32,290 research outputs found
Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease
No full textParkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor impairment, as well as tremors, stiffness, and rigidity. Besides the typical motor symptomatology, some Parkinsonians experience non-motor symptoms such as hyposmia, constipation, urinary dysfunction, orthostatic hypotension, memory loss, depression, pain, and sleep disturbances. The correct diagnosis of PD cannot be easy since there is no standard objective approach to it. After the incorporation of machine learning (ML) algorithms in medical diagnoses, the accuracy of disease predictions has improved. In this work, we have used three deep-learning-type cascaded neural network models based on the audial voice features of PD patients, called Recurrent Neural Networks (RNN), Multilayer Perception (MLP), and Long Short-Term Memory (LSTM), to estimate the accuracy of PD diagnosis. A performance comparison between the three models was performed on a sample of the subjects’ voice biomarkers. Experimental outcomes suggested that the LSTM model outperforms others with 99% accuracy. This study has also presented loss function curves on the relevance of good-fitting models to the detection of neurodegenerative diseases such as PD
Variations on the Author
No full text“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Real-time Vehicle Detection and Classification on the Padma Multipurpose Bridge in Bangladesh Using a Deep Learning Model
No full textRapid and accurate recognition and classification of vehicles are essential for the Intelligent Transportation System (ITS) of Bangladesh. The paper presents a deep learning-based object detection model called Vehicle-YOLOv7 that can detect and classify moving vehicles in real-time on the Padma Multipurpose Bridge (PMB) in Bangladesh. Initially, six hundred-fifty-five (655) still pictures and a video frame containing vehicle images: Bus, Microbus, Car, Truck, Minitruck, Pickup, and Trailer are collected from the PMB to create an original PMB-vehicle image dataset. Thereafter, pre-processing techniques and augmentation processes were employed to produce a training dataset of 7205 image samples. The model was trained and tested using 80% and 20% of the images respectively. Two variations of the YOLOv7 model were evaluated. The Vehicle-YOLOv7 (i.e., YOLOv7x) model performed better than the YOLOv7 model and other state-of-the-art vehicle identification models. The proposed model attained accuracy (A), precision (P), Recall (R), F1-score, and mean-average-precision (mAP) of 98.12%, 97.20%, 98.0%, 96.80%, and 96.86%, respectively. The model accurately detected vehicles with a bounding box and showed detection score and classified the moving vehicles into eight classes: Bus, Microbus, Car, Truck, Minitruck, Motorcycle, Pickup, and Trailer. In addition, the proposed model automatically calculated the vehicles' toll, which reduces the complexity of toll collection by ITS. Therefore, the Vehicle-YOLOv7 detection model is a trustworthy method that can be used to detect and classify the vehicles in the ITS of Bangladesh.No Full Tex
Climate model results of Fram Strait and Greenland-Scotland Ridge gateway sensitivity studies of COSMOS in NetCDF format
No full textHerein, we publish the simulated global annual mean temperature (THO), salinity (SAO), ice compactness (SICOMO), Atlantic Meridional Overturning Circulation (AMOC), Global Meridional Overturning Circulation (GMOC), zonal velocity (UKO), meridional velocity (VKE), 10m u-velocity (u10), 10m v-velocity (v10), mixed layer depth (zmld), horizontal barotropic streamfunction (PSIUWE) and sealevel (ZO) over a time period of 100 years retrieved from equilibrium climate simulations for the Miocene (~23-15 Ma) and use different Greenland-Scotland Ridge (GSR) and Fram Strait (FS) sill depths as a representative for different tectonic settings that occur during the subsidence interval and utilized in the publication by Hossain et al. (2020). The climate data has been produced with COSMOS (ECHAM5/JSBACH/MPIOM/OASIS3), utilized at a resolution of T31 in the atmosphere (19 hybrid sigma-pressure levels) and a resolution of GR30 (bipolar orthogonal curvilinear grid, formal resolution of ~3.0°x1.8°) in the ocean (40 z-coordinate levels). The model setup refers to boundary conditions (incl. changes in orography, bathymetry, physical land surface characteristics, ice sheets, atmospheric CO2) representative for the Miocene. Details on setup and identifiers of Miocene model simulations can be found in Table 1 and Supplementary Table 1 of Hossain et al., 2020
Control strategy review for hydrogen-renewable energy power system
No full textHydrogen is emerging as a crucial component for the advancement and integration of renewable energy sources (RESs) within modern power systems. It plays a vital role as an energy storage system (ESS), ensuring stability and reliability in the power grid. Due to its high energy density, large storage capacity, and fast operational capabilities, hydrogen is rapidly gaining popularity as a preferred choice among other ESSs. In a hydrogen energy system, hydrogen stored in the hydrogen storage system is converted into direct current (DC) power by a hydrogen fuel cell during energy shortages in the power system. Conversely, an electrolyzer converts excess power from the grid into hydrogen, which is stored in the hydrogen storage system. These operations necessitate the implementation of various control systems to facilitate the connection of fuel cells and electrolyzers to the power grid. These control systems include power electronic converters and DC link regulation control systems. This review article presents a comprehensive examination of the current challenges related to the control aspects of integrating hydrogen energy storage technologies into modern power grids. It provides an in-depth analysis of the advancements and deployments of control systems associated with these technologies, along with the barriers and prospects they entail. By focusing on the integration of renewable energy sources, this study aims to assist researchers, engineers, and policymakers in gaining a comprehensive understanding of the current state and future possibilities of hydrogen energy storage systems.No Full Tex
DC-link voltage regulation of inverters to enhance microgrid stability during network contingencies
No full textEqual power-rating inverters operating with different power set-points in either an islanded or grid-connected mode may lead to inter-unit circulating power caused by a large mismatch between power generation and demand during network contingencies (faults on the heavy load side or unintentional islanding). This circulating power may violate the dc-link voltage limit and, as a result, the protection scheme may shut down the inverter and reduce the microgrids reliability. This paper proposes a regulator for controlling the dc-link voltage of the microgrid's inverter during a period of circulating power. It includes a discharging resistor with a series-connected switch across the dc-link capacitor which is turned on through a control algorithm if the dc-link voltage exceeds its pre-defined limit. Case studies of parallel-connected inverters are conducted and their stability assessed through a small-signal analysis. In addition, a realistic microgrid is designed as a low-voltage (LV) network and tested to verify the concept and regulator actions presented. The simulation results validate the effectiveness of the proposed regulator during network contingencies.Full Tex
Climate model results of different Miocene and Preindustrial atmospheric CO2 concentrations experiments of AWI-ESM2 in NetCDF format
No full textHerein, we publish the simulated global annual mean surface air temperature (SAT), sea surface temperature (SST), sea surface salinity (SSS), sea ice cover (seaice), surface albedo (albedo) and total cloud cover (aclcov) over a time period of 100 years retrieved from equilibrium climate simulations for the Middle Miocene and Preindustrial. We simulate Miocene and Preindustrial climate states at different atmospheric CO2 concentrations. The model data has been used in the publication by Hossain et al., 2022. The climate data has been produced with AWI Earth System Model (AWI-ESM2.1; ECHAM6/JSBACH/MPIOM2/ OASIS3‐MCT), utilized at a spectral resolution of T63 (~1.88° x 1.88°) in the atmosphere with 47 vertical layers. FESOM2 uses the COREII mesh. The Miocene model setup is based on the combined high-resolution (0.1° x 0.1°) global bathymetry and topography (Middle Miocene; ~14 Ma) of Paxman et al. (2019), Hochmuth et al. (2020) and Straume et al. (2020). The model setup refers to boundary conditions (incl. changes in orography, bathymetry, physical land surface characteristics, ice sheets, atmospheric CO2) representative for the Miocene and Preindustrial. Details on setup and identifiers of Miocene and Preindustrial model simulations can be found in Table 1 of Hossain et al., 2022
Climate model results of Fram Strait widening sensitivity studies of COSMOS in NetCDF format
No full textHerein, we publish the simulated global annual mean sea surface salinity (SAO), sea surface temperature (THO), ice compactness (SICOMO), zonal velocity (UKO), meridional velocity (VKE) and Atlantic Meridional Overturning Circulation (AMOC) over a time period of 100 years retrieved from equilibrium climate simulations for the Miocene (~23-15 Ma). We investigate the sensitivity of stratification in the Arctic Ocean to the widening of Fram Strait (FS) and different levels of atmospheric CO2 concentrations. The model data has been used in the publication by Hossain et al., 2020. The climate data has been produced with COSMOS (ECHAM5/JSBACH/MPIOM/OASIS3), utilized at a resolution of T31 in the atmosphere with 19 vertical layers and a resolution of GR30 (~3.0°x1.8°) in the ocean with 40 vertical layers. The model setup refers to boundary conditions (incl. changes in orography, bathymetry, physical land surface characteristics, ice sheets, atmospheric CO2) representative for the Miocene. Details on setup and identifiers of Miocene model simulations can be found in Table 1 of Hossain et al., 2020
Recent changes in ecosystem services and human well-being in the Bangladesh coastal zone
No full textThis study takes an historical approach in order to establish how the form and function of the social-ecological system that represents the Bangladesh south-western coastal zone has changed over recent decades. Time series data for a range of ecosystem services and drivers are analysed to define the range of trends, the presence of change points, slow and fast variables and the significant drivers of change. Since the 1980s, increasing gross domestic product and per capita income mirror rising levels of food and inland fish production. As a result, the size of population below the poverty line has reduced by ~17 %. In contrast, non-food ecosystem services such as water availability, water quality and land stability have deteriorated. Conversion of rice fields to shrimp farms is almost certainly a factor in increasing soil and surface water salinity. Most of the services experienced statistically significant change points between 1975 and 1980, and among the services, water availability, shrimp farming and maintenance of biodiversity appear to have passed tipping points. An environmental Kuznets curve analysis suggests that the point at which growing economic wealth feeds back into effective environmental protection has not yet been reached for water resources. Trends in indicators of ecosystem services and human well-being point to widespread non-stationary dynamics governed by slowly changing variables with an increased likelihood of systemic threshold changes/tipping points in the near future. The results will feed into simulation models and strategies that can define alternative and sustainable paths for land management
Recommendation domains for pond aquaculture: country case study: development and status of freshwater aquaculture in Bangladesh
No full textThis report is an output of the project ôDetermination of high-potential aquaculture development areas and impact in Africa and Asiaö. This monograph is the case study for Bangladesh. Written in three parts, it describes the historical background, practices, stakeholder profiles, production levels, economic and institutional environment, policy issues, and prospects for aquaculture in the country. First, it documents the history and current status of the aquaculture in the country. Second, it assesses the technologies and approaches that either succeeded or failed to foster aquaculture development and discusses why. Third, it identifies the key reasons for aquaculture adoption.Freshwater aquaculture, Economic analysis, Trade, Ecosystems, Pond culture, Fish consumption, Food security, Policies, Regulations, Legislation, Socioeconomic aspects, Yield, Bangladesh,
- …
