Search results for: bare machine computing

Authors: Wanchalerm Patanacharoenwong, Panaya Sudta, Prachya Bumrungkun

Abstract:

The paper focuses on the development of a system that combines Internet of Things (IoT) technologies and deep learning algorithms for anomaly detection in residential Electric Vehicle (EV) charging in smart cities. With the increasing number of EVs, ensuring efficient and reliable charging systems has become crucial. The aim of this research is to develop an integrated IoT and deep learning system for detecting anomalies in residential EV charging and enhancing EV load profiling and event detection in smart cities. This approach utilizes IoT devices equipped with infrared cameras to collect thermal images and household EV charging profiles from the database of Thailand utility, subsequently transmitting this data to a cloud database for comprehensive analysis. The methodology includes the use of advanced deep learning techniques such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) algorithms. IoT devices equipped with infrared cameras are used to collect thermal images and EV charging profiles. The data is transmitted to a cloud database for comprehensive analysis. The researchers also utilize feature-based Gaussian mixture models for EV load profiling and event detection. Moreover, the research findings demonstrate the effectiveness of the developed system in detecting anomalies and critical profiles in EV charging behavior. The system provides timely alarms to users regarding potential issues and categorizes the severity of detected problems based on a health index for each charging device. The system also outperforms existing models in event detection accuracy. This research contributes to the field by showcasing the potential of integrating IoT and deep learning techniques in managing residential EV charging in smart cities. The system ensures operational safety and efficiency while also promoting sustainable energy management. The data is collected using IoT devices equipped with infrared cameras and is stored in a cloud database for analysis. The collected data is then analyzed using RNN, LSTM, and feature-based Gaussian mixture models. The approach includes both EV load profiling and event detection, utilizing a feature-based Gaussian mixture model. This comprehensive method aids in identifying unique power consumption patterns among EV owners and outperforms existing models in event detection accuracy. In summary, the research concludes that integrating IoT and deep learning techniques can effectively detect anomalies in residential EV charging and enhance EV load profiling and event detection accuracy. The developed system ensures operational safety and efficiency, contributing to sustainable energy management in smart cities.

Keywords: cloud computing framework, recurrent neural networks, long short-term memory, Iot, EV charging, smart grids

Procedia PDF Downloads 68

Authors: B. Mohammadi, A. Riazati, P. Soltan Sanjari, S. Azimbeik

Abstract:

The ever-increasing development of civic demands on one hand; and the urban constrains for newly establish of infrastructures, on the other hand, perforce the engineering committees to apply non-conflicting methods in order to optimize the results. One of these optimized procedures to establish the main sewerage networks is the pipe jacking and micro-tunneling method. The raw information and researches are based on the experiments of the slurry micro-tunneling project of the Tehran main sewerage network that it has executed by the KAYSON co. The 4985 meters route of the mentioned project that is located nearby the Azadi square and the most vital arteries of Tehran is faced to 45% physical progress nowadays. The boring machine is made by the Herrenknecht and the diameter of the using concrete-polymer pipes are 1600 and 1800 millimeters. Placing and excavating several shafts on the ground and direct Tunnel boring between the axes of issued shafts is one of the requirements of the micro-tunneling. Considering the stream of the ground located shafts should care the hydraulic circumstances, civic conditions, site geography, traffic cautions and etc. The profile length has to convert to many shortened segment lines so the generated angle between the segments will be based in the manhole centers. Each segment line between two continues drive and receive the shaft, displays the jack location, driving angle and the path straight, thus, the diversity of issued angle causes the variety of jack positioning in the shaft. The jacking frame fixing conditions and it's associated dynamic load direction produces various patterns of Stress and Strain distribution and creating fatigues in the shaft wall and the soil surrounded the shaft. This pattern diversification makes the shaft wall transformed, unbalanced subsidence and alteration in the pipe jacking Stress Contour. This research is based on experiments of the Tehran's west sewerage plan and the numerical analysis the interaction of the soil around the shaft, shaft walls and the Jacking frame direction and finally, the suitable or unsuitable location of the pipe jacking shaft will be determined.

Keywords: underground structure, micro-tunneling, fatigue analysis, dynamic-soil–structure interaction, underground water, finite element analysis

Procedia PDF Downloads 320

Authors: Nareshkumar Harale, B. B. Meshram

Abstract:

The continued exponential growth of successful cyber intrusions against today’s businesses has made it abundantly clear that traditional perimeter security measures are no longer adequate and effective. We evolved the network trust architecture from trust-untrust to Zero-Trust, With Zero Trust, essential security capabilities are deployed in a way that provides policy enforcement and protection for all users, devices, applications, data resources, and the communications traffic between them, regardless of their location. Information exchange over the Internet, in spite of inclusion of advanced security controls, is always under innovative, inventive and prone to cyberattacks. TCP/IP protocol stack, the adapted standard for communication over network, suffers from inherent design vulnerabilities such as communication and session management protocols, routing protocols and security protocols are the major cause of major attacks. With the explosion of cyber security threats, such as viruses, worms, rootkits, malwares, Denial of Service attacks, accomplishing efficient and effective intrusion detection and prevention is become crucial and challenging too. In this paper, we propose a design and analysis model for next generation network intrusion detection and protection system as part of layered security strategy. The proposed system design provides intrusion detection for wide range of attacks with layered architecture and framework. The proposed network intrusion classification framework deals with cyberattacks on standard TCP/IP protocol, routing protocols and security protocols. It thereby forms the basis for detection of attack classes and applies signature based matching for known cyberattacks and data mining based machine learning approaches for unknown cyberattacks. Our proposed implemented software can effectively detect attacks even when malicious connections are hidden within normal events. The unsupervised learning algorithm applied to network audit data trails results in unknown intrusion detection. Association rule mining algorithms generate new rules from collected audit trail data resulting in increased intrusion prevention though integrated firewall systems. Intrusion response mechanisms can be initiated in real-time thereby minimizing the impact of network intrusions. Finally, we have shown that our approach can be validated and how the analysis results can be used for detecting and protection from the new network anomalies.

Keywords: network intrusion detection, network intrusion prevention, association rule mining, system analysis and design

Procedia PDF Downloads 228

Authors: Tassadit Issaadi Hamitouche, Nicolas Gillard, Jean Petit, Valerie Lavaste, Celine Mayousse

Abstract:

Water is a fundamental resource for the industry. It is taken from the environment either from municipal distribution networks or from various natural water sources such as the sea, ocean, rivers, aquifers, etc. Once used, water is discharged into the environment, reprocessed at the plant or treatment plants. These withdrawals and discharges have a direct impact on natural water resources. These impacts can apply to the quantity of water available, the quality of the water used, or to impacts that are more complex to measure and less direct, such as the health of the population downstream from the watercourse, for example. Based on the analysis of data (meteorological, river characteristics, physicochemical substances), we wish to predict water stress episodes and anticipate prefectoral decrees, which can impact the performance of plants and propose improvement solutions, help industrialists in their choice of location for a new plant, visualize possible interactions between companies to optimize exchanges and encourage the pooling of water treatment solutions, and set up circular economies around the issue of water. The development of a system for the collection, processing, and use of data related to water resources requires the functional constraints specific to the latter to be made explicit. Thus the system will have to be able to store a large amount of data from sensors (which is the main type of data in plants and their environment). In addition, manufacturers need to have 'near-real-time' processing of information in order to be able to make the best decisions (to be rapidly notified of an event that would have a significant impact on water resources). Finally, the visualization of data must be adapted to its temporal and geographical dimensions. In this study, we set up an infrastructure centered on the TICK application stack (for Telegraf, InfluxDB, Chronograf, and Kapacitor), which is a set of loosely coupled but tightly integrated open source projects designed to manage huge amounts of time-stamped information. The software architecture is coupled with the cross-industry standard process for data mining (CRISP-DM) data mining methodology. The robust architecture and the methodology used have demonstrated their effectiveness on the study case of learning the level of a river with a 7-day horizon. The management of water and the activities within the plants -which depend on this resource- should be considerably improved thanks, on the one hand, to the learning that allows the anticipation of periods of water stress, and on the other hand, to the information system that is able to warn decision-makers with alerts created from the formalization of prefectoral decrees.

Keywords: data mining, industry, machine Learning, shortage, water resources

Procedia PDF Downloads 122

Authors: Sahar El Kasmi, Ayoub Aziz, Saadia Lharti, Mohammed El Janati, Boubker Boukili, Nacer El Motawakil, Mayom Chol Luka Awan

Abstract:

Two types of geomaterials (Red Triassic clay from the Maaziz region and Yellow Pliocene clay from the Akrach region) were used to create different mixtures for the fabrication of ceramic bricks. This study investigated the influence of the Pliocene clay on the overall composition and mechanical properties of the Triassic clay. The red Triassic clay, sourced from Maaziz, underwent various mechanical processes and treatments to facilitate its transformation into ceramic bricks for construction. The triassic clay was subjected to a drying chamber and a heating chamber at 100°C to remove moisture. Subsequently, the dried clay samples were processed using a Planetary Babs ll Mill to reduce particle size and improve homogeneity. The resulting clay material was sieved, and the fine particles below 100 mm were collected for further analysis. In parallel, the Miocene marl obtained from the Akrach region was fragmented into finer particles and subjected to similar drying, grinding, and sieving procedures as the triassic clay. The two clay samples are then amalgamated and homogenized in different proportions. Precise measurements were taken using a weighing balance, and mixtures of 90%, 80%, and 70% Triassic clay with 10%, 20%, and 30% yellow clay were prepared, respectively. To evaluate the impact of Pliocene marl on the composition, the prepared clay mixtures were spread evenly and treated with a water modifier to enhance plasticity. The clay was then molded using a brick-making machine, and the initial manipulation process was observed. Additional batches were prepared with incremental amounts of Pliocene marl to further investigate its effect on the fracture behavior of the clay, specifically their resistance. The molded clay bricks were subjected to compression tests to measure their strength and resistance to deformation. Additional tests, such as water absorption tests, were also conducted to assess the overall performance of the ceramic bricks fabricated from the different clay mixtures. The results were analyzed to determine the influence of the Pliocene marl on the strength and durability of the Triassic clay bricks. The results indicated that the incorporation of Pliocene clay reduced the fracture of the triassic clay, with a noticeable reduction observed at 10% addition. No fractures were observed when 20% and 30% of yellow clay are added. These findings suggested that yellow clay can enhance the mechanical properties and structural integrity of red clay-based products.

Keywords: triassic clay, pliocene clay, mineralogical composition, geo-materials, ceramics, akach region, maaziz region, morocco.

Procedia PDF Downloads 90

Authors: Eva Laryea, Clement Yeboah Authors

Abstract:

A pretest-posttest within subjects, experimental design was employed to examine the effects of a computerized basic statistics learning game on achievement and statistics-related anxiety of students enrolled in introductory graduate statistics course. Participants (N = 34) were graduate students in a variety of programs at state-funded research university in the Southeast United States. We analyzed pre-test posttest differences using paired samples t-tests for achievement and for statistics anxiety. The results of the t-test for knowledge in statistics were found to be statistically significant indicating significant mean gains for statistical knowledge as a function of the game-based intervention. Likewise, the results of the t-test for statistics-related anxiety were also statistically significant indicating a decrease in anxiety from pretest to posttest. The implications of the present study are significant for both teachers and students. For teachers, using computer games developed by the researchers can help to create a more dynamic and engaging classroom environment, as well as improve student learning outcomes. For students, playing these educational games can help to develop important skills such as problem solving, critical thinking, and collaboration. Students can develop interest in the subject matter and spend quality time to learn the course as they play the game without knowing that they are even learning the presupposed hard course. The future directions of the present study are promising, as technology continues to advance and become more widely available. Some potential future developments include the integration of virtual and augmented reality into educational games, the use of machine learning and artificial intelligence to create personalized learning experiences, and the development of new and innovative game-based assessment tools. It is also important to consider the ethical implications of computer game-based pedagogy, such as the potential for games to perpetuate harmful stereotypes and biases. As the field continues to evolve, it will be crucial to address these issues and work towards creating inclusive and equitable learning experiences for all students. This study has the potential to revolutionize the way basic statistics graduate students learn and offers exciting opportunities for future development and research. It is an important area of inquiry for educators, researchers, and policymakers, and will continue to be a dynamic and rapidly evolving field for years to come.

Keywords: pretest-posttest within subjects, experimental design, achievement, statistics-related anxiety

Procedia PDF Downloads 59

Authors: Jeremy Jenrette, Z. Y. C. Liu, Pranav Chimote, Edward Fox, Trevor Hastie, Francesco Ferretti

Abstract:

Suitable shark conservation depends on well-informed population assessments. Direct methods such as scientific surveys and fisheries monitoring are adequate for defining population statuses, but species-specific indices of abundance and distribution coming from these sources are rare for most shark species. We can rapidly fill these information gaps by boosting media-based remote monitoring efforts with machine learning and automation. We created a database of shark images by sourcing 24,546 images covering 219 species of sharks from the web application spark pulse and the social network Instagram. We used object detection to extract shark features and inflate this database to 53,345 images. We packaged object-detection and image classification models into a Shark Detector bundle. We developed the Shark Detector to recognize and classify sharks from videos and images using transfer learning and convolutional neural networks (CNNs). We applied these models to common data-generation approaches of sharks: boosting training datasets, processing baited remote camera footage and online videos, and data-mining Instagram. We examined the accuracy of each model and tested genus and species prediction correctness as a result of training data quantity. The Shark Detector located sharks in baited remote footage and YouTube videos with an average accuracy of 89\%, and classified located subjects to the species level with 69\% accuracy (n =\ eight species). The Shark Detector sorted heterogeneous datasets of images sourced from Instagram with 91\% accuracy and classified species with 70\% accuracy (n =\ 17 species). Data-mining Instagram can inflate training datasets and increase the Shark Detector’s accuracy as well as facilitate archiving of historical and novel shark observations. Base accuracy of genus prediction was 68\% across 25 genera. The average base accuracy of species prediction within each genus class was 85\%. The Shark Detector can classify 45 species. All data-generation methods were processed without manual interaction. As media-based remote monitoring strives to dominate methods for observing sharks in nature, we developed an open-source Shark Detector to facilitate common identification applications. Prediction accuracy of the software pipeline increases as more images are added to the training dataset. We provide public access to the software on our GitHub page.

Keywords: classification, data mining, Instagram, remote monitoring, sharks

Procedia PDF Downloads 122

Authors: Kevin De Castro Cogle, Mirian Kubo, Maria Anastasiadi, Fady Mohareb, Claire Rossi

Abstract:

Background: The bioaccessibility of bioactive compounds is a critical determinant of the nutritional quality of various food products. Despite its importance, there is a limited number of comprehensive studies aimed at assessing how the composition of a food matrix influences the bioaccessibility of a compound of interest. This knowledge gap has prompted a growing need to investigate the intricate relationship between food matrix formulations and the bioaccessibility of bioactive compounds. One such class of bioactive compounds that has attracted considerable attention is curcuminoids. These naturally occurring phytochemicals, extracted from the roots of Curcuma longa, have gained popularity owing to their purported health benefits and also well known for their poor bioaccessibility Project aim: The primary objective of this research project is to systematically assess the influence of matrix composition on the bioaccessibility of curcuminoids. Additionally, this study aimed to develop a series of predictive models for bioaccessibility, providing valuable insights for optimising the formula for functional foods and provide more descriptive nutritional information to potential consumers. Methods: Food formulations enriched with curcuminoids were subjected to in vitro digestion simulation, and their bioaccessibility was characterized with chromatographic and spectrophotometric techniques. The resulting data served as the foundation for the development of predictive models capable of estimating bioaccessibility based on specific physicochemical properties of the food matrices. Results: One striking finding of this study was the strong correlation observed between the concentration of macronutrients within the food formulations and the bioaccessibility of curcuminoids. In fact, macronutrient content emerged as a very informative explanatory variable of bioaccessibility and was used, alongside other variables, as predictors in a Bayesian hierarchical model that predicted curcuminoid bioaccessibility accurately (optimisation performance of 0.97 R2) for the majority of cross-validated test formulations (LOOCV of 0.92 R2). These preliminary results open the door to further exploration, enabling researchers to investigate a broader spectrum of food matrix types and additional properties that may influence bioaccessibility. Conclusions: This research sheds light on the intricate interplay between food matrix composition and the bioaccessibility of curcuminoids. This study lays a foundation for future investigations, offering a promising avenue for advancing our understanding of bioactive compound bioaccessibility and its implications for the food industry and informed consumer choices.

Keywords: bioactive bioaccessibility, food formulation, food matrix, machine learning, probabilistic modelling

Procedia PDF Downloads 68

Authors: S. Agarwal, A. Rani

Abstract:

Catechol is a natural polyphenolic compound that widely exists in higher plants such as teas, vegetables, fruits, tobaccos, and some traditional Chinese medicines. The fly ash-based zeolites are capable of absorbing a wide range of pollutants. But the process of zeolite synthesis is time-consuming and requires technical setups by the industries. The marketed costs of zeolites are quite high restricting its use by small-scale industries for the removal of phenolic compounds. The present research proposes a simple method of alkaline treatment of FA to produce an effective adsorbent for catechol removal from wastewater. The experimental parameter such as pH, temperature, initial concentration and adsorbent dose on the removal of catechol were studied in batch reactor. For this purpose the adsorbent materials were mixed with aqueous solutions containing catechol ranging in 50 – 200 mg/L initial concentrations and then shaken continuously in a thermostatic Orbital Incubator Shaker at 30 ± 0.1 °C for 24 h. The samples were withdrawn from the shaker at predetermined time interval and separated by centrifugation (Centrifuge machine MBL-20) at 2000 rpm for 4 min. to yield a clear supernatant for analysis of the equilibrium concentrations of the solutes. The concentrations were measured with Double Beam UV/Visible spectrophotometer (model Spectrscan UV 2600/02) at the wavelength of 275 nm for catechol. In the present study, the use of low-cost adsorbent (BTFA) derived from coal fly ash (FA), has been investigated as a substitute of expensive methods for the sequestration of catechol. The FA and BTFA adsorbents were well characterized by XRF, FE-SEM with EDX, FTIR, and surface area and porosity measurement which proves the chemical constituents, functional groups and morphology of the adsorbents. The catechol adsorption capacities of synthesized BTFA and native material were determined. The adsorption was slightly increased with an increase in pH value. The monolayer adsorption capacities of FA and BTFA for catechol were 100 mg g⁻¹ and 333.33 mg g⁻¹ respectively, and maximum adsorption occurs within 60 minutes for both adsorbents used in this test. The equilibrium data are fitted by Freundlich isotherm found on the basis of error analysis (RMSE, SSE, and χ²). Adsorption was found to be spontaneous and exothermic on the basis of thermodynamic parameters (ΔG°, ΔS°, and ΔH°). Pseudo-second-order kinetic model better fitted the data for both FA and BTFA. BTFA showed large adsorptive characteristics, high separation selectivity, and excellent recyclability than FA. These findings indicate that BTFA could be employed as an effective and inexpensive adsorbent for the removal of catechol from wastewater.

Keywords: catechol, fly ash, isotherms, kinetics, thermodynamic parameters

Procedia PDF Downloads 127

Authors: Rio Hirakawa, Christian Gundlach, Sven Hartwig

Abstract:

In recent years, the use of aluminium has further expanded and is expected to replace steel in the future as vehicles become lighter and more recyclable in order to reduce greenhouse gas (GHG) emissions and improve fuel economy. In line with this, structures and components are becoming increasingly multi-material, with different materials, including aluminium, being used in combination to improve mechanical utility and performance. A common method of assembling dissimilar materials is mechanical fastening, but it has several drawbacks, such as increased manufacturing processes and the influence of substrate-specific mechanical properties. Adhesive bonding and fusion bonding are methods that overcome the above disadvantages. In these two joining methods, surface pre-treatment of the substrate is always necessary to ensure the strength and durability of the joint. Previous studies have shown that laser surface treatment improves the strength and durability of the joint. Yan et al. showed that laser surface treatment of aluminium alloys changes α-Al2O3 in the oxide layer to γ-Al2O3. As γ-Al2O3 has a large specific surface area, is very porous and chemically active, laser-treated aluminium surfaces are expected to undergo physico-chemical changes over time and adsorb moisture and organic substances from the air or storage atmosphere. The impurities accumulated on the laser-treated surface may be released at the adhesive and bonding interface by the heat input to the bonding system during the joining phase, affecting the strength and durability of the joint. However, only a few studies have discussed the effect of such storage periods on laser-treated surfaces. This paper, therefore, investigates the ageing of laser-treated aluminium alloy surfaces through thermal analysis, electrochemical analysis and microstructural observations.AlMg3 of 0.5 mm and 1.5 mm thickness was cut using a water-jet cutting machine, cleaned and degreased with isopropanol and surface pre-treated with a pulsed fibre laser at 1060 nm wavelength, 70 W maximum power and 55 kHz repetition frequency. The aluminium surface was then analysed using SEM, thermogravimetric analysis (TGA), Fourier transform infrared spectroscopy (FTIR) and cyclic voltammetry (CV) after storage in air for various periods ranging from one day to several months TGA and FTIR analysed impurities adsorbed on the aluminium surface, while CV revealed changes in the true electrochemically active surface area. SEM also revealed visual changes on the treated surface. In summary, the changes in the laser-treated aluminium surface with storage time were investigated, and the final results were used to determine the appropriate storage period.

Keywords: laser surface treatment, pre-treatment, adhesion, bonding, corrosion, durability, dissimilar material interface, automotive, aluminium alloys

Procedia PDF Downloads 80

Authors: Piret Pernik

Abstract:

Based on strategic, operational, and technical analysis of the ongoing armed conflict in Ukraine, this paper will examine the opportunities and risks of using small commercial drones (dual-use unmanned aerial vehicles, UAV) for military purposes. The paper discusses the opportunities and risks in the information domain, encompassing both cyber and electromagnetic interference and attacks. The paper will draw conclusions on a possible strategic impact to the battlefield outcomes in the modern armed conflicts by the widespread use of dual-use UAVs. This article will contribute to filling the gap in the literature by examining based on empirical data cyberattacks and electromagnetic interference. Today, more than one hundred states and non-state actors possess UAVs ranging from low cost commodity models, widely are dual-use, available and affordable to anyone, to high-cost combat UAVs (UCAV) with lethal kinetic strike capabilities, which can be enhanced with Artificial Intelligence (AI) and Machine Learning (ML). Dual-use UAVs have been used by various actors for intelligence, reconnaissance, surveillance, situational awareness, geolocation, and kinetic targeting. Thus they function as force multipliers enabling kinetic and electronic warfare attacks and provide comparative and asymmetric operational and tactical advances. Some go as far as argue that automated (or semi-automated) systems can change the character of warfare, while others observe that the use of small drones has not changed the balance of power or battlefield outcomes. UAVs give considerable opportunities for commanders, for example, because they can be operated without GPS navigation, makes them less vulnerable and dependent on satellite communications. They can and have been used to conduct cyberattacks, electromagnetic interference, and kinetic attacks. However, they are highly vulnerable to those attacks themselves. So far, strategic studies, literature, and expert commentary have overlooked cybersecurity and electronic interference dimension of the use of dual use UAVs. The studies that link technical analysis of opportunities and risks with strategic battlefield outcomes is missing. It is expected that dual use commercial UAV proliferation in armed and hybrid conflicts will continue and accelerate in the future. Therefore, it is important to understand specific opportunities and risks related to the crowdsourced use of dual-use UAVs, which can have kinetic effects. Technical countermeasures to protect UAVs differ depending on a type of UAV (small, midsize, large, stealth combat), and this paper will offer a unique analysis of small UAVs both from the view of opportunities and risks for commanders and other actors in armed conflict.

Keywords: dual-use technology, cyber attacks, electromagnetic warfare, case studies of cyberattacks in armed conflicts

Procedia PDF Downloads 102

Authors: Xiangtuo Chen, Paul-Henry Cournéde

Abstract:

Crop yield prediction is a paramount issue in agriculture. The main idea of this paper is to find out efficient way to predict the yield of corn based meteorological records. The prediction models used in this paper can be classified into model-driven approaches and data-driven approaches, according to the different modeling methodologies. The model-driven approaches are based on crop mechanistic modeling. They describe crop growth in interaction with their environment as dynamical systems. But the calibration process of the dynamic system comes up with much difficulty, because it turns out to be a multidimensional non-convex optimization problem. An original contribution of this paper is to propose a statistical methodology, Multi-Scenarios Parameters Estimation (MSPE), for the parametrization of potentially complex mechanistic models from a new type of datasets (climatic data, final yield in many situations). It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction is free of the complex biophysical process. But it has some strict requirements about the dataset. A second contribution of the paper is the comparison of these model-driven methods with classical data-driven methods. For this purpose, we consider two classes of regression methods, methods derived from linear regression (Ridge and Lasso Regression, Principal Components Regression or Partial Least Squares Regression) and machine learning methods (Random Forest, k-Nearest Neighbor, Artificial Neural Network and SVM regression). The dataset consists of 720 records of corn yield at county scale provided by the United States Department of Agriculture (USDA) and the associated climatic data. A 5-folds cross-validation process and two accuracy metrics: root mean square error of prediction(RMSEP), mean absolute error of prediction(MAEP) were used to evaluate the crop prediction capacity. The results show that among the data-driven approaches, Random Forest is the most robust and generally achieves the best prediction error (MAEP 4.27%). It also outperforms our model-driven approach (MAEP 6.11%). However, the method to calibrate the mechanistic model from dataset easy to access offers several side-perspectives. The mechanistic model can potentially help to underline the stresses suffered by the crop or to identify the biological parameters of interest for breeding purposes. For this reason, an interesting perspective is to combine these two types of approaches.

Keywords: crop yield prediction, crop model, sensitivity analysis, paramater estimation, particle swarm optimization, random forest

Procedia PDF Downloads 232

Authors: Rangrong Yoksan, Amporn Sane, Nattaporn Khanoonkon, Chanakorn Yokesahachart, Narumol Noivoil, Khanh Minh Dang

Abstract:

Polylactic acid (PLA) is the most commercially available bio-based and biodegradable plastic at present. PLA has been used in plastic related industries including single-used containers, disposable and environmentally friendly packaging owing to its renewability, compostability, biodegradability, and safety. Although PLA demonstrates reasonably good optical, physical, mechanical, and barrier properties comparable to the existing petroleum-based plastics, its brittleness and mold shrinkage as well as its price are the points to be concerned for the production of rigid and semi-rigid packaging. Blending PLA with other bio-based polymers including thermoplastic starch (TPS) is an alternative not only to achieve a complete bio-based plastic, but also to reduce the brittleness, shrinkage during molding and production cost of the PLA-based products. TPS is a material produced mainly from starch which is cheap, renewable, biodegradable, compostable, and non-toxic. It is commonly prepared by a plasticization of starch under applying heat and shear force. Although glycerol has been reported as one of the most plasticizers used for preparing TPS, its migration caused the surface stickiness of the TPS products. In some cases, mixed plasticizers or natural fibers have been applied to impede the retrogradation of starch or reduce the migration of glycerol. The introduction of fibers into TPS-based materials could reinforce the polymer matrix as well. Therefore, the objective of the present research is to study the effect of starch type (i.e. native starch and phosphate starch), plasticizer type (i.e. glycerol and xylitol with a weight ratio of glycerol to xylitol of 100:0, 75:25, 50:50, 25:75, and 0:100), and fiber content (i.e. in the range of 1-25 % wt) on properties of PLA/TPS blend and composite. PLA/TPS blends and composites were prepared using a twin-screw extruder and then converted into dumbbell-shaped specimens using an injection molding machine. The PLA/TPS blends prepared by using phosphate starch showed higher tensile strength and stiffness than the blends prepared by using the native one. In contrast, the blends from native starch exhibited higher extensibility and heat distortion temperature (HDT) than those from the modified starch. Increasing xylitol content resulted in enhanced tensile strength, stiffness, and water resistance, but decreased extensibility and HDT of the PLA/TPS blend. Tensile properties and hydrophobicity of the blend could be improved by incorporating silane treated-jute fibers.

Keywords: polylactic acid, thermoplastic starch, Jute fiber, composite, blend

Procedia PDF Downloads 424

Authors: Chetra Mang, Ahmadali Tahmasebimoradi, Xavier Lorang

Abstract:

Lattice structures are widely used in various applications, especially in aeronautic, aerospace, and medical applications because of their high performance properties. Thanks to advancement of the additive manufacturing technology, the lattice structures can be manufactured by different methods such as laser beam melting technology. However, the presence of geometric defects in the lattice structures is inevitable due to the manufacturing process. The geometric defects may have high impact on the mechanical strength of the structures. This work analyzes the correlation between the manufacturing parameters and the mechanical strengths of the lattice structures. To do that, two types of the lattice structures; body-centered cubic with z-struts (BCCZ) structures made of Inconel718, and body-centered cubic (BCC) structures made of Scalmalloy, are manufactured by laser melting beam machine using Taguchi design of experiment. Each structure is placed on the substrate with a specific position and orientation regarding the roller direction of deposed metal powder. The position and orientation are considered as the manufacturing parameters. The geometric defects of each beam in the lattice are characterized and used to build the geometric model in order to perform simulations. Then, the mechanical strengths are defined by the homogeneous response as Young's modulus and yield strength. The distribution of mechanical strengths is observed as a function of manufacturing parameters. The mechanical response of the BCCZ structure is stretch-dominated, i.e., the mechanical strengths are directly dependent on the strengths of the vertical beams. As the geometric defects of vertical beams are slightly changed based on their position/orientation on the manufacturing substrate, the mechanical strengths are less dispersed. The manufacturing parameters are less influenced on the mechanical strengths of the structure BCCZ. The mechanical response of the BCC structure is bending-dominated. The geometric defects of inclined beam are highly dispersed within a structure and also based on their position/orientation on the manufacturing substrate. For different position/orientation on the substrate, the mechanical responses are highly dispersed as well. This shows that the mechanical strengths are directly impacted by manufacturing parameters. In addition, this work is carried out to study the uncertainty propagation of the geometric defects on the mechanical strength of the BCC lattice structure made of Scalmalloy. To do that, we observe the distribution of mechanical strengths of the lattice according to the distribution of the geometric defects. A probability density law is determined based on a statistical hypothesis corresponding to the geometric defects of the inclined beams. The samples of inclined beams are then randomly drawn from the density law to build the lattice structure samples. The lattice samples are then used for simulation to characterize the mechanical strengths. The results reveal that the distribution of mechanical strengths of the structures with the same manufacturing parameters is less dispersed than one of the structures with different manufacturing parameters. Nevertheless, the dispersion of mechanical strengths due to the structures with the same manufacturing parameters are unneglectable.

Keywords: geometric defects, lattice structure, mechanical strength, uncertainty propagation

Procedia PDF Downloads 124

Authors: Tadele Tesfaw, Ajit Pal Singh, Abebaw Mekonnen Gezahegn

Abstract:

Welding is a basic manufacturing process for making components or assemblies. Recent welding economics research has focused on developing the reliable machinery database to ensure optimum production. Research on welding of materials like steel is still critical and ongoing. Welding input parameters play a very significant role in determining the quality of a weld joint. The metal active gas (MAG) welding parameters are the most important factors affecting the quality, productivity and cost of welding in many industrial operations. The aim of this study is to investigate the optimization process parameters for metal active gas welding for 60x60x5mm dead mild steel plate work-piece using Taguchi method to formulate the statistical experimental design using semi-automatic welding machine. An experimental study was conducted at Bishoftu Automotive Industry, Bishoftu, Ethiopia. This study presents the influence of four welding parameters (control factors) like welding voltage (volt), welding current (ampere), wire speed (m/min.), and gas (CO2) flow rate (lit./min.) with three different levels for variability in the welding hardness. The objective functions have been chosen in relation to parameters of MAG welding i.e., welding hardness in final products. Nine experimental runs based on an L9 orthogonal array Taguchi method were performed. An orthogonal array, signal-to-noise (S/N) ratio and analysis of variance (ANOVA) are employed to investigate the welding characteristics of dead mild steel plate and used in order to obtain optimum levels for every input parameter at 95% confidence level. The optimal parameters setting was found is welding voltage at 22 volts, welding current at 125 ampere, wire speed at 2.15 m/min and gas flow rate at 19 l/min by using the Taguchi experimental design method within the constraints of the production process. Finally, six conformations welding have been carried out to compare the existing values; the predicated values with the experimental values confirm its effectiveness in the analysis of welding hardness (quality) in final products. It is found that welding current has a major influence on the quality of welded joints. Experimental result for optimum setting gave a better hardness of welding condition than initial setting. This study is valuable for different material and thickness variation of welding plate for Ethiopian industries.

Keywords: Weld quality, metal active gas welding, dead mild steel plate, orthogonal array, analysis of variance, Taguchi method

Procedia PDF Downloads 482

Authors: África Vicario, Fernando J. Álvarez, Felipe Parralejo, Fernando Aranda

Abstract:

The irrigation systems of traditional agriculture, such as gravity-fed irrigation, produce a great waste of water because, generally, there is no control over the amount of water supplied in relation to the water needed. The AIRON Project tries to solve this problem by implementing an IoT-based system to sensor the irrigation plots so that the state of the crops and the amount of water used for irrigation can be known remotely. The IoT system consists of a sensor network that measures the humidity of the soil, the weather conditions (temperature, relative humidity, wind and solar radiation) and the irrigation water flow. The communication between this network and a central gateway is conducted by means of long-range wireless communication that depends on the characteristics of the irrigation plot. The main objective of the AIRON project is to deploy an IoT sensor network in two different plots of the irrigation community of Aranjuez in the Spanish region of Madrid. The first plot is 2 km away from the central gateway, so LoRa has been used as the base communication technology. The problem with this plot is the absence of mains electric power, so devices with energy-saving modes have had to be used to maximize the external batteries' use time. An ESP32 SOC board with a LoRa module is employed in this case to gather data from the sensor network and send them to a gateway consisting of a Raspberry Pi with a LoRa hat. The second plot is located 18 km away from the gateway, a range that hampers the use of LoRa technology. In order to establish reliable communication in this case, the long-term evolution (LTE) standard is used, which makes it possible to reach much greater distances by using the cellular network. As mains electric power is available in this plot, a Raspberry Pi has been used instead of the ESP32 board to collect sensor data. All data received from the two plots are stored on a proprietary server located at the irrigation management company's headquarters. The analysis of these data by means of machine learning algorithms that are currently under development should allow a short-term prediction of the irrigation water demand that would significantly reduce the waste of this increasingly valuable natural resource. The major finding of this work is the real possibility of deploying a remote sensing system for irrigated plots by using Commercial-Off-The-Shelf (COTS) devices, easily scalable and adaptable to design requirements such as the distance to the control center or the availability of mains electrical power at the site.

Keywords: internet of things, irrigation water control, LoRa, LTE, smart farming

Procedia PDF Downloads 87

Authors: Zainab Atia, Hongwei He, Panagiotis Sarantopoulos

Abstract:

Over the past few years, firms have witnessed a massive increase in sophisticated algorithmic deployment, which has become quite pervasive in today’s modern society. With the wide availability of data for retailers, the ability to track consumers using algorithmic pricing has become an integral option in online platforms. As more companies are transforming their businesses and relying more on massive technological advancement, pricing algorithmic systems have brought attention and given rise to its wide adoption, with many accompanying benefits and challenges to be found within its usage. With the overall aim of increasing profits by organizations, algorithmic pricing is becoming a sound option by enabling suppliers to cut costs, allowing better services, improving efficiency and product availability, and enhancing overall consumer experiences. The adoption of algorithms in retail has been pioneered and widely used in literature across varied fields, including marketing, computer science, engineering, economics, and public policy. However, what is more, alarming today is the comprehensive understanding and focus of this technology and its associated ethical influence on consumers’ perceptions and behaviours. Indeed, due to algorithmic ethical concerns, consumers are found to be reluctant in some instances to share their personal data with retailers, which reduces their retention and leads to negative consumer outcomes in some instances. This, in its turn, raises the question of whether firms can still manifest the acceptance of such technologies by consumers while minimizing the ethical transgressions accompanied by their deployment. As recent modest research within the area of marketing and consumer behavior, the current research advances the literature on algorithmic pricing, pricing ethics, consumers’ perceptions, and price fairness literature. With its empirical focus, this paper aims to contribute to the literature by applying the distinction of the two common types of algorithmic pricing, dynamic and personalized, while measuring their relative effect on consumers’ behavioural outcomes. From a managerial perspective, this research offers significant implications that pertain to providing a better human-machine interactive environment (whether online or offline) to improve both businesses’ overall performance and consumers’ wellbeing. Therefore, by allowing more transparent pricing systems, businesses can harness their generated ethical strategies, which fosters consumers’ loyalty and extend their post-purchase behaviour. Thus, by defining the correct balance of pricing and right measures, whether using dynamic or personalized (or both), managers can hence approach consumers more ethically while taking their expectations and responses at a critical stance.

Keywords: algorithmic pricing, dynamic pricing, personalized pricing, price ethicality

Procedia PDF Downloads 92

Authors: Douglas N. Simoes, Michele Pittol, Vanda F. Ribeiro, Daiane Tomacheski, Ruth M. C. Santana

Abstract:

Thermoplastic elastomers (TPE) compounds are used in a wide range of applications, like home appliances, automotive components, medical devices, footwear, and others. These materials are susceptible to microbial attack, causing a crack in polymer chains compounds based on SEBS copolymers, poly (styrene-b-(ethylene-co-butylene)-b-styrene, are a class of TPE, largely used in domestic appliances like refrigerator seals (gaskets), bath mats and sink squeegee. Moisture present in some areas (such as shower area and sink) in addition to organic matter provides favorable conditions for microbial survival and proliferation, contributing to the spread of diseases besides the reduction of product life cycle due the biodegradation process. Zinc oxide (ZnO) has been studied as an alternative antibacterial additive due its biocidal effect. It is important to know the influence of these additives in the properties of the compounds, both at the beginning and during the life cycle. In that sense, the aim of this study was to evaluate the effect of accelerated aging in oven on antibacterial and mechanical properties of ZnO loaded SEBS based TPE compounds. Two different comercial zinc oxide, named as WR and Pe were used in proportion of 1%. A compound with no antimicrobial additive (standard) was also tested. The compounds were prepared using a co-rotating double screw extruder (L/D ratio of 40/1 and 16 mm screw diameter). The extrusion parameters were kept constant for all materials, screw rotation rate was set at 226 rpm, with a temperature profile from 150 to 190 ºC. Test specimens were prepared using the injection molding machine at 190 ºC. The Standard Test Method for Rubber Property—Effect of Liquids was applied in order to simulate the exposition of TPE samples to detergent ingredients during service. For this purpose, ZnO loaded TPE samples were immersed in a 3.0% w/v detergent (neutral) and accelerated aging in oven at 70°C for 7 days. Compounds were characterized by changes in mechanical (hardness and tension properties) and mass. The Japan Industrial Standard (JIS) Z 2801:2010 was applied to evaluate antibacterial properties against Staphylococcus aureus (S. aureus) and Escherichia coli (E. coli). The microbiological tests showed a reduction up to 42% in E. coli and up to 49% in S. aureus population in non-aged samples. There were observed variations in elongation and hardness values with the addition of zinc The changes in tensile at rupture and mass were not significant between non-aged and aged samples.

Keywords: antimicrobial, domestic appliance, sebs, zinc oxide

Procedia PDF Downloads 247

Authors: Amir Nazemi, Milad Ramezankhani, Marian Kӧrber, Abbas S. Milani

Abstract:

The excellent strength to weight ratio of woven fabric composites, along with their high formability, is one of the primary design parameters defining their increased use in modern manufacturing processes, including those in aerospace and automotive. However, for emerging automated preform processes under the smart manufacturing paradigm, complex geometries of finished components continue to bring several challenges to the designers to cope with manufacturing defects on site. Wrinklinge. g. is a common defectoccurring during the forming process and handling of semi-finished textile composites. One of the main reasons for this defect is the weak bending stiffness of fibers in unconsolidated state, causing excessive relative motion between them. Further challenges are represented by the automated handling of large-area fiber blanks with specialized gripper systems. For fabric composites forming simulations, the finite element (FE)method is a longstanding tool usedfor prediction and mitigation of manufacturing defects. Such simulations are predominately meant, not only to predict the onset, growth, and shape of wrinkles but also to determine the best processing condition that can yield optimized positioning of the fibers upon forming (or robot handling in the automated processes case). However, the need for use of small-time steps via explicit FE codes, facing numerical instabilities, as well as large computational time, are among notable drawbacks of the current FEtools, hindering their extensive use as fast and yet efficient digital twins in industry. This paper presents a novel woven fabric simulation technique through the application of the material point method (MPM), which enables the use of much larger time steps, facing less numerical instabilities, hence the ability to run significantly faster and efficient simulationsfor fabric materials handling and forming processes. Therefore, this method has the ability to enhance the development of automated fiber handling and preform processes by calculating the physical interactions with the MPM fiber models and rigid tool components. This enables the designers to virtually develop, test, and optimize their processes based on either algorithmicor Machine Learning applications. As a preliminary case study, forming of a hemispherical plain weave is shown, and the results are compared to theFE simulations, as well as experiments.

Keywords: material point method, woven fabric composites, forming, material handling

Procedia PDF Downloads 182

Authors: Bahar Salavati Vie Le Sage, Ismaïl Ben Hariz, Flavien Viguier, Sirine Noura Kahil, Audrey Jacquin, Maxime Convert

Abstract:

The ballast layer plays a key role in railroad maintenance and the geometry of the track structure. Ballast also holds the track in place as the trains roll over it. Track ballast is packed between the sleepers and on the sides of railway tracks. An imbalance in ballast volume on the tracks can lead to safety issues as well as a quick degradation of the overall quality of the railway segment. If there is a lack of ballast in the track bed during the summer, there is a risk that the rails will expand and buckle slightly due to the high temperatures. Furthermore, the knowledge of the ballast quantities that will be excavated during renewal works is important for efficient ballast management. The volume of excavated ballast per meter of track can be calculated based on excavation depth, excavation width, volume of track skeleton (sleeper and rail) and sleeper spacing. Since 2012, SNCF has been collecting 3D points cloud data covering its entire railway network by using 3D laser scanning technology (LiDAR). This vast amount of data represents a modelization of the entire railway infrastructure, allowing to conduct various simulations for maintenance purposes. This paper aims to present an automated method for ballast volume estimation based on the processing of LiDAR data. The estimation of abnormal volumes in ballast on the tracks is performed by analyzing the cross-section of the track. Further, since the amount of ballast required varies depending on the track configuration, the knowledge of the ballast profile is required. Prior to track rehabilitation, excess ballast is often present in the ballast shoulders. Based on 3D laser scans, a Digital Terrain Model (DTM) was generated and automatic extraction of the ballast profiles from this data is carried out. The surplus in ballast is then estimated by performing a comparison between this ballast profile obtained empirically, and a geometric modelization of the theoretical ballast profile thresholds as dictated by maintenance standards. Ideally, this excess should be removed prior to renewal works and recycled to optimize the output of the ballast renewal machine. Based on these parameters, an application has been developed to allow the automatic measurement of ballast profiles. We evaluated the method on a 108 kilometers segment of railroad LiDAR scans, and the results show that the proposed algorithm detects ballast surplus that amounts to values close to the total quantities of spoil ballast excavated.

Keywords: ballast, railroad, LiDAR , cloud point, track ballast, 3D point

Procedia PDF Downloads 112

Authors: Leonard Tiong, Sonit Singh, Kevin Ho Shon, Sarah Lewis

Abstract:

Investigation into the use of artificial intelligence in radiology continues to develop at a rapid rate. During the coronavirus pandemic, the combination of an exponential increase in chest x-rays and unpredictable staff shortages resulted in a huge strain on the department's workload. There is a World Health Organisation estimate that two-thirds of the global population does not have access to diagnostic radiology. Therefore, there could be demand for a program that could detect acute changes in imaging compatible with infection to assist with screening. We generated a conventional neural network and tested its efficacy in recognizing changes compatible with coronavirus infection. Following ethics approval, a deidentified set of 77 normal and 77 abnormal chest x-rays in patients with confirmed coronavirus infection were used to generate an algorithm that could train, validate and then test itself. DICOM and PNG image formats were selected due to their lossless file format. The model was trained with 100 images (50 positive, 50 negative), validated against 28 samples (14 positive, 14 negative), and tested against 26 samples (13 positive, 13 negative). The initial training of the model involved training a conventional neural network in what constituted a normal study and changes on the x-rays compatible with coronavirus infection. The weightings were then modified, and the model was executed again. The training samples were in batch sizes of 8 and underwent 25 epochs of training. The results trended towards an 85.71% true positive/true negative detection rate and an area under the curve trending towards 0.95, indicating approximately 95% accuracy in detecting changes on chest X-rays compatible with coronavirus infection. Study limitations include access to only a small dataset and no specificity in the diagnosis. Following a discussion with our programmer, there are areas where modifications in the weighting of the algorithm can be made in order to improve the detection rates. Given the high detection rate of the program, and the potential ease of implementation, this would be effective in assisting staff that is not trained in radiology in detecting otherwise subtle changes that might not be appreciated on imaging. Limitations include the lack of a differential diagnosis and application of the appropriate clinical history, although this may be less of a problem in day-to-day clinical practice. It is nonetheless our belief that implementing this program and widening its scope to detecting multiple pathologies such as lung masses will greatly assist both the radiology department and our colleagues in increasing workflow and detection rate.

Keywords: artificial intelligence, COVID, neural network, machine learning

Procedia PDF Downloads 94

Authors: Saman Ahani, Aboozar Dehghan, Roham Vali, Hamid Salehian, Amin Ebrahimi

Abstract:

Pulsed-wave (PW) doppler ultrasonography is a non-invasive, relatively accurate imaging technique that can measure blood speed. The imaging could be obtained via the common carotid artery, as one of the main vessels supplying the blood of vital organs. In horses, factors such as susceptibility to depression of the cardiovascular system and their large muscular mass have rendered them vulnerable to changes in blood speed. One of the most important factors causing blood velocity changes is the administration of anesthetic drugs, including Ketamine and Acepromazine. Thus, in this study, the Pulsed-wave doppler technique was performed to assess the highest blood velocity in the common carotid artery following administration of Ketamine and Acepromazine. Six male and six female healthy Kurdish horses weighing 351 ± 46 kg (mean ± SD) and aged 9.2 ± 1.7 years (mean ± SD) were housed under animal welfare guidelines. After fasting for six hours, the normal blood flow velocity in the common carotid artery was measured using a Pulsed-wave doppler ultrasonography machine (BK Medical, Denmark), and a high-frequency linear transducer (12 MHz) without applying any sedative drugs as a control group. The same procedure was repeated after each individual received the following medications: 1.1, 2.2 mg/kg Ketamine (Pfizer, USA), and 0.5, 1 mg/kg Acepromizine (RACEHORSE MEDS, Ukraine), with an interval of 21 days between the administration of each dose and/or drug. The ultrasonographic study was done five (T5) and fifteen (T15) minutes after injecting each dose intravenously. Lastly, the statistical analysis was performed using SPSS software version 22 for Windows and a P value less than 0.05 was considered to be statistically significant. Five minutes after administration of Ketamine (1.1, 2.2 mg/kg) in both male and female horses, the blood velocity decreased to 38.44, 34.53 cm/s in males, and 39.06, 34.10 cm/s in females in comparison to the control group (39.59 and 40.39 cm/s in males and females respectively) while administration of 0.5 mg/kg Acepromazine led to a significant rise (73.15 and 55.80 cm/s in males and females respectively) (p<0.05). It means that the most drastic change in blood velocity, regardless of gender, refers to the latter dose/drug. In both medications and both genders, the increase in doses led to a decrease in blood velocity compared to the lower dose of the same drug. In all experiments in this study, the blood velocity approached its normal value at T15. In another study comparing the blood velocity changes affected by Ketamine and Acepromazine through femoral arteries, the most drastic changes were attributed to Ketamine; however, in this experiment, the maximum blood velocity was observed following administration of Acepromazine via the common carotid artery. Therefore, further experiments using the same medications are suggested using Pulsed-wave doppler measuring the blood velocity changes in both femoral and common carotid arteries simultaneously.

Keywords: Acepromazine, common carotid artery, horse, ketamine, pulsed-wave doppler ultrasonography

Procedia PDF Downloads 128

Authors: Anne C. Richer-De-Forges, Dominique Arrouays, Songchao Chen, Mercedes Roman Dobarco

Abstract:

Most of the digital soil mapping (DSM) products rely on machine learning (ML) prediction models and/or the use or pedotransfer functions (PTF) in which calibration data come from soil analyses performed in labs. However, many other observations (often qualitative, nominal, or ordinal) could be used as proxies of lab measurements or as input data for ML of PTF predictions. DSM and ML are briefly described with some examples taken from the literature. Then, we explore the potential of an ordinal qualitative variable, i.e., the hand-feel soil texture (HFST) estimating the mineral particle distribution (PSD): % of clay (0-2µm), silt (2-50µm) and sand (50-2000µm) in 15 classes. The PSD can also be measured by lab measurements (LAST) to determine the exact proportion of these particle-sizes. However, due to cost constraints, HFST are much more numerous and spatially dense than LAST. Soil texture (ST) is a very important soil parameter to map as it is controlling many of the soil properties and functions. Therefore, comes an essential question: is it possible to use HFST as a proxy of LAST for calibration and/or validation of DSM predictions of ST? To answer this question, the first step is to compare HFST with LAST on a representative set where both information are available. This comparison was made on ca 17,400 samples representative of a French region (34,000 km2). The accuracy of HFST was assessed, and each HFST class was characterized by a probability distribution function (PDF) of its LAST values. This enables to randomly replace HFST observations by LAST values while respecting the PDF previously calculated and results in a very large increase of observations available for the calibration or validation of PTF and ML predictions. Some preliminary results are shown. First, the comparison between HFST classes and LAST analyses showed that accuracies could be considered very good when compared to other studies. The causes of some inconsistencies were explored and most of them were well explained by other soil characteristics. Then we show some examples applying these relationships and the increase of data to several issues related to DSM. The first issue is: do the PDF functions that were established enable to use HSFT class observations to improve the LAST soil texture prediction? For this objective, we replaced all HFST for topsoil by values from the PDF 100 time replicates). Results were promising for the PTF we tested (a PTF predicting soil water holding capacity). For the question related to the ML prediction of LAST soil texture on the region, we did the same kind of replacement, but we implemented a 10-fold cross-validation using points where we had LAST values. We obtained only preliminary results but they were rather promising. Then we show another example illustrating the potential of using HFST as validation data. As in numerous countries, the HFST observations are very numerous; these promising results pave the way to an important improvement of DSM products in all the countries of the world.

Keywords: digital soil mapping, improvement of digital soil mapping predictions, potential of using hand-feel soil texture, soil texture prediction

Procedia PDF Downloads 226

Authors: Junior Akunzi

Abstract:

In the matter of patient treatment planning quality assurance in 3D conformational therapy (3D-CRT) and volumetric arc therapy (VMAT or RapidArc), the independent monitor unit verification calculation (MUVC) is an indispensable part of the process. Concerning 3D-CRT treatment planning, the MUVC can be performed manually applying the standard ESTRO formalism. However, due to the complex shape and the amount of beams in advanced treatment planning technic such as RapidArc, the manual independent MUVC is inadequate. Therefore, commercially available software such as RadCalc can be used to perform the MUVC in complex treatment planning been. Indeed, RadCalc (version 6.3 LifeLine Inc.) uses a simplified Clarkson algorithm to compute the dose contribution for individual RapidArc fields to the isocenter. The purpose of this project is the validation of RadCalc in 3D-CRT and RapidArc for treatment planning dosimetry quality assurance at Antoine Lacassagne center (Nice, France). Firstly, the interfaces between RadCalc and our treatment planning systems (TPS) Isogray (version 4.2) and Eclipse (version13.6) were checked for data transfer accuracy. Secondly, we created test plans in both Isogray and Eclipse featuring open fields, wedges fields, and irregular MLC fields. These test plans were transferred from TPSs according to the radiotherapy protocol of DICOM RT to RadCalc and the linac via Mosaiq (version 2.5). Measurements were performed in water phantom using a PTW cylindrical semiflex ionisation chamber (0.3 cm³, 31010) and compared with the TPSs and RadCalc calculation. Finally, 30 3D-CRT plans and 40 RapidArc plans created with patients CT scan were recalculated using the CT scan of a solid PMMA water equivalent phantom for 3D-CRT and the Octavius II phantom (PTW) CT scan for RapidArc. Next, we measure the doses delivered into these phantoms for each plan with a 0.3 cm³ PTW 31010 cylindrical semiflex ionisation chamber (3D-CRT) and 0.015 cm³ PTW PinPoint ionisation chamber (Rapidarc). For our test plans, good agreements were found between calculation (RadCalc and TPSs) and measurement (mean: 1.3%; standard deviation: ± 0.8%). Regarding the patient plans, the measured doses were compared to the calculation in RadCalc and in our TPSs. Moreover, RadCalc calculations were compared to Isogray and Eclispse ones. Agreements better than (2.8%; ± 1.2%) were found between RadCalc and TPSs. As for the comparison between calculation and measurement the agreement for all of our plans was better than (2.3%; ± 1.1%). The independent MU verification calculation software RadCal has been validated for clinical use and for both 3D-CRT and RapidArc techniques. The perspective of this project includes the validation of RadCal for the Tomotherapy machine installed at centre Antoine Lacassagne.

Keywords: 3D conformational radiotherapy, intensity modulated radiotherapy, monitor unit calculation, dosimetry quality assurance

Procedia PDF Downloads 216

Authors: Bahareh Ansari

Abstract:

Background: The Open Government Data (OGD) movement in the last decade has encouraged many government organizations around the world to make their data publicly available to advance democratic processes. But current open data platforms have not yet reached to their full potential in supporting all interested parties. To make the data useful and understandable for everyone, scholars suggested that opening the data should be supplemented by visualization. However, different visualizations of the same information can dramatically change an individual’s cognitive and emotional experience in working with the data. This study reviews the data visualization literature to create a list of the methods empirically tested to enhance users’ performance and experience in working with a visualization tool. This list can be used in evaluating the OGD visualization practices and informing the future open data initiatives. Methods: Previous reviews of visualization literature categorized the visualization outcomes into four categories including recall/memorability, insight/comprehension, engagement, and enjoyment. To identify the papers, a search for these outcomes was conducted in the abstract of the publications of top-tier visualization venues including IEEE Transactions for Visualization and Computer Graphics, Computer Graphics, and proceedings of the CHI Conference on Human Factors in Computing Systems. The search results are complemented with a search in the references of the identified articles, and a search for 'open data visualization,' and 'visualization evaluation' keywords in the IEEE explore and ACM digital libraries. Articles are included if they provide empirical evidence through conducting controlled user experiments, or provide a review of these empirical studies. The qualitative synthesis of the studies focuses on identification and classifying the methods, and the conditions under which they are examined to positively affect the visualization outcomes. Findings: The keyword search yields 760 studies, of which 30 are included after the title/abstract review. The classification of the included articles shows five distinct methods: interactive design, aesthetic (artistic) style, storytelling, decorative elements that do not provide extra information including text, image, and embellishment on the graphs), and animation. Studies on decorative elements show consistency on the positive effects of these elements on user engagement and recall but are less consistent in their examination of the user performance. This inconsistency could be attributable to the particular data type or specific design method used in each study. The interactive design studies are consistent in their findings of the positive effect on the outcomes. Storytelling studies show some inconsistencies regarding the design effect on user engagement, enjoyment, recall, and performance, which could be indicative of the specific conditions required for the use of this method. Last two methods, aesthetics and animation, have been less frequent in the included articles, and provide consistent positive results on some of the outcomes. Implications for e-government: Review of the visualization best-practice methods show that each of these methods is beneficial under specific conditions. By using these methods in a potentially beneficial condition, OGD practices can promote a wide range of individuals to involve and work with the government data and ultimately engage in government policy-making procedures.

Keywords: best practices, data visualization, literature review, open government data

Procedia PDF Downloads 107

Authors: Óscar Muñoz Garrigós, José Manuel Bernabeu Aubán

Abstract:

Time-sensitive services are the base of the cloud services industry. Keeping low service saturation is essential for controlling response time. All auto-scalable services make use of reactive auto-scaling. However, reactive auto-scaling has few in-depth studies. This presentation shows a model for reactive auto-scaling methodologies with a MAPE-k architecture. Queuing theory can compute different properties of static services but lacks some parameters related to the transition between models. Our model uses queuing theory parameters to relate the transition between models. It associates MAPE-k related times, the sampling frequency, the cooldown period, the number of requests that an instance can handle per unit of time, the number of incoming requests at a time instant, and a function that describes the acceleration in the service's ability to handle more requests. This model is later used as a solution to horizontally auto-scale time-sensitive services composed of microservices, reevaluating the model’s parameters periodically to allocate resources. The solution requires limiting the acceleration of the growth in the number of incoming requests to keep a constrained response time. Business benefits determine such limits. The solution can add a dynamic number of instances and remains valid under different system sizes. The study includes performance recommendations to improve results according to the incoming load shape and business benefits. The exposed methodology is tested in a simulation. The simulator contains a load generator and a service composed of two microservices, where the frontend microservice depends on a backend microservice with a 1:1 request relation ratio. A common request takes 2.3 seconds to be computed by the service and is discarded if it takes more than 7 seconds. Both microservices contain a load balancer that assigns requests to the less loaded instance and preemptively discards requests if they are not finished in time to prevent resource saturation. When load decreases, instances with lower load are kept in the backlog where no more requests are assigned. If the load grows and an instance in the backlog is required, it returns to the running state, but if it finishes the computation of all requests and is no longer required, it is permanently deallocated. A few load patterns are required to represent the worst-case scenario for reactive systems: the following scenarios test response times, resource consumption and business costs. The first scenario is a burst-load scenario. All methodologies will discard requests if the rapidness of the burst is high enough. This scenario focuses on the number of discarded requests and the variance of the response time. The second scenario contains sudden load drops followed by bursts to observe how the methodology behaves when releasing resources that are lately required. The third scenario contains diverse growth accelerations in the number of incoming requests to observe how approaches that add a different number of instances can handle the load with less business cost. The exposed methodology is compared against a multiple threshold CPU methodology allocating/deallocating 10 or 20 instances, outperforming the competitor in all studied metrics.

Keywords: reactive auto-scaling, auto-scaling, microservices, cloud computing

Procedia PDF Downloads 96

Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti

Abstract:

Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.

Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement

Procedia PDF Downloads 124

Authors: Mahshid Arabi

Abstract:

In recent years, remarkable advancements in the fields of artificial intelligence and machine learning have led to the development of facial recognition technologies. These technologies are now employed in a wide range of applications, including security, surveillance, healthcare, and education. In the field of education, the identification of university entrance exam candidates has been one of the fundamental challenges. Traditional methods such as using ID cards and handwritten signatures are not only inefficient and prone to fraud but also susceptible to errors. In this context, utilizing advanced technologies like facial recognition can be an effective and efficient solution to increase the accuracy and reliability of identity verification in entrance exams. This article examines the use of FaceMatch software for recognizing the faces of university entrance exam candidates in Iran. The main objective of this research is to evaluate the efficiency and accuracy of FaceMatch software in identifying university entrance exam candidates to prevent fraud and ensure the authenticity of individuals' identities. Additionally, this research investigates the advantages and challenges of using this technology in Iran's educational systems. This research was conducted using an experimental method and random sampling. In this study, 1000 university entrance exam candidates in Iran were selected as samples. The facial images of these candidates were processed and analyzed using FaceMatch software. The software's accuracy and efficiency were evaluated using various metrics, including accuracy rate, error rate, and processing time. The research results indicated that FaceMatch software could accurately identify candidates with a precision of 98.5%. The software's error rate was less than 1.5%, demonstrating its high efficiency in facial recognition. Additionally, the average processing time for each candidate's image was less than 2 seconds, indicating the software's high efficiency. Statistical evaluation of the results using precise statistical tests, including analysis of variance (ANOVA) and t-test, showed that the observed differences were significant, and the software's accuracy in identity verification is high. The findings of this research suggest that FaceMatch software can be effectively used as a tool for identifying university entrance exam candidates in Iran. This technology not only enhances security and prevents fraud but also simplifies and streamlines the exam administration process. However, challenges such as preserving candidates' privacy and the costs of implementation must also be considered. The use of facial recognition technology with FaceMatch software in Iran's educational systems can be an effective solution for preventing fraud and ensuring the authenticity of university entrance exam candidates' identities. Given the promising results of this research, it is recommended that this technology be more widely implemented and utilized in the country's educational systems.

Keywords: facial recognition, FaceMatch software, Iran, university entrance exam

Procedia PDF Downloads 49

Authors: Shanaka Gunasekara, Maleen Jayasuriya, Nalin Harischandra, Lilantha Samaranayake, Gamini Dissanayake

Abstract:

One serious facet of the worsening Human-Elephant conflict (HEC) in nations such as Sri Lanka involves elephant-train collisions. Endangered Asian elephants are maimed or killed during such accidents, which also often result in orphaned or disabled elephants, contributing to the phenomenon of lone elephants. These lone elephants are found to be more likely to attack villages and showcase aggressive behaviour, which further exacerbates the overall HEC. Furthermore, Railway Services incur significant financial losses and disruptions to services annually due to such accidents. Most elephant-train collisions occur due to a lack of adequate reaction time. This is due to the significant stopping distance requirements of trains, as the full braking force needs to be avoided to minimise the risk of derailment. Thus, poor driver visibility at sharp turns, nighttime operation, and poor weather conditions are often contributing factors to this problem. Initial investigations also indicate that most collisions occur in localised “hotspots” where elephant pathways/corridors intersect with railway tracks that border grazing land and watering holes. Taking these factors into consideration, this work proposes the leveraging of recent developments in Convolutional Neural Network (CNN) technology to detect elephants using an RGB/infrared capable camera around known hotspots along the railway track. The CNN was trained using a curated dataset of elephants collected on field visits to elephant sanctuaries and wildlife parks in Sri Lanka. With this vision-based detection system at its core, a prototype unit of an early warning system was designed and tested. This weatherised and waterproofed unit consists of a Reolink security camera which provides a wide field of view and range, an Nvidia Jetson Xavier computing unit, a rechargeable battery, and a solar panel for self-sufficient functioning. The prototype unit was designed to be a low-cost, low-power and small footprint device that can be mounted on infrastructures such as poles or trees. If an elephant is detected, an early warning message is communicated to the train driver using the GSM network. A mobile app for this purpose was also designed to ensure that the warning is clearly communicated. A centralized control station manages and communicates all information through the train station network to ensure coordination among important stakeholders. Initial results indicate that detection accuracy is sufficient under varying lighting situations, provided comprehensive training datasets that represent a wide range of challenging conditions are available. The overall hardware prototype was shown to be robust and reliable. We envision a network of such units may help contribute to reducing the problem of elephant-train collisions and has the potential to act as an important surveillance mechanism in dealing with the broader issue of human-elephant conflicts.

Keywords: computer vision, deep learning, human-elephant conflict, wildlife early warning technology

Procedia PDF Downloads 226

Authors: Wisdom Robert Duruji

Abstract:

The outbreak of SARS-CoV-2 serotype infection was recorded in January 2020 in Wuhan City, Hubei Province, China. This study examines the concepts of the COVID-19 pandemic and the implications of vaccines for health security in Nigeria and Diasporas. It challenges the widely accepted assumption that the first case of coronavirus infection in Nigeria was recorded on February 27th, 2020, in Lagos. The study utilizes a range of research methods to achieve its objectives. These include the double-layered culture technique, literature review, website knowledge, Google search, news media information, academic journals, fieldwork, and on-site observations. These diverse methods allow for a comprehensive analysis of the concepts and the implications being studied. The study finds that coronavirus infection can be asymptomatic; it may be the antigenicity of the leukocytes (white blood cells), which produce immunogenic hapten or interferons (α, β and γ) that fight infectious parasites, was an immune response that prevented severe virulence in healthy individuals; the reason healthy patients of coronavirus infection in Nigeria naturally recovered after two to three weeks of on-set of infection and test negative. However, the fatality data from the Nigerian Centre for Disease Control (NCDC) is incorrect in this study’s finding; it perused that the fatalities were primarily due to underlying ailments, hunger, and malnutrition in debilitated, comorbid, or compromised patients. This study concluded that the kits and Polymerase Chain Reaction (PCR) machine currently used by the Nigerian Centre for Disease Control (NCDC) in testing and confirming COVID-19 in Nigeria is not ideal; it is programmed and negates separating the strain to its specific serotypes amongst its genera coronavirus, and family Coronaviridae; and might have confirmed patients with the symptoms of febrile caused by cough, catarrh, typhoid and malaria parasites as Covid-19 positive. Therefore, it is recommended that the coronavirus species infected in Nigeria are opportunistic parasites that thrive in human immuno-suppressed conditions like the herpesvirus; it cannot be eradicated by vaccines; the only virucides are interferons, immunoglobulins, and probably synthetic antiviral guanosine drugs like copegus or ribavirin. The findings emphasized that COVID-19 is not the primary pandemic disease in Nigeria; the lockdown was a mirage and not necessary; but rather, pandemic diseases in Nigeria are corruption, nepotism, hunger, and malnutrition caused by ineptitude in governance, religious dichotomy, and ethnic conflicts.

Keywords: coronavirus, corruption, Covid-19 pandemic, lock-down, Nigeria, vaccine

Procedia PDF Downloads 69