space in the Fuzhou high-tech zone into seven types of elements with different ecological definitions and simulates the noise condition of the urban environment with the presence of green space as well as without the presence of green space by computer simulation, calculates the distribution map of the noise reduction produced by the urban green space, and analyzes the correlation between the seven types of green space elements and the noise reduction with the geographically weighted regression modeling analysis. The study finds that (1) Urban green space patterns can significantly affect the net noise reduction of green space. Areas with high green coverage can produce a stronger green space noise reduction effect. (2) More complex green space shapes and more fragmented urban green space can produce higher noise reduction. (3) The green space close to the source of noise can exert a stronger noise reduction effect. Therefore, in the process of planning and design, from the perspective of improving the urban acoustic environment, the configuration of high-quality green spaces in areas with higher levels of noise pollution should be given priority, which may have better noise reduction effects.

Noise pollution in urban areas is an emerging environmental threat which local agencies and state authorities must consider in planning and development. Excessive noise is becoming a significant problem adversely affecting the physiological and psychological health of the citizens. Present study was carried out to assess and quantitatively evaluate ambient noise levels in Mumbai Metropolitan Region (MMR) consisting of 9 cities namely Bhiwandi-Nizampur, Kalyan-Dombivli, Mira-Bhayandar, Mumbai, Navi Mumbai, Panvel, Thane, Ulhasnagar and Vasai-Virar. The noise environment was assessed on the basis of equivalent continuous sound pressure levels (L eq ), day-night noise levels (L DN ) and noise limit exceedance factor (NEF) during day and night time of working and non-working days in four different area categories, viz. industrial, commercial, residential and silence zones. Present study shows that silence zones have been the worst affected areas where noise pollution levels and NEF indicate excessive violation of permissible noise limits due to unplanned, congested and unruly spaces for developmental and commercial activities, followed closely by residential and commercial zones. Cities with separate industrial and commercial zones showed less noisy surroundings in comparison with those cities where land use pattern of industrial and commercial zones is around or overlapping each other. It can thus be concluded that appropriate demarcation and planned use of city space is important to avoid exposure to rising noise pollution levels. Based on the noise pollution in (MMR), various control measures are suggested including awareness campaign and strict compliance of the rules and regulations.

Noise level assessment of a fully residential academic campus of the National Institute of Technology Kurukshetra, Haryana (India) has been presented in this paper. Weekday and weekend noise levels at 39 key locations in various functional areas (29 academic, 3 sensitive, 3 residential, 3 commercial and 1 outdoor activity) were measured, analysed, and compared with Indian standards for day and night time. The average equivalent continuous noise level ( L Aeq ) values on weekdays during day time in academic (instructional), sensitive, residential, commercial, and outdoor activity areas were 65.88, 57.44, 56.00, 63.90 and 51.30 dB respectively; and during night time 47.70, 40.86, 56.72, 49.73 and 45.20 dB respectively. The average L Aeq values on the weekend during the day time in academic, sensitive, residential, commercial, and outdoor activity areas were 57.73, 54.98, 55.49, 61.98 and 54.20 dB respectively; and during night time 45.77, 41.69, 50.84, 49.66 and 45.80 dB respectively. The noise levels were observed to be generally within the permissible limits in the commercial and outdoor activity areas; but exceeding the permissible levels in the academic area, sensitive areas (except central park) and residential areas during day time and night time on weekdays as well as weekends. The average L Aeq values for the entire campus as one educational unit on weekdays during day time (64.98 dB), weekday night time (49.49 dB), weekend day time (57.92 dB) and weekend night time (46.69 dB) were also observed to be 29.96%, 23.72%, 15.85% and 16.72% respectively higher than the prescribed standards for educational/ academic campuses in India. The spatial noise map of the campus prepared by using ArcGIS software revealed noise hotspots in academic areas, in boy’s and girl’s hostel complexes, market complex, traffic junctions/crossings, and parking area near the main entrance of the Institute.

Traffic noise is a significant source of noise pollution, disrupting urban environments with fluctuating sound. The existing research on traffic noise prediction predominantly focuses on statistical methods to identify significant predictors affecting noise levels. While these approaches offer valuable insights, they often lack the interpretability and adaptability needed for complex urban environments. The proposed framework is aimed at presenting the insights of explainable AI (XAI) for the regression analysis of traffic noise levels which is predicted with the help of advanced machine learning (ML) models such as K-Nearest Neighbor (KNN), Extreme Gradient Boosting (XGBoost), Long-Short Term Memory (LSTM) and Random Forest (RF). Statistical analysis of these models was tested with a performance matrix by utilizing a comprehensive traffic dataset of Dhanbad city that includes vehicle speed and categories of vehicle type. Notably, the RF model excelled over other models with an RMSE of 1.27 and of 0.94. The XAI model was developed with the base of RF regressor which records the highest score. The analysis revealed that the number of 2-wheeler vehicle categories is a key predictor of traffic noise levels. The finding of this study can act as an automated information system for the benefit of the urban planners and decision-making bodies to mitigate noise pollution effectively in mid-sized cities. It is worth mentioning that the primary purpose of employing multiple ML models (RF, XGBoost, KNN, LSTM) in this study is to conduct a comparative analysis and identify the most suitable algorithm for urban traffic noise prediction in a Tier-2 Indian city.