Search results for: iterative algorithms

Authors: Jia-Shiun Chen, Hsiu-Ying Hwang

Abstract:

Hybrid electric vehicles can reduce pollution and improve fuel economy. Power-split hybrid electric vehicles (HEVs) provide two power paths between the internal combustion engine (ICE) and energy storage system (ESS) through the gears of an electrically variable transmission (EVT). EVT allows ICE to operate independently from vehicle speed all the time. Therefore, the ICE can operate in the efficient region of its characteristic brake specific fuel consumption (BSFC) map. The two-mode powertrain can operate in input-split or compound-split EVT modes and in four different fixed gear configurations. Power-split architecture is advantageous because it combines conventional series and parallel power paths. This research focuses on input-split and compound-split modes in the two-mode power-split powertrain. Fuzzy Logic Control (FLC) for an internal combustion engine (ICE) and PI control for electric machines (EMs) are derived for the urban driving cycle simulation. These control algorithms reduce vehicle fuel consumption and improve ICE efficiency while maintaining the state of charge (SOC) of the energy storage system in an efficient range.

Keywords: hybrid electric vehicle, fuel economy, two-mode hybrid, fuzzy control

Procedia PDF Downloads 384

Authors: Silvio Ricardo Rodrigues Sanches, Bianca Cogo Barbosa, Beatriz Regina Brum, Cléber Gimenez Corrêa

Abstract:

To evaluate the quality of a segmentation algorithm, the authors use subjective or objective metrics. Although subjective metrics are more accurate than objective ones, objective metrics do not require user feedback to test an algorithm. Objective metrics require subjective experiments only during their development. Subjective experiments typically display to users some videos (generated from frames with segmentation errors) that simulate the environment of an application domain. This user feedback is crucial information for metric definition. In the subjective experiments applied to develop some state-of-the-art metrics used to test segmentation algorithms, the videos displayed during the experiments did not contain audio. Audio is an essential component in applications such as videoconference and augmented reality. If the audio influences the user’s perception, using only videos without audio in subjective experiments can compromise the efficiency of an objective metric generated using data from these experiments. This work aims to identify if the audio influences the user’s perception of segmentation quality in background substitution applications with audio. The proposed approach used a subjective method based on formal video quality assessment methods. The results showed that audio influences the quality of segmentation perceived by a user.

Keywords: background substitution, influence of audio, segmentation evaluation, segmentation quality

Procedia PDF Downloads 118

Authors: Lokes Parvatha Kumaran S., Sakthi Jay Mahenthar C., Sathyaprakash P., Jayakumar V., Shobanadevi A.

Abstract:

With the evolution of technology, the need to solve complex computational problems like machine learning and deep learning has shot up. But even the most powerful classical supercomputers find it difficult to execute these tasks. With the recent development of quantum computing, researchers and tech-giants strive for new quantum circuits for machine learning tasks, as present works on Quantum Machine Learning (QML) ensure less memory consumption and reduced model parameters. But it is strenuous to simulate classical deep learning models on existing quantum computing platforms due to the inflexibility of deep quantum circuits. As a consequence, it is essential to design viable quantum algorithms for QML for noisy intermediate-scale quantum (NISQ) devices. The proposed work aims to explore Variational Quantum Circuits (VQC) for Deep Reinforcement Learning by remodeling the experience replay and target network into a representation of VQC. In addition, to reduce the number of model parameters, quantum information encoding schemes are used to achieve better results than the classical neural networks. VQCs are employed to approximate the deep Q-value function for decision-making and policy-selection reinforcement learning with experience replay and the target network.

Keywords: quantum computing, quantum machine learning, variational quantum circuit, deep reinforcement learning, quantum information encoding scheme

Procedia PDF Downloads 136

Authors: Bruk Gebregziabher

Abstract:

The safe and efficient operation of Autonomous Mobile Robots (AMRs) in complex environments, such as manufacturing, logistics, and agriculture, necessitates accurate multiobject tracking and predictive collision avoidance. This paper presents algorithms and techniques for addressing these challenges using Lidar sensor data, emphasizing ensemble Kalman filter. The developed predictive collision avoidance algorithm employs the data provided by lidar sensors to track multiple objects and predict their velocities and future positions, enabling the AMR to navigate safely and effectively. A modification to the dynamic windowing approach is introduced to enhance the performance of the collision avoidance system. The overall system architecture encompasses object detection, multi-object tracking, and predictive collision avoidance control. The experimental results, obtained from both simulation and real-world data, demonstrate the effectiveness of the proposed methods in various scenarios, which lays the foundation for future research on global planners, other controllers, and the integration of additional sensors. This thesis contributes to the ongoing development of safe and efficient autonomous systems in complex and dynamic environments.

Keywords: autonomous mobile robots, multi-object tracking, predictive collision avoidance, ensemble Kalman filter, lidar sensors

Procedia PDF Downloads 84

Authors: Amit Kumar, Amanpreet Chander, Ashish Sahani

Abstract:

This paper presents our recent work on real-time human activity detection based on the media pipe pipeline and machine learning algorithms. The proposed system can detect human activities, including running, jumping, squatting, bending to the left or right, and standing still. This is a robust solution for developing a yoga, dance, metaverse, and fitness application that checks for the correction of the pose without having any additional monitor like a personal trainer. MediaPipe solution offers an open-source cross-platform which utilizes a two-step detector-tracker ML pipeline for live detection of key landmarks on our body which can be used for motion data collection. The prediction of real-time poses uses a variety of machine learning techniques and different types of analysis. Without primarily relying on powerful desktop environments for inference, our method achieves real-time performance on the majority of contemporary mobile phones, desktops/laptops, Python, or even the web. Experimental results show that our method outperforms the existing method in terms of accuracy and real-time capability, achieving an accuracy of 99.92% on testing datasets.

Keywords: human activity detection, media pipe, machine learning, metaverse applications

Procedia PDF Downloads 180

Authors: Ayadi Aya, Ghorbel Oussama, M. Obeid Abdulfattah, Abid Mohamed

Abstract:

Nowadays, many wireless sensor networks have been distributed in the real world to collect valuable raw sensed data. The challenge is to extract high-level knowledge from this huge amount of data. However, the identification of outliers can lead to the discovery of useful and meaningful knowledge. In the field of wireless sensor networks, an outlier is defined as a measurement that deviates from the normal behavior of sensed data. Many detection techniques of outliers in WSNs have been extensively studied in the past decade and have focused on classic based algorithms. These techniques identify outlier in the real transaction dataset. This survey aims at providing a structured and comprehensive overview of the existing researches on classification based outlier detection techniques as applicable to WSNs. Thus, we have identified key hypotheses, which are used by these approaches to differentiate between normal and outlier behavior. In addition, this paper tries to provide an easier and a succinct understanding of the classification based techniques. Furthermore, we identified the advantages and disadvantages of different classification based techniques and we presented a comparative guide with useful paradigms for promoting outliers detection research in various WSN applications and suggested further opportunities for future research.

Keywords: bayesian networks, classification-based approaches, KPCA, neural networks, one-class SVM, outlier detection, wireless sensor networks

Procedia PDF Downloads 499

Authors: Francisca Margarita Ocran

Abstract:

Underwear, and more particularly bras and panties, are defined as intimate clothing. Strictly speaking, they enhance the place of women in the public or private satchel. Therefore, women's lingerie is a complex garment with a high involvement profile, motivating consumers to buy it not only by its functional utility but also by the multisensory experience it provides them. Customer behavior models are generally based on customer data mining, and each model is designed to answer questions at a specific time. Predicting the customer experience is uncertain and difficult. Thus, knowledge of consumers' tastes in lingerie deserves to be treated as an experiential product, where the dimensions of the experience motivating consumers to buy a lingerie product and to remain faithful to it must be analyzed in detail by the manufacturers and retailers to engage and retain consumers, which is why this research aims to identify the variables that push consumers to choose their lingerie product, based on an in-depth analysis of the types of fabrics used to make lingerie. The data used in this study comes from online purchases. Machine learning approach with the use of Python programming language and Pycaret gives us a precision of 86.34%, 85.98%, and 84.55% for the three algorithms to use concerning the preference of a buyer in front of a range of lingerie. Gradient Boosting, random forest, and K Neighbors were used in this study; they are very promising and rich in the classification of preference in the textile industry.

Keywords: consumer behavior, data mining, lingerie, machine learning, preference

Procedia PDF Downloads 92

Authors: Ismael Zamora, Elisabeth Ortega, Tatiana Radchenko, Guillem Plasencia

Abstract:

The structure elucidation based on Mass Spectra (MS) data of unknown substances is an unresolved problem that affects many different fields of application. The recent overview of software available for structure elucidation of small molecules has shown the demand for efficient computational tool that will be able to perform structure elucidation of unknown small molecules and peptides. We developed an algorithm for De-Novo fragment analysis based on MS data that proposes a set of scored and ranked structures that are compatible with the MS and MSMS spectra. Several different algorithms were developed depending on the initial set of fragments and the structure building processes. Also, in all cases, several scores for the final molecule ranking were computed. They were validated with small and middle databases (DB) with the eleven test set compounds. Similar results were obtained from any of the databases that contained the fragments of the expected compound. We presented an algorithm. Or De-Novo fragment analysis based on only mass spectrometry (MS) data only that proposed a set of scored/ranked structures that was validated on different types of databases and showed good results as proof of concept. Moreover, the solutions proposed by Mass Spectrometry were submitted to the prediction of NMR spectra in order to elucidate which of the proposed structures was compatible with the NMR spectra collected.

Keywords: De Novo, structure elucidation, mass spectrometry, NMR

Procedia PDF Downloads 297

Authors: Belinda du Plooy, Ruth Albertyn, Christel Troskie-De Bruin, Ella Belcher

Abstract:

In the academy, scholarliness or intellectual craftsmanship is considered the highest level of achievement, culminating in being consistently successfully published in impactful, peer-reviewed journals and books. Scholarliness implies rigorous methods, systematic exposition, in-depth analysis and evaluation, and the highest level of critical engagement and reflexivity. However, being a scholar does not happen automatically when one becomes an academic or completes graduate studies. A graduate qualification is an indication of one’s level of research competence but does not necessarily prepare one for the type of scholarly writing for publication required after a postgraduate qualification has been conferred. Scholarly writing for publication requires a high-level skillset and a specific mindset, which must be intentionally developed. The rite of passage to become a scholar is an iterative process with liminal spaces, thresholds, transitions, and transformations. The journey from researcher to published author is often fraught with rejection, insecurity, and disappointment and requires resilience and tenacity from those who eventually triumph. It cannot be achieved without support, guidance, and mentorship. In this article, the authors use collective auto-ethnography (CAE) to describe the phases and types of liminality encountered during the liminal journey toward scholarship. The authors speak as long-time facilitators of Writing for Academic Publication (WfAP) capacity development events (training workshops and writing retreats) presented at South African universities. Their WfAP facilitation practice is structured around experiential learning principles that allow them to act as critical reading partners and reflective witnesses for the writer-participants of their WfAP events. They identify three essential facilitation features for the effective holding of a generative, liminal, and transformational writing space for novice academic writers in order to enable their safe passage through the various liminal spaces they encounter during their scholarly development journey. These features are that facilitators should be agents of disruption and liminality while also guiding writers through these liminal spaces; that there should be a sense of mutual trust and respect, shared responsibility and accountability in order for writers to produce publication-worthy scholarly work; and that this can only be accomplished with the continued application of high levels of sensitivity and discernment by WfAP facilitators. These are key features for successful WfAP scholarship training events, where focused, individual input triggers personal and professional transformational experiences, which in turn translate into high-quality scholarly outputs.

Keywords: academic writing, liminality, scholarship, scholarliness, threshold experience, writing for publication

Procedia PDF Downloads 44

Authors: Yavuz Unal, Kemal Polat, H. Erdinc Kocer

Abstract:

In this study, a decision support system comprising three stages has been proposed to detect the disc abnormalities of the lumbar region. In the first stage named the feature extraction, T2-weighted sagittal and axial Magnetic Resonance Images (MRI) were taken from 55 people and then 27 appearance and shape features were acquired from both sagittal and transverse images. In the second stage named the feature weighting process, k-means clustering based feature weighting (KMCBFW) proposed by Gunes et al. Finally, in the third stage named the classification process, the classifier algorithms including multi-layer perceptron (MLP- neural network), support vector machine (SVM), Naïve Bayes, and decision tree have been used to classify whether the subject has lumbar disc or not. In order to test the performance of the proposed method, the classification accuracy (%), sensitivity, specificity, precision, recall, f-measure, kappa value, and computation times have been used. The best hybrid model is the combination of k-means clustering based feature weighting and decision tree in the detecting of lumbar disc disease based on both sagittal and axial MR images.

Keywords: lumbar disc abnormality, lumbar MRI, lumbar spine, hybrid models, hybrid features, k-means clustering based feature weighting

Procedia PDF Downloads 521

Authors: D. Li

Abstract:

Optical thin films are used in a wide variety of optical components and there are many software tools programmed for advancing multilayer thin film design. The available software packages for designing the thin film structure may not provide optimum designs. Normally, almost all current software programs obtain their final designs either from optimizing a starting guess or by technique, which may or may not involve a pseudorandom process, that give different answers every time, depending upon the initial conditions. With the increasing power of personal computers, functional methods in optimization and synthesis of optical multilayer systems have been developed such as DGL Optimization, Simulated Annealing, Genetic Algorithms, Needle Optimization, Inductive Optimization and Flip-Flop Optimization. Among these, DGL Optimization has proved its efficiency in optical thin film designs. The application of the DGL optimization technique to the design of optical coating is presented. A DGL optimization technique is provided, and its main features are discussed. Guidelines on the application of the DGL optimization technique to various types of design problems are given. The innovative global optimization strategies used in a software tool, OnlyFilm, to optimize multilayer thin film designs through different filter designs are outlined. OnlyFilm is a powerful, versatile, and user-friendly thin film software on the market, which combines optimization and synthesis design capabilities with powerful analytical tools for optical thin film designers. It is also the only thin film design software that offers a true global optimization function.

Keywords: optical coatings, optimization, design software, thin film design

Procedia PDF Downloads 316

Authors: Kemka C. Ihemelandu, Chukwuemeka U. Ihemelandu

Abstract:

The incidence of melanoma has been increasing rapidly over the past two decades, making melanoma a current public health crisis. Unfortunately, even as screening efforts continue to expand in an effort to ameliorate the death rate from melanoma, there is a need to improve diagnostic accuracy to decrease misdiagnosis. Artificial intelligence (AI) a new frontier in patient care has the ability to improve the accuracy of melanoma diagnosis. Convolutional neural network (CNN) a form of deep neural network, most commonly applied to analyze visual imagery, has been shown to outperform the human brain in pattern recognition. However, there are noted limitations with the accuracy of the CNN models. Our aim in this study was the optimization of convolutional neural network algorithms for the automated diagnosis of melanoma. We hypothesized that Optimal selection of the momentum and batch hyperparameter increases model accuracy. Our most successful model developed during this study, showed that optimal selection of momentum of 0.25, batch size of 2, led to a superior performance and a faster model training time, with an accuracy of ~ 83% after nine hours of training. We did notice a lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone. Training set image transformations did not result in a superior model performance in our study.

Keywords: melanoma, convolutional neural network, momentum, batch hyperparameter

Procedia PDF Downloads 101

Authors: Andrii Shalaginov, Katrin Franke, Xiongwei Huang

Abstract:

One of the leading problems in Cyber Security today is the emergence of targeted attacks conducted by adversaries with access to sophisticated tools. These attacks usually steal senior level employee system privileges, in order to gain unauthorized access to confidential knowledge and valuable intellectual property. Malware used for initial compromise of the systems are sophisticated and may target zero-day vulnerabilities. In this work we utilize common behaviour of malware called ”beacon”, which implies that infected hosts communicate to Command and Control servers at regular intervals that have relatively small time variations. By analysing such beacon activity through passive network monitoring, it is possible to detect potential malware infections. So, we focus on time gaps as indicators of possible C2 activity in targeted enterprise networks. We represent DNS log files as a graph, whose vertices are destination domains and edges are timestamps. Then by using four periodicity detection algorithms for each pair of internal-external communications, we check timestamp sequences to identify the beacon activities. Finally, based on the graph structure, we infer the existence of other infected hosts and malicious domains enrolled in the attack activities.

Keywords: malware detection, network security, targeted attack, computational intelligence

Procedia PDF Downloads 267

Authors: Lee Boudreau, Ash Kumar Khaitu, Laura A. S. MacDonald

Abstract:

In April 2015, a magnitude 7.8 earthquake struck Nepal, killing, injuring, and displacing thousands of people. The earthquake also damaged water and sanitation service networks, leading to a high risk of diarrheal disease and the associated negative health impacts. In response to the disaster, the Environment and Public Health Organization (ENPHO), a Kathmandu-based non-governmental organization, worked with the Centre for Affordable Water and Sanitation Technology (CAWST), a Canadian education, training and consulting organization, to develop two training programs to educate volunteers on water, sanitation, and hygiene (WASH) needs. The first training program was intended for acute response, with the second focusing on longer term recovery. A key focus was to equip the volunteers with the knowledge and skills to formulate useful WASH advice in the unanticipated circumstances they would encounter when working in affected areas. Within the first two weeks of the disaster, a two-day acute response training was developed, which focused on enabling volunteers to educate those affected by the disaster about local WASH issues, their link to health, and their increased importance immediately following emergency situations. Between March and October 2015, a total of 19 training events took place, with over 470 volunteers trained. The trained volunteers distributed hygiene kits and liquid chlorine for household water treatment. They also facilitated health messaging and WASH awareness activities in affected communities. A three-day recovery phase training was also developed and has been delivered to volunteers in Nepal since October 2015. This training focused on WASH issues during the recovery and reconstruction phases. The interventions and recommendations in the recovery phase training focus on long-term WASH solutions, and so form a link between emergency relief strategies and long-term development goals. ENPHO has trained 226 volunteers during the recovery phase, with training ongoing as of April 2016. In the aftermath of the earthquake, ENPHO found that its existing pool of volunteers were more than willing to help those in their communities who were more in need. By training these and new volunteers, ENPHO was able to reach many more communities in the immediate aftermath of the disaster; together they reached 11 of the 14 earthquake-affected districts. The collaboration between ENPHO and CAWST in developing the training materials was a highly collaborative and iterative process, which enabled the training materials to be developed within a short response time. By training volunteers on basic WASH topics during both the immediate response and the recovery phase, ENPHO and CAWST have been able to link immediate emergency relief to long-term developmental goals. While the recovery phase training continues in Nepal, CAWST is planning to decontextualize the training used in both phases so that it can be applied to other emergency situations in the future. The training materials will become part of the open content materials available on CAWST’s WASH Resources website.

Keywords: water and sanitation, emergency response, education and training, building resilience

Procedia PDF Downloads 307

Authors: Christine Böckmann, Julia Rosemann

Abstract:

We present an inversion algorithm that is used in the European Aerosol Lidar Network for the inversion of data collected with multi-wavelength Raman lidar. These instruments measure backscatter coefficients at 355, 532, and 1064 nm, and extinction coefficients at 355 and 532 nm. The algorithm is based on manually controlled inversion of optical data which allows for detailed sensitivity studies and thus provides us with comparably high quality of the derived data products. The algorithm allows us to derive particle effective radius, volume, surface-area concentration with comparably high confidence. The retrieval of the real and imaginary parts of the complex refractive index still is a challenge in view of the accuracy required for these parameters in climate change studies in which light-absorption needs to be known with high accuracy. Single-scattering albedo (SSA) can be computed from the retrieve microphysical parameters and allows us to categorize aerosols into high and low absorbing aerosols. From mathematical point of view the algorithm is based on the concept of using truncated singular value decomposition as regularization method. This method was adapted to work for the retrieval of the particle size distribution function (PSD) and is called hybrid regularization technique since it is using a triple of regularization parameters. The inversion of an ill-posed problem, such as the retrieval of the PSD, is always a challenging task because very small measurement errors will be amplified most often hugely during the solution process unless an appropriate regularization method is used. Even using a regularization method is difficult since appropriate regularization parameters have to be determined. Therefore, in a next stage of our work we decided to use two regularization techniques in parallel for comparison purpose. The second method is an iterative regularization method based on Pade iteration. Here, the number of iteration steps serves as the regularization parameter. We successfully developed a semi-automated software for spherical particles which is able to run even on a parallel processor machine. From a mathematical point of view, it is also very important (as selection criteria for an appropriate regularization method) to investigate the degree of ill-posedness of the problem which we found is a moderate ill-posedness. We computed the optical data from mono-modal logarithmic PSD and investigated particles of spherical shape in our simulations. We considered particle radii as large as 6 nm which does not only cover the size range of particles in the fine-mode fraction of naturally occurring PSD but also covers a part of the coarse-mode fraction of PSD. We considered errors of 15% in the simulation studies. For the SSA, 100% of all cases achieve relative errors below 12%. In more detail, 87% of all cases for 355 nm and 88% of all cases for 532 nm are well below 6%. With respect to the absolute error for non- and weak-absorbing particles with real parts 1.5 and 1.6 in all modes the accuracy limit +/- 0.03 is achieved. In sum, 70% of all cases stay below +/-0.03 which is sufficient for climate change studies.

Keywords: aerosol particles, inverse problem, microphysical particle properties, regularization

Procedia PDF Downloads 343

Authors: A. D. Tayal

Abstract:

The energy industry is undergoing significant disruption. This research outlines that, whilst challenging; this disruption is also an emerging opportunity for electricity utilities. One such opportunity is leveraging the developments in data analytics and machine learning. As the uptake of renewable energy technologies and complimentary control systems increases, electricity grids will likely transform towards dense microgrids with high penetration of renewable generation sources, rich in network and customer data, and linked through intelligent, wireless communications. Data digitisation and analytics have already impacted numerous industries, and its influence on the energy sector is growing, as computational capabilities increase to manage big data, and as machines develop algorithms to solve the energy challenges of the future. The objective of this paper is to address how far the uptake of renewable technologies can go given the constraints of existing grid infrastructure and provides a qualitative assessment of how higher levels of renewable energy penetration can be facilitated by incorporating even broader technological advances in the fields of data analytics and machine learning. Western Australia is used as a contextualised case study, given its abundance and diverse renewable resources (solar, wind, biomass, and wave) and isolated networks, making a high penetration of renewables a feasible target for policy makers over coming decades.

Keywords: data, innovation, renewable, solar

Procedia PDF Downloads 367

Authors: Adinew Gebremeskel Tizazu

Abstract:

The effect of soil-structure interaction on the dynamic response of reinforced concrete buildings of regular and symmetrical geometry are considered in this study. The structures are presumed to be generally embedded in a homogenous soil formation underlain by very stiff material or bedrock. The structure-foundation–soil system is excited at the base by an earthquake ground motion. The superstructure is idealized as a system with lumped masses concentrated at the floor levels, and coupled with the substructure. The substructure system, which comprises of the foundation and soil, is represented, and replaced by springs and dashpots. Frequency-dependent impedances of the foundation system are incorporated in the discrete model in terms of the springs and dashpots coefficients. The excitation applied to the model is field ground motions of actual earthquake records. Modal superposition principle is employed to transform the equations of motion in geometrical coordinates to modal coordinates. However, the modal equations remain coupled with respect to damping terms due to the difference in damping mechanisms of the superstructure and the soil. Hence, proportional damping for the coupled structural system may not be assumed. An iterative approach is adopted and programmed to solve the system of coupled equations of motion in modal coordinates to obtain the displacement responses of the system. Parametric studies for responses of building structures with regular and symmetric plans of different structural properties and heights are made for fixed and flexible base conditions, for different soil conditions encountered in Addis Ababa. The displacement, base shear and base overturning moments are used in the comparison of different types of structures for various foundation embedment depths, site conditions and height of structures. These values are compared against those of fixed base structure. The study shows that the flexible base structures, generally exhibit different responses from those structures with fixed base. Basically, the natural circular frequencies, the base shears and the inter-story displacements for the flexible base are less than those of the fixed base structures. This trend is particularly evident when the flexible soil has large thickness. In contrast, the trend becomes less predictable, when the thickness of the flexible soil decreases. Moreover, in the latter case, the iteration undulates significantly making the prediction difficult. This is attributed to the highly jagged nature of the impedance functions of frequencies for such formations. In this case, it is difficult to conclude whether the conventional fixed-base approach yields conservative design forces, as is the case for soil formations of large thickness.

Keywords: effect of soil structure, dynamic response corroborated, the modal superposition principle, parametric studies

Procedia PDF Downloads 36

Authors: Gautam Kumar Saharia, Sagardeep Talukdar, Riki Dutta, Sudipta Nandy

Abstract:

The physics-informed neural network (PINN) method opens up an approach for numerically solving nonlinear partial differential equations leveraging fast calculating speed and high precession of modern computing systems. We construct the PINN based on a strong universal approximation theorem and apply the initial-boundary value data and residual collocation points to weekly impose initial and boundary conditions to the neural network and choose the optimization algorithms adaptive moment estimation (ADAM) and Limited-memory Broyden-Fletcher-Golfard-Shanno (L-BFGS) algorithm to optimize learnable parameter of the neural network. Next, we improve the PINN with a weighted loss function to obtain both the bright and dark soliton solutions of the Fokas-Lenells equation (FLE). We find the proposed scheme of adjustable weight coefficients into PINN has a better convergence rate and generalizability than the basic PINN algorithm. We believe that the PINN approach to solve the partial differential equation appearing in nonlinear optics would be useful in studying various optical phenomena.

Keywords: deep learning, optical soliton, physics informed neural network, partial differential equation

Procedia PDF Downloads 70

Authors: C. Fernanda da S. Sampaio, M. Gabriela Sadith Perez Paredes, V. Antonio de O. Martins

Abstract:

Today the transport sector is undergoing a revolution, with the rise of Advanced Driver Assistance Systems (ADAS), industry and society itself will undergo a major transformation. However, the technological development of these applications is a challenge that requires new techniques and great machine learning and artificial intelligence. The study proposes to develop a vehicular perception system called Veibra, which consists of two front cameras for day/night viewing and an embedded device capable of working with Yolov2 image processing algorithms with low computational cost. The strategic version for the market is to assist the driver on the road with the detection of day/night objects, such as road signs, pedestrians, and animals that will be viewed through the screen of the phone or tablet through an application. The system has the ability to perform real-time driver detection and recognition to identify muscle movements and pupils to determine if the driver is tired or inattentive, analyzing the student's characteristic change and following the subtle movements of the whole face and issuing alerts through beta waves to ensure the concentration and attention of the driver. The system will also be able to perform tracking and monitoring through GSM (Global System for Mobile Communications) technology and the cameras installed in the vehicle.

Keywords: advanced driver assistance systems, tracking, traffic signal detection, vehicle perception system

Procedia PDF Downloads 155

Authors: Xiang Jianhong, Wang Cong, Wang Linyu

Abstract:

With the rise of medical IoT technologies, Wireless body area networks (WBANs) can collect fetal electrocardiogram (FECG) signals to support telemedicine analysis. The compressed sensing (CS)-based WBANs system can avoid the sampling of a large amount of redundant information and reduce the complexity and computing time of data processing, but the existing algorithms have poor signal compression and reconstruction performance. In this paper, a Joint block multi-orthogonal least squares (JBMOLS) algorithm is proposed. We apply the FECG signal to the Joint block sparse model (JBSM), and a comparative study of sparse transformation and measurement matrices is carried out. A FECG signal compression transmission mode based on Rbio5.5 wavelet, Bernoulli measurement matrix, and JBMOLS algorithm is proposed to improve the compression and reconstruction performance of FECG signal by CS-based WBANs. Experimental results show that the compression ratio (CR) required for accurate reconstruction of this transmission mode is increased by nearly 10%, and the runtime is saved by about 30%.

Keywords: telemedicine, fetal ECG, compressed sensing, joint sparse reconstruction, block sparse signal

Procedia PDF Downloads 129

Authors: Chandra Prayaga, Aaron Wade, Lakshmi Prayaga, Gopi Shankar Mallu

Abstract:

This paper presents the use of machine learning algorithms to predict the success of students in an introductory physics course. Data having 140 rows pertaining to the performance of two batches of students was used. The lack of sufficient data to train robust machine learning models was compensated for by generating synthetic data similar to the real data. CTGAN and CTGAN with Gaussian Copula (Gaussian) were used to generate synthetic data, with the real data as input. To check the similarity between the real data and each synthetic dataset, pair plots were made. The synthetic data was used to train machine learning models using the PyCaret package. For the CTGAN data, the Ada Boost Classifier (ADA) was found to be the ML model with the best fit, whereas the CTGAN with Gaussian Copula yielded Logistic Regression (LR) as the best model. Both models were then tested for accuracy with the real data. ROC-AUC analysis was performed for all the ten classes of the target variable (Grades A, A-, B+, B, B-, C+, C, C-, D, F). The ADA model with CTGAN data showed a mean AUC score of 0.4377, but the LR model with the Gaussian data showed a mean AUC score of 0.6149. ROC-AUC plots were obtained for each Grade value separately. The LR model with Gaussian data showed consistently better AUC scores compared to the ADA model with CTGAN data, except in two cases of the Grade value, C- and A-.

Keywords: machine learning, student success, physics course, grades, synthetic data, CTGAN, gaussian copula CTGAN

Procedia PDF Downloads 44

Authors: Rong-Terng Juang

Abstract:

Autonomous vehicles offer the possibility of significant benefits to social welfare. However, fully automated cars might not be going to happen in the near further. To speed the adoption of the self-driving technologies, many governments worldwide are passing laws requiring data recorders for the testing of autonomous vehicles. Currently, the self-driving vehicle, (e.g., shuttle bus) has to be monitored from a remote control center. When an autonomous vehicle encounters an unexpected driving environment, such as road construction or an obstruction, it should request assistance from a remote operator. Nevertheless, large amounts of data, including images, radar and lidar data, etc., have to be transmitted from the vehicle to the remote center. Therefore, this paper proposes a data compression method of in-vehicle networks for remote monitoring of autonomous vehicles. Firstly, the time-series data are rearranged into a multi-dimensional signal space. Upon the arrival, for controller area networks (CAN), the new data are mapped onto a time-data two-dimensional space associated with the specific CAN identity. Secondly, the data are sampled based on differential sampling. Finally, the whole set of data are encoded using existing algorithms such as Huffman, arithmetic and codebook encoding methods. To evaluate system performance, the proposed method was deployed on an in-house built autonomous vehicle. The testing results show that the amount of data can be reduced as much as 1/7 compared to the raw data.

Keywords: autonomous vehicle, data compression, remote monitoring, controller area networks (CAN), Lidar

Procedia PDF Downloads 164

Authors: S. Valarmathi, P. B. Harathi, R. Sridhar, S. Balasubramanian

Abstract:

Machine learning tools in medical diagnosis is increasing due to the improved effectiveness of classification and recognition systems to help medical experts in diagnosing breast cancer. In this study, ID3 chooses the splitting attribute with the highest gain in information, where gain is defined as the difference between before the split versus after the split. It is applied for age, location, taluk, stage, year, period, martial status, treatment, heredity, sex, and habitat against Very Serious (VS), Very Serious Moderate (VSM), Serious (S) and Not Serious (NS) to calculate the gain of information. The ranked histogram gives the gain of each field for the breast cancer data. The doctors use TNM staging which will decide the risk level of the breast cancer and play an important decision making field in fuzzy logic for perception based measurement. Spatial risk area (taluk) of the breast cancer is calculated. Result clearly states that Coimbatore (North and South) was found to be risk region to the breast cancer than other areas at 20% criteria. Weighted value of taluk was compared with criterion value and integrated with Map Object to visualize the results. ID3 algorithm shows the high breast cancer risk regions in the study area. The study has outlined, discussed and resolved the algorithms, techniques / methods adopted through soft computing methodology like ID3 algorithm for prognostic decision making in the seriousness of the breast cancer.

Keywords: ID3 algorithm, breast cancer, fuzzy logic, MATLAB

Procedia PDF Downloads 519

Authors: Yulong Jia, Xiang Zhang, Ziyuan Wu, Shiji Hu

Abstract:

The calculation of bilinear pairing is the core of the SM9 algorithm, which relies on the underlying prime domain algorithm and the quadratic extension domain algorithm. Among the field algorithms, modular multiplication operation is the most time-consuming part. Therefore, the underlying modular multiplication algorithm is optimized to maximize the operation speed of bilinear pairings. This paper uses a modular multiplication method based on non-least positive (NLP) combined with Karatsuba and schoolbook multiplication to improve the Montgomery algorithm. At the same time, according to the characteristics of multiplication operation in quadratic extension domain, a quadratic extension domain FP2-NLP modular multiplication algorithm for bilinear pairings is proposed, which effectively reduces the operation time of modular multiplication in quadratic extension domain. The subexpanded domain 𝐹ₚ₂ -NLP modular multiplication algorithm effectively reduces the operation time of modular multiplication under the second-expanded domain. The multiplication unit in the quadratic extension domain is implemented using SMIC55nm process, and two different implementation architectures are designed to cope with different application scenarios. Compared with the existing related literature, the output latency of this design can reach a minimum of 15 cycles. The shortest time for calculating the (𝐴𝐵 + 𝐶𝐷)𝑟⁻¹ mod 𝑀 form is 37.5ns, and the comprehensive area-time product (AT) is 11400. The final R-ate pairing algorithm hardware accelerator consumes 2670k equivalent logic gates and 1.8ms computing time in 55nm process.

Keywords: sm9, hardware, NLP, Montgomery

Procedia PDF Downloads 11

Authors: Indri Mahadiraka Rumamby, R. R. Dwinanti Rika Marthanty, Jessica Sjah

Abstract:

Smoothed particle hydrodynamics (SPH) was originally created to simulate nonaxisymmetric phenomena in astrophysics. However, this method still has several shortcomings, namely the high computational cost required to model values with high resolution and problems with boundary conditions. The difficulty of modeling boundary conditions occurs because the SPH method is influenced by particle deficiency due to the integral of the kernel function being truncated by boundary conditions. This research aims to answer if SPH modeling with a focus on boundary layer interactions and continuous flow can produce quantifiably accurate values with low computational cost. This research will combine algorithms and coding in the main program of meandering river, continuous flow algorithm, and solid-fluid algorithm with the aim of obtaining quantitatively accurate results on solid-fluid interactions with the continuous flow on a meandering channel using the SPH method. This study uses the Fortran programming language for modeling the SPH (Smoothed Particle Hydrodynamics) numerical method; the model is conducted in the form of a U-shaped meandering open channel in 3D, where the channel walls are soil particles and uses a continuous flow with a limited number of particles.

Keywords: smoothed particle hydrodynamics, computational fluid dynamics, numerical simulation, fluid mechanics

Procedia PDF Downloads 133

Authors: Balamurali Gunji, B. B. V. L. Deepak, B. B. Biswal, Amrutha Rout, Golak Bihari Mohanta

Abstract:

Robots play an important role in the operations like pick and place, assembly, spot welding and much more in manufacturing industries. Out of those, assembly is a very important process in manufacturing, where 20% of manufacturing cost is wholly occupied by the assembly process. To do the assembly task effectively, Assembly Sequences Planning (ASP) is required. ASP is one of the multi-objective non-deterministic optimization problems, achieving the optimal assembly sequence involves huge search space and highly complex in nature. Many researchers have followed different algorithms to solve ASP problem, which they have several limitations like the local optimal solution, huge search space, and execution time is more, complexity in applying the algorithm, etc. By keeping the above limitations in mind, in this paper, a new automated optimal robotic assembly sequence planning using Artificial Bee Colony (ABC) Algorithm is proposed. In this algorithm, automatic extraction of assembly predicates is done using Computer Aided Design (CAD) interface instead of extracting the assembly predicates manually. Due to this, the time of extraction of assembly predicates to obtain the feasible assembly sequence is reduced. The fitness evaluation of the obtained feasible sequence is carried out using ABC algorithm to generate the optimal assembly sequence. The proposed methodology is applied to different industrial products and compared the results with past literature.

Keywords: assembly sequence planning, CAD, artificial Bee colony algorithm, assembly predicates

Procedia PDF Downloads 237

Authors: Surajit Bhattacharya, Daniel Veltri, Atit A. Patel, Daniel N. Cox

Abstract:

miRNAs have emerged as key post-transcriptional regulators of gene expression, however identification of biologically-relevant target genes for this epigenetic regulatory mechanism remains a significant challenge. To address this knowledge gap, we have developed a novel tool in R, Intra-miR-ExploreR, that facilitates integrated discovery of miRNA targets by incorporating target databases and novel target prediction algorithms, using statistical methods including Pearson and Distance Correlation on microarray data, to arrive at high confidence intragenic miRNA target predictions. We have explored the efficacy of this tool using Drosophila melanogaster as a model organism for bioinformatics analyses and functional validation. A number of putative targets were obtained which were also validated using qRT-PCR analysis. Additional features of the tool include downloadable text files containing GO analysis from DAVID and Pubmed links of literature related to gene sets. Moreover, we are constructing interaction maps of intragenic miRNAs, using both micro array and RNA-seq data, focusing on neural tissues to uncover regulatory codes via which these molecules regulate gene expression to direct cellular development.

Keywords: miRNA, miRNA:mRNA target prediction, statistical methods, miRNA:mRNA interaction network

Procedia PDF Downloads 513

Authors: Milad Yousefi, Moslem Yousefi, Ricarpo Poley, Amer Nordin Darus

Abstract:

Design optimization of heat exchangers is a very complicated task that has been traditionally carried out based on a trial-and-error procedure. To overcome the difficulties of the conventional design approaches especially when a large number of variables, constraints and objectives are involved, a new method based on a well-stablished evolutionary algorithm, particle swarm optimization (PSO), weighted sum approach and a novel constraint handling strategy is presented in this study. Since, the conventional constraint handling strategies are not effective and easy-to-implement in multi-objective algorithms, a novel feasibility-based ranking strategy is introduced which is both extremely user-friendly and effective. A case study from industry has been investigated to illustrate the performance of the presented approach. The results show that the proposed algorithm can find the near pareto-optimal with higher accuracy when it is compared to conventional non-dominated sorting genetic algorithm II (NSGA-II). Moreover, the difficulties of a trial-and-error process for setting the penalty parameters is solved in this algorithm.

Keywords: Heat exchanger, Multi-objective optimization, Particle swarm optimization, NSGA-II Constraints handling.

Procedia PDF Downloads 556

Authors: Zhengkun Yi

Abstract:

Surface texture discrimination using artificial tactile sensors has attracted increasing attentions in the past decade as it can endow technical and robot systems with a key missing ability. However, as a major component of texture, roughness has rarely been explored. This paper presents an approach for tactile surface roughness discrimination, which includes two parts: (1) design and fabrication of a bioinspired artificial fingertip, and (2) tactile signal processing for tactile surface roughness discrimination. The bioinspired fingertip is comprised of two polydimethylsiloxane (PDMS) layers, a polymethyl methacrylate (PMMA) bar, and two perpendicular polyvinylidene difluoride (PVDF) film sensors. This artificial fingertip mimics human fingertips in three aspects: (1) Elastic properties of epidermis and dermis in human skin are replicated by the two PDMS layers with different stiffness, (2) The PMMA bar serves the role analogous to that of a bone, and (3) PVDF film sensors emulate Meissner’s corpuscles in terms of both location and response to the vibratory stimuli. Various extracted features and classification algorithms including support vector machines (SVM) and k-nearest neighbors (kNN) are examined for tactile surface roughness discrimination. Eight standard rough surfaces with roughness values (Ra) of 50 μm, 25 μm, 12.5 μm, 6.3 μm 3.2 μm, 1.6 μm, 0.8 μm, and 0.4 μm are explored. The highest classification accuracy of (82.6 ± 10.8) % can be achieved using solely one PVDF film sensor with kNN (k = 9) classifier and the standard deviation feature.

Keywords: bioinspired fingertip, classifier, feature extraction, roughness discrimination

Procedia PDF Downloads 313

Authors: A. K. M. Kamrul Islam, Abdelhamid Bouchachia, Suang Cang, Hongnian Yu

Abstract:

Forecasting model has a great impact in terms of prediction and continues to do so into the future. Although many forecasting models have been studied in recent years, most researchers focus on different forecasting methods based on fuzzy time series to solve forecasting problems. The forecasted models accuracy fully depends on the two terms that are the length of the interval in the universe of discourse and the content of the forecast rules. Moreover, a hybrid forecasting method can be an effective and efficient way to improve forecasts rather than an individual forecasting model. There are different hybrids forecasting models which combined fuzzy time series with evolutionary algorithms, but the performances are not quite satisfactory. In this paper, we proposed a hybrid forecasting model which deals with the first order as well as high order fuzzy time series and particle swarm optimization to improve the forecasted accuracy. The proposed method used the historical enrollments of the University of Alabama as dataset in the forecasting process. Firstly, we considered an automatic clustering algorithm to calculate the appropriate interval for the historical enrollments. Then particle swarm optimization and fuzzy time series are combined that shows better forecasting accuracy than other existing forecasting models.

Keywords: fuzzy time series (fts), particle swarm optimization, clustering algorithm, hybrid forecasting model

Procedia PDF Downloads 252