Search results for: algorithms

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 120

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 94

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 13

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 127

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 488

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 87

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 208

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 465

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 522

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 271

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 218

Authors: Mohammed Abdullah Alshahrani

Abstract:

This research focuses on the investigation of partial least squares (PLS) methodology to deal with high-dimensional correlated data. Current developments in technology have enabled experiments to produce data that are characterized by, first, the number of variables that far exceeds the number of observations and, second, variables that are substantially correlated between them. These types of data are commonly found in, first, chemometrics, where absorbance levels of chemical samples are recorded across hundreds of wavelengths in a calibration of a near-infrared (NIR) spectrometer. Second, they are also common to be found in genomics where copy number alterations (CNA) are recorded across thousands of genomic regions from cancer patients. In our study, we investigated key areas to address these challenges. Firstly, we tackled the issue of three main PLS algorithms having potentially different interpretations of relevant quantities. We unified these interpretations by identifying scenarios where all three algorithms yield the same estimates. Secondly, we explored the phenomenon of unusual negative shrinkage factors encountered during PLS model fitting. Unlike ridge regression or principal component regression, where shrinkage factors range between zero and one, PLS can exhibit factors greater than one or even negative, hence more aptly termed ‘filter factors’ rather than ‘shrinkage factors’. This characteristic allows PLS to effectively handle high-dimensional data by applying shrinkage to estimates. To our knowledge, there has been no previous meaningful investigation on the negative filter factors (NFF) in PLS. In this research we present a novel result whereby we identify the condition for NFF to happen and investigate characteristics of the data that are associated with NFF to get an insight. Lastly, the main challenge of the application of PLS is in the interpretation of weights associated with the predictors. With hundreds and thousands of predictors, each and every predictor variable has non-zero weight. However, we expect that only some predictor variables are contributing to the association with the outcome variable. We, therefore, resort to the sparse estimation of predictor weights where some weights are zero estimated and the other weights are non-zero. A (standard) lasso estimation has a weakness in dealing with correlated variables as it picks up one variable within a correlation block without knowing the reason. A novel approach is needed to consider the dependencies between predictor variables in estimating the weights. We propose a new method where a new penalty function is introduced in the likelihood function associated with the estimation of weights. The penalty function is a combination of a lasso penalty that imposes sparsity and a penalty based on Cauchy distribution with a smoother matrix to take into account dependencies between genomic regions. The results show that the estimates of the weights are sparse: many weights are zero estimated, and those non-zero estimates are grouped and exhibit smoothness within them. The interpretation of genomic regions becomes easy, and the identification of important regions for each component can be done simultaneously with prediction in a single modeling framework. We investigate the relation between PLS and graphical modeling using the information in the weights to construct the graph with unsuccessful results. High-dimensional data where the number of predictors (p) exceeds the number of observations (n) are widely used in many applications of regression analysis. Ordinary least squares regression (OLS), which is the most well-known method for regression problems, has less performance with high-dimensional and highly- correlated data. Previous studies have shown that there is an association between copy number alterations (CNA) in some key genes and disease phenotypes. Moreover, it is very important in high-dimensional data to classify the samples into groups, such as tumor types, of gene expression data in bioinformatics and biology. However, the standard regression of classification methods will fail in these cases because the predictors matrix is singular and so, cannot be inverted. Hence, regularised methods are needed such as shrinkage methods and dimension reduction methods. One of the most suggested methods in the literature is partial least squares regression (PLS) for linear regression and classification.

Keywords: negative filter factors, partial least square regression, high-dimensional data, biostatistics, bioinformatics

Procedia PDF Downloads 11

Authors: Deepak K. Gupta, T. R. Ravindran

Abstract:

Holographic Optical Tweezers (HOTs) in general use iterative algorithms such as weighted Gerchberg-Saxton (WGS) to generate multiple traps, which produce traps with 99% uniformity theoretically. But in experiments, it is the phase response of the spatial light modulator (SLM) which ultimately determines the efficiency, uniformity, and quality of the trap spots. In general, SLMs show a nonlinear phase response behavior, and they may even have asymmetric phase modulation depth before and after π. This affects the resolution with which the gray levels are addressed before and after π, leading to a degraded trap performance. We present a method to optimize the SLM for a linear phase response behavior along with a symmetric phase modulation depth around π. Further, we optimize the SLM for its varying phase response over different spatial regions by optimizing the brightness/contrast and gamma of the hologram in different subsections. We show the effect of the optimization on an array of trap spots resulting in improved efficiency and uniformity. We also calculate the spot sharpness metric and trap performance metric and show a tightly focused spot with reduced aberration. The trap performance is compared by calculating the trap stiffness of a trapped particle in a given trap spot before and after aberration correction. The trap stiffness is found to improve by 200% after the optimization.

Keywords: spatial light modulator, optical trapping, aberration, phase modulation

Procedia PDF Downloads 138

Authors: Sirus Mohammadi, Rohala Moghimi

Abstract:

The main advantages of microgrids are high energy efficiency through the application of Combined Heat and Power (CHP), high quality and reliability of the delivered electric energy and environmental and economic advantages. This study presents an energy management system (EMS) to optimize the operation of the microgrid (MG). In this paper an Adaptive Modified Firefly Algorithm (AMFA) is presented for optimal operation of a typical MG with renewable energy sources (RESs) accompanied by a back-up Micro-Turbine/Fuel Cell/Battery hybrid power source to level the power mismatch or to store the energy surplus when it’s needed. The problem is formulated as a nonlinear constraint problem to minimize the total operating cost. The management of Energy storage system (ESS), economic load dispatch and operation optimization of distributed generation (DG) are simplified into a single-object optimization problem in the EMS. The proposed algorithm is tested on a typical grid-connected MG including WT/PV/Micro Turbine/Fuel Cell and Energy Storage Devices (ESDs) then its superior performance is compared with those from other evolutionary algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Fuzzy Self Adaptive PSO (FSAPSO), Chaotic Particle PSO (CPSO), Adaptive Modified PSO (AMPSO), and Firefly Algorithm (FA).

Keywords: microgrid, operation management, optimization, firefly algorithm (AMFA)

Procedia PDF Downloads 312

Authors: Dimitrios Ntardas, Alexandros Tzanetos, Georgios Dounias

Abstract:

High Voltage Substations (HVS) are the intermediate step between production of power and successfully transmitting it to clients, making them one of the most important checkpoints in power grids. Nowadays - renewable resources and consequently distributed generation are growing fast, the construction of HVS is of high importance both in terms of quality and time completion so that new energy producers can quickly and safely intergrade in power grids. The resources needed, such as machines and workers, should be carefully allocated so that the construction of a HVS is completed on time, with the lowest possible cost (e.g. not spending additional cost that were not taken into consideration, because of project delays), but in the highest quality. In addition, there are milestones and several checkpoints to be precisely achieved during construction to ensure the cost and timeline control and to ensure that the percentage of governmental funding will be granted. The management of such a demanding project is a NP-hard problem that consists of prerequisite constraints and resource limits for each task of the project. In this work, a hybrid meta-heuristic method is implemented to solve this problem. Meta-heuristics have been proven to be quite useful when dealing with high-dimensional constraint optimization problems. Hybridization of them results in boost of their performance.

Keywords: hybrid meta-heuristic methods, substation construction, resource allocation, time-cost efficiency

Procedia PDF Downloads 114

Authors: Aqsa Ali, Aleem Mushtaq, Attaullah Memon, Monna

Abstract:

In this paper, we present a low cost design for a smart glove that can perform sign language recognition to assist the speech impaired people. Specifically, we have designed and developed an Assistive Hand Gesture Interpreter that recognizes hand movements relevant to the American Sign Language (ASL) and translates them into text for display on a Thin-Film-Transistor Liquid Crystal Display (TFT LCD) screen as well as synthetic speech. Linear Bayes Classifiers and Multilayer Neural Networks have been used to classify 11 feature vectors obtained from the sensors on the glove into one of the 27 ASL alphabets and a predefined gesture for space. Three types of features are used; bending using six bend sensors, orientation in three dimensions using accelerometers and contacts at vital points using contact sensors. To gauge the performance of the presented design, the training database was prepared using five volunteers. The accuracy of the current version on the prepared dataset was found to be up to 99.3% for target user. The solution combines electronics, e-textile technology, sensor technology, embedded system and machine learning techniques to build a low cost wearable glove that is scrupulous, elegant and portable.

Keywords: American sign language, assistive hand gesture interpreter, human-machine interface, machine learning, sensing glove

Procedia PDF Downloads 259

Authors: Abhijeet Ostawal, Parmjit Lall

Abstract:

The run times for a large strategic model that we were managing had become too long leading to delays in project delivery, increased costs and loss in productivity. Software developers are continuously working towards developing more efficient tools by changing their algorithms and processes. The issue faced by our team was how do you apply the latest technologies on validated existing models which are based on much older versions of software that do not have the latest software capabilities. The multi-model transport model that we had could only be run in sequential assignment order. Recent upgrades to the software now allowed the assignment to be run in parallel, a concept called parallelization. Parallelization is a Python script working only within the latest version of the software. A full model transfer to the latest version was not possible due to time, budget and the potential changes in trip assignment. This article is to show the method to adapt and update the Python script in such a way that it can be used in older software versions by calling the latest version and then recalling the old version for assignment model without affecting the results. Through a process of trial-and-error run time savings of up to 30-40% have been achieved. Assignment results were maintained within the older version and through this learning process we’ve applied this methodology to other even older versions of the software resulting in huge time savings, more productivity and efficiency for both client and consultant.

Keywords: model run time, demand model, parallelisation, python scripting

Procedia PDF Downloads 85

Authors: Seyed Esmail Seyedi Bariran, Khairul Salleh Mohamed Sahari

Abstract:

In robotics literature, the simultaneous localization and mapping (SLAM) is commonly associated with a priori-posteriori problem. The autonomous vehicle needs a neutral map to spontaneously track its local position, i.e., “localization” while at the same time a precise path estimation of the environment state is required for effective route planning and obstacle avoidance. On the other hand, the environmental noise factors can significantly intensify the inherent uncertainties in using odometry information and measurements obtained from the robot’s exteroceptive sensor which in return directly affect the overall performance of the corresponding SLAM. Therefore, the current work is primarily dedicated to provide a diagnostic analysis of six SLAM algorithms including FastSLAM, L-SLAM, GraphSLAM, Grid SLAM and DP-SLAM. A SLAM simulated environment consisting of two sets of landmark locations and robot waypoints was set based on modified EKF and UKF in MATLAB using two separate maps for indoor and outdoor route planning subject to natural and artificial obstacles. The simulation results are expected to provide an unbiased platform to compare the estimation performances of the five SLAM models as well as on the reliability of each SLAM model for indoor and outdoor applications.

Keywords: route planning, obstacle, estimation performance, FastSLAM, L-SLAM, GraphSLAM, Grid SLAM, DP-SLAM

Procedia PDF Downloads 405

Authors: Khalid Ali, Manar Jammal

Abstract:

In order to meet the stringent latency and reliability requirements of the upcoming 5G networks, Open Radio Access Networks (O-RAN) have been proposed. The virtualization of O-RAN has allowed it to be treated as a Network Function Virtualization (NFV) architecture, while its components are considered Virtualized Network Functions (VNFs). Hence, intelligent Machine Learning (ML) based solutions can be utilized to apply different resource management and allocation techniques on O-RAN. However, intelligently allocating resources for O-RAN VNFs can prove challenging due to the dynamicity of traffic in mobile networks. Network providers need to dynamically scale the allocated resources in response to the incoming traffic. Elastically allocating resources can provide a higher level of flexibility in the network in addition to reducing the OPerational EXpenditure (OPEX) and increasing the resources utilization. Most of the existing elastic solutions are reactive in nature, despite the fact that proactive approaches are more agile since they scale instances ahead of time by predicting the incoming traffic. In this work, we propose and evaluate traffic forecasting models based on the ML algorithm. The algorithms aim at predicting future O-RAN traffic by using previous traffic data. Detailed analysis of the traffic data was carried out to validate the quality and applicability of the traffic dataset. Hence, two ML models were proposed and evaluated based on their prediction capabilities.

Keywords: O-RAN, traffic forecasting, NFV, ARIMA, LSTM, elasticity

Procedia PDF Downloads 173

Authors: Rujia Chen, Ajit Narayanan

Abstract:

Convolutional neural networks (CNN), as typically applied in deep learning, use layer-wise backpropagation (BP) to construct filters and kernels for feature extraction. Such filters are 2D or 3D groups of weights for constructing feature maps at subsequent layers of the CNN and are shared across the entire input. BP as a gradient descent algorithm has well-known problems of getting stuck at local optima. The use of genetic algorithms (GAs) for evolving weights between layers of standard artificial neural networks (ANNs) is a well-established area of neuroevolution. In particular, the use of crossover techniques when optimizing weights can help to overcome problems of local optima. However, the application of GAs for evolving the weights of filters and kernels in CNNs is not yet an established area of neuroevolution. In this paper, a GA-based filter development algorithm is proposed. The results of the proof-of-concept experiments described in this paper show the proposed GA algorithm can find filter weights through evolutionary techniques rather than BP learning. For some simple classification tasks like geometric shape recognition, the proposed algorithm can achieve 100% accuracy. The results for MNIST classification, while not as good as possible through standard filter learning through BP, show that filter and kernel evolution warrants further investigation as a new subarea of neuroevolution for deep architectures.

Keywords: neuroevolution, convolutional neural network, genetic algorithm, filters, kernels

Procedia PDF Downloads 154

Authors: Abdulbaset Saad, Adel Younis, Zuomin Dong

Abstract:

For design optimization with high-dimensional expensive problems, an effective and efficient optimization methodology is desired. This work proposes a series of modification to the Differential Evolution (DE) algorithm for solving computation Intensive Black-Box Problems. The proposed methodology is called Radial Basis Meta-Model Algorithm Assisted Differential Evolutionary (RBF-DE), which is a global optimization algorithm based on the meta-modeling techniques. A meta-modeling assisted DE is proposed to solve computationally expensive optimization problems. The Radial Basis Function (RBF) model is used as a surrogate model to approximate the expensive objective function, while DE employs a mechanism to dynamically select the best performing combination of parameters such as differential rate, cross over probability, and population size. The proposed algorithm is tested on benchmark functions and real life practical applications and problems. The test results demonstrate that the proposed algorithm is promising and performs well compared to other optimization algorithms. The proposed algorithm is capable of converging to acceptable and good solutions in terms of accuracy, number of evaluations, and time needed to converge.

Keywords: differential evolution, engineering design, expensive computations, meta-modeling, radial basis function, optimization

Procedia PDF Downloads 359

Authors: Aishwarya Ravindra Fursule, Shruti Kshirsagar

Abstract:

In the intersection of artificial intelligence and human-centered computing, this paper delves into speech emotion recognition (SER). It presents a comparative analysis of machine learning models such as K-Nearest Neighbors (KNN),logistic regression, support vector machines (SVM), decision trees, ensemble classifiers, and random forests, applied to SER. The research employs four datasets: Crema D, SAVEE, TESS, and RAVDESS. It focuses on extracting salient audio signal features like Zero Crossing Rate (ZCR), Chroma_stft, Mel Frequency Cepstral Coefficients (MFCC), root mean square (RMS) value, and MelSpectogram. These features are used to train and evaluate the models’ ability to recognize eight types of emotions from speech: happy, sad, neutral, angry, calm, disgust, fear, and surprise. Among the models, the Random Forest algorithm demonstrated superior performance, achieving approximately 79% accuracy. This suggests its suitability for SER within the parameters of this study. The research contributes to SER by showcasing the effectiveness of various machine learning algorithms and feature extraction techniques. The findings hold promise for the development of more precise emotion recognition systems in the future. This abstract provides a succinct overview of the paper’s content, methods, and results.

Keywords: comparison, ML classifiers, KNN, decision tree, SVM, random forest, logistic regression, ensemble classifiers

Procedia PDF Downloads 7

Authors: Najrullah Khan, Athar Ali Khan

Abstract:

The Topp-Leone distribution was introduced by Topp- Leone in 1955. In this paper, an attempt has been made to fit Topp-Leone Generalized exponential (TPGE) distribution. A real survival data set is used for illustrations. Implementation is done using R and JAGS and appropriate illustrations are made. R and JAGS codes have been provided to implement censoring mechanism using both optimization and simulation tools. The main aim of this paper is to describe and illustrate the Bayesian modelling approach to the analysis of survival data. Emphasis is placed on the modeling of data and the interpretation of the results. Crucial to this is an understanding of the nature of the incomplete or 'censored' data encountered. Analytic approximation and simulation tools are covered here, but most of the emphasis is on Markov chain based Monte Carlo method including independent Metropolis algorithm, which is currently the most popular technique. For analytic approximation, among various optimization algorithms and trust region method is found to be the best. In this paper, TPGE model is also used to analyze the lifetime data in Bayesian paradigm. Results are evaluated from the above mentioned real survival data set. The analytic approximation and simulation methods are implemented using some software packages. It is clear from our findings that simulation tools provide better results as compared to those obtained by asymptotic approximation.

Keywords: Bayesian Inference, JAGS, Laplace Approximation, LaplacesDemon, posterior, R Software, simulation

Procedia PDF Downloads 496

Authors: Dennis L. Owuor, Okuthe P. Kogeda, Johnson I. Agbinya

Abstract:

Mobile localization has attracted a great deal of attention recently due to the introduction of wireless networks. Although several localization algorithms and systems have been implemented and discussed in the literature, very few researchers have exploited the gap that exists between indoor localization, tracking, external storage of location information and outdoor localization for the purpose of digital forensics during and after a disaster. The contribution of this paper lies in the implementation of a robust system that is capable of locating, tracking mobile device users and store location information for both indoor and partially outdoor the cloud. The system can be used during disaster to track and locate mobile phone users. The developed system is a mobile application built based on Android, Hypertext Preprocessor (PHP), Cascading Style Sheets (CSS), JavaScript and MATLAB for the Android mobile users. Using Waterfall model of software development, we have implemented a three level system that is able to track, locate and store mobile device information in secure database (cloud) on almost a real time basis. The outcome of the study showed that the developed system is efficient with regard to the tracking and locating mobile devices. The system is also flexible, i.e. can be used in any building with fewer adjustments. Finally, the system is accurate for both indoor and outdoor in terms of locating and tracking mobile devices.

Keywords: indoor localization, digital forensics, fingerprinting, tracking and cloud

Procedia PDF Downloads 297

Authors: Cristian Crespo

Abstract:

Conditional cash transfers (CCTs) have been targeted towards the poor. Thus, their targeting assessments check whether these schemes have been allocated to low-income households or individuals. However, CCTs have more than one goal and target group. An additional goal of CCTs is to increase school enrolment. Hence, students at risk of dropping out of school also are a target group. This paper analyses whether one of the most common targeting mechanisms of CCTs, a proxy means test (PMT), is suitable to identify the poor and future school dropouts. The PMT is compared with alternative approaches that use the outputs of a predictive model of school dropout. This model was built using machine learning algorithms and rich administrative datasets from Chile. The paper shows that using machine learning outputs in conjunction with the PMT increases targeting effectiveness by identifying more students who are either poor or future dropouts. This joint targeting approach increases effectiveness in different scenarios except when the social valuation of the two target groups largely differs. In these cases, the most likely optimal approach is to solely adopt the targeting mechanism designed to find the highly valued group.

Keywords: conditional cash transfers, machine learning, poverty, proxy means tests, school dropout prediction, targeting

Procedia PDF Downloads 170

Authors: Zhangquan Zhou, Guilin Qi

Abstract:

Materialization is an important reasoning service for applications built on the Web Ontology Language (OWL). To make materialization efficient in practice, current research focuses on deciding tractability of an ontology language and designing parallel reasoning algorithms. However, some well-known large-scale ontologies, such as YAGO, have been shown to have good performance for parallel reasoning, but they are expressed in ontology languages that are not parallelly tractable, i.e., the reasoning is inherently sequential in the worst case. This motivates us to study the problem of parallel tractability of ontology materialization from a theoretical perspective. That is we aim to identify the ontologies for which materialization is parallelly tractable, i.e., in the NC complexity. Since the NC complexity is defined based on Boolean circuit that is widely used to investigate parallel computing problems, we first transform the problem of materialization to evaluation of Boolean circuits, and then study the problem of parallel tractability based on circuits. In this work, we focus on datalog rewritable ontology languages. We use Boolean circuits to identify two classes of datalog rewritable ontologies (called parallelly tractable classes) such that materialization over them is parallelly tractable. We further investigate the parallel tractability of materialization of a datalog rewritable OWL fragment DHL (Description Horn Logic). Based on the above results, we analyze real-world datasets and show that many ontologies expressed in DHL belong to the parallelly tractable classes.

Keywords: ontology materialization, parallel reasoning, datalog, Boolean circuit

Procedia PDF Downloads 235

Authors: Rashid Javed, Hardy Lehmkuehler, Franz Josef-Behr

Abstract:

Web Processing Services (WPS) have up growing concern in geoinformation research. However, teaching about them is difficult because of the generally complex circumstances of their use. They limit the possibilities for hands- on- exercises on Web Processing Services. To support understanding however a Training Tools Collection was brought on the way at University of Applied Sciences Stuttgart (HFT). It is limited to the scope of Geostatistical Interpolation of sample point data where different algorithms can be used like IDW, Nearest Neighbor etc. The Tools Collection aims to support understanding of the scope, definition and deployment of Web Processing Services. For example it is necessary to characterize the input of Interpolation by the data set, the parameters for the algorithm and the interpolation results (here a grid of interpolated values is assumed). This paper reports on first experiences using a pilot installation. This was intended to find suitable software interfaces for later full implementations and conclude on potential user interface characteristics. Experiences were made with Deegree software, one of several Services Suites (Collections). Being strictly programmed in Java, Deegree offers several OGC compliant Service Implementations that also promise to be of benefit for the project. The mentioned parameters for a WPS were formalized following the paradigm that any meaningful component will be defined in terms of suitable standards. E.g. the data output can be defined as a GML file. But, the choice of meaningful information pieces and user interactions is not free but partially determined by the selected WPS Processing Suite.

Keywords: deegree, interpolation, IDW, web processing service (WPS)

Procedia PDF Downloads 327

Authors: F. Jiménez, R. Jódar, M. Martín, G. Sánchez, G. Sciavicco

Abstract:

Abstract—Attribute or feature selection is one of the basic strategies to improve the performances of data classification tasks, and, at the same time, to reduce the complexity of classifiers, and it is a particularly fundamental one when the number of attributes is relatively high. Its application to unsupervised classification is restricted to a limited number of experiments in the literature. Evolutionary computation has already proven itself to be a very effective choice to consistently reduce the number of attributes towards a better classification rate and a simpler semantic interpretation of the inferred classifiers. We present a feature selection wrapper model composed by a multi-objective evolutionary algorithm, the clustering method Expectation-Maximization (EM), and the classifier C4.5 for the unsupervised classification of data extracted from a psychological test named BASC-II (Behavior Assessment System for Children - II ed.) with two objectives: Maximizing the likelihood of the clustering model and maximizing the accuracy of the obtained classifier. We present a methodology to integrate feature selection for unsupervised classification, model evaluation, decision making (to choose the most satisfactory model according to a a posteriori process in a multi-objective context), and testing. We compare the performance of the classifier obtained by the multi-objective evolutionary algorithms ENORA and NSGA-II, and the best solution is then validated by the psychologists that collected the data.

Keywords: evolutionary computation, feature selection, classification, clustering

Procedia PDF Downloads 334

Authors: K. Bresilla, L. Manfrini, B. Morandi, A. Boini, G. Perulli, L. C. Grappadelli

Abstract:

Image/video processing for fruit in the tree using hard-coded feature extraction algorithms have shown high accuracy during recent years. While accurate, these approaches even with high-end hardware are computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks (CNNs), specifically an algorithm (YOLO - You Only Look Once) with 24+2 convolution layers. Using deep-learning techniques eliminated the need for hard-code specific features for specific fruit shapes, color and/or other attributes. This CNN is trained on more than 5000 images of apple and pear fruits on 960 cores GPU (Graphical Processing Unit). Testing set showed an accuracy of 90%. After this, trained data were transferred to an embedded device (Raspberry Pi gen.3) with camera for more portability. Based on correlation between number of visible fruits or detected fruits on one frame and the real number of fruits on one tree, a model was created to accommodate this error rate. Speed of processing and detection of the whole platform was higher than 40 frames per second. This speed is fast enough for any grasping/harvesting robotic arm or other real-time applications.

Keywords: artificial intelligence, computer vision, deep learning, fruit recognition, harvesting robot, precision agriculture

Procedia PDF Downloads 380

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed-length window in the past as an explicit input. In this paper, we study how the performance of predictive models changes as a function of different look-back window sizes and different amounts of time to predict the future. We also consider the performance of the recent attention-based Transformer models, which have had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (RNN, LSTM, GRU, and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the UCI website, which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Average Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: air quality prediction, deep learning algorithms, time series forecasting, look-back window

Procedia PDF Downloads 120