Search results for: inverse filters

Authors: Aubrey Langeland, Richard Neitzel, Kowit Nambunmee

Abstract:

Electronic waste, ‘e-waste’, refers generally to discarded electronics and electrical equipment, including products from cell phones and laptops to wires, batteries and appliances. While e-waste represents a transformative source of income in low- and middle-income countries, informal e-waste workers use rudimentary methods to recover materials, simultaneously releasing harmful chemicals into the environment and creating a health hazard for themselves and surrounding communities. Valuable materials such as precious metals, copper, aluminum, ferrous metals, plastic and components are recycled from e-waste. However, persistent organic pollutants such as polychlorinated biphenyls (PCBs) and some polybrominated diphenyl ethers (PBDEs), and heavy metals are toxicants contained within e-waste and are of great concern to human and environmental health. The current study seeks to evaluate the environmental contamination resulting from informal e-waste recycling in a predominantly agricultural community in northeastern Thailand. To accomplish this objective, five types of environmental samples were collected and analyzed for concentrations of eight metals commonly associated with e-waste recycling during the period of July 2016 through July 2017. Rice samples from the community were collected after harvest and analyzed using inductively coupled plasma mass spectrometry (ICP-MS) and gas furnace atomic spectroscopy (GF-AS). Soil samples were collected and analyzed using methods similar to those used in analyzing the rice samples. Surface water samples were collected and analyzed using absorption colorimetry for three heavy metals. Environmental air samples were collected using a sampling pump and matched-weight PVC filters, then analyzed using Inductively Coupled Argon Plasma-Atomic Emission Spectroscopy (ICAP-AES). Finally, surface wipe samples were collected from surfaces in homes where e-waste recycling activities occur and were analyzed using ICAP-AES. Preliminary1 results indicate that some rice samples have concentrations of lead and cadmium significantly higher than limits set by the United States Department of Agriculture (USDA) and the World Health Organization (WHO). Similarly, some soil samples show levels of copper, lead and cadmium more than twice the maximum permissible level set by the USDA and WHO, and significantly higher than other areas of Thailand. Surface water samples indicate that areas near e-waste recycling activities, particularly the burning of e-waste products, result in increased levels of cadmium, lead and copper in surface waters. This is of particular concern given that many of the surface waters tested are used in irrigation of crops. Surface wipe samples measured concentrations of metals commonly associated with e-waste, suggesting a danger of ingestion of metals during cooking and other activities. Of particular concern is the relevance of surface contamination of metals to child health. Finally, air sampling showed that the burning of e-waste presents a serious health hazard to workers and the environment through inhalation and deposition2. Our research suggests a need for improved methods of e-waste recycling that allows workers to continue this valuable revenue stream in a sustainable fashion that protects both human and environmental health. 1Statistical analysis to be finished in October 2017 due to follow-up field studies occurring in July and August 2017. 2Still awaiting complete analytic results.

Keywords: e-waste, environmental contamination, informal recycling, metals

Procedia PDF Downloads 347

Authors: Mingxin Li, Liya Ni

Abstract:

Autonomous parking is a valuable feature applicable to many robotics applications such as tour guide robots, UV sanitizing robots, food delivery robots, and warehouse robots. With auto-parking, the robot will be able to park at the charging zone and charge itself without human intervention. As compared to self-driving vehicles, auto-parking is more challenging for a small-scale mobile robot only equipped with a front camera due to the camera view limited by the robot’s height and the narrow Field of View (FOV) of the inexpensive camera. In this research, auto-parking of a small-scale mobile robot with a front camera only was achieved in a four-step process: Firstly, transfer learning was performed on the AlexNet, a popular pre-trained convolutional neural network (CNN). It was trained with 150 pictures of empty parking slots and 150 pictures of occupied parking slots from the view angle of a small-scale robot. The dataset of images was divided into a group of 70% images for training and the remaining 30% images for validation. An average success rate of 95% was achieved. Secondly, the image of detected empty parking space was processed with edge detection followed by the computation of parametric representations of the boundary lines using the Hough Transform algorithm. Thirdly, the positions of the entrance point and center of available parking space were predicted based on the robot kinematic model as the robot was driving closer to the parking space because the boundary lines disappeared partially or completely from its camera view due to the height and FOV limitations. The robot used its wheel speeds to compute the positions of the parking space with respect to its changing local frame as it moved along, based on its kinematic model. Lastly, the predicted entrance point of the parking space was used as the reference for the motion control of the robot until it was replaced by the actual center when it became visible again by the robot. The linear and angular velocities of the robot chassis center were computed based on the error between the current chassis center and the reference point. Then the left and right wheel speeds were obtained using inverse kinematics and sent to the motor driver. The above-mentioned four subtasks were all successfully accomplished, with the transformed learning, image processing, and target prediction performed in MATLAB, while the motion control and image capture conducted on a self-built small scale differential drive mobile robot. The small-scale robot employs a Raspberry Pi board, a Pi camera, an L298N dual H-bridge motor driver, a USB power module, a power bank, four wheels, and a chassis. Future research includes three areas: the integration of all four subsystems into one hardware/software platform with the upgrade to an Nvidia Jetson Nano board that provides superior performance for deep learning and image processing; more testing and validation on the identification of available parking space and its boundary lines; improvement of performance after the hardware/software integration is completed.

Keywords: autonomous parking, convolutional neural network, image processing, kinematics-based prediction, transfer learning

Procedia PDF Downloads 118

Authors: Hassan Sheikh, Mehdi Nilipour, Amiraslan Fila

Abstract:

Many conventional town planning processes do little to give children and young people a voice on what is important about the urban environment. As a result of paying little attention to the children, their physical, social and mental needs are hardly met in urban environments. Therefore, urban spaces are impotent to attract children, while their recreational space has been confined to home or virtual spaces. Since children are just taking the first steps to learn the world beyond house borders, their living environment will profoundly influence almost all aspects of their lives. This puts a great deal of responsibility on the shoulders of planners, who need to balance a number of different issues in urban design to make places more child-friendly. The main purpose of present research is to analyze and plan a child-friendly environment in an on-going urban settlement development for the benefit of all residents. Assessing children’s needs and regard them in development strategies and policies will help to “plan for children”. Following this purpose, based on child-friendly environment studies, indicators of child-friendly environments were collected. Then three distinct characteristics of case study, which are being under-construction, lack of social ties between dwellers and high-rise building, determined seven indicators included basic services, Urban and environmental qualities, Family, kin, peers and community, Sense of belonging and continuity, participation, Safety, security and freedom of movement and human scale. With the survey, Informal observation and participation in small communities, essential data has been collected and analyzed by SPSS software. The field study is Shahid-Keshvari town in Isfahan, Iran. Eighty-six middle childhood, children (ages 8-13) participated. The results show Children's satisfaction is correlated with basic services and the quality of the environment, social environment and the safety and security. The considerable number of children and youth (55%) like to live somewhere other than the town. Satisfaction and sense of belonging and continuity have a strong inverse correlation with age. In other words, as age increases, satisfaction and consequently a sense of belonging will be reduced; thus children and youth consider their future somewhere out of the town. The main reason for dissatisfaction was the basic services and social environment. More than half of children (55%) expressed their wish to develop basic services in terms of availability, hierarchy, and quality. Among all recreational places, children showed more interest to the parks. About three-quarters (76%) considered building a park as a crucial item for residents. The significant number of children (54%) want to have a relationship with more friends. This could be due to the serious shortage of the leisure spaces such as parks or playgrounds. Also, the space around the house or space between the apartments has not been designed for play or children’s activities. Moreover, the presence of strangers and construction workers have a negative impact on children's sense of peace and security; 60% of children are afraid of theft and 36% of children found strangers as a menace. The analysis of children’s issues and suggestions provides an insight to plan and design of child-friendly environment in new towns.

Keywords: child-friendly city (CFC), child-friendly environment, child participation, under-construction environment, Isfahan Shahid-Keshvari Town

Procedia PDF Downloads 355

Authors: Dhekra Khazri, Hakim Gabtni

Abstract:

Because of Sidi Bouzid water table overexploitation, this study aims at integrating geophysical methods to determinate aquifers geometry assessing their geological situation and geophysical characteristics. However in highly tectonic zones controlled by Atlassic structural features with NE-SW major directions (central Tunisia), Bouguer gravimetric responses of some areas can be as much dominated by the regional structural tendency, as being non-identified or either defectively interpreted such as the case of Sidi Bouzid basin. This issue required a residual gravity anomaly elaboration isolating the Sidi Bouzid basin gravity response ranging between -8 and -14 mGal and crucial for its aquifers geometry characterization. Several gravity techniques helped constructing the Sidi Bouzid basin's residual gravity anomaly, such as Upwards continuation compared to polynomial regression trends and power spectrum analysis detecting deep basement sources at (3km), intermediate (2km) and shallow sources (1km). A 3D Euler Deconvolution was also performed detecting deepest accidents trending NE-SW, N-S and E-W with depth values reaching 5500 m and delineating the main outcropping structures of the study area. Further gravity treatments highlighted the subsurface geometry and structural features of Sidi Bouzid basin over Horizontal and vertical gradient, and also filters based on them such as Tilt angle and Source Edge detector locating rooted edges or peaks from potential field data detecting a new E-W lineament compartmentalizing the Sidi Bouzid gutter into two unequally residual anomaly and subsiding domains. This subsurface morphology is also detected by the used 2D seismic reflection sections defining the Sidi Bouzid basin as a deep gutter within a tectonic set of negative flower structures, and collapsed and tilted blocks. Furthermore, these structural features were confirmed by forward gravity modeling process over several modeled residual gravity profiles crossing the main area. Sidi Bouzid basin (central Tunisia) is also of a big interest cause of the unknown total thickness and the undefined substratum of its siliciclastic Tertiary package, and its aquifers unbounded structural subsurface features and deep accidents. The Combination of geological, hydrogeological and geophysical methods is then of an ultimate need. Therefore, a geophysical methods integration based on gravity survey supporting available seismic data through forward gravity modeling, enhanced lateral and vertical extent definition of the basin's complex sedimentary fill via 3D gravity models, improved depth estimation by a depth to basement modeling approach, and provided 3D isochronous seismic mapping visualization of the basin's Tertiary complex refining its geostructural schema. A subsurface basin geomorphology mapping, over an ultimate matching between the basin's residual gravity map and the calculated theoretical signature map, was also displayed over the modeled residual gravity profiles. An ultimate multidisciplinary geophysical study of the Sidi Bouzid basin aquifers can be accomplished via an aeromagnetic survey and a 4D Microgravity reservoir monitoring offering temporal tracking of the target aquifer's subsurface fluid dynamics enhancing and rationalizing future groundwater exploitation in this arid area of central Tunisia.

Keywords: aquifer geometry, geophysics, 3D gravity modeling, improved depths, source edge detector

Procedia PDF Downloads 260

Authors: Tuji Jemal Ahmed, Hussen Beker Yusuf

Abstract:

Food safety is a major concern worldwide, with microbial contamination being one of the leading causes of foodborne illnesses. In Ethiopia, drinking water and untreated groundwater are a primary source of microbial contamination, leading to significant health risks. East Hararghe, Oromia, is one of the regions in Ethiopia that has been affected by this problem. This paper provides an overview of the impact of untreated groundwater on human health in Haramaya Rural District, East Hararghe and highlights the urgent need for sustained efforts to address the water sanitation supply problem. The use of untreated groundwater for drinking and household purposes in Haramaya Rural District, East Hararghe is prevalent, leading to high rates of waterborne illnesses such as diarrhea, typhoid fever, and cholera. The impact of these illnesses on human health is significant, resulting in significant morbidity and mortality, especially among vulnerable populations such as children and the elderly. In addition to the direct health impacts, waterborne illnesses also have indirect impacts on human health, such as reduced productivity and increased healthcare costs. Groundwater sources are susceptible to microbial contamination due to the infiltration of surface water, human and animal waste, and agricultural runoff. In Haramaya Rural District, East Hararghe, poor water management practices, inadequate sanitation facilities, and limited access to clean water sources contribute to the prevalence of untreated groundwater as a primary source of drinking water. These underlying causes of microbial contamination highlight the need for improved water sanitation infrastructure, including better access to safe drinking water sources and the implementation of effective treatment methods. The paper emphasizes the need for regular water quality monitoring, especially for untreated groundwater sources, to ensure safe drinking water for the population. The implementation of effective preventive measures, such as the use of effective disinfectants, proper waste disposal methods, and regular water quality monitoring, is crucial to reducing the risk of contamination and improving public health outcomes in the region. Community education and awareness-raising campaigns can also play a critical role in promoting safe water practices and reducing the risk of contamination. These campaigns can include educating the population on the importance of boiling water before drinking, the use of water filters, and proper sanitation practices. In conclusion, the use of untreated groundwater as a primary source of drinking water in East Hararghe, Oromia, Ethiopia, has significant impacts on human health, leading to widespread waterborne illnesses and posing a significant threat to public health. Sustained efforts are urgently needed to address the root causes of contamination, such as poor sanitation and hygiene practices, improper waste management, and the water sanitation supply problem, including the implementation of effective preventive measures and community-based education programs, ultimately improving public health outcomes in the region. A comprehensive approach that involves community-based water management systems, point-of-use water treatment methods, and awareness-raising campaigns can contribute to reducing the incidence of microbial contamination in the region.

Keywords: food safety, health risks, microbial contamination, untreated groundwater

Procedia PDF Downloads 80

Authors: Manuel de Pazos-Liano, Manuel Cifuentes-Antonio, Juan Fisac-Gozalo, Sara Perales-Momparler, Carlos Martinez-Montero

Abstract:

The first-ever game in the Wanda Metropolitano Stadium, the new home of the Club Atletico de Madrid, was played on September 16, 2017, thanks to the work of a multidisciplinary team that made it possible to combine urban development with sustainability goals. The new football ground sits on a 1.2 km² land owned by the city of Madrid. Its construction has dramatically increased the sealed area of the site (transforming the runoff coefficient from 0.35 to 0.9), and the surrounding sewer network has no capacity for that extra flow. As an alternative to enlarge the existing 2.5 m diameter pipes, it was decided to detain runoff on site by means of an integrated and durable infrastructure that would not blow up the construction cost nor represent a burden on the municipality’s maintenance tasks. Instead of the more conventional option of building a large concrete detention tank, the decision was taken on the use of pervious pavement on the 3013 car parking spaces for sub-surface water storage, a solution aligned with the city water ordinance and the Madrid + Natural project. Making the idea a reality, in only five months and during the summer season (which forced to pour the porous concrete only overnight), was a challenge never faced before in Spain, that required of innovation both at the material as well as the machinery side. The process consisted on: a) defining the characteristics required for the porous concrete (compressive strength of 15 N/mm2 and 20% voids); b) testing of different porous concrete dosages at the construction company laboratory; c) stablishing the cross section in order to provide structural strength and sufficient water detention capacity (20 cm porous concrete over a 5 cm 5/10 gravel, that sits on a 50 cm coarse 40/50 aggregate sub-base separated by a virgin fiber polypropylene geotextile fabric); d) hydraulic computer modelling (using the Full Hydrograph Method based on the Wallingford Procedure) to estimate design peak flows decrease (an average of 69% at the three car parking lots); e) use of a variety of machinery for the application of the porous concrete to achieve both structural strength and permeable surface (including an inverse rotating rolling imported from USA, and the so-called CMI, a sliding concrete paver used in the construction of motorways with rigid pavements); f) full-scale pilots and final construction testing by an accredited laboratory (pavement compressive strength average value of 15 N/mm2 and 0,0032 m/s permeability). The continuous testing and innovating construction process explained in detail within this article, allowed for a growing performance with time, finally proving the use of the CMI valid also for large porous car park applications. All this process resulted in a successful story that converts the Wanda Metropolitano Stadium into a great demonstration site that will help the application of the Spanish Royal Decree 638/2016 (it also counts with rainwater harvesting for grass irrigation).

Keywords: construction machinery, permeable carpark, porous concrete, SUDS, sustainable develpoment

Procedia PDF Downloads 123

Authors: Nicola Colaninno, Eugenio Morello

Abstract:

The urban environment affects local-to-global climate and, in turn, suffers global warming phenomena, with worrying impacts on human well-being, health, social and economic activities. Physic-morphological features of the built-up space affect urban air temperature, locally, causing the urban environment to be warmer compared to surrounding rural. This occurrence, typically known as the Urban Heat Island (UHI), is normally assessed by means of air temperature from fixed weather stations and/or traverse observations or based on remotely sensed Land Surface Temperatures (LST). The information provided by ground weather stations is key for assessing local air temperature. However, the spatial coverage is normally limited due to low density and uneven distribution of the stations. Although different interpolation techniques such as Inverse Distance Weighting (IDW), Ordinary Kriging (OK), or Multiple Linear Regression (MLR) are used to estimate air temperature from observed points, such an approach may not effectively reflect the real climatic conditions of an interpolated point. Quantifying local UHI for extensive areas based on weather stations’ observations only is not practicable. Alternatively, the use of thermal remote sensing has been widely investigated based on LST. Data from Landsat, ASTER, or MODIS have been extensively used. Indeed, LST has an indirect but significant influence on air temperatures. However, high-resolution near-surface air temperature (NSAT) is currently difficult to retrieve. Here we have experimented Geographically Weighted Regression (GWR) as an effective approach to enable NSAT estimation by accounting for spatial non-stationarity of the phenomenon. The model combines on-site measurements of air temperature, from fixed weather stations and satellite-derived LST. The approach is structured upon two main steps. First, a GWR model has been set to estimate NSAT at low resolution, by combining air temperature from discrete observations retrieved by weather stations (dependent variable) and the LST from satellite observations (predictor). At this step, MODIS data, from Terra satellite, at 1 kilometer of spatial resolution have been employed. Two time periods are considered according to satellite revisit period, i.e. 10:30 am and 9:30 pm. Afterward, the results have been downscaled at 30 meters of spatial resolution by setting a GWR model between the previously retrieved near-surface air temperature (dependent variable), the multispectral information as provided by the Landsat mission, in particular the albedo, and Digital Elevation Model (DEM) from the Shuttle Radar Topography Mission (SRTM), both at 30 meters. Albedo and DEM are now the predictors. The area under investigation is the Metropolitan City of Milan, which covers an area of approximately 1,575 km2 and encompasses a population of over 3 million inhabitants. Both models, low- (1 km) and high-resolution (30 meters), have been validated according to a cross-validation that relies on indicators such as R2, Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). All the employed indicators give evidence of highly efficient models. In addition, an alternative network of weather stations, available for the City of Milano only, has been employed for testing the accuracy of the predicted temperatures, giving and RMSE of 0.6 and 0.7 for daytime and night-time, respectively.

Keywords: urban climate, urban heat island, geographically weighted regression, remote sensing

Procedia PDF Downloads 172

Authors: Deon Bezuidenhout

Abstract:

Pre-seeding with autologous endothelial cells improves the long-term patency of synthetic vascular grafts levels obtained with autografts, but is limited to a single centre due to resource, time and other constraints. Spontaneous in vivo endothelialization would obviate the need for pre-seeding, but has been shown to be absent in man due to limited transanastomotic and fallout healing, and the lack of transmural ingrowth due to insufficient porosity. Two types of graft scaffolds with increased interconnected porosity for improved tissue ingrowth and healing are thus proposed and described. Foam-type polyurethane (PU) scaffolds with small, medium and large, interconnected pores were made by phase inversion and spherical porogen extraction, with and without additional surface modification with covalently attached heparin and subsequent loading with and delivery of growth factors. Fibrillar scaffolds were made either by standard electrospinning using degradable PU (Degrapol®), or by dual electrospinning using non-degradable PU. The latter process involves sacrificial fibres that are co-spun with structural fibres and subsequently removed to increased porosity and pore size. Degrapol samples were subjected to in vitro degradation, and all scaffold types were evaluated in vivo for tissue ingrowth and vascularization using rat subcutaneous model. The foam scaffolds were additionally evaluated in a circulatory (rat infrarenal aortic interposition) model that allows for the grafts to be anastomotically and/or ablumenally isolated to discern and determine endothelialization mode. Foam-type grafts with large (150 µm) pores showed improved subcutaneous healing in terms of vascularization and inflammatory response over smaller pore sizes (60 and 90µm), and vascularization of the large porosity scaffolds was significantly increased by more than 70% by heparin modification alone, and by 150% to 400% when combined with growth factors. In the circulatory model, extensive transmural endothelialization (95±10% at 12 w) was achieved. Fallout healing was shown to be sporadic and limited in groups that were ablumenally isolated to prevent transmural ingrowth (16±30% wrapped vs. 80±20% control; p<0.002). Heparinization and GF delivery improved both mural vascularization and lumenal endothelialization. Degrapol electrospun scaffolds showed decrease in molecular mass and corresponding tensile strength over the first 2 weeks, but very little decrease in mass over the 4w test period. Studies on the effect of tissue ingrowth with and without concomitant degradation of the scaffolds, are being used to develop material models for the finite element modelling. In the case of the dual-spun scaffolds, the PU fibre fraction could be controlled shown to vary linearly with porosity (P = −0.18FF +93.5, r2=0.91), which in turn showed inverse linear correlation with tensile strength and elastic modulus (r2 > 0.96). Calculated compliance and burst pressures of the scaffolds increased with fibre fraction, and compliances matching the human popliteal artery (5-10 %/100 mmHg), and high burst pressures (> 2000 mmHg) could be achieved. Increasing porosity (76 to 82 and 90%) resulted in increased tissue ingrowth from 33±7 to 77±20 and 98±1% after 28d. Transmural endothelialization of highly porous foamed grafts is achievable in a circulatory model, and the enhancement of porosity and tissue ingrowth may hold the key the development of spontaneously endothelializing electrospun grafts.

Keywords: electrospinning, endothelialization, porosity, scaffold, vascular graft

Procedia PDF Downloads 271

Authors: Eliska Smidova, Petr Kabele

Abstract:

This paper describes non-linear finite element simulation of laminated veneer lumber (LVL) under tensile and shear loads that induce cracking along fibers. For this purpose, we use 2D homogeneous orthotropic constitutive model of tensile and shear fracture in timber that has been recently developed and implemented into ATENA® finite element software by the authors. The model captures (i) material orthotropy for small deformations in both linear and non-linear range, (ii) elastic behavior until anisotropic failure criterion is fulfilled, (iii) inelastic behavior after failure criterion is satisfied, (iv) different post-failure response for cracks along and across the grain, (v) unloading/reloading behavior. The post-cracking response is treated by fixed smeared crack model where Reinhardt-Hordijk function is used. The model requires in total 14 input parameters that can be obtained from standard tests, off-axis test results and iterative numerical simulation of compact tension (CT) or compact tension-shear (CTS) test. New engineered timber composites, such as laminated veneer lumber (LVL), offer improved structural parameters compared to sawn timber. LVL is manufactured by laminating 3 mm thick wood veneers aligned in one direction using water-resistant adhesives (e.g. polyurethane). Thus, 3 main grain directions, namely longitudinal (L), tangential (T), and radial (R), are observed within the layered LVL product. The core of this work consists in 3 numerical simulations of experiments where Radiata Pine LVL and Yellow Poplar LVL were involved. The first analysis deals with calibration and validation of the proposed model through off-axis tensile test (at a load-grain angle of 0°, 10°, 45°, and 90°) and CTS test (at a load-grain angle of 30°, 60°, and 90°), both of which were conducted for Radiata Pine LVL. The second finite element simulation reproduces load-CMOD curve of compact tension (CT) test of Yellow Poplar with the aim of obtaining cohesive law parameters to be used as an input in the third finite element analysis. That is four point bending test of small-size arch of 780 mm span that is made of Yellow Poplar LVL. The arch is designed with a through crack between two middle layers in the crown. Curved laminated beams are exposed to high radial tensile stress compared to timber strength in radial tension in the crown area. Let us note that in this case the latter parameter stands for tensile strength in perpendicular direction with respect to the grain. Standard tests deliver most of the relevant input data whereas traction-separation law for crack along the grain can be obtained partly by inverse analysis of compact tension (CT) test or compact tension-shear test (CTS). The initial crack was modeled as a narrow gap separating two layers in the middle the arch crown. Calculated load-deflection curve is in good agreement with the experimental ones. Furthermore, crack pattern given by numerical simulation coincides with the most important observed crack paths.

Keywords: compact tension (CT) test, compact tension shear (CTS) test, fixed smeared crack model, four point bending test, laminated arch, laminated veneer lumber LVL, off-axis test, orthotropic elasticity, orthotropic fracture criterion, Radiata Pine LVL, traction-separation law, yellow poplar LVL, 2D constitutive model

Procedia PDF Downloads 259

Authors: Gabrielle Robertson, Matthew Downs, Joseph Dagher

Abstract:

Iron deposition in the brain has been linked with a host of neurological disorders such as Alzheimer’s, Parkinson’s, and Multiple Sclerosis. While some treatment options exist, there are no objective measurement tools that allow for the monitoring of iron levels in the brain in vivo. An emerging Magnetic Resonance Imaging (MRI) method has been recently proposed to deduce iron concentration through quantitative measurement of magnetic susceptibility. This is a multi-step process that involves repeated modeling of physical processes via approximate numerical solutions. For example, the last two steps of this Quantitative Susceptibility Mapping (QSM) method involve I) mapping magnetic field into magnetic susceptibility and II) mapping magnetic susceptibility into iron concentration. Process I involves solving an ill-posed inverse problem by using regularization via injection of prior belief. The end result from Process II highly depends on the model used to describe the molecular content of each voxel (type of iron, water fraction, etc.) Due to these factors, the accuracy and repeatability of QSM have been an active area of research in the MRI and medical imaging community. This work aims to estimate iron concentration in the brain via a single step. A synthetic numerical model of the human head was created by automatically and manually segmenting the human head on a high-resolution grid (640x640x640, 0.4mm³) yielding detailed structures such as microvasculature and subcortical regions as well as bone, soft tissue, Cerebral Spinal Fluid, sinuses, arteries, and eyes. Each segmented region was then assigned tissue properties such as relaxation rates, proton density, electromagnetic tissue properties and iron concentration. These tissue property values were randomly selected from a Probability Distribution Function derived from a thorough literature review. In addition to having unique tissue property values, different synthetic head realizations also possess unique structural geometry created by morphing the boundary regions of different areas within normal physical constraints. This model of the human brain is then used to create synthetic MRI measurements. This is repeated thousands of times, for different head shapes, volume, tissue properties and noise realizations. Collectively, this constitutes a training-set that is similar to in vivo data, but larger than datasets available from clinical measurements. This 3D convolutional U-Net neural network architecture was used to train data-driven Deep Learning models to solve for iron concentrations from raw MRI measurements. The performance was then tested on both synthetic data not used in training as well as real in vivo data. Results showed that the model trained on synthetic MRI measurements is able to directly learn iron concentrations in areas of interest more effectively than other existing QSM reconstruction methods. For comparison, models trained on random geometric shapes (as proposed in the Deep QSM method) are less effective than models trained on realistic synthetic head models. Such an accurate method for the quantitative measurement of iron deposits in the brain would be of important value in clinical studies aiming to understand the role of iron in neurological disease.

Keywords: magnetic resonance imaging, MRI, iron deposition, machine learning, quantitative susceptibility mapping

Procedia PDF Downloads 106

Authors: Chung-Ming Lo, Chung-Chien Lee

Abstract:

In many countries, the lifetime prevalence of shoulder pain is up to 70%. In America, the health care system spends 7 billion per year about the healthy issues of shoulder pain. With respect to the origin, up to 70% of shoulder pain is attributed to rotator cuff lesions This study proposed a computer-aided diagnosis (CAD) system to assist radiologists classifying rotator cuff lesions with less operator dependence. Quantitative features were extracted from the shoulder ultrasound images acquired using an ALOKA alpha-6 US scanner (Hitachi-Aloka Medical, Tokyo, Japan) with linear array probe (scan width: 36mm) ranging from 5 to 13 MHz. During examination, the postures of the examined patients are standard sitting position and are followed by the regular routine. After acquisition, the shoulder US images were drawn out from the scanner and stored as 8-bit images with pixel value ranging from 0 to 255. Upon the sonographic appearance, the boundary of each lesion was delineated by a physician to indicate the specific pattern for analysis. The three lesion categories for classification were composed of 20 cases of tendon inflammation, 18 cases of calcific tendonitis, and 18 cases of supraspinatus tear. For each lesion, second-order statistics were quantified in the feature extraction. The second-order statistics were the texture features describing the correlations between adjacent pixels in a lesion. Because echogenicity patterns were expressed via grey-scale. The grey-scale co-occurrence matrixes with four angles of adjacent pixels were used. The texture metrics included the mean and standard deviation of energy, entropy, correlation, inverse different moment, inertia, cluster shade, cluster prominence, and Haralick correlation. Then, the quantitative features were combined in a multinomial logistic regression classifier to generate a prediction model of rotator cuff lesions. Multinomial logistic regression classifier is widely used in the classification of more than two categories such as the three lesion types used in this study. In the classifier, backward elimination was used to select a feature subset which is the most relevant. They were selected from the trained classifier with the lowest error rate. Leave-one-out cross-validation was used to evaluate the performance of the classifier. Each case was left out of the total cases and used to test the trained result by the remaining cases. According to the physician’s assessment, the performance of the proposed CAD system was shown by the accuracy. As a result, the proposed system achieved an accuracy of 86%. A CAD system based on the statistical texture features to interpret echogenicity values in shoulder musculoskeletal ultrasound was established to generate a prediction model for rotator cuff lesions. Clinically, it is difficult to distinguish some kinds of rotator cuff lesions, especially partial-thickness tear of rotator cuff. The shoulder orthopaedic surgeon and musculoskeletal radiologist reported greater diagnostic test accuracy than general radiologist or ultrasonographers based on the available literature. Consequently, the proposed CAD system which was developed according to the experiment of the shoulder orthopaedic surgeon can provide reliable suggestions to general radiologists or ultrasonographers. More quantitative features related to the specific patterns of different lesion types would be investigated in the further study to improve the prediction.

Keywords: shoulder ultrasound, rotator cuff lesions, texture, computer-aided diagnosis

Procedia PDF Downloads 261

Authors: Juergen Orasche, Vesta Kohlmeier, George C. Dragan, Gert Jakobi, Patricia Forbes, Ralf Zimmermann

Abstract:

Underground mining poses a difficult environment for both man and machines. At more than 1000 meters underneath the surface of the earth, ores and other mineral resources are still gained by conventional and motorised mining. Adding to the hazards caused by blasting and stone-chipping, the working conditions are best described by the high temperatures of 35-40°C and high humidity, at low air exchange rates. Separate ventilation shafts lead fresh air into a mine and others lead expended air back to the surface. This is essential for humans and machines working deep underground. Nevertheless, mines are widely ramified. Thus the air flow rate at the far end of a tunnel is sensed to be close to zero. In recent years, conventional mining was supplemented by mining with heavy diesel machines. These very flat machines called Load Haul Dump (LHD) vehicles accelerate and ease work in areas favourable for heavy machines. On the other hand, they emit non-filtered diesel exhaust, which constitutes an occupational hazard for the miners. Combined with a low air exchange, high humidity and inorganic dust from the mining it leads to 'black smog' underneath the earth. This work focuses on the air quality in mines employing LHDs. Therefore we performed personal sampling (samplers worn by miners during their work), stationary sampling and aethalometer (Microaeth MA200, Aethlabs) measurements in a platinum mine in around 1000 meters under the earth’s surface. We compared areas of high diesel exhaust emission with areas of conventional mining where no diesel machines were operated. For a better assessment of health risks caused by air pollution we applied a separated gas-/particle-sampling tool (or system), with first denuder section collecting intermediate VOCs. These multi-channel silicone rubber denuders are able to trap IVOCs while allowing particles ranged from 10 nm to 1 µm in diameter to be transmitted with an efficiency of nearly 100%. The second section is represented by a quartz fibre filter collecting particles and adsorbed semi-volatile organic compounds (SVOC). The third part is a graphitized carbon black adsorber – collecting the SVOCs that evaporate from the filter. The compounds collected on these three sections were analyzed in our labs with different thermal desorption techniques coupled with gas chromatography and mass spectrometry (GC-MS). VOCs and IVOCs were measured with a Shimadzu Thermal Desorption Unit (TD20, Shimadzu, Japan) coupled to a GCMS-System QP 2010 Ultra with a quadrupole mass spectrometer (Shimadzu). The GC was equipped with a 30m, BP-20 wax column (0.25mm ID, 0.25µm film) from SGE (Australia). Filters were analyzed with In-situ derivatization thermal desorption gas chromatography time-of-flight-mass spectrometry (IDTD-GC-TOF-MS). The IDTD unit is a modified GL sciences Optic 3 system (GL Sciences, Netherlands). The results showed black carbon concentrations measured with the portable aethalometers up to several mg per m³. The organic chemistry was dominated by very high concentrations of alkanes. Typical diesel engine exhaust markers like alkylated polycyclic aromatic hydrocarbons were detected as well as typical lubrication oil markers like hopanes.

Keywords: diesel emission, personal sampling, aethalometer, mining

Procedia PDF Downloads 131

Authors: Joel A. Gordon, Nazmiye Balta-Ozkan, Seyed Ali Nabavi

Abstract:

Hydrogen-fueled technologies are rapidly advancing as a critical component of the low-carbon energy transition. In countries historically reliant on natural gas for home heating, such as the UK, hydrogen may prove fundamental for decarbonizing the residential sector, alongside other technologies such as heat pumps and district heat networks. While the UK government is set to take a long-term policy decision on the role of domestic hydrogen by 2026, there are considerable uncertainties regarding consumer preferences for ‘hydrogen homes’ (i.e., hydrogen-fueled appliances for space heating, hot water, and cooking. In comparison to other hydrogen energy technologies, such as road transport applications, to date, few studies have engaged with the social acceptance aspects of the domestic hydrogen transition, resulting in a stark knowledge deficit and pronounced risk to policymaking efforts. In response, this study aims to safeguard against undesirable policy measures by revealing the underlying relationships between the factors of domestic hydrogen acceptance and their respective dimensions: attitudinal, socio-political, community, market, and behavioral acceptance. The study employs an online survey (n=~2100) to gauge how different UK householders perceive the proposition of switching from natural gas to hydrogen-fueled appliances. In addition to accounting for housing characteristics (i.e., housing tenure, property type and number of occupants per dwelling) and several other socio-structural variables (e.g. age, gender, and location), the study explores the impacts of consumer heterogeneity on hydrogen acceptance by recruiting respondents from across five distinct groups: (1) fuel poor householders, (2) technology engaged householders, (3) environmentally engaged householders, (4) technology and environmentally engaged householders, and (5) a baseline group (n=~700) which filters out each of the smaller targeted groups (n=~350). This research design reflects the notion that supporting a socially fair and efficient transition to hydrogen will require parallel engagement with potential early adopters and demographic groups impacted by fuel poverty while also accounting strongly for public attitudes towards net zero. Employing a second-order multigroup confirmatory factor analysis (CFA) in Mplus, the proposed hydrogen acceptance model is tested to fit the data through a partial least squares (PLS) approach. In addition to testing differences between and within groups, the findings provide policymakers with critical insights regarding the significance of knowledge and awareness, safety perceptions, perceived community impacts, cost factors, and trust in key actors and stakeholders as potential explanatory factors of hydrogen acceptance. Preliminary results suggest that knowledge and awareness of hydrogen are positively associated with support for domestic hydrogen at the household, community, and national levels. However, with the exception of technology and/or environmentally engaged citizens, much of the population remains unfamiliar with hydrogen and somewhat skeptical of its application in homes. Knowledge and awareness present as critical to facilitating positive safety perceptions, alongside higher levels of trust and more favorable expectations for community benefits, appliance performance, and potential cost savings. Based on these preliminary findings, policymakers should be put on red alert about diffusing hydrogen into the public consciousness in alignment with energy security, fuel poverty, and net-zero agendas.

Keywords: hydrogen homes, social acceptance, consumer heterogeneity, heat decarbonization

Procedia PDF Downloads 82

Authors: H. K. Esfahani, B. Datta

Abstract:

Groundwater is one of the most important natural resources in many parts of the world; however it is widely polluted due to human activities. Currently, effective and reliable groundwater management and remediation strategies are obtained using characterization of groundwater pollution sources, where the measured data in monitoring locations are utilized to estimate the unknown pollutant source location and magnitude. However, accurately identifying characteristics of contaminant sources is a challenging task due to uncertainties in terms of predicting source flux injection, hydro-geological and geo-chemical parameters, and the concentration field measurement. Reactive transport of chemical species in contaminated groundwater systems, especially with multiple species, is a complex and highly non-linear geochemical process. Although sufficient concentration measurement data is essential to accurately identify sources characteristics, available data are often sparse and limited in quantity. Therefore, this inverse problem-solving method for characterizing unknown groundwater pollution sources is often considered ill-posed, complex and non- unique. Different methods have been utilized to identify pollution sources; however, the linked simulation-optimization approach is one effective method to obtain acceptable results under uncertainties in complex real life scenarios. With this approach, the numerical flow and contaminant transport simulation models are externally linked to an optimization algorithm, with the objective of minimizing the difference between measured concentration and estimated pollutant concentration at observation locations. Concentration measurement data are very important to accurately estimate pollution source properties; therefore, optimal design of the monitoring network is essential to gather adequate measured data at desired times and locations. Due to budget and physical restrictions, an efficient and effective approach for groundwater pollutant source characterization is to design an optimal monitoring network, especially when only inadequate and arbitrary concentration measurement data are initially available. In this approach, preliminary concentration observation data are utilized for preliminary source location, magnitude and duration of source activity identification, and these results are utilized for monitoring network design. Further, feedback information from the monitoring network is used as inputs for sequential monitoring network design, to improve the identification of unknown source characteristics. To design an effective monitoring network of observation wells, optimization and interpolation techniques are used. A simulation model should be utilized to accurately describe the aquifer properties in terms of hydro-geochemical parameters and boundary conditions. However, the simulation of the transport processes becomes complex when the pollutants are chemically reactive. Three dimensional transient flow and reactive contaminant transport process is considered. The proposed methodology uses HYDROGEOCHEM 5.0 (HGCH) as the simulation model for flow and transport processes with chemically multiple reactive species. Adaptive Simulated Annealing (ASA) is used as optimization algorithm in linked simulation-optimization methodology to identify the unknown source characteristics. Therefore, the aim of the present study is to develop a methodology to optimally design an effective monitoring network for pollution source characterization with reactive species in polluted aquifers. The performance of the developed methodology will be evaluated for an illustrative polluted aquifer sites, for example an abandoned mine site in Queensland, Australia.

Keywords: monitoring network design, source characterization, chemical reactive transport process, contaminated mine site

Procedia PDF Downloads 211

Authors: Simone Dell'Agnello

Abstract:

There are laser retroreflectors on the Moon and no laser retroreflectors on Mars. Here we describe the design, construction, qualification and imminent deployment of next-generation, optimized laser retroreflectors on the Moon and on Mars (where they will be the first ones). These instruments are positioned by time-of-flight measurements of short laser pulses, the so-called 'laser ranging' technique. Data analysis is carried out with PEP, the Planetary Ephemeris Program of CfA (Center for Astrophysics). Since 1969 Lunar Laser Ranging (LLR) to Apollo/Lunokhod laser retro-reflector (CCR) arrays supplied accurate tests of General Relativity (GR) and new gravitational physics: possible changes of the gravitational constant Gdot/G, weak and strong equivalence principle, gravitational self-energy (Parametrized Post Newtonian parameter beta), geodetic precession, inverse-square force-law; it can also constraint gravitomagnetism. Some of these measurements also allowed for testing extensions of GR, including spacetime torsion, non-minimally coupled gravity. LLR has also provides significant information on the composition of the deep interior of the Moon. In fact, LLR first provided evidence of the existence of a fluid component of the deep lunar interior. In 1969 CCR arrays contributed a negligible fraction of the LLR error budget. Since laser station range accuracy improved by more than a factor 100, now, because of lunar librations, current array dominate the error due to their multi-CCR geometry. We developed a next-generation, single, large CCR, MoonLIGHT (Moon Laser Instrumentation for General relativity high-accuracy test) unaffected by librations that supports an improvement of the space segment of the LLR accuracy up to a factor 100. INFN also developed INRRI (INstrument for landing-Roving laser Retro-reflector Investigations), a microreflector to be laser-ranged by orbiters. Their performance is characterized at the SCF_Lab (Satellite/lunar laser ranging Characterization Facilities Lab, INFN-LNF, Frascati, Italy) for their deployment on the lunar surface or the cislunar space. They will be used to accurately position landers, rovers, hoppers, orbiters of Google Lunar X Prize and space agency missions, thanks to LLR observations from station of the International Laser Ranging Service in the USA, in France and in Italy. INRRI was launched in 2016 with the ESA mission ExoMars (Exobiology on Mars) EDM (Entry, descent and landing Demonstration Module), deployed on the Schiaparelli lander and is proposed for the ExoMars 2020 Rover. Based on an agreement between NASA and ASI (Agenzia Spaziale Italiana), another microreflector, LaRRI (Laser Retro-Reflector for InSight), was delivered to JPL (Jet Propulsion Laboratory) and integrated on NASA’s InSight Mars Lander in August 2017 (launch scheduled in May 2018). Another microreflector, LaRA (Laser Retro-reflector Array) will be delivered to JPL for deployment on the NASA Mars 2020 Rover. The first lunar landing opportunities will be from early 2018 (with TeamIndus) to late 2018 with commercial missions, followed by opportunities with space agency missions, including the proposed deployment of MoonLIGHT and INRRI on NASA’s Resource Prospectors and its evolutions. In conclusion, we will extend significantly the CCR Lunar Geophysical Network and populate the Mars Geophysical Network. These networks will enable very significantly improved tests of GR.

Keywords: general relativity, laser retroreflectors, lunar laser ranging, Mars geodesy

Procedia PDF Downloads 248

Authors: Dmitriy Berillo, Areej K. A. Al-Jwaid, Jonathan L. Caplin, Andrew Cundy, Irina Savina

Abstract:

Chlorophenols (CPs) are used as a precursor in the production of higher CPs and dyestuffs, and as a preservative. Contamination by CPs of the ground water is located in the range from 0.15-100mg/L. The EU has set maximum concentration limits for pesticides and their degradation products of 0.1μg/L and 0.5μg/L, respectively. People working in industries which produce textiles, leather products, domestic preservatives, and petrochemicals are most heavily exposed to CPs. The International Agency for Research on Cancers categorized CPs as potential human carcinogens. Existing multistep water purification processes for CPs such as hydrogenation, ion exchange, liquid-liquid extraction, adsorption by activated carbon, forward and inverse osmosis, electrolysis, sonochemistry, UV irradiation, and chemical oxidation are not always cost effective and can cause the formation of even more toxic or mutagenic derivatives. Bioremediation of CPs derivatives utilizing microorganisms results in 60 to 100% decontamination efficiency and the process is more environmentally-friendly compared with existing physico-chemical methods. Microorganisms immobilized onto a substrate show many advantages over free bacteria systems, such as higher biomass density, higher metabolic activity, and resistance to toxic chemicals. They also enable continuous operation, avoiding the requirement for biomass-liquid separation. The immobilized bacteria can be reused several times, which opens the opportunity for developing cost-effective processes for wastewater treatment. In this study, we develop a bioremediation system for CPs based on macroporous materials, which can be efficiently used for wastewater treatment. Conditions for the preparation of the macroporous material from specific bacterial strains (Pseudomonas mendocina and Rhodococus koreensis) were optimized. The concentration of bacterial cells was kept constant; the difference was only the type of cross-linking agents used e.g. glutaraldehyde, novel polymers, which were utilized at concentrations of 0.5 to 1.5%. SEM images and rheology analysis of the material indicated a monolithic macroporous structure. Phenol was chosen as a model system to optimize the function of the cryogel material and to estimate its enzymatic activity, since it is relatively less toxic and harmful compared to CPs. Several types of macroporous systems comprising live bacteria were prepared. The viability of the cross-linked bacteria was checked using Live/Dead BacLight kit and Laser Scanning Confocal Microscopy, which revealed the presence of viable bacteria with the novel cross-linkers, whereas the control material cross-linked with glutaraldehyde(GA), contained mostly dead cells. The bioreactors based on bacteria were used for phenol degradation in batch mode at an initial concentration of 50mg/L, pH 7.5 and a temperature of 30°C. Bacterial strains cross-linked with GA showed insignificant ability to degrade phenol and for one week only, but a combination of cross-linking agents illustrated higher stability, viability and the possibility to be reused for at least five weeks. Furthermore, conditions for CPs degradation will be optimized, and the chlorophenol degradation rates will be compared to those for phenol. This is a cutting-edge bioremediation approach, which allows the purification of waste water from sustainable compounds without a separation step to remove free planktonic bacteria. Acknowledgments: Dr. Berillo D. A. is very grateful to Individual Fellowship Marie Curie Program for funding of the research.

Keywords: bioremediation, cross-linking agents, cross-linked microbial cell, chlorophenol degradation

Procedia PDF Downloads 196

Authors: Mohammadjavad Sotoudeheian, Navid Farahmandian

Abstract:

Cardiac hypertrophy arises in response to persistent increases in hemodynamic loads. In comparison, diabetic cardiomyopathy is defined by an abnormal myocardial changes without other cardiac-related risk factors. Pathological cardiac hypertrophy and myocardial remodeling are hallmarks of cardiovascular diseases and are risk factors for heart failure. The transcription factor forkhead box class O (FOXOs) can protect heart tissue by hostile oxidative stress and stimulating apoptosis and autophagy. FOXO proteins, as sensitive elements and mediators in response to environmental changes, have been revealed to prevent and inverse cardiac hypertrophy. FOXOs are inhibited by insulin and are critical mediators of insulin action. Insulin deficiency and uncontrolled diabetes lead to a catabolic state. FOXO1 acts downstream of the insulin-dependent pathways, which are dysregulated in diabetes. It regulates cardiomyocyte hypertrophy downstream of IGF1R/PI3K/Akt activation, which are critical regulators of cardiac hypertrophy. The complex network of signaling pathways comprising insulin/IGF-1 signaling, AMPK, JNK, and Sirtuins regulate the development of cardiovascular dysfunction by modulating the activity of FOXOs. Insulin receptors and IGF1R act via the PI3k/Akt and the MAPK/ERK pathways. Activation of Akt in response to insulin or IGF-1 induces phosphorylation of FOXOs. Increased protein synthesis induced by activation of the IGF-I/Akt/mTOR signaling pathway leads to hypertrophy. This pathway and the myostatin/Smad pathway are potent negative muscle development regulators. In cardiac muscle, insulin receptor substrates (IRS)-1 or IRS-2 activates the Akt signaling pathway and inactivate FOXO1. Under metabolic stress, p38 MAPK promotes degradation of IRS-1 and IRS-2 in cardiac myocytes and activates FOXO1, leading to cardiomyopathy. Sirt1 and FOXO1 interaction play an essential role in starvation-induced autophagy in cardiac metabolism. Inhibition of Angiotensin-II induced cardiomyocyte hypertrophy is associated with reduced FOXO1 acetylation and activation of Sirt1. The NF-κB, ERK, and FOXOs are de-acetylated by SIRT1. De-acetylation of FOXO1 induces the expression of genes involved in autophagy and stimulates autophagy flux. Therefore, under metabolic stress, FOXO1 can cause diabetic cardiomyopathy. The overexpression of FOXO1 leads to decreased cardiomyocyte size and suppresses cardiac hypertrophy through inhibition of the calcineurin–NFAT pathway. Diabetes mellitus is associated with elevation of O-GlcNAcylation. Some of its binding partners regulate the substrate selectivity of O-GlcNAc transferase (OGT). O-GlcNAcylation of essential contractile proteins may inhibit protein-protein interactions, reduce calcium sensitivity, and modulate contractile function. Uridine diphosphate (UDP)-GlcNAc is the obligatory substrate of OGT, which catalyzes a reversible post-translational protein modification. The increase of O-GlcNAcylation is accompanied by impaired cardiac hypertrophy in diabetic hearts. Inhibition of O-GlcNAcylation blocks activation of ERK1/2 and hypertrophic growth. O-GlcNAc modification on NFAT is required for its translocation from the cytosol to the nucleus, where NFAT stimulates the transcription of various hypertrophic genes. Inhibition of O-GlcNAcylation dampens NFAT-induced cardiac hypertrophic growth. Transcriptional activity of FOXO1 is enriched by improved O-GlcNAcylation upon high glucose stimulation or OGT overexpression. In diabetic conditions, the modification of FOXO1 by O-GlcNAc is promoted in cardiac troponin I and myosin light chain 2. Therefore targeting O-GlcNAcylation represents a potential therapeutic option to prevent hypertrophy in the diabetic heart.

Keywords: diabetes, cardiac hypertrophy, O-GlcNAcylation, FOXO1, Akt, PI3K, AMPK, insulin

Procedia PDF Downloads 88

Authors: Reza Nematirad, Anil Pahwa, Balasubramaniam Natarajan

Abstract:

Time series data consist of successive data points collected over a period of time. Accurate prediction of future values is essential for informed decision-making in several real-world applications, including electricity load demand forecasting, lifetime estimation of industrial machinery, traffic planning, weather prediction, and the stock market. Due to their critical relevance and wide application, there has been considerable interest in time series forecasting in recent years. However, the proliferation of sensors and IoT devices, real-time monitoring systems, and high-frequency trading data introduce significant intricate temporal variations, rapid changes, noise, and non-linearities, making time series forecasting more challenging. Classical methods such as Autoregressive integrated moving average (ARIMA) and Exponential Smoothing aim to extract pre-defined temporal variations, such as trends and seasonality. While these methods are effective for capturing well-defined seasonal patterns and trends, they often struggle with more complex, non-linear patterns present in real-world time series data. In recent years, deep learning has made significant contributions to time series forecasting. Recurrent Neural Networks (RNNs) and their variants, such as Long short-term memory (LSTMs) and Gated Recurrent Units (GRUs), have been widely adopted for modeling sequential data. However, they often suffer from the locality, making it difficult to capture local trends and rapid fluctuations. Convolutional Neural Networks (CNNs), particularly Temporal Convolutional Networks (TCNs), leverage convolutional layers to capture temporal dependencies by applying convolutional filters along the temporal dimension. Despite their advantages, TCNs struggle with capturing relationships between distant time points due to the locality of one-dimensional convolution kernels. Transformers have revolutionized time series forecasting with their powerful attention mechanisms, effectively capturing long-term dependencies and relationships between distant time points. However, the attention mechanism may struggle to discern dependencies directly from scattered time points due to intricate temporal patterns. Lastly, Multi-Layer Perceptrons (MLPs) have also been employed, with models like N-BEATS and LightTS demonstrating success. Despite this, MLPs often face high volatility and computational complexity challenges in long-horizon forecasting. To address intricate temporal variations in time series data, this study introduces Times2D, a novel framework that parallelly integrates 2D spectrogram and derivative heatmap techniques. The spectrogram focuses on the frequency domain, capturing periodicity, while the derivative patterns emphasize the time domain, highlighting sharp fluctuations and turning points. This 2D transformation enables the utilization of powerful computer vision techniques to capture various intricate temporal variations. To evaluate the performance of Times2D, extensive experiments were conducted on standard time series datasets and compared with various state-of-the-art algorithms, including DLinear (2023), TimesNet (2023), Non-stationary Transformer (2022), PatchTST (2023), N-HiTS (2023), Crossformer (2023), MICN (2023), LightTS (2022), FEDformer (2022), FiLM (2022), SCINet (2022a), Autoformer (2021), and Informer (2021) under the same modeling conditions. The initial results demonstrated that Times2D achieves consistent state-of-the-art performance in both short-term and long-term forecasting tasks. Furthermore, the generality of the Times2D framework allows it to be applied to various tasks such as time series imputation, clustering, classification, and anomaly detection, offering potential benefits in any domain that involves sequential data analysis.

Keywords: derivative patterns, spectrogram, time series forecasting, times2D, 2D representation

Procedia PDF Downloads 18