Individual Locations Research Articles

The comparison and processing of Electromyography (EMG) signals under different actions

The experiment first investigates the working principle and the applications of Electromyography (EMG). Then, the effect of electrode location and electrode size on the EMG signal is explored by the raw data and theory. The reasons for choosing generic surface Ag/AgCl adhesive electrodes are also described. After obtaining the raw EMG signals, suitable data processing methods, such as Root Mean Square (RMS) and digital filtering are applied to generate signals that can drive the motor of a prosthetic arm. The results obtained by the two methods are also compared, where RMS can provide larger peak and mean values, and the digital filtering method can minimise the phase shift. Finally, the limitations of the EMG for prostheses are also analysed by three aspects: different flexion forces, individual finger motion and different reference locations.

Validation of the lead-in method in a practical shooting scenario.

The ability to determine bullet trajectories after a shooting incident can allow investigators to reconstruct the locations of individuals and the sequence of events that took place. By using trajectory rods, investigators can be provided with an immediate visual estimate as to what the path of the projectile may have been. In certain instances, the use of the probing method with trajectory rods is not appropriate due to their being a single, thin target material, or no secondary bullet impact site. In these cases, other methods such as the lead-in or the ellipse method may be useful. Overall, the lead-in method has not been well studied in the application to practical scenarios, such as those including bullet impacts on vehicle metal surfaces. This study has explored the accuracy of the lead-in method when a bullet impacts a typical vehicle metal surface using three firearm calibers, three blind participants, and two non-blind participants. The results of this study have shown that each caliber has its own characteristic error curve. In general, it was found that the lower the impact angle, the less errors were made by the participants. As the impact angle increases, the measurement errors increased, due to the smaller lead-in area present. The errors were found to have a wide range, with some being as low as 1° and some being as high as 13.9°. Further, it was found there was no significant effect on the errors of blind versus non-blind participants.

Relationship of skin complexion with gingival tissue color and hyperpigmentation. A multi-ethnic comparative study

Background and ObjectiveThe most frequently seen intra-oral soft tissue is the gingiva. Most often, it is seen as coral-pink tissue that surrounds the neck of the teeth. Gingiva that encircles the tooth necks and covers the alveolar processes of the jaws is an intra-oral tissue that exhibits biomimetic features. The wide range of colors of the gingiva depends on the configuration of gingival vascularity, the degree of epithelial cornification, level of melanogenesis, and the depth of epithelialization. However, the color of the gingiva varies depending on the degree of melanin pigmentation. The current study aimed to identify the different distribution patterns of gingival color and determine the correlation between skin color, gender, and geographical area of origin.Materials and methodsA total of 839 subjects were involved in the study where the gingival color and skin tone were measured using the Dummett-Gupta Oral pigmentation Index (DOPI) combined with VITA VMK MASTER and skin shade method developed by Revlon (USA) and L’Oreal (France) for makeup foundation shades. One investigator was calibrated for the examination of the colors after being tested for normal color vision and color aptitude using the line test.ResultsA significant association was found between skin color and gingival pigmentation (χ2 value (6) = 114.48; P = 0.001). It was also found that females (67.1%) significantly had darker gingiva than males (58.3%). The study statistics display that location of the individual was also statistically associated with melanin pigmentation of the gingiva (χ2 value (57) = 559.33; P = 0.001).ConclusionThe study concluded that gender, skin color, and individual location are significantly associated with gingival melanin pigmentation.

Congestion-aware Stackelberg pricing game in urban Internet-of-Things networks: A case study

We consider a one-leader multi-follower Stackelberg pricing game in urban Internet-of-Things networks. The leader manages multiple services and sets service prices to maximize profit, while followers seek the most cost-effective services, taking into account service prices, service congestion, and individual locations. Existing approaches often simplify the game process by neglecting followers’ locations, but they are not applicable to real-world complex spatial distributions. In this paper, we focus on the congestion-aware Stackelberg pricing game in urban Internet-of-Things networks, using electric vehicle charging as a case study. The game is reformulated as a mathematical program with equilibrium constraints (MPEC) that considers both congestion effects and followers’ spatial distributions. To solve the MPEC, we introduce the Segmentation-based Pricing with ITERative Optimization (SPITER) algorithm, which converges to a local maximum. Additionally, optimization techniques are developed to improve the performance of solving SPITER in urban environments. We evaluate the performance of SPITER using extensive experiments with two real-life urban datasets, demonstrating the advantages of our model and illustrating SPITER’s effectiveness and convergence.

Optimization of Cabin Virus Transmission Suppression Technology Based on Hanging Curtain Physical Isolation

This study presents an innovative physical isolation measure for commercial scenarios, namely, hanging curtains, to prevent the spread of respiratory infections. Using computational fluid dynamics simulation techniques, the closed spaces within cruise cabins were modeled and numerically analyzed, focusing on the dispersion characteristics of droplets. Additionally, orthogonal methods were employed to investigate various arrangements of hanging curtains and their effects on droplet dispersion based on spatial positioning. The research findings indicated that hanging curtains can effectively alter the airflow within a space, realizing the innovative concept of localized pollutant containment. It was found that the spatial partitioning method based on the location of individuals contributes more to reducing droplet dispersion than other methods. Moreover, the sag height of curtains emerges as the most influential factor on individual infection risk, while the scheme for hanging curtain positions has the least impact. Finally, the optimal configuration recommendation is provided: a curtain bottom coordinate of Z = 2.3 m and a top coordinate of Z = 2.8 m when the infection source was positioned at the center of the space. This configuration has also been validated by varying the location of the infection source. The research findings provide valuable insights for formulating preventive measures for passengers on cruise ships and for pandemic control in similar scenarios.

Power and vertical locations: A socioecological perspective

High-rise construction increasingly dominates the contemporary urban landscape. We show that the physical built environment is linked to lay theories about social power. In five experiments (N = 1091), we comprehensively test the bi-directional causal link between floor location in high-rises and perceived social power. First, using immersive virtual reality (VR) experience of floor location within a physical urban environment (Experiment 1) and traditional experimental designs (Experiments 2–3), we demonstrate that information about a person's floor location affects perceptions regarding that individual's social power. Second, we find that information about a person's social power influences inferences about that individual's location on higher floors (Experiment 4) and encourages greater monetary outlays for the higher locations of powerful employees (Experiment 5). These findings carry important implications for social hierarchies and inequality, individual choices and policy implications in the urban environment, and the use of VR in environmental perception and cognition research.

Global Warming and Anthropogenic Emissions of Water Vapor.

The two major components of greenhouse gases, CO2 and water, are indispensable for sustaining life on Earth. Water vapor is the most significant greenhouse gas that has provided the earth with an "atmospheric blanket" and prevented the surface of the earth from freezing. However, contemporary climate models largely consider the influence of water vapor as a factor within positive feedback loops, while the possibility of direct anthropogenic emissions of water vapor as primary drivers of global warming remains underexplored. In particular, a common assumption has been that the global atmospheric water vapor will increase by about 6 to 7% in response to each 1 °C of warming caused by the nonaqueous greenhouse gases in accordance with the Clausius-Clapeyron equation, and this increased moisture content will lead to an increased greenhouse gas effect. However, the Clausius-Clapeyron equation is based on two-phase equilibrium, and there is no a priori physical basis that it can be applied to the earth's climate for which the water vapor does not always coexist with a condensed phase. Here, we utilized global specific humidity data from the NCEP/NCAR reanalysis data set to examine whether the Clausius-Clapeyron equation can form a basis for such positive feedback commonly assumed in the contemporary climate models. Our results show (1) qualitiatively, the linear nature of the Clausius-Clapeyron equation demonstrates a significant level of consistency when averaged over expansive regions like specific latitudes around the globe, (2) this consistency does not extend to individual locations where a plot of (ln Pv) vs (1/T) becomes nonlinear, indicating substantial undersaturation that varies with time, (3) quantitatively, the discrepancies between the observed and the expected values of the slopes are wide-ranging, and (4) the absolute amount of water vapor increased substantially above the population centers and the agricultural areas in the Northern Hemisphere between 1960 and 2020. Human activities appear to have substantial impacts on the local water vapor content in the atmosphere. Once we assume that anthropogenic emissions of water vapor are the source of local water vapor content in the atmosphere, it can, together with the air circulation patterns (Hadler, Ferrel and polar), provide an explanation for the observations that Arctic ice has been melting at a much more accelerated rate than Antarctic ice.

Home alone: Evaluating the implications of government mandates and disease prevalence on time usage during the pandemic

During the COVID-19 pandemic governments and individuals alike faced incentives to limit the spread of the disease. Our objective is to assess the extent to which government mandates and private actions influenced time allocated to specific activities and the social interactions of individuals. Information on how individuals spent their time before and during the early stages of the pandemic come from the American Time Use Survey (ATUS), which identifies time use for a 24-hour period and includes each individual's activities, locations and companions. We combine the time diary data with data on state-level restrictions from the Kaiser Family Foundation and state-level COVID-19 infection and death rates from Johns Hopkins University. Our findings suggest that private actions in response to reported death rates are comparable to the effects of state-level public mandates on the outcome variables of time alone and time at home. In evaluating effects based on sex and age, we find that young males experienced the largest disruption in time use, significantly changing both their location and their companions. We also find important age profile differences between males and females.

The Epidemiology of Lower Limb Fractures: A Major United Kingdom (UK) Trauma Centre Study.

Understanding the epidemiology and incidence of fractures can help inform policymakers and clinicians about the needs of the population and highlight trends over time, allowing for tailoring of healthcare delivery to the population. This study reports on the lower limb fractures treated at a major trauma centre over a seven-year period. We collected data on fracture locations, age, gender, BMI, hospital admission length, and treatment options of all lower limb fractures treated at a level I trauma centre from January 2015 to December 2021. We included data on the femur, tibia, and fibula, which were each split up into distinct regions.Fractures were subdivided by location and graphed, separated by gender, over age group. Finally, each location area's frequency was graphed over the entire study period. A total of 8,511 patients sustained 8,613 fractures, given an overall incidence of 215.9 fractures per 100,000 patients per year. The mean age was 62.3 years, and 56.3% of patients were female. Fractures of the peri trochanteric region of the femur had the highest mean average age (79.9 years), which was closely followed by fractures of the head and neck of the femur (78.2 years). Fractures of the head and neck of the femur and the peri trochanteric region of the femur also had the highest proportion of females suffering from these fractures (67 and 66% female, respectively). Femur shaft fractures had the lowest average age (36.5 years) and the lowest proportion of female patients (29%). On graphing by location, separated by gender, over age group, overall fractures showed a bi-peak distribution of younger males and older, post-menopausal females having their respective peaks. Three further distinct distributions were observed in individual location fractures. Identifying the relative incidence and demographic associations with lower limb fractures helps highlight a changing population's needs. There is an absence of such study in literature in the United Kingdom (UK) since 2006. Our study's insights and results aid clinicians and policymakers in the creation of guidelines and the distribution of resources based on the most recent information and elucidate changing healthcare service needs for the population.

Changes in spatial self-consciousness elicit grid cell–like representation in the entorhinal cortex

Grid cells in the entorhinal cortex (EC) encode an individual's location in space, integrating both environmental and multisensory bodily cues. Notably, body-derived signals are also primary signals for the sense of self. While studies have demonstrated that continuous application of visuo-tactile bodily stimuli can induce perceptual shifts in self-location, it remains unexplored whether these illusory changes suffice to trigger grid cell-like representation (GCLR) within the EC, and how this compares to GCLR during conventional virtual navigation. To address this, we systematically induced illusory drifts in self-location toward controlled directions using visuo-tactile bodily stimulation, while maintaining the subjects' visual viewpoint fixed (absent conventional virtual navigation). Subsequently, we evaluated the corresponding GCLR in the EC through functional MRI analysis. Our results reveal that illusory changes in perceived self-location (independent of changes in environmental navigation cues) can indeed evoke entorhinal GCLR, correlating in strength with the magnitude of perceived self-location, and characterized by similar grid orientation as during conventional virtual navigation in the same virtual room. These data demonstrate that the same grid-like representation is recruited when navigating based on environmental, mainly visual cues, or when experiencing illusory forward drifts in self-location, driven by perceptual multisensory bodily cues.

Sediment particle tracking data for the Carpathian reservoir under climate and land use change scenarios

AbstractAlthough the Carpathian Mts. area is considered as extremely prone to surface erosion which results in capacity loss of the dammed reservoirs, a lack of data to follow details of this process is perceivable. The research of the selected sediment fractions transport tracking was conducted using the capabilities of the digital platform—Macromodel DNS (Discharge‐Nutrient‐Sea) for the catchment with drinking water reservoir in the Polish part of Western Carpathian. The continuity of sediment transport simulation in two hydrologically different elements of the catchment—the river and the reservoir—was possible due to consolidation of two models in the platform—SWAT (Soil & Water Assessment Tool) and AdH/PTM (Adaptive Hydraulics Model/Particle Tracking Model). The result of those modules' integration was a database for tracking the individual sediment fractions delivered to the reservoir and deposited in specific reservoir zones. The implementation of climate and land use change scenarios allowed additionally to analyse the estimation of those processes in the future. The simulation outcomes consist of daily flows and monthly sediment loads at the reservoir inflow and the individual sediment particle fractions deposition location inside of the reservoir.

Proactive safety assessment of urban through-roads based on GPS data

Road safety is a worldwide issue, while urban roads account for a high share of serious road injuries, especially involving vulnerable road users, such as pedestrians or cyclists. Specifically, the safety of major roads through built-up areas (through-roads) is insufficient due to mixed traffic conditions including vulnerable road users, varying driving behaviour, and many disruptions, which are combined with excessive speed.. In this context, various traffic calming measures have been implemented to improve road safety, such as gateways or pedestrian refuge islands. However, the specific safety impacts of traffic calming combined with specific characteristics of through-roads are often unknown, since most traditional evaluations have been limited by small sample sizes of crash data, as well as wide variations in physical and road characteristics. To overcome the limitations of crash-based evaluations, we used the GPS-based data from a sample of 21 Czech and 12 Polish through-roads to develop the Speed-Safety Index, which combines speed, speed variance, and traffic volume. Our study has three novelty features: (1) To assess safety, we used speed and speed variance simultaneously. (2) To complete the missing link between specific traffic calming measures and safety, we validated the statistical relationship between the developed Speed-Safety Index and crash history. (3) To prove the usefulness of the developed index, we also showed its practical interpretation by proving the effect of spacing between traffic calming measures on safety. The index proved to be well correlated to crash frequency and it also proved the effect of spacing between traffic calming measures: the longer spacing, the smaller speed-reducing effect. The paper concludes with a discussion on the limitations, which we plan to address in further research, by moving from the current macro-perspective (Speed-Safety Index on the level of through-roads) to the micro-perspective (focusing on individual directions, locations, and traffic calming measures). We also plan to investigate the method’s applicability in different contexts. If the approach proves feasible, with reliable and valid results, it may become an alternative for a proactive network-wide road assessment, as called for by the European Road Infrastructure Safety Management Directive.

Using Co-Ordinate Systems in Hedonic Housing Regressions

Hedonic house price studies typically incorporate information about location by including either a set of dummy variables to represent individual locations called “neighborhoods” or by using a set of distance (or travel time) variables to characterize locations in terms of proximity to amenities and dis-amenities. As an alternative to these, relatively recent research advocates a latitude–longitude co-ordinate system for incorporating distance information into hedonic house price regressions. This study shows that many of the claims made in this research, particularly those referencing the elimination or diminution of “biases of coefficients of non-distance variables”, are given the particulars of the Monte Carlo experiments, not possible to investigate. We further show, both analytically and with our simulations, that there is no omitted variable bias present in their simulations because their randomly generated non-distance variable is uncorrelated with any of the other variables used in their regression models.

Satellite Hyperspectral Nighttime Light Observation and Identification with DESIS

The satellite imagery of nighttime lights (NTLs) has been studied to understand human activities, economic development, and more recently, the ecological impact of brighter night skies. The Visible Infrared Imaging Radiometer Suite (VIIRS) Day–Night Band (DNB) offers perhaps the most advanced nighttime imaging capabilities to date, but its large pixel size and single band capture large-scale changes in NTL while missing granular but important details, such as lighting type and brightness. To better understand individual NTL sources in a region, the spectra of nighttime lights captured by the DLR Earth Sensing Imaging Spectrometer (DESIS) were extracted and compared against near-coincident VIIRS DNB imagery. The analysis shows that DESIS’s finer spatial and spectral resolutions can detect individual NTL locations and types beyond what is possible with the DNB. Extracted night light spectra, validated against ground truth measurements, demonstrate DESIS’s ability to accurately detect and identify narrow-band atomic emission lines that characterize the spectra of high-intensity discharge (HID) light sources and the broader spectral features associated with different light-emitting diode (LED) lights. These results suggest the possible application of using hyperspectral data from moderate-resolution sensors to identify lamp construction details, such as illumination source type and light quality in low-light contexts. NTL data from DESIS and other hyperspectral sensors may improve the scientific understanding of light pollution, lighting quality, and energy efficiency by identifying, evaluating, and mapping individual and small groups of light sources.

Fitness benefits of grouping during foraging in beef cattle: Social behaviour or affinity to vegetation resources?

Grouping behaviour in gregarious species expresses a dynamic cost-benefit equilibrium. The balance between costs and benefits differs amongst individuals that were selected to maximize their individual fitness. In environments where resources are limited, benefits of grouping may come at the expense of increased competition over resources. This study aimed to test whether grouping behaviour during foraging in a free-ranging beef cattle herd is a social choice bearing fitness benefits for all participants, or reflects affinity to vegetation resources with possible differentiating fitness benefits. GPS location data were recorded in a herd of 60 beef cows grazing a semi-arid pasture in northern Israel. Pasture vegetation was chemically and spectrally analysed. GPS location data were used to investigate individual and shared foraging locations and the temporal sequence of initiating foraging movement. Co-travel function in ArcPro v3.0 was used to investigate the amount and variability of individual proximity associations and their correlation with fitness. Fitness proxies were conception result (yes/no) and the interval between calving and conception within the cows who conceived. A positive correlation was found between fitness and the individual number of proximity associations, but not with the variability in associations' partners. No significant correlations were found between fitness and vegetation biomass, N content and spectral properties measured by REEVI2 index in foraging locations. Individual sequence of arrival at shared foraging locations and foraging movement initiation sequence were also not correlated with fitness. Vegetation biomass in grouping locations was lower than in individually foraged locations, but no difference was found in N content between individual and shared foraging locations. No differences were found in vegetation biomass and N content between herd foraging locations and random locations, thus no evidence for herd foraging strategy aimed to increase biomass or N consumption was found. No further differences in pasture resources availability, i.e., water, shade, human or predator presence could explain grouping. Circular variance values implied the absence of preferred movement direction. Our results suggest that grouping during foraging is fitness beneficial and is not related to vegetation biomass or N content. Our results further suggest the absence of consistent leading individuals and no significant correlations between foraging movement initiation and fitness. This study provides insights into social and vegetation factors affecting cattle foraging behaviour in constrained pasture, and may allow ranchers to improve grazing management systems. We suggest that further research into pasture characteristics that affect beef cattle pasture location choice is needed.

One small step for a robot, one giant leap for habitat monitoring: A structural survey of EU forest habitats with Robotically-mounted Mobile Laser Scanning (RMLS)

EU States are mandated by the 92/43/EEC Habitats Directive to generate recurring reports on the conservation status and functionality of habitats at the national level. This assessment is based on their floristic and, especially for forest habitats, structural characterization. Currently, habitat field monitoring efforts are carried out only by trained human operators. The H2020 Project “Natural Intelligence for Robotic Monitoring of Habitats – NI” aims to develop quadrupedal robots able to move autonomously in the unstructured environment of forest habitats. In this work, we tested the locomotion performance, efficiency and the accuracy of a robot performing structural habitat monitoring, comparing it with traditional field survey methods inside selected stands of Luzulo-Fagetum beech forests (9110 Annex I Habitat). We used a quadrupedal robot equipped with a Mobile Laser Scanning system (MLS), implementing for the first time a structural monitoring of EU forest habitats with a Robotically-mounted Mobile Laser Scanning (RMLS) platform. Two different scanning trajectories were used to automatically map individual tree locations and extract tree Diameter at Breast Height (DBH) from point clouds. Results were compared with field human measurements in terms of accuracy and efficiency of the survey. The robot was able to successfully execute both scanning trajectories, for which we obtained a tree detection rate of 100 %. Circular scanning trajectory performed better in terms of battery consumption, Root Mean Square Error (RMSE) of the extracted DBH (2.43 cm or 10.73 %) and prediction power (R2adj = 0.72, p < 0.001). The RMLS platform improved survey efficiency with 19.31 m2/min or 1.77 trees/min in comparison with 3.45 m2/min or 0.32 trees/min of traditional survey. Finally, a processing script was developed to allow the repeatability of RMLS surveys in similar habitat monitoring missions. In the future, a human-robotic monitoring framework might represent an accurate support for those repetitive and time-consuming activities in habitat monitoring, offering a valuable benefit for biodiversity conservation.

Quantitative and qualitative yield loss caused by red deer (Cervus elaphus L.) grazing on permanent organic grasslands

ABSTRACT This paper addresses yield loss due to red deer (Cervus elaphus) grazing on permanent grasslands on three organic farms in SE Slovenia over two consecutive years. Deer graze on permanent grasslands throughout the year, but the resulting crop loss varies during the growing season. Accounting for three mowings, the quantitative yield loss due to deer grazing totalled 48–52%, or 3.9–4.3 t/ha. Deer had the highest consumption capacity in the spring (first mowing: yield loss of 1.7–1.9 t of air-dried hay/ha), and towards the end of the growing season, consumption decreased (third mowing: loss of 0.9 t/ha). A floristic inventory indicated low species diversity and production in permanent grasslands in SE Slovenia. The crude protein content in unprotected plots was generally greater than that in protected plots, but due to a large quantitative yield loss, the yield of crude protein and net energy for lactation on heavily grazed land were much lower than those on protected land in all mowings. The average additional cost per unit of heavily grazed area ranged from 182 to 344 EUR/ha, and the differences are the result of the different intensities of game grazing in individual locations and grassland production capacities.

The impact of sampling scale: A comparison of methods for estimating external contaminant exposure in free-ranging wildlife

The impacts of contaminants on wildlife are dose dependent, and thus being able to track or predict exposure following contamination events is important for monitoring ecosystem health. However, the ability to track exposure in free-ranging wildlife is often severely limited. Consequently, researchers have predominantly relied on simple methods for estimating contaminant exposures in wildlife with little regard for spatial contaminant heterogeneity or an animal's use of diverse habitats. We evaluated the influence sampling scale (i.e., how finely contaminant distribution and organism's spatial use of the landscape is mapped) has on (1) realism and (2) conservativeness of exposure estimates. To do this, we monitored the actual exposure of wild boar (Sus scrofa) in Fukushima, Japan to radioactive contamination using GPS-coupled contaminant monitors placed on individual animals. We compared empirical exposures to estimates generated by combining varying amounts of information about an individual boar's location and/or movement, with the distribution of contamination on the landscape. We found that the most realistic exposure estimates were produced when finer-scale contaminant distribution surveys (e.g., airborne surveys) were combined with more accurate estimates of an individual's space use (e.g., home ranges or core areas). Importantly, estimates of exposure based on single point surveys at a trap site (a simple method commonly used in the literature), did not correlate with actual exposure rates, suggesting dose-effects studies using this method may result in spurious conclusions. These results suggest that researchers seeking realistic estimates of exposure, such as in dose-effect studies, should ensure they have adequately accounted for fine-scale contaminant distribution patterns and areas of higher use by study organisms. However, conservative estimates of exposure (i.e., intentionally over-predicting exposure as is done in initial tiers of ecological risk analyses) were not as scale sensitive and could be achieved with a single known location and coarse contaminant distribution maps.

Micro-Credentialing in Hospitality Education: A Human Capital Approach to Combating Human Trafficking

ABSTRACT The benefits of micro-credentialing on topics that promote a more socially conscious and thoughtful university graduate cannot be overstated. Through the lens of human capital theory, this research note extends the application of workplace education beyond financial and productivity growth to include social well-being of the individual, organization, and geographic location with an emphasis on identifying and combating human trafficking. A five module micro-credential was developed to satisfy the knowledge, skills and aptitudes required to help mitigate this increasingly pervasive criminal activity in the hospitality industry. The implications for hospitality educators and professionals include the benefits of an informed hospitality graduate. Theoretically, this type of educational offering extends our understanding of human capital theory.

Multi-task learning using non-linear autoregressive models and recurrent neural networks for tide level forecasting

Tide level forecasting plays an important role in environmental management and development. Current tide level forecasting methods are usually implemented for solving single task problems, that is, a model built based on the tide level data at an individual location is only used to forecast tide level of the same location but is not used for tide forecasting at another location. This study proposes a new method for tide level prediction at multiple locations simultaneously. The method combines nonlinear autoregressive moving average with exogenous inputs (NARMAX) model and recurrent neural networks (RNNs), and incorporates them into a multi-task learning (MTL) framework. Experiments are designed and performed to compare single task learning (STL) and MTL with and without using non-linear autoregressive models. Three different RNN variants, namely, long short-term memory (LSTM), gated recurrent unit (GRU) and bidirectional LSTM (BiLSTM) are employed together with non-linear autoregressive models. A case study on tide level forecasting at many different geographical locations (5 to 11 locations) is conducted. Experimental results demonstrate that the proposed architectures outperform the classical single-task prediction methods.