Search results for: DFIG machine

Authors: Toktam Khatibi

Abstract:

Self-supervised learning (SSL) includes machine learning models that are trained on one aspect and/or one part of the input to learn other aspects and/or part of it. SSL models are divided into two different categories, including pre-text task-based models and contrastive learning ones. Pre-text tasks are some auxiliary tasks learning pseudo-labels, and the trained models are further fine-tuned for downstream tasks. However, one important disadvantage of SSL using pre-text task solving is defining an appropriate pre-text task for each image dataset with a variety of image modalities. Therefore, it is required to design an appropriate pretext task automatically for each dataset and each downstream task. To the best of our knowledge, the automatic designing of pretext tasks for image analysis has not been considered yet. In this paper, we present a framework based on In-context learning that describes each task based on its input and output data using a pre-trained image transformer. Our proposed method combines the input image and its learned description for optimizing the pre-text task design and its hyper-parameters using Meta-learning models. The representations learned from the pre-text tasks are fine-tuned for solving the downstream tasks. We demonstrate that our proposed framework outperforms the compared ones on unseen tasks and image modalities in addition to its superior performance for previously known tasks and datasets.

Keywords: in-context learning (ICL), meta learning, self-supervised learning (SSL), vision-language domain, transformers

Procedia PDF Downloads 80

Authors: Shital Suresh Borse, Vijayalaxmi Kadroli

Abstract:

E-commerce industries nowadays implement the latest AI, ML Techniques to improve their own performance and prediction accuracy. This helps to gain a huge profit from the online market. Ant Colony Optimization, Genetic algorithm, Particle Swarm Optimization, Neural Network & GWO help many e-commerce industries for up-gradation of their predictive performance. These algorithms are providing optimum results in various applications, such as stock price prediction, prediction of drug-target interaction & user ratings of similar products in e-commerce sites, etc. In this study, customer reviews will play an important role in prediction analysis. People showing much interest in buying a lot of services& products suggested by other customers. This ultimately increases net profit. In this work, a convolution neural network (CNN) is proposed which further is useful to optimize the prediction accuracy of an e-commerce website. This method shows that CNN is used to optimize hyperparameters of GWO algorithm using an appropriate coding scheme. Accurate model results are verified by comparing them to PSO results whose hyperparameters have been optimized by CNN in Amazon's customer review dataset. Here, experimental outcome proves that this proposed system using the GWO algorithm achieves superior execution in terms of accuracy, precision, recovery, etc. in prediction analysis compared to the existing systems.

Keywords: prediction analysis, e-commerce, machine learning, grey wolf optimization, particle swarm optimization, CNN

Procedia PDF Downloads 113

Authors: Jie Zhao, Meng Su

Abstract:

Image recognition, as one of the most critical technologies in computer vision, works to help machine-like robotics understand a scene, that is, if deployed appropriately, will trigger the revolution in remote sensing and industry automation. With the developments of AI technologies, there are many prevailing and sophisticated neural networks as technologies developed for image recognition. However, computer vision platforms as hardware, supporting neural networks for image recognition, as crucial as the neural network technologies, need to be more congruently addressed as the research subjects. In contrast, different computer vision platforms are deterministic to leverage the performance of different neural networks for recognition. In this paper, three different computer vision platforms – Jetson Nano(with 4GB), a standalone laptop(with RTX 3000s, using CUDA), and Google Colab (web-based, using GPU) are explored and four prominent neural network architectures (including AlexNet, VGG(16/19), GoogleNet, and ResNet(18/34/50)), are investigated. In the context of pairwise usage between different computer vision platforms and distinctive neural networks, with the merits of recognition accuracy and time efficiency, the performances are evaluated. In the case study using public imageNets, our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.

Keywords: alexNet, VGG, googleNet, resNet, Jetson nano, CUDA, COCO-NET, cifar10, imageNet large scale visual recognition challenge (ILSVRC), google colab

Procedia PDF Downloads 90

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 161

Authors: Walter Bernhofer, Peter Haber, Tobias Mayer, Manfred Mayr, Markus Ziegler

Abstract:

Current preventive maintenance measures are cost intensive and not efficient. With the available sensor data of state of the art internet of things devices new possibilities of automated data processing emerge. Current advances in data science and in machine learning enable new, so called predictive maintenance technologies, which empower data scientists to forecast possible system failures. The goal of this approach is to cut expenses in preventive maintenance by automating the detection of possible failures and to improve efficiency and quality of maintenance measures. Additionally, a centralization of the sensor data monitoring can be achieved by using this approach. This paper describes the approach of three students to define a reference architecture for a predictive maintenance solution in the internet of things domain with a connected smartphone app for service technicians. The reference architecture is validated by a case study. The case study is implemented with current Microsoft Azure cloud technologies. The results of the case study show that the reference architecture is valid and can be used to achieve a system for predictive maintenance execution with the cloud components of Microsoft Azure. The used concepts are technology platform agnostic and can be reused in many different cloud platforms. The reference architecture is valid and can be used in many use cases, like gas station maintenance, elevator maintenance and many more.

Keywords: case study, internet of things, predictive maintenance, reference architecture

Procedia PDF Downloads 252

Authors: Disaphon Boobpachat, Nuttaset Manimmanakorn, Apiwan Manimmanakorn, Worrawut Thuwakum, Michael J. Hamlin

Abstract:

Objectives: To evaluate effect of kinesio tape compared to placebo tape and static stretching on recovery of anaerobic power and maximal oxygen uptake (Vo₂max) after intensive exercise. Methods: Thirty nine untrained healthy volunteers were randomized to 3 groups for each intervention: elastic tape, placebo tape and stretching. The participants performed intensive exercise on the dominant quadriceps by using isokinetic dynamometry machine. The recovery process was evaluated by creatine kinase (CK), pressure pain threshold (PPT), muscle soreness scale (MSS), maximum voluntary contraction (MVC), jump height, anaerobic power and Vo₂max at baseline, immediately post-exercise and post-exercise day 1, 2, 3 and 7. Results: The kinesio tape, placebo tape and stretching groups had significant changes of PPT, MVC, jump height at immediately post-exercise compared to baseline (p < 0.05), and changes of MSS, CK, anaerobic power and Vo₂max at day 1 post-exercise compared to baseline (p < 0.05). There was no significant difference of those outcomes among three groups. Additionally, all experimental groups had little effects on anaerobic power and Vo₂max compared to baseline and compared among three groups (p > 0.05). Conclusion: Kinesio tape and stretching did not improve recovery of anaerobic power and Vo₂max after eccentric exercise compared to placebo tape.

Keywords: stretching, eccentric exercise, Wingate test, muscle soreness

Procedia PDF Downloads 130

Authors: Yu-Hsiu Lin, Wen-Chun Lin, Yen-Chang Cheng, Chia-Ju Yeh, Yu-Chuan Chen, Tai-You Li

Abstract:

Demand-Side Management (DSM) has the potential to reduce electricity costs and carbon emission, which are associated with electricity used in the modern society. A home Energy Management System (EMS) commonly used by residential consumers in a down-stream sector of a smart grid to monitor, control, and optimize energy efficiency to domestic appliances is a system of computer-aided functionalities as an energy audit for residential DSM. Implementing fault detection and classification to domestic appliances monitored, controlled, and optimized is one of the most important steps to realize preventive maintenance, such as residential air conditioning and heating preventative maintenance in residential/industrial DSM. In this study, a cloud intelligence-based green EMS that comes up with an Internet of Things (IoT) technology stack for residential DSM is developed. In the EMS, Arduino MEGA Ethernet communication-based smart sockets that module a Real Time Clock chip to keep track of current time as timestamps via Network Time Protocol are designed and implemented for readings of load phenomena reflecting on voltage and current signals sensed. Also, a Network-Attached Storage providing data access to a heterogeneous group of IoT clients via Hypertext Transfer Protocol (HTTP) methods is configured to data stores of parsed sensor readings. Lastly, a desktop computer with a WAMP software bundle (the Microsoft® Windows operating system, Apache HTTP Server, MySQL relational database management system, and PHP programming language) serves as a data science analytics engine for dynamic Web APP/REpresentational State Transfer-ful web service of the residential DSM having globally-Advanced Internet of Artificial Intelligence (AI)/Computational Intelligence. Where, an abstract computing machine, Java Virtual Machine, enables the desktop computer to run Java programs, and a mash-up of Java, R language, and Python is well-suited and -configured for AI in this study. Having the ability of sending real-time push notifications to IoT clients, the desktop computer implements Google-maintained Firebase Cloud Messaging to engage IoT clients across Android/iOS devices and provide mobile notification service to residential/industrial DSM. In this study, in order to realize edge intelligence that edge devices avoiding network latency and much-needed connectivity of Internet connections for Internet of Services can support secure access to data stores and provide immediate analytical and real-time actionable insights at the edge of the network, we upgrade the designed and implemented smart sockets to be embedded AI Arduino ones (called embedded AIduino). With the realization of edge analytics by the proposed embedded AIduino for data analytics, an Arduino Ethernet shield WizNet W5100 having a micro SD card connector is conducted and used. The SD library is included for reading parsed data from and writing parsed data to an SD card. And, an Artificial Neural Network library, ArduinoANN, for Arduino MEGA is imported and used for locally-embedded AI implementation. The embedded AIduino in this study can be developed for further applications in manufacturing industry energy management and sustainable energy management, wherein in sustainable energy management rotating machinery diagnostics works to identify energy loss from gross misalignment and unbalance of rotating machines in power plants as an example.

Keywords: demand-side management, edge intelligence, energy management system, fault detection and classification

Procedia PDF Downloads 251

Authors: Lal Hussain, Wajid Aziz, Sajjad Ahmed Nadeem, Saeed Arif Shah, Abdul Majid

Abstract:

Brain electrical activity as reflected in Electroencephalography (EEG) have been analyzed and diagnosed using various techniques. Among them, complexity measure, nonlinearity, disorder, and unpredictability play vital role due to the nonlinear interconnection between functional and anatomical subsystem emerged in brain in healthy state and during various diseases. There are many social and economical issues of alcoholic abuse as memory weakness, decision making, impairments, and concentrations etc. Alcoholism not only defect the brains but also associated with emotional, behavior, and cognitive impairments damaging the white and gray brain matters. A recently developed signal analysis method i.e. Multiscale Permutation Entropy (MPE) is proposed to estimate the complexity of long-range temporal correlation time series EEG of Alcoholic and Control subjects acquired from University of California Machine Learning repository and results are compared with MSE. Using MPE, coarsed grained series is first generated and the PE is computed for each coarsed grained time series against the electrodes O1, O2, C3, C4, F2, F3, F4, F7, F8, Fp1, Fp2, P3, P4, T7, and T8. The results computed against each electrode using MPE gives higher significant values as compared to MSE as well as mean rank differences accordingly. Likewise, ROC and Area under the ROC also gives higher separation against each electrode using MPE in comparison to MSE.

Keywords: electroencephalogram (EEG), multiscale permutation entropy (MPE), multiscale sample entropy (MSE), permutation entropy (PE), mann whitney test (MMT), receiver operator curve (ROC), complexity measure

Procedia PDF Downloads 495

Authors: Jacqueline Miller, Dongyuan Y. Wang, F. Dan Richard

Abstract:

Before trying to make an ethical machine that holds a higher ethical standard than humans, a better understanding of human moral standards that could be used as a guide is crucial. How humans make decisions in dangerous driving situations like moral dilemmas can contribute to developing acceptable ethical principles for autonomous vehicles (AVs). This study uses a driving simulator to investigate whether drivers make utilitarian choices (choices that maximize lives saved and minimize harm) in unavoidable automobile accidents (moral dilemmas) with time pressure manipulated. This study also investigates how impulsiveness influences drivers’ behavior in moral dilemmas. Manipulating time pressure results in collisions that occur at varying time intervals (4 s, 5 s, 7s). Manipulating time pressure helps investigate how time pressure may influence drivers’ response behavior. Thirty-one undergraduates participated in this study using a STISM driving simulator to respond to driving moral dilemmas. The results indicated that the percentage of utilitarian choices generally increased when given more time to respond (from 4 s to 7 s). Additionally, participants in vehicle scenarios preferred responding right over responding left. Impulsiveness did not influence utilitarian choices. However, as time pressure decreased, response time increased. Findings have potential implications and applications on the regulation of driver assistance technologies and AVs.

Keywords: time pressure, automobile moral dilemmas, impulsiveness, reaction time

Procedia PDF Downloads 54

Authors: Parwinder Singh, Ashok Kumar

Abstract:

Aim: The aim of the study was to investigate the relationship between selected Anthropometric and physical fitness variables of Junior Free Style Wrestlers. Method: one hundred fifty (N = 150) male Junior Free Style Wrestlers were selected as subjects, and they were categorized into five groups according to their weight categories; each group was comprised of 30 wrestlers. Body Mass Index can be considered according to the World Health Organization. Body fat percentage was assessed by using Durnin and Womersley equation, and Bodyweight was checked with a weighing machine. Cardiovascular endurance was checked by the Havard Step test of junior freestyle wrestlers. Results: A statistically positive significant correlation was found between Body Weight and Body Mass Index, skinfold thickness, and Percentage Body Fat. Fitness index was observed as negatively significant relationship related with Body Weight, Percent Body Fat, and Body Mass Index. Conclusion: It is concluded that freestyle wrestling is a weight classified sport and physical fitness is the most important factor in freestyle wrestling; therefore, the correlation of the fitness index of the wrestlers with body composition is important. The results of the present study also demonstrated the effect of Age, Body Height, Body Weight, Body Mass Index, and percentage body fat of the aerobic fitness of junior freestyle wrestlers.

Keywords: aerobic fitness, anthropometry, fat percentage, free style wrestling, skinfold, strength

Procedia PDF Downloads 208

Authors: Tarang Varmora, Krupa Shah, Karan Patel

Abstract:

Environmental pollution and shortage of conventional fuel are the main concerns in the transportation sector. Most of the vehicles use an internal combustion engine (ICE), powered by gasoline fuels. This results into emission of toxic gases. Hybrid electric vehicle (HEV) powered by electric machine and ICE is capable of reducing emission of toxic gases and fuel consumption. However to build HEV, it is required to accommodate motor and batteries in the vehicle along with engine and fuel tank. Thus, overall weight of the vehicle increases. To improve the fuel economy and acceleration, the weight of the HEV can be minimized. In this paper, the design methodology to reduce the weight of the hybrid racing car is proposed. To this end, the chassis design is optimized. Further, attempt is made to obtain the maximum strength with minimum material weight. The best configuration out of the three main configurations such as series, parallel and the dual-mode (series-parallel) is chosen. Moreover, the most suitable type of motor, battery, braking system, steering system and suspension system are identified. The racing car is designed and analyzed in the simulating software. The safety of the vehicle is assured by performing static and dynamic analysis on the chassis frame. From the results, it is observed that, the weight of the racing car is reduced by 11 % without compromising on safety and cost. It is believed that the proposed design and specifications can be implemented practically for manufacturing hybrid racing car.

Keywords: design optimization, hybrid racing car, simulation, vehicle, weight reduction

Procedia PDF Downloads 295

Authors: Umm-E-Hani, Faiza Babar, Hanif Durad

Abstract:

Malware-detecting approaches suffer many limitations, due to which all anti-malware solutions have failed to be reliable enough for detecting zero-day malware. Signature-based solutions depend upon the signatures that can be generated only when malware surfaces at least once in the cyber world. Another approach that works by detecting the anomalies caused in the environment can easily be defeated by diligently and intelligently written malware. Solutions that have been trained to observe the behavior for detecting malicious files have failed to cater to the malware capable of detecting the sandboxed or protected environment. Machine learning and deep learning-based approaches greatly suffer in training their models with either an imbalanced dataset or an inadequate number of samples. AI-based anti-malware solutions that have been trained with enough samples targeted a selected feature vector, thus ignoring the input of leftover features in the maliciousness of malware just to cope with the lack of underlying hardware processing power. Our research focuses on producing an anti-malware solution for detecting malicious PE files by circumventing the earlier-mentioned shortcomings. Our proposed framework, which is based on automated feature engineering through autoencoders, trains the model over a fairly large dataset. It focuses on the visual patterns of malware samples to automatically extract the meaningful part of the visual pattern. Our experiment has successfully produced a state-of-the-art accuracy of 99.54 % over test data.

Keywords: malware, auto encoders, automated feature engineering, classification

Procedia PDF Downloads 72

Authors: Qassun S. Mohammed Shafiqu, Murtadha A. Abdulrasool

Abstract:

The design of shallow foundations to withstand different dynamic loads has given considerable attention in recent years. Dynamic loads may be due to the earthquakes, pile driving, blasting, water waves, and machine vibrations. But, predicting the behavior of shallow foundations during earthquakes remains a difficult task for geotechnical engineers. A database for dynamic and static parameters for different soils in seismic active zones in Iraq is prepared which has been collected from geophysical and geotechnical investigation works. Then, analysis of a typical 3-D soil-raft foundation system under earthquake loading is carried out using the database. And a parametric study has been carried out taking into consideration the influence of some parameters on the dynamic behavior of the raft foundation, such as raft stiffness, damping ratio as well as the influence of the earthquake acceleration-time records. The results of the parametric study show that the settlement caused by the earthquake can be decreased by about 72% with increasing the thickness from 0.5 m to 1.5 m. But, it has been noticed that reduction in the maximum bending moment by about 82% was predicted by decreasing the raft thickness from 1.5 m to 0.5 m in all sites model. Also, it has been observed that the maximum lateral displacement, the maximum vertical settlement and the maximum bending moment for damping ratio 0% is about 14%, 20%, and 18% higher than that for damping ratio 7.5%, respectively for all sites model.

Keywords: shallow foundation, seismic behavior, raft thickness, damping ratio

Procedia PDF Downloads 148

Authors: Julius Onyancha, Valentina Plekhanova

Abstract:

One of the significant issues facing web users is the amount of noise in web data which hinders the process of finding useful information in relation to their dynamic interests. Current research works consider noise as any data that does not form part of the main web page and propose noise web data reduction tools which mainly focus on eliminating noise in relation to the content and layout of web data. This paper argues that not all data that form part of the main web page is of a user interest and not all noise data is actually noise to a given user. Therefore, learning of noise web data allocated to the user requests ensures not only reduction of noisiness level in a web user profile, but also a decrease in the loss of useful information hence improves the quality of a web user profile. Noise Web Data Learning (NWDL) tool/algorithm capable of learning noise web data in web user profile is proposed. The proposed work considers elimination of noise data in relation to dynamic user interest. In order to validate the performance of the proposed work, an experimental design setup is presented. The results obtained are compared with the current algorithms applied in noise web data reduction process. The experimental results show that the proposed work considers the dynamic change of user interest prior to elimination of noise data. The proposed work contributes towards improving the quality of a web user profile by reducing the amount of useful information eliminated as noise.

Keywords: web log data, web user profile, user interest, noise web data learning, machine learning

Procedia PDF Downloads 265

Authors: Atefeh Heydari, Mohammadali Tavakoli, Naomie Salim

Abstract:

In recent years, we have witnessed that online reviews are the most important source of customers’ opinion. They are progressively more used by individuals and organisations to make purchase and business decisions. Unfortunately, for the reason of profit or fame, frauds produce deceptive reviews to hoodwink potential customers. Their activities mislead not only potential customers to make appropriate purchasing decisions and organisations to reshape their business, but also opinion mining techniques by preventing them from reaching accurate results. Spam reviews could be divided into two main groups, i.e. multiple and singleton spam reviews. Detecting a singleton spam review that is the only review written by a user ID is extremely challenging due to lack of clue for detection purposes. Singleton spam reviews are very harmful and various features and proofs used in multiple spam reviews detection are not applicable in this case. Current research aims to propose a novel supervised technique to detect singleton spam reviews. To achieve this, various features are proposed in this study and are to be combined with the most appropriate features extracted from literature and employed in a classifier. In order to compare the performance of different classifiers, SVM and naive Bayes classification algorithms were used for model building. The results revealed that SVM was more accurate than naive Bayes and our proposed technique is capable to detect singleton spam reviews effectively.

Keywords: classification algorithms, Naïve Bayes, opinion review spam detection, singleton review spam detection, support vector machine

Procedia PDF Downloads 309

Authors: Cheng-Yang Lee, Petrus Tang, Tzu-Hao Chang

Abstract:

Copy number variations (CNVs) have played an important role in many kinds of human diseases, such as Autism, Schizophrenia and a number of cancers. Many diseases are found in genome coding regions and whole exome sequencing (WES) is a cost-effective and powerful technology in detecting variants that are enriched in exons and have potential applications in clinical setting. Although several algorithms have been developed to detect CNVs using WES and compared with other algorithms for finding the most suitable methods using their own samples, there were not consistent datasets across most of algorithms to evaluate the ability of CNV detection. On the other hand, most of algorithms is using command line interface that may greatly limit the analysis capability of many laboratories. We create a series of simulated WES datasets from UCSC hg19 chromosome 22, and then evaluate the CNV detective ability of 19 algorithms from OMICtools database using our simulated WES datasets. We compute the sensitivity, specificity and accuracy in each algorithm for validation of the exome-derived CNVs. After comparison of 19 algorithms from OMICtools database, we construct a platform to install all of the algorithms in a virtual machine like VirtualBox which can be established conveniently in local computers, and then create a simple script that can be easily to use for detecting CNVs using algorithms selected by users. We also build a table to elaborate on many kinds of events, such as input requirement, CNV detective ability, for all of the algorithms that can provide users a specification to choose optimum algorithms.

Keywords: whole exome sequencing, copy number variations, omictools, pipeline

Procedia PDF Downloads 319

Authors: James R. Wilson

Abstract:

Music is typically defined as having the attributes of melody, harmony, and rhythm. In this paper, a fourth element is proposed -"flow". "Flow" is a new dimension in music that has always been present but only recently identified and measured. The Adagio "Flow Machine" enables us to envision this component and even suggests a new approach to music theory and analysis. The Adagio was created specifically to measure the underlying “flow” in music. The Adagio is an entirely new way to experience and visualize the music, to assist in performing music (both as a conductor and/or performer), and to provide a whole new methodology for music analysis and theory. The Adagio utilizes musical “hit points”, such as a transition from one musical section to another (for example, in a musical composition utilizing the sonata form, a transition from the exposition to the development section) to help define the compositions flow rate. Once the flow rate is established, the Adagio can be used to determine if the composer/performer/conductor has correctly maintained the proper rate of flow throughout the performance. An example is provided using Mozart’s Piano Concerto Number 21. Working with the Adagio yielded an unexpected windfall; it was determined via an empirical study conducted at Nova University’s Biofeedback Lab that watching the Adagio helped volunteers participating in a controlled experiment recover from stressors significantly faster than the control group. The Adagio can be thought of as a new arrow in the Musicologist's quiver. It provides a new, unique way of viewing the psychological impact and esthetic effectiveness of music composition. Additionally, with the current worldwide access to multi-media via the internet, flow analysis can be performed and shared with others with little time and/or expense.

Keywords: musicology, music analysis, music flow, music therapy

Procedia PDF Downloads 177

Authors: A. Razavykia, A. Esmaeilzadeh, S. Iranmanesh

Abstract:

Many orthopedic implants like proximal humerus cases require lower surface roughness and almost immediate/short lead time surgery. Thus, rapid response from the manufacturer is very crucial. Tool path strategy of milling process has a direct influence on the surface roughness and lead time of medical implant. High-speed milling as promised process would improve the machined surface quality, but conventional or super-abrasive grinding still required which imposes some drawbacks such as additional costs and time. Currently, many CAD/CAM software offers some different tool path strategies to milling free form surfaces. Nevertheless, the users must identify how to choose the strategies according to cutting tool geometry, geometry complexity, and their effects on the machined surface. This study investigates the effect of different tool path strategies for milling a proximal humerus head during finishing operation on stainless steel 316L. Experiments have been performed using MAHO MH700 S vertical milling machine and four machining strategies, namely, spiral outward, spiral inward, and radial as well as zig-zag. In all cases, the obtained surfaces were analyzed in terms of roughness and dimension accuracy compared with those obtained by simulation. The findings provide evidence that surface roughness, dimensional accuracy, and machining time have been affected by the considered tool path strategy.

Keywords: CAD/CAM software, milling, orthopedic implants, tool path strategy

Procedia PDF Downloads 213

Authors: Emmanuel Okechukwu Nwafor, Folake Olubunmi Akintayo, Denis Alcides Rezende

Abstract:

Decision tree models are versatile and interpretable machine learning algorithms widely used for both classification and regression tasks, which can be related to cities, whether physical or digital. The aim of this research is to assess how well decision tree algorithms can predict trip purposes in Makurdi, Nigeria, while also exploring their connection to the strategic digital city initiative. The research methodology involves formalizing household demographic and trips information datasets obtained from extensive survey process. Modelling and Prediction were achieved using Python Programming Language and the evaluation metrics like R-squared and mean absolute error were used to assess the decision tree algorithm's performance. The results indicate that the model performed well, with accuracies of 84% and 68%, and low MAE values of 0.188 and 0.314, on training and validation data, respectively. This suggests the model can be relied upon for future prediction. The conclusion reiterates that This model will assist decision-makers, including urban planners, transportation engineers, government officials, and commuters, in making informed decisions on transportation planning and management within the framework of a strategic digital city. Its application will enhance the efficiency, sustainability, and overall quality of transportation services in Makurdi, Nigeria.

Keywords: decision tree algorithm, trip purpose, intelligent transport, strategic digital city, travel pattern, sustainable transport

Procedia PDF Downloads 21

Authors: Opeyemi Atiba-Oyewo, Maurice S. Onyango, Christian Wolkersdorfer

Abstract:

Characterization and nanostructure formation of banana peels as sorbent material are described in this paper. The transformation of this agricultural waste via mechanical milling to enhance its properties such as changed in microstructure and surface area for water pollution control and other applications were studied. Mechanical milling was employed using planetary continuous milling machine with ethanol as a milling solvent and the samples were taken at time intervals between 10 h to 30 h to examine the structural changes. The samples were characterised by X-ray diffraction (XRD), scanning electron microscopy (SEM), Fourier transform infra-red (FTIR), Transmission electron microscopy (TEM) and Brunauer Emmett and teller (BET). Results revealed three typical structures with different deformation mechanisms and the grain-sizes within the range of (71-12 nm), nanostructure of the particles and fibres. The particle size decreased from 65µm to 15 nm as the milling progressed for a period of 30 h. The morphological properties of the materials indicated that the particle shapes becomes regular and uniform as the milling progresses. Furthermore, particles fracturing resulted in surface area increment from 1.0694-4.5547 m2/g. The functional groups responsible for the banana peels capacity to coordinate and remove metal ions, such as the carboxylic and amine groups were identified at absorption bands of 1730 and 889 cm-1, respectively. However, the choice of this sorbent material for the sorption or any application will depend on the composition of the pollutant to be eradicated.

Keywords: characterization, nanostructure, nanosorbent, eco-friendly, banana peels, mechanical milling, water quality

Procedia PDF Downloads 286

Authors: Kyung Bae Park, Sung Ho Ha

Abstract:

Online user-generated contents (UGC) significantly change the way customers behave (e.g., shop, travel), and a pressing need to handle the overwhelmingly plethora amount of various UGC is one of the paramount issues for management. However, a current approach (e.g., sentiment analysis) is often ineffective for leveraging textual information to detect the problems or issues that a certain management suffers from. In this paper, we employ text mining of Latent Dirichlet Allocation (LDA) on a popular online review site dedicated to complaint from users. We find that the employed LDA efficiently detects customer complaints, and a further inspection with the visualization technique is effective to categorize the problems or issues. As such, management can identify the issues at stake and prioritize them accordingly in a timely manner given the limited amount of resources. The findings provide managerial insights into how analytics on social media can help maintain and improve their reputation management. Our interdisciplinary approach also highlights several insights by applying machine learning techniques in marketing research domain. On a broader technical note, this paper illustrates the details of how to implement LDA in R program from a beginning (data collection in R) to an end (LDA analysis in R) since the instruction is still largely undocumented. In this regard, it will help lower the boundary for interdisciplinary researcher to conduct related research.

Keywords: latent dirichlet allocation, R program, text mining, topic model, user generated contents, visualization

Procedia PDF Downloads 187

Authors: Shan Faiz, Arfat Anis, Saeed M. Al-Zarani

Abstract:

High density polyethylene (HDPE) and poly benzimidazole fiber (PBI) composites were prepared by melt blending in a twin screw extruder (TSE). The thermo-mechanical properties of PBI fiber reinforced HDPE composite samples (1%, 4% and 8% fiber content) of fiber lengths 3 mm and 6 mm were investigated using differential scanning calorimeter (DSC), universal testing machine (UTM), rheometer and scanning electron microscopy (SEM). The effect of fiber content and fiber lengths on the thermo-mechanical properties of the HDPE-PBI composites was studied. The DSC analysis showed decrease in crystallinity of HDPE-PBI composites with the increase of fiber loading. Maximum decrease observed was 12% at 8% fiber length. The thermal stability was found to increase with the addition of fiber. T50% was notably increased to 40oC for both grades of HDPE using 8% of fiber content. The mechanical properties were not much affected by the increase in fiber content. The optimum value of tensile strength was achieved using 4% fiber content and slight increase of 9% in tensile strength was observed. No noticeable change was observed in flexural strength. In rheology study, the complex viscosities of HDPE-PBI composites were higher than the HDPE matrix and substantially increased with even minimum increase of PBI fiber loading i.e. 1%. We found that the addition of the PBI fiber resulted in a modest improvement in the thermal stability and mechanical properties of the prepared composites.

Keywords: PBI fiber, high density polyethylene, composites, melt blending

Procedia PDF Downloads 366

Authors: Nitin Dewangan, Nitin Kattula, Megha Anawat

Abstract:

Hydraulic reservoir is the key component in the mobile construction vehicles; most of the off-road earth moving construction machinery requires bigger side hydraulic reservoirs. Their reservoir construction is very much non-uniform and designers used such design to utilize the space available under the vehicle. There is no way to find out the space utilization of the reservoir by oil and validity of design except virtual simulation. Computational fluid dynamics (CFD) helps to predict the reservoir space utilization by vortex mapping, path line plots and dwell time prediction to make sure the design is valid and efficient for the vehicle. The dwell time acceptance criteria for effective reservoir design is 15 seconds. The paper will describe the hydraulic reservoir simulation which is carried out using CFD tool acuSolve using automated mesh strategy. The free surface flow and moving reference mesh is used to define the oil flow level inside the reservoir. The first baseline design is not able to meet the acceptance criteria, i.e., dwell time below 15 seconds because the oil entry and exit ports were very close. CFD is used to redefine the port locations for the reservoir so that oil dwell time increases in the reservoir. CFD also proposed baffle design the effective space utilization. The final design proposed through CFD analysis is used for physical validation on the machine.

Keywords: reservoir, turbulence model, transient model, level set, free-surface flow, moving frame of reference

Procedia PDF Downloads 152

Authors: Faruk Ozdemir, Roy Kalawsky, Peter Hubbard

Abstract:

Accurate estimation of RUL provides a basis for effective predictive maintenance, reducing unexpected downtime for industrial equipment. However, while models such as the Random Forest have effective predictive capabilities, they are the so-called ‘black box’ models, where interpretability is at a threshold to make critical diagnostic decisions involved in industries related to aviation. The purpose of this work is to present a prognostic framework that embeds Explainable Artificial Intelligence (XAI) techniques in order to provide essential transparency in Machine Learning methods' decision-making mechanisms based on sensor data, with the objective of procuring actionable insights for the aviation industry. Sensor readings have been gathered from critical equipment such as turbofan jet engine and landing gear, and the prediction of the RUL is done by a Random Forest model. It involves steps such as data gathering, feature engineering, model training, and evaluation. These critical components’ datasets are independently trained and evaluated by the models. While suitable predictions are served, their performance metrics are reasonably good; such complex models, however obscure reasoning for the predictions made by them and may even undermine the confidence of the decision-maker or the maintenance teams. This is followed by global explanations using SHAP and local explanations using LIME in the second phase to bridge the gap in reliability within industrial contexts. These tools analyze model decisions, highlighting feature importance and explaining how each input variable affects the output. This dual approach offers a general comprehension of the overall model behavior and detailed insight into specific predictions. The proposed framework, in its third component, incorporates the techniques of causal analysis in the form of Granger causality tests in order to move beyond correlation toward causation. This will not only allow the model to predict failures but also present reasons, from the key sensor features linked to possible failure mechanisms to relevant personnel. The causality between sensor behaviors and equipment failures creates much value for maintenance teams due to better root cause identification and effective preventive measures. This step contributes to the system being more explainable. Surrogate Several simple models, including Decision Trees and Linear Models, can be used in yet another stage to approximately represent the complex Random Forest model. These simpler models act as backups, replicating important jobs of the original model's behavior. If the feature explanations obtained from the surrogate model are cross-validated with the primary model, the insights derived would be more reliable and provide an intuitive sense of how the input variables affect the predictions. We then create an iterative explainable feedback loop, where the knowledge learned from the explainability methods feeds back into the training of the models. This feeds into a cycle of continuous improvement both in model accuracy and interpretability over time. By systematically integrating new findings, the model is expected to adapt to changed conditions and further develop its prognosis capability. These components are then presented to the decision-makers through the development of a fully transparent condition monitoring and alert system. The system provides a holistic tool for maintenance operations by leveraging RUL predictions, feature importance scores, persistent sensor threshold values, and autonomous alert mechanisms. Since the system will provide explanations for the predictions given, along with active alerts, the maintenance personnel can make informed decisions on their end regarding correct interventions to extend the life of the critical machinery.

Keywords: predictive maintenance, explainable artificial intelligence, prognostic, RUL, machine learning, turbofan engines, C-MAPSS dataset

Procedia PDF Downloads 7

Authors: Stelios A. Mitilineos, Nicolas-Alexander Tatlas, Georgia Korompili, Lampros Kokkalas, Stelios M. Potirakis

Abstract:

Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS) is a widespread chronic disease that mostly remains undetected, mainly due to the fact that it is diagnosed via polysomnography which is a time and resource-intensive procedure. Screening the disease’s symptoms at home could be used as an alternative approach in order to alert individuals that potentially suffer from OSAHS without compromising their everyday routine. Since snoring is usually linked to OSAHS, developing a snore detector is appealing as an enabling technology for screening OSAHS at home using ubiquitous equipment like commodity microphones (included in, e.g., smartphones). In this context, this study developed a snore detection tool and herein present the approach and selection of specific sound features that discriminate snoring vs. environmental sounds, as well as the performance of the proposed tool. Furthermore, a Real-Time Snore Detector (RTSD) is built upon the snore detection tool and employed in whole-night sleep sound recordings resulting to a large dataset of snoring sound excerpts that are made freely available to the public. The RTSD may be used either as a stand-alone tool that offers insight to an individual’s sleep quality or as an independent component of OSAHS screening applications in future developments.

Keywords: obstructive sleep apnea hypopnea syndrome, apnea screening, snoring detection, machine learning, neural networks

Procedia PDF Downloads 207

Authors: M. Saiful Islam, M. Mohandes, S. Rehman, S. Badran

Abstract:

Increasing necessity of wind power is directing us to have precise knowledge on wind resources. Methodical investigation of potential locations is required for wind power deployment. High penetration of wind energy to the grid is leading multi megawatt installations with huge investment cost. This fact appeals to determine appropriate places for wind farm operation. For accurate assessment, detailed examination of wind speed profile, relative humidity, temperature and other geological or atmospheric parameters are required. Among all of these uncertainty factors influencing wind power estimation, vertical extrapolation of wind speed is perhaps the most difficult and critical one. Different approaches have been used for the extrapolation of wind speed to hub height which are mainly based on Log law, Power law and various modifications of the two. This paper proposes a Artificial Neural Network (ANN) and Genetic Algorithm (GA) based hybrid model, namely GA-NN for vertical extrapolation of wind speed. This model is very simple in a sense that it does not require any parametric estimations like wind shear coefficient, roughness length or atmospheric stability and also reliable compared to other methods. This model uses available measured wind speeds at 10m, 20m and 30m heights to estimate wind speeds up to 100m. A good comparison is found between measured and estimated wind speeds at 30m and 40m with approximately 3% mean absolute percentage error. Comparisons with ANN and power law, further prove the feasibility of the proposed method.

Keywords: wind profile, vertical extrapolation of wind, genetic algorithm, artificial neural network, hybrid machine learning

Procedia PDF Downloads 490

Authors: Kamélia Bouderbala, Hichem Nouira, Etienne Videcoq, Manuel Girault, Daniel Petit

Abstract:

Thermal drifts caused by the power dissipated by the mechanical guiding systems constitute the main limit to enhance the accuracy of an ultra-high precision cylindricity measuring machine. For this reason, a high precision compact prototype has been designed to simulate the behaviour of the instrument. It ensures in situ calibration of four capacitive displacement probes by comparison with four laser interferometers. The set-up includes three heating wires for simulating the powers dissipated by the mechanical guiding systems, four additional heating wires located between each laser interferometer head and its respective holder, 19 Platinum resistance thermometers (Pt100) to observe the temperature evolution inside the set-up and four Pt100 sensors to monitor the ambient temperature. Both a Reduced Model (RM), based on the Modal Identification Method (MIM) was developed and optimized by comparison with the experimental results. Thereafter, time dependent tests were performed under several conditions to measure the temperature variation at 19 fixed positions in the system and compared to the calculated RM results. The RM results show good agreement with experiment and reproduce as well the temperature variations, revealing the importance of the RM proposed for the evaluation of the thermal behaviour of the system.

Keywords: modal identification method (MIM), thermal behavior and drift, dimensional metrology, measurement

Procedia PDF Downloads 396

Authors: Sushma Ghogale

Abstract:

With a surge in user-generated content or feedback or reviews on the internet, it has become possible and important to know consumers' opinions about products and services. This data is important for both potential customers and businesses providing the services. Data from social media is attracting significant attention and has become the most prominent channel of expressing an unregulated opinion. Prospective customers look for reviews from experienced customers before deciding to buy a product or service. Several websites provide a platform for users to post their feedback for the provider and potential customers. However, the biggest challenge in analyzing such data is in extracting latent features and providing term-level analysis of the data. This paper proposes an approach to use topic modeling to classify the reviews into topics and conduct sentiment analysis to mine the opinions. This approach can analyse and classify latent topics mentioned by reviewers on business sites or review sites, or social media using topic modeling to identify the importance of each topic. It is followed by sentiment analysis to assess the satisfaction level of each topic. This approach provides a classification of hotel reviews using multiple machine learning techniques and comparing different classifiers to mine the opinions of user reviews through sentiment analysis. This experiment concludes that Multinomial Naïve Bayes classifier produces higher accuracy than other classifiers.

Keywords: latent Dirichlet allocation, topic modeling, text classification, sentiment analysis

Procedia PDF Downloads 97

Authors: Mohammad Bakhshandeh

Abstract:

Structural Health Monitoring (SHM) is a crucial and necessary practice that plays a vital role in ensuring the safety and integrity of critical structures, and in particular, bridges. The continuous monitoring of bridges for signs of damage or degradation through Bridge Health Monitoring (BHM) enables early detection of potential problems, allowing for prompt corrective action to be taken before significant damage occurs. Although all monitoring techniques aim to provide accurate and decisive information regarding the remaining useful life, safety, integrity, and serviceability of bridges, understanding the development and propagation of damage is vital for maintaining uninterrupted bridge operation. Over the years, extensive research has been conducted on BHM methods, and experts in the field have increasingly adopted new methodologies. In this article, we provide a comprehensive exploration of the various BHM approaches, including sensor-based, non-destructive testing (NDT), model-based, and artificial intelligence (AI)-based methods. We also discuss the challenges associated with BHM, including sensor placement and data acquisition, data analysis and interpretation, cost and complexity, and environmental effects, through an extensive review of relevant literature and research studies. Additionally, we examine potential solutions to these challenges and propose future research ideas to address critical gaps in BHM.

Keywords: structural health monitoring (SHM), bridge health monitoring (BHM), sensor-based methods, machine-learning algorithms, and model-based techniques, sensor placement, data acquisition, data analysis

Procedia PDF Downloads 90

Authors: Vu H. N. Khue, Marian Pavelka, Georg Jocher, Jiří Dušek, Le T. Son, Bui T. An, Ho Q. Bang, Pham Q. Huong

Abstract:

Agriculture is an important economic sector of Vietnam, the most popular of which is wet rice cultivation. These activities are also known as the main contributor to the national greenhouse gas. In order to understand more about greenhouse gas exchange in these activities and to investigate the factors influencing carbon cycling and sequestration in these types of ecosystems, since 2019, the first eddy covariance station has been installed in a paddy field in Long An province, Mekong Delta. The station was equipped with state-of-the-art equipment for CO₂ and CH₄ gas exchange and micrometeorology measurements. In this study, data from the station was processed following the ICOS recommendations (Integrated Carbon Observation System) standards for CO₂, while CH₄ was manually processed and gap-filled using a random forest model from methane-gapfill-ml, a machine learning package, as there is no standard method for CH₄ flux gap-filling yet. Finally, the carbon equivalent (Ce) balance based on CO₂ and CH₄ fluxes was estimated. The results show that in 2020, even though a new water management practice - alternate wetting and drying - was applied to reduce methane emissions, the paddy field released 928 g Cₑ.m⁻².yr⁻¹, and in 2021, it was reduced to 707 g Cₑ.m⁻².yr⁻¹. On a provincial level, rice cultivation activities in Long An, with a total area of 498,293 ha, released 4.6 million tons of Cₑ in 2020 and 3.5 million tons of Cₑ in 2021.

Keywords: eddy covariance, greenhouse gas, methane, rice cultivation, Mekong Delta

Procedia PDF Downloads 142