Search results for: software modeling

Authors: Meza-Quintero Myriam, Lobo Torrado Katty Andrea, Sanchez Picon Yesenia, Hurtado-Lugo Naudin

Abstract:

The objective of the study was to evaluate the internal and external quality of the egg in the three production housing systems: floor, cage, and grazing of laying birds of the Isa Brown line, in the laying period between weeks 35 to 41; 135 hens distributed in 3 treatments of 45 birds per repetition were used (the replicas were the seven weeks of the trial). The feeding treatment supplied in the floor and cage systems contained 114 g/bird/day; for the grazing system, 14 grams less concentrate was provided. Nine eggs were collected to be studied and analyzed in the animal nutrition laboratory (3 eggs per housing system). The random statistical model was implemented: for the statistical analysis of the data, the statistical software of IBM® Statistical Products and Services Solution (SPSS) version 2.3 was used. The evaluation and follow-up instruments were the vernier caliper for the measurement in millimeters, a YolkFan™16 from Roche DSM for the evaluation of the egg yolk pigmentation, a digital scale for the measurement in grams, a micrometer for the measurement in millimeters and evaluation in the laboratory using dry matter, ashes, and ethereal extract. The results suggested that equivalent to the size of the egg (0.04 ± 3.55) and the thickness of the shell (0.46 ± 3.55), where P-Value> 0.05 was obtained, weight albumen (0.18 ± 3.55), albumen height (0.38 ± 3.55), yolk weight (0.64 ± 3.55), yolk height (0.54 ± 3.55) and for yolk pigmentation (1.23 ± 3.55). It was concluded that the hens in the three production systems, floor, cage, and grazing, did not show significant statistical differences in the internal and external quality of the chicken in the parameters studied egg for the production system.

Keywords: biological, territories, genetic resource, egg

Procedia PDF Downloads 69

Authors: Rohini Hariharan, Yazhini R, Bhamidipati Naga Shrikarti

Abstract:

In the realm of cricket, particularly within the context of the Indian Premier League (IPL), the ability to predict team scores accurately holds significant importance for both cricket enthusiasts and stakeholders alike. This paper presents a comprehensive study on IPL score prediction utilizing various machine learning algorithms, including Support Vector Machines (SVM), XGBoost, Multiple Regression, Linear Regression, K-nearest neighbors (KNN), and Random Forest. Through meticulous data preprocessing, feature engineering, and model selection, we aimed to develop a robust predictive framework capable of forecasting team scores with high precision. Our experimentation involved the analysis of historical IPL match data encompassing diverse match and player statistics. Leveraging this data, we employed state-of-the-art machine learning techniques to train and evaluate the performance of each model. Notably, Multiple Regression emerged as the top-performing algorithm, achieving an impressive accuracy of 77.19% and a precision of 54.05% (within a threshold of +/- 10 runs). This research contributes to the advancement of sports analytics by demonstrating the efficacy of machine learning in predicting IPL team scores. The findings underscore the potential of advanced predictive modeling techniques to provide valuable insights for cricket enthusiasts, team management, and betting agencies. Additionally, this study serves as a benchmark for future research endeavors aimed at enhancing the accuracy and interpretability of IPL score prediction models.

Keywords: indian premier league (IPL), cricket, score prediction, machine learning, support vector machines (SVM), xgboost, multiple regression, linear regression, k-nearest neighbors (KNN), random forest, sports analytics

Procedia PDF Downloads 30

Authors: Berhan Fikru

Abstract:

The objective of this study was to develop new complementary food from maize, soybean and moringa for young children. The complementary foods were formulated with linear programming (LP Nutri-survey software) and Faffa (corn soya blend) use as control. Analysis were made for formulated blends and compared with the control and recommended daily intake (RDI). Three complementary foods composed of maize, soya bean, moringa and sugar with ratio of 65:20:15:0, 55:25:15:5 and 65:20:10:5 for blend 1, 2 and 3, respectively. The blends were formulated based on the protein, energy, mineral (iron, zinc an calcium) and vitamin (vitamin A and C) content of foods. The overall results indicated that nutrient content of faffa (control) was 16.32 % protein, 422.31 kcal energy, 64.47 mg calcium, 3.8 mg iron, 1.87mg zinc, 0.19 mg vitamin A and 1.19 vitamin C; blend 1 had 17.16 % protein, 429.84 kcal energy, 330.40 mg calcium, 6.19 mg iron, 1.62 mg zinc, 6.33 mg vitamin A and 4.05 mg vitamin C; blend 2 had 20.26 % protein, 418.79 kcal energy, 417.44 mg calcium, 9.26 mg iron, 2.16 mg zinc, 8.43 mg vitamin A and 4.19 mg vitamin C whereas blend 3 exhibited 16.44 % protein, 417.42 kcal energy, 242.4 mg calcium, 7.09 mg iron, 2.22 mg zinc, 3.69 mg vitamin A and 4.72 mg vitamin C, respectively. The difference was found between all means statically significance (P < 0.05). Sensory evaluation showed that the faffa control and blend 3 were preferred by semi-trained panelists. Blend 3 had better in terms of its mineral and vitamin content than FAFFA corn soya blend and comparable with WFP proprietary products CSB+, CSB++ and fulfills the WHO recommendation for protein, energy and calcium. The suggested formulation with Moringa powder can therefore be used as a complementary food to improve the nutritional status and also help solve problems associated with protein energy and micronutrient malnutrition for young children in developing countries, particularly in Ethiopia.

Keywords: corn soya blend, proximate composition, micronutrient, mineral chelating agents, complementary foods

Procedia PDF Downloads 286

Authors: Mohammadreza Kolaei, Vahid Ghasemi, Ebrahim Ansari

Abstract:

This research was carried out with the aim of investigating the relationship between social capital and aggressive behavior of students (Case study: male students of middle school in Isfahan). In terms of methodology, this research is an applied research which is done by descriptive-analytical method and survey method. The instrument for collecting the data was a questionnaire consisting of: questionnaire for measuring aggressive behavior and social capital questionnaire, which was used after the validity and reliability of this questionnaire. On the other hand, the statistical population of the study consisted of all students in the guidance school of Isfahan in the academic year of 2016. For determining the sample size, the Kerjesy and Morgan tables were used and the sampling method of this multi-stage random sampling was used. After collecting the data, they were analyzed by SPSS software. The findings of the research showed that at 95% confidence level, the student's social capital increases, reducing his aggressiveness. Also, the amount of student aggression is estimated at 4% according to its social capital. Also, with increasing social capital of the school, the student's student aggression is reduced, with the student's student aggression's exposure to her social capital being estimated at 3%. On the other hand, increasing the amount of mother's presence in the home decreases the amount of student aggression. Also, the amount of student aggression is estimated at 1% according to the amount of mother's presence in her home. Ultimately, the amount of student aggression decreases with increasing presence of father at home. Also, the amount of student aggression is estimated at 2% according to the variable of father's presence in his home.

Keywords: investigating, social capital, aggressive behavior, students, middle school, Isfahan

Procedia PDF Downloads 271

Authors: Rahimah Akbar, Abdullah Al-Hashemi, Hanan Taqi, Taiba Sadeq

Abstract:

As technology continues to develop, teaching curriculums in both schools and universities have begun adopting a more computer/digital based approach to the transmission of knowledge and information, as opposed to the more old-fashioned use of textbooks. This gives rise to the question: Are there any differences in learning from a digital source over learning from a printed source, as in from a textbook? More specifically, which medium of information results in better long-term retention? A review of the confounding factors implicated in understanding the relationship between learning from the two different mediums was done. Alongside this, a 4-week cohort study involving 76 1st year English Language female students was performed, whereby the participants were divided into 2 groups. Group A studied material from a paper source (referred to as the Print Medium), and Group B studied material from a digital source (Digital Medium). The dependent variables were grading of memory recall indexed by a 4 point grading system, and total frequency of item repetition. The study was facilitated by advanced computer software called Super Memo. Results showed that, contrary to prevailing evidence, the Digital Medium group showed no statistically significant differences in terms of the shift from Remember (Episodic) to Know (Semantic) when all confounding factors were accounted for. The shift from Random Guess and Familiar to Remember occurred faster in the Digital Medium than it did in the Print Medium.

Keywords: digital medium, print medium, long-term memory recall, episodic memory, semantic memory, super memo, forgetting index, frequency of repetitions, total time spent

Procedia PDF Downloads 275

Authors: Sarra Bouhallel, Sara Legbedj, Rima Messaoud, Sofia Saffarbatti

Abstract:

In the context of global waste management and sustainable resource utilization, millets emerge as a vital yet underutilized cereal resource. Despite their exceptional nutritional profile and resilience to harsh environmental conditions, their potential remains largely untapped. This study aims to contribute to the valorization of seven Algerian pearl millet landraces (Pennisetum glaucum (L.) R. Br) from the southern region by focusing on the characterization of their starches. Utilizing both conventional wet milling, incorporating sodium azide as a microbial growth inhibitor, and a novel green technology—Ultrasound-assisted isolation, we explore avenues for enhancing the functional properties of these starches. Analysis of key functional properties such as swelling power and water solubility index reveals significant enhancements, particularly during heat treatment near the gelatinization temperature [70 - 80 °C]. Furthermore, our investigation into the influence of pre-treatment methods on isolated starches highlights the potential of Ultrasound-assisted isolation in reducing absorbency and water solubility compared to conventional methods. Through rigorous data analysis using SPSS software (Version 23), we ascertain the efficiency of Ultrasound-assisted isolation, underscoring its promising role in the valorization of pearl millet waste. This research not only sheds light on the functional properties of pearl millet starch but also underscores the imperative of sustainable waste management in harnessing the full potential of underutilized cereal resources.

Keywords: isolation, solubility, starch, swelling, ultrasound

Procedia PDF Downloads 37

Authors: Paria Saadatjoo

Abstract:

Given that HVAC systems are the main sources of carbon dioxide producers, developing ways to reduce dependence on these systems and making use of natural resources is too important to achieve environmentally friendly buildings. A major part of building potential in terms of using natural energy resources depends on its physical features. So architectural decisions at the first step of the design process can influence the building's energy efficiency significantly. Implementation of semi-open spaces into solid apartment blocks inspired by the concept of courtyard in ancient buildings as a passive cooling strategy is currently enjoying great popularity. However, the analysis of these features and their effect on wind behavior at initial design steps is a difficult task for architects. The main objective of this research was to investigate the influence of semi-open to closed space ratio on airflow patterns in and around midrise buildings and introduce the best ratio in terms of harnessing natural ventilation. The main strategy of this paper was semi-experimental, and the research methodology was descriptive statistics. At the first step, by changing the terrace area, 6 models with various open to closed space ratios were created. These forms were then transferred to CFD software to calculate the primary indicators of natural ventilation potentials such as wind force coefficient, air flow rate, age of air distribution, etc. Investigations indicated that modifying the terrace area and, in other words, the open to closed space ratio influenced the wind force coefficient, airflow rate, and age of air distribution.

Keywords: natural ventilation, wind, midrise, open space, energy

Procedia PDF Downloads 155

Authors: Zerihun Yohannes Amare, Belayneh Birku Geremew, Nigatu Melise Kebede, Sisaynew Getahun Amera

Abstract:

In Ethiopia, agricultural production is predominantly rainfed. The El Niño Southern Oscillation (ENSO) is the driver of climate variability, which affects the agricultural production system in the country. This paper aims to study trends, variability of rainfall, and impacts of El Niño Southern Oscillation (ENSO) on rainfall amount. The study was carried out in Ethiopia's Western Amhara National Regional State, which features a variety of seasons that characterize the nation. Monthly rainfall data were collected from fifteen meteorological stations of Western Amhara. Selected El Niño and La Niña years were also extracted from National Oceanic and Atmospheric Administration (NOAA) from 1986 to 2015. Once the data quality was checked and inspected, the monthly rainfall data of the selected stations were arranged in Microsoft Excel Spreadsheet and analyzed using XLSTAT software. The coefficient of variation and the Mann-Kendall non-parametric statistical test was employed to analyze trends and variability of rainfall and temperature. The long-term recorded annual rainfall data indicated that there was an increasing trend from 1986 to 2015 insignificantly. The rainfall variability was less (Coefficient of Variation, CV = 8.6%); also, the mean monthly rainfall of Western Amhara decreased during El Niño years and increased during La Niña years, especially in the rainy season (JJAS) over 30 years. This finding will be useful to suggest possible adaptation strategies and efficient use of resources during planning and implementation.

Keywords: rainfall, Mann-Kendall test, El Niño, La Niña, Western Amhara, Ethiopia

Procedia PDF Downloads 76

Authors: Sanjai Sureshkumar, Sathish G. Kumar, P. V. V. Sathyanarayana

Abstract:

For e-gear drivetrain, the transmission error and the resulting variation in mesh stiffness is one of the main source of excitation in High performance Electric Vehicle. These vibrations are transferred through the shaft to the bearings and then to the e-Gear drive housing eventually radiating noise. A parametrical model developed in 1-D system simulation by optimizing the micro and macro geometry along with bearing properties and oil filtration to achieve least transmission error and high contact ratio. Histogram analysis is performed to condense the actual road load data into condensed duty cycle to find the bearing forces. The structural vibration generated by these forces will be simulated in a nonlinear solver obtaining the normal surface velocity of the housing and the results will be carried forward to Acoustic software wherein a virtual environment of the surrounding (actual testing scenario) with accurate microphone position will be maintained to predict the sound pressure level of radiated noise and directivity plot of the e-Gear Drive. Order analysis will be carried out to find the root cause of the vibration and whine noise. Broadband spectrum will be checked to find the rattle noise source. Further, with the available results, the design will be optimized, and the next loop of simulation will be performed to build a best e-Gear Drive on NVH aspect. Structural analysis will be also carried out to check the robustness of the e-Gear Drive.

Keywords: 1-D system simulation, contact ratio, e-Gear, mesh stiffness, micro and macro geometry, transmission error, radiated noise, NVH

Procedia PDF Downloads 140

Authors: Rishab Das, Arnab Banerjee, Bappaditya Manna

Abstract:

Mono-pile foundations are often used in soft soils in order to support heavy mega-structures, whereby often these deep footings may undergo dynamic excitation due to many causes like earthquake, wind or wave loads acting on the superstructure, blasting, and unbalanced machines, etc. A comprehensive analytical study is performed to study the dynamics of the mono-pile system embedded in cohesion-less soil. The soil is considered homogeneous and visco-elastic in nature and is analytically modeled using complex springs. Considering the N number of the elements of the pile, the final global stiffness matrix is obtained by using the theories of the spectral element matrix method. Further, statically condensing the intermediate internal nodes of the global stiffness matrix results to a smaller sub matrix containing the nodes experiencing the external translation and rotation, and the stiffness and damping functions (impedance functions) of the embedded piles are determined. Proper plots showing the variation of the real and imaginary parts of these impedance functions with the dimensionless frequency parameter are obtained. The plots obtained from this study are validated by that provided by Novak,1974. Further, the dynamic analysis of the resonator impregnated pile is proposed within this study. Moreover, with the aid of Wood's 1g laboratory scaling law, a proper scaled-down resonator-pile model is 3D printed using PLA material. Dynamic analysis of the scaled model is carried out in the time domain, whereby the lateral loads are imposed on the pile head. The response obtained from the sensors through the LabView software is compared with the proposed theoretical data.

Keywords: mono-pile, visco-elastic, impedance, LabView

Procedia PDF Downloads 98

Authors: Husaini Sama

Abstract:

The study was conducted, in a 120 - day’s trial, to monitor the performance of growing Rahaji bulls fed different crop residues. There were four experimental treatments, each containing three (3) bull-calves. The first three (experimental) diets were prepared with rice straw, millet stalks and a combination of the two in equal proportions. These 3 diets were supplemented with concentrates. Treatments 1, 2 and 3 consisted of rice straw, millet stalk and combination of rice straw and millet stalk in equal ratio, respectively as basal feeds, while, Treatment 4 (containing standard diet of cow pea haulms, rice straw and wheat offal) served as control to compare with the other treatments. Data on feed intake and livability was collected on daily basis and that of live weight gain and feed conversion ratio were collected fortnightly, but data on apparent nutrient retention trial was collected towards the end of the experiment. Water was offered ad libitum. Records obtained were subjected to statistical analysis using SPSS (1988) software package in accordance with a Completely Randomized Design (CRD). Results obtained indicated that feed intake was significantly higher (P<0.05) for calves on treatments 3 and 4 compared to those on treatments 1and 2. The study observed that it was cheaper to formulate diets 2 and 3 than the other 2 diets. The control diet (T4) was observed to be relatively more expensive than the other 3 formulated diets. It was concluded from the findings that, concentrate containing combination of rice straw and cereal stalks was economical and satisfactory for feeding growing Rahaji bulls in this ecological zone (Semi-arid environment).

Keywords: rahaji bulls, crop residues, concentrates, semi-arid environment

Procedia PDF Downloads 173

Authors: M. Ntšolo, D. Kalumba, N. Lefu, G. Letlatsa

Abstract:

Rock mass damage due to shear tectonic activity has been investigated largely in geoscience where fluid transport is of major interest. However, little has been studied on the effect of shear zones on rock mass behavior and its impact on stability of rock slopes. At Letšeng Diamonds open pit mine in Lesotho, the shear zone composed of sheared kimberlite material, calcite and altered basalt is forming part of the haul ramp into the main pit cut 3. The alarming rate at which the shear zone is deteriorating has triggered concerns about both local and global stability of pit the walls. This study presents the numerical modelling of the open pit slope affected by shear zone at Letšeng Diamond Mine (LDM). Analysis of the slope involved development of the slope model by using a two-dimensional finite element code RS2. Interfaces between shear zone and host rock were represented by special joint elements incorporated in the finite element code. The analysis of structural geological mapping data provided a good platform to understand the joint network. Major joints including shear zone were incorporated into the model for simulation. This approach proved successful by demonstrating that continuum modelling can be used to evaluate evolution of stresses, strain, plastic yielding and failure mechanisms that are consistent with field observations. Structural control due to geological shear zone structure proved to be important in its location, size and orientation. Furthermore, the model analyzed slope deformation and sliding possibility along shear zone interfaces. This type of approach can predict shear zone deformation and failure mechanism, hence mitigation strategies can be deployed for safety of human lives and property within mine pits.

Keywords: numerical modeling, open pit mine, shear zone, slope stability

Procedia PDF Downloads 285

Authors: Taher M. Abou-deif, Esmail M. El-Bialy, Essam E. Khalil

Abstract:

The paper is devoted to numerically investigating the influence of the air supply outlets geometry on human comfort inside living looms. A computational fluid dynamics model is developed to examine the air flow characteristics of a room with different supply air diffusers. The work focuses on air flow patterns, thermal behavior in the room with few number of occupants. As an input to the full-scale 3-D room model, a 2-D air supply diffuser model that supplies direction and magnitude of air flow into the room is developed. Air distribution effect on thermal comfort parameters was investigated depending on changing the air supply diffusers type, angles and velocity. Air supply diffusers locations and numbers were also investigated. The pre-processor Gambit is used to create the geometric model with parametric features. Commercially available simulation software “Fluent 6.3” is incorporated to solve the differential equations governing the conservation of mass, three momentum and energy in the processing of air flow distribution. Turbulence effects of the flow are represented by the well-developed two equation turbulence model. In this work, the so-called standard k-ε turbulence model, one of the most widespread turbulence models for industrial applications, was utilized. Basic parameters included in this work are air dry bulb temperature, air velocity, relative humidity and turbulence parameters are used for numerical predictions of indoor air distribution and thermal comfort. The thermal comfort predictions through this work were based on ADPI (Air Diffusion Performance Index),the PMV (Predicted Mean Vote) model and the PPD (Percentage People Dissatisfied) model, the PMV and PPD were estimated using Fanger’s model.

Keywords: thermal comfort, Fanger's model, ADPI, energy effeciency

Procedia PDF Downloads 400

Authors: Juan José Mesas, Luis Sainz

Abstract:

The motivation for the development of this paper lies in the need for energy networks to reduce losses, improve performance, optimize their operation and try to benefit from the interconnection capacity with other networks enabled for other energy carriers. These interconnections generate interdependencies between some energy networks and others, which requires suitable models and methods for their analysis. Traditionally, the modeling and study of energy networks have been carried out independently for each energy carrier. Thus, there are well-established models and methods for the steady-state analysis of electrical networks, gas networks, and thermal networks separately. What is intended is to extend and combine them adequately to be able to face in an integrated way the steady-state analysis of networks with multiple energy carriers. Firstly, the added value of multi-energy networks, their operation, and the basic principles that characterize them are explained. In addition, two current aspects of great relevance are exposed: the storage technologies and the coupling elements used to interconnect one energy network with another. Secondly, the characteristic equations of the different energy networks necessary to carry out the steady-state analysis are detailed. The electrical network, the natural gas network, and the thermal network of heat and cold are considered in this paper. After the presentation of the equations, a particular case of the steady-state analysis of a specific multi-energy network is studied. This network is represented graphically, the interconnections between the different energy carriers are described, their technical data are exposed and the equations that have previously been presented theoretically are formulated and developed. Finally, the two iterative numerical resolution methods considered in this paper are presented, as well as the resolution procedure and the results obtained. The pros and cons of the application of both methods are explained. It is verified that the results obtained for the electrical network (voltages in modulus and angle), the natural gas network (pressures), and the thermal network (mass flows and temperatures) are correct since they comply with the distribution, operation, consumption and technical characteristics of the multi-energy network under study.

Keywords: coupling elements, energy carriers, multi-energy networks, steady-state analysis

Procedia PDF Downloads 64

Authors: Pramod Jagtap, Kisan Jadhav, Neha Dand

Abstract:

Risperidone (RISP) is an antipsychotic agent and has low water solubility and nontargeted delivery results in numerous side effects. Hence, an attempt was made to develop SLNs hydrogel for intranasal delivery of RISP to achieve maximum bioavailability and reduction of side effects. RISP loaded SLNs composed of 1.65% (w/v) lipid mass were produced by high shear homogenization (HSH) coupled ultrasound (US) method using glyceryl monostearate (GMS) or Imwitor 900K (solid lipid). The particles were loaded with 0.2% (w/v) of the RISP & surface-tailored with a 2.02% (w/v) non-ionic surfactant Tween® 80. Optimization was done using 32 factorial design using Design Expert® software. The prepared SLNs dispersion incorporated into Polycarbophil AA1 hydrogel (0.5% w/v). The final gel formulation was evaluated for entrapment efficiency, particle size, rheological properties, X ray diffraction, in vitro diffusion, ex vivo permeation using sheep nasal mucosa and histopathological studies for nasocilliary toxicity. The entrapment efficiency of optimized SLNs was found to be 76 ± 2 %, polydispersity index <0.3., particle size 278 ± 5 nm. This optimized batch was incorporated into hydrogel. The pH was found to be 6.4 ± 0.14. The rheological behaviour of hydrogel formulation revealed no thixotropic behaviour. In histopathology study, there was no nasocilliary toxicity observed in nasal mucosa after ex vivo permeation. X-ray diffraction data shows drug was in amorphous form. Ex vivo permeation study shows controlled release profile of drug.

Keywords: ex vivo, particle size, risperidone, solid lipid nanoparticles

Procedia PDF Downloads 403

Authors: Mohamed ElMasry, Ahmad Ragheb, Tareq AbdelAziz, Mohamed Ghazy

Abstract:

Choosing the suitable infrastructure system is becoming more challenging with the increase in demand for heavier structures contemporarily. This is the case where piled raft foundations have been widely used around the world to support heavy structures without extensive settlement. In the latter system, piles are rigidly connected to the raft, and most of the load goes to the soil layer on which the piles are bearing. In spite of that, when soil profiles contain thicker soft clay layers near the surface, or at relatively shallow depths, it is unfavorable to use the rigid piled raft foundation system. Consequently, the disconnected piled raft system was introduced as an alternative approach for the rigidly connected system. In this system, piles are disconnected from the raft using a cushion of soil, mostly of a granular interlayer. The cushion is used to redistribute the stresses among the piles and the subsoil. Piles are also used to stiffen the subsoil, and by this way reduce the settlement without being rigidly connected to the raft. However, the seismic loading effect on such disconnected foundation systems remains a problem, since the soil profiles may include thick clay layers which raise risks of amplification of the dynamic earthquake loads. In this paper, the effects of seismic behavior on the connected and disconnected piled raft systems are studied through a numerical model using Midas GTS NX Software. The study concerns the soil-structure interaction and the expected behavior of the systems. Advantages and disadvantages of each foundation approach are studied, and a comparison between the results are presented to show the effects of using disconnected piled raft systems in highly seismic zones. This was done by showing the excitation amplification in each of the foundation systems.

Keywords: soil-structure interaction, disconnected piled-raft, risks, seismic zones

Procedia PDF Downloads 251

Authors: Abdelkrim Belhaoua, Jean-Pierre Radoux, Mariana Kuras, Vincent Récamier, Martial Piotto, Karim Elbayed, François Proust, Izzie Namer

Abstract:

This paper proposes an augmented reality system dedicated to neurosurgery in order to assist the surgeon during an operation. This work is part of the ExtempoRMN project (Funded by Bpifrance) which aims at analyzing during a surgical operation the metabolic content of tumoral brain biopsy specimens by HRMAS NMR. Patients affected with a brain tumor (gliomas) frequently need to undergo an operation in order to remove the tumoral mass. During the operation, the neurosurgeon removes biopsy specimens using image-guided surgery. The biopsy specimens removed are then sent for HRMAS NMR analysis in order to obtain a better diagnosis and prognosis. Image-guided refers to the use of MRI images and a computer to precisely locate and target a lesion (abnormal tissue) within the brain. This is performed using preoperative MRI images and the BrainLab neuro-navigation system. With the patient MRI images loaded on the Brainlab Cranial neuro-navigation system in the operating theater, surgeons can better identify their approach before making an incision. The Brainlab neuro-navigation tool tracks in real time the position of the instruments and displays their position on the patient MRI data. The results of the biopsy analysis by 1H HRMAS NMR are then sent back to the operating theater and superimposed on the 3D localization system directly on the MRI images. The method we have developed to communicate between the HRMAS NMR analysis software and Brainlab makes use of a combination of C++, VTK and the Insight Toolkit using OpenIGTLink protocol.

Keywords: neuro-navigation, augmented reality, biopsy, BrainLab, HR-MAS NMR

Procedia PDF Downloads 355

Authors: Demiraw Bikila, Tadesse Lejisa, Yosef Tolcha, Chala Bashea, Mehari Meles Tigist Getahun Genet Ashebir, Wossene Habtu, Feyissa Challa, Ousman Mohammed, Melkitu Kassaw, Adisu Kebede, Letebrhan G. Egzeabher, Endalkachew Befekadu, Mistire Wolde, Aster Tsegaye

Abstract:

Background: Even though several factors affect reference intervals (RIs), the company-derived values are currently in use in many laboratories worldwide. However, little or no data is available regarding serum protein RIs, mainly in resource-limited setting countries like Ethiopia. Objective: To establish a reference interval for serum protein electrophoresis of apparently healthy adults in Addis Ababa, Ethiopia. Method: A cross-sectional study was conducted on a total of 297 apparently healthy adults from April-October 2019 in four selected sub-cities (Akaki, Kirkos, Arada, Yeka) of Addis Ababa, Ethiopia. Laboratory analysis of collected samples was performed using Capillarys 2 Flex Piercing analyzer, while statistical analysis was done using SPSS version 23 and med-cal software. Mann-Whitney test was used to check Partitions. Non-parametric method of reference range establishment was performed as per CLSI guideline EP28A3C. Result: The established RIs were: Albumin 53.83-64.59%, 52.24-63.55%; Alpha-1 globulin 3.04-5.40%, 3.44-5.60%; Alpha-2 globulin 8.0-12.67%, 8.44-12.87%; and Beta-1 globulin 5.01-7.38%, 5.14-7.86%. Moreover, Albumin to globulin ratio was 1.16-1.8, 1.09-1.74 for males and females, respectively. The combined RIs for Beta-2 globulin and Gamma globulin were 2.54-4.90% and 12.40-21.66%, respectively. Conclusion: The established reference interval for serum protein fractions revealed gender-specific differences except for Beta-2 globulin and Gamma globulin.

Keywords: serum protein electrophoresis, reference interval, Addis Ababa, Ethiopia

Procedia PDF Downloads 215

Authors: Adel A. Ghobbar

Abstract:

The airline industry is continuously challenging how to safely increase the service life of the aircraft with limited maintenance budgets. Operators are looking for the most qualified maintenance providers of aircraft components, offering the finest customer service. Component owner and maintenance provider is offering an Abacus agreement (Aircraft Component Leasing) to increase the efficiency and productivity of the customer service. To increase the customer service, the current focus on No Fault Found (NFF) units must change into the focus on Early Failure (EF) units. Since the effect of EF units has a significant impact on customer satisfaction, this needs to increase the reliability of EF units at minimal cost, which leads to the goal of this paper. By identifying the reliability of early failure (EF) units with regards to No Fault Found (NFF) units, in particular, the root cause analysis with an integrated cost analysis of EF units with the use of a failure mode analysis tool and a cost model, there will be a set of EF maintenance improvements. The data used for the investigation of the EF units will be obtained from the Pentagon system, an Enterprise Resource Planning (ERP) system used by Fokker Services. The Pentagon system monitors components, which needs to be repaired from Fokker aircraft owners, Abacus exchange pool, and commercial customers. The data will be selected on several criteria’s: time span, failure rate, and cost driver. When the selected data has been acquired, the failure mode and root cause analysis of EF units are initiated. The failure analysis approach tool was implemented, resulting in the proposed failure solution of EF. This will lead to specific EF maintenance improvements, which can be set-up to decrease the EF units and, as a result of this, increasing the reliability. The investigated EFs, between the time period over ten years, showed to have a significant reliability impact of 32% on the total of 23339 unscheduled failures. Since the EFs encloses almost one-third of the entire population.

Keywords: supportability, no fault found, FMEA, early failure, availability, operational reliability, predictive model

Procedia PDF Downloads 109

Authors: Raheleh Farzanmanesh, Christopher J. Weston

Abstract:

Mangroves are forest ecosystems located in the inter-tidal regions of tropical and subtropical coastlines that provide many valuable economic and ecological benefits for millions of people, such as preventing coastal erosion, providing breeding, and feeding grounds, improving water quality, and supporting the well-being of local communities. In addition, mangroves capture and store high amounts of carbon in biomass and soils that play an important role in combating climate change. The decline in mangrove area has prompted government and private sector interest in mangrove conservation and restoration projects to achieve multiple Sustainable Development Goals, from reducing poverty to improving life on land. Mangrove aboveground biomass plays an essential role in the global carbon cycle, climate change mitigation and adaptation by reducing CO2 emissions. However, little information is available about the effectiveness of mangrove sustainable management on mangrove change area and aboveground biomass (AGB). Here, we proposed a method for mapping, modeling, and assessing mangrove area and AGB in two Global Environment Facility (GEF) blue forests projects based on Sentinel-2 Level 1C imagery during their conservation lifetime. The SVR regression model was used to estimate AGB in Tahiry Honko project in Madagascar and the Abu Dhabi Blue Carbon Demonstration Project (Abu Dhabi Emirates. The results showed that mangrove forests and AGB declined in the Tahiry Honko project, while in the Abu Dhabi project increased after the conservation initiative was established. The results provide important information on the impact of mangrove conservation activities and contribute to the development of remote sensing applications for mapping and assessing mangrove forests in blue carbon initiatives.

Keywords: blue carbon, mangrove forest, REDD+, aboveground biomass, Sentinel-2

Procedia PDF Downloads 55

Authors: Mulu G. Gencha, Gebremedhin Simon, Menna Olango

Abstract:

This study was conducted at Hawassa University (HwU) in the Southern Nation Nationalities Peoples Regional State (SNNPRS) of Ethiopia. The prime concern of this study was to examine the writing performances of experimental and control group students, perception of experimental group students, and subject instructors. The course was blended learning (BL). Blended learning is a hybrid of classroom and on-line learning. Participants were eighty students from the School of Computer Science. Forty students attended the BL delivery involved using Face-to-Face (FTF) and campus-based online instruction. All instructors, fifty, of School of Language and Communication Studies along with 10 FGD members participated in the study. The experimental group went to the computer lab two times a week for four months, March-June, 2012, using the local area network (LAN), and software (MOODLE) writing program. On the other hand, the control group, forty students, took the FTF writing course five times a week for four months in similar academic calendar. The three instruments, the attitude questionnaire, tests and FGD were designed to identify views of students, instructors, and FGD participants on BL. At the end of the study, students’ final course scores were evaluated. Data were analyzed using independent samples t-tests. A statistically, significant difference was found between the FTF and BL (p<0.05). The analysis showed that the BL group was more successful than the conventional group. Besides, both instructors and students had positive attitude towards BL. The final section of the thesis showed the potential benefits and challenges, considering the pedagogical implications for the BL, and recommended possible avenues for further works.

Keywords: blended learning, computer attitudes, computer usefulness, computer liking, computer confidence, computer phobia

Procedia PDF Downloads 400

Authors: Prittesh Patel, Rushabh Shah, Krishnamurthy Ramar, Vakulbhushan Bhaskar

Abstract:

The present research work aims at finding genetic differences in the genomes of sugarcane red rot isolates Colletotrichum falcatum Went using Random Amplified Polymorphic DNA (RAPD) and interspersed simple sequence repeat (ISSR) molecular markers. Ten isolates of C. falcatum isolated from different red rot infected sugarcane cultivars stalk were used in present study. The amplified bands were scored across the lanes obtained in 15 RAPD primes and 21 ISSR primes successfully. The data were analysed using NTSYSpc 2.2 software. The results showed 80.6% and 68.07% polymorphism in RPAD and ISSR analysis respectively. Based on the RAPD analysis, ten genotypes were grouped into two major clusters at a cut-off value of 0.75. Geographically distant C. falcatum isolate cfGAN from south Gujarat had a level of similarity with Coimbatore isolate cf8436 presented on separate clade of bootstrapped dendrograms. First and second cluster consisted of five and three isolates respectively, indicating the close relation among them. The 21 ISSR primers produced 119 distinct and scorable loci in that 38 were monomorphic. The number of scorable loci for each primer varied from 2 (ISSR822) to 8 (ISSR807, ISSR823 and ISSR15) with an average of 5.66 loci per primer. Primer ISSR835 amplified the highest number of bands (57), while only 16 bands were obtained by primers ISSR822. Four primers namely ISSR830, ISSR845, ISSR4 and ISSR15 showed the highest value of percentage of polymorphism (100%). The results indicated that both of the marker systems RAPD and ISSR, individually can be effectively used in determination of genetic relationship among C falcatum accessions collected from different parts of south Gujarat.

Keywords: Colletotrichum falcatum, ISSR, RAPD, Red Rot

Procedia PDF Downloads 347

Authors: Ruichong Zhang, Fadi Sawaged, Lotfi Gargab

Abstract:

This paper introduces a wave-based approach for system identification of high-rise building structures with a pair of seismic recordings, which can be used to evaluate structural integrity and detect damage in post-earthquake structural condition assessment. The fundamental of the approach is based on wave features of generalized impulse and frequency response functions (GIRF and GFRF), i.e., wave responses at one structural location to an impulsive motion at another reference location in time and frequency domains respectively. With a pair of seismic recordings at the two locations, GFRF is obtainable as Fourier spectral ratio of the two recordings, and GIRF is then found with the inverse Fourier transformation of GFRF. With an appropriate continuous model for the structure, a closed-form solution of GFRF, and subsequent GIRF, can also be found in terms of wave transmission and reflection coefficients, which are related to structural physical properties above the impulse location. Matching the two sets of GFRF and/or GIRF from recordings and the model helps identify structural parameters such as wave velocity or shear modulus. For illustration, this study examines ten-story Millikan Library in Pasadena, California with recordings of Yorba Linda earthquake of September 3, 2002. The building is modelled as piecewise continuous layers, with which GFRF is derived as function of such building parameters as impedance, cross-sectional area, and damping. GIRF can then be found in closed form for some special cases and numerically in general. Not only does this study reveal the influential factors of building parameters in wave features of GIRF and GRFR, it also shows some system-identification results, which are consistent with other vibration- and wave-based results. Finally, this paper discusses the effectiveness of the proposed model in system identification.

Keywords: wave-based approach, seismic responses of buildings, wave propagation in structures, construction

Procedia PDF Downloads 222

Authors: Shashank Gupta, Iteash Agarwal, Vijayalaxmi Mogiligidda, Rajesh Kumar Krishnan, Sruthi Chennuri, Deepika Aggarwal, Anwesha Hoodati, Sheroy Cooper, Ranjan, Mohammad Bilal Sheik, Bhavya K. M., Manasa Hegde, M. Naveen Krishna, Amit Kumar Chauhan, Mallikarjun Korrapati, Sumit Singh, J. B. Singh, Sunil Sud, Sunil Gupta, Sidhartha Pant, Sankar, Neha Agrawal, Ashish Ranjan, Piyush Mohapatra, Roopak T., Arsh Ahmad, Nanjunda M., Dilip Singh

Abstract:

Major research interests on quantum key distribution (QKD) are primarily focussed on increasing 1. point-to-point transmission distance (1000 Km), 2. secure key rate (Mbps), 3. security of quantum layer (device-independence). It is great to push the boundaries on these fronts, but these isolated approaches are neither scalable nor cost-effective due to the requirements of specialised hardware and different infrastructure. Current and future QKD network requires addressing different sets of challenges apart from distance, key rate, and quantum security. In this regard, we present ChaQra -a sub-quantum network with core features as 1) Crypto agility (integration in the already deployed telecommunication fibres), 2) Software defined networking (SDN paradigm for routing different nodes), 3) reliability (addressing denial-of-service with hybrid quantum safe cryptography), 4) upgradability (modules upgradation based on scientific and technological advancements), 5) Beyond QKD (using QKD network for distributed computing, multi-party computation etc). Our results demonstrate a clear path to create and accelerate quantum secure Indian subcontinent under the national quantum mission.

Keywords: quantum network, quantum key distribution, quantum security, quantum information

Procedia PDF Downloads 31

Authors: Ravneet Kaur, Joydeep Acharya, Sudhanshu Gaur

Abstract:

Artificial Intelligence (AI) has the potential to transform manufacturing by improving shop floor processes such as production, maintenance and quality. However, industrial datasets are notoriously difficult to extract in a real-time, streaming fashion thus, negating potential AI benefits. The main example is some specialized industrial controllers that are operated by custom software which complicates the process of connecting them to an Information Technology (IT) based data acquisition network. Security concerns may also limit direct physical access to these controllers for data acquisition. To connect the Operational Technology (OT) data stored in these controllers to an AI application in a secure, reliable and available way, we propose a novel Industrial IoT (IIoT) solution in this paper. In this solution, we demonstrate how video cameras can be installed in a factory shop floor to continuously obtain images of the controller HMIs. We propose image pre-processing to segment the HMI into regions of streaming data and regions of fixed meta-data. We then evaluate the performance of multiple Optical Character Recognition (OCR) technologies such as Tesseract and Google vision to recognize the streaming data and test it for typical factory HMIs and realistic lighting conditions. Finally, we use the meta-data to match the OCR output with the temporal, domain-dependent context of the data to improve the accuracy of the output. Our IIoT solution enables reliable and efficient data extraction which will improve the performance of subsequent AI applications.

Keywords: human machine interface, industrial internet of things, internet of things, optical character recognition, video analytics

Procedia PDF Downloads 97

Authors: Titus A. Beu

Abstract:

Many modern gene-delivery protocols rely on condensed complexes of DNA with polycations to introduce the genetic payload into cells by endocytosis. In particular, polyethyleneimine (PEI) stands out by a high buffering capacity (enabling the efficient condensation of DNA) and relatively simple fabrication. Realistic computational studies can offer essential insights into the formation process of DNA-PEI polyplexes, providing hints on efficient designs and engineering routes. We present comprehensive computational investigations of solvated PEI and DNA-PEI polyplexes involving calculations at three levels: ab initio, all-atom (AA), and coarse-grained (CG) molecular mechanics. In the first stage, we developed a rigorous AA CHARMM (Chemistry at Harvard Macromolecular Mechanics) force field (FF) for PEI on the basis of accurate ab initio calculations on protonated model pentamers. We validated this atomistic FF by matching the results of extensive molecular dynamics (MD) simulations of structural and dynamical properties of PEI with experimental data. In a second stage, we developed a CG MARTINI FF for PEI by Boltzmann inversion techniques from bead-based probability distributions obtained from AA simulations and ensuring an optimal match between the AA and CG structural and dynamical properties. In a third stage, we combined the developed CG FF for PEI with the standard MARTINI FF for DNA and performed comprehensive CG simulations of DNA-PEI complex formation and condensation. Various technical aspects which are crucial for the realistic modeling of DNA-PEI polyplexes, such as options of treating electrostatics and the relevance of polarizable water models, are discussed in detail. Massive CG simulations (with up to 500 000 beads) shed light on the mechanism and provide time scales for DNA polyplex formation independence of PEI chain size and protonation pattern. The DNA-PEI condensation mechanism is shown to primarily rely on the formation of DNA bundles, rather than by changes of the DNA-strand curvature. The gained insights are expected to be of significant help for designing effective gene-delivery applications.

Keywords: DNA condensation, gene-delivery, polyethylene-imine, molecular dynamics.

Procedia PDF Downloads 108

Authors: Majid Alsubaie, Hamed Sarbazhosseini

Abstract:

Many working environments have experienced increased uncertainty due to the fast-moving and unpredictable world. IT systems development projects, in particular, face several challenges because of their rapidly changing environments and emerging technologies. Information technology organizations within these contexts adapt systems development methodology and new software approaches to address this issue. One of these methodologies is the Agile method, which has gained huge attention in recent years. However, due to failure rates in IT projects, there is an increasing demand for the use of hybrid Agile methods among organizations. The scarce research in the area means that organizations do not have solid evidence-based knowledge for the use of hybrid Agile. This research was designed to provide further insights into the development of hybrid Agile methods within systems development projects, including how frameworks and processes are used and what benefits and challenges are gained and faced as a result of hybrid Agile methods. This paper presents how three organizations (two government and one private) use hybrid Agile methods in their Agile environments. The data was collected through interviews and a review of relevant documents. The results indicate that these organizations do not predominantly use pure Agile. Instead, they are waterfall organizations by virtue of systems nature and complexity, and Agile is used underneath as the delivery model. Prince2 Agile framework, SAFe, Scrum, and Kanban were the identified models and frameworks followed. This study also found that customer satisfaction and the ability to build quickly are the most frequently perceived benefits of using hybrid Agile methods. In addition, team resistance and scope changes are the common challenges identified by research participants in their working environments. The findings can help to understand Agile environmental conditions and projects that can help get better success rates and customer satisfaction.

Keywords: agile, hybrid, IT systems, management, success rate, technology

Procedia PDF Downloads 95

Authors: Ayal Siegel, Moshe Inbar, Amatzya Peled

Abstract:

This study examined the characteristic runoff coefficient in different urban areas. The main area studied is located in the city of Haifa, northern Israel. Haifa spreads out eastward from the Mediterranean seacoast to the top of the Carmel Mountain range with an elevation of 300 m. above sea level. For this research project, four watersheds were chosen, each characterizing a different part of the city; 1) Upper Hadar, a spacious suburb on the upper mountain side; 2) Qiryat Eliezer, a crowded suburb on a level plane of the watershed; 3) Technion, a large technical research university which is located halfway between the top of the mountain range and the coast line. 4) Keret, a remote suburb, on the southwestern outskirts of Haifa. In all of the watersheds found suitable, instruments were installed to continuously measure the water level flowing in the channels. Three rainfall gauges scattered in the study area complete the hydrological requirements for this research project. The runoff coefficient C in peak discharge events was determined by the Rational Formula. The main research finding is the significant relationship between the intensity of rainfall, and the impervious area which is connected to the drainage system of the watershed. For less intense rainfall, the full potential of the connected impervious area will not be exploited. As a result, the runoff coefficient value decreases as do the peak discharge rate and the runoff yield from the storm event. The research results will enable application to other areas by means of hydrological model to be be set up on GIS software that will make it possible to estimate the runoff coefficient of any given city watershed.

Keywords: runoff coefficient, rational method, time of concentration, connected impervious area.

Procedia PDF Downloads 338

Authors: Yu-Hsuan Liu, Ying-Fang Wang

Abstract:

The objectives of the present study are to characterize nanoparticles generated from the laser metal deposition (LMD) process and to estimate particle concentrations deposited in the head (H), that the tracheobronchial (TB) and alveolar (A) regions, respectively. The studied LMD chamber (3.6m × 3.8m × 2.9m) is installed with a robot laser metal deposition machine. Direct-reading instrument of a scanning mobility particle sizer (SMPS, Model 3082, TSI Inc., St. Paul, MN, USA) was used to conduct static sampling inside the chamber for nanoparticle number concentration and particle size distribution measurements. The SMPS obtained particle number concentration at every 3 minutes, the diameter of the SMPS ranged from 11~372 nm when the aerosol and sheath flow rates were set at 0.6 and 6 L / min, respectively. The resultant size distributions were used to predict depositions of nanoparticles at the H, TB, and A regions of the respiratory tract using the UK National Radiological Protection Board’s (NRPB’s) LUDEP Software. Result that the number concentrations of nanoparticles in indoor background and LMD chamber were 4.8×10³ and 4.3×10⁵ # / cm³, respectively. However, the nanoparticles emitted from the LMD process was in the form of the uni-modal with number median diameter (NMD) and geometric standard deviation (GSD) as 142nm and 1.86, respectively. The fractions of the nanoparticles deposited on the alveolar region (A: 69.8%) were higher than the other two regions of the head region (H: 10.9%), tracheobronchial region (TB: 19.3%). This study conducted static sampling to measure the nanoparticles in the LMD process, and the results show that the fraction of particles deposited on the A region was higher than the other two regions. Therefore, applying the characteristics of nanoparticles emitted from LMD process could be provided valuable scientific-based evidence for exposure assessments in the future.

Keywords: exposure assessment, laser metal deposition process, nanoparticle, respiratory region

Procedia PDF Downloads 270

Authors: Richard Ren

Abstract:

Air pollution is a serious danger to international well-being and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.

Keywords: air quality prediction, air pollution, artificial intelligence, machine learning algorithms

Procedia PDF Downloads 107