Search results for: back propagation algorithm

Authors: Hongbo Zhang, Xinlu Tang, Jiangwei Li, Chi Yan

Abstract:

Home zone parking pilot (HPP) is a fast-growing segment in low-speed autonomous driving applications. It requires the car automatically cruise around a parking lot and park itself in a range of up to 100 meters inside a recurrent home/office parking lot, which requires precise parking lot mapping and localization solution. Although Lidar is ideal for SLAM, the car OEMs favor a low-cost fish-eye camera based visual SLAM approach. Recent approaches have employed segmentation models to extract semantic features and improve mapping accuracy, but these AI models are memory unfriendly and computationally expensive, making deploying on embedded ADAS systems difficult. To address this issue, we proposed a new method that utilizes object detection models to extract robust and accurate parking lot features. The proposed method could reduce computational costs while maintaining high accuracy. Once combined with vehicles’ wheel-pulse information, the system could construct maps and locate the vehicle in real-time. This article will discuss in detail (1) the fish-eye based Around View Monitoring (AVM) with transparent chassis images as the inputs, (2) an Object Detection (OD) based feature point extraction algorithm to generate point cloud, (3) a low computational parking lot mapping algorithm and (4) the real-time localization algorithm. At last, we will demonstrate the experiment results with an embedded ADAS system installed on a real car in the underground parking lot.

Keywords: ADAS, home zone parking pilot, object detection, visual SLAM

Procedia PDF Downloads 67

Authors: Monojit Manna, Arpan Adhikary

Abstract:

In Mobile cloud sensing across the globe, an emerging paradigm is selected by the user to compute sensing tasks. In urban cities current days, Mobile vehicles are adapted to perform the task of data sensing and data collection for universality and mobility. In this work, we focused on the optimality and mobile nodes that can be selected in order to collect the maximum amount of data from urban areas and fulfill the required data in the future period within a couple of minutes. We map out the requirement of the vehicle to configure the maximum data optimization problem and budget. The Application implementation is basically set up to generalize a realistic online platform in which real-time vehicles are moving apparently in a continuous manner. The data center has the authority to select a set of vehicles immediately. A deep learning-based scheme with the help of mobile vehicles (DLMV) will be proposed to collect sensing data from the urban environment. From the future time perspective, this work proposed a deep learning-based offline algorithm to predict mobility. Therefore, we proposed a greedy approach applying an online algorithm step into a subset of vehicles for an NP-complete problem with a limited budget. Real dataset experimental extensive evaluations are conducted for the real mobility dataset in Rome. The result of the experiment not only fulfills the efficiency of our proposed solution but also proves the validity of DLMV and improves the quantity of collecting the sensing data compared with other algorithms.

Keywords: mobile crowdsensing, deep learning, vehicle recruitment, sensing coverage, data collection

Procedia PDF Downloads 77

Authors: U.V. Suryawanshi, S.S. Chowhan, U.V Kulkarni

Abstract:

Accuracy of segmentation methods is of great importance in brain image analysis. Tissue classification in Magnetic Resonance brain images (MRI) is an important issue in the analysis of several brain dementias. This paper portraits performance of segmentation techniques that are used on Brain MRI. A large variety of algorithms for segmentation of Brain MRI has been developed. The objective of this paper is to perform a segmentation process on MR images of the human brain, using Fuzzy c-means (FCM), Kernel based Fuzzy c-means clustering (KFCM), Spatial Fuzzy c-means (SFCM) and Improved Fuzzy c-means (IFCM). The review covers imaging modalities, MRI and methods for noise reduction and segmentation approaches. All methods are applied on MRI brain images which are degraded by salt-pepper noise demonstrate that the IFCM algorithm performs more robust to noise than the standard FCM algorithm. We conclude with a discussion on the trend of future research in brain segmentation and changing norms in IFCM for better results.

Keywords: image segmentation, preprocessing, MRI, FCM, KFCM, SFCM, IFCM

Procedia PDF Downloads 331

Authors: Nino Chomakhashvili, Nino Chikhladze, Nato Pitskhelauri, Maia Bitskhinashvili

Abstract:

The dental practice is associated with occupational health challenges. Ergonomic risks in the workplace can significantly impair a dentist's work capacity and may even result in the premature end of their career. Implementing ergonomic principles in dental practice aims to prevent work-related musculoskeletal disorders. Many studies have been conducted in various countries such as Sweden, Denmark, Germany, Poland, and Australia to examine the prevalence of musculoskeletal disorders among dentists. However, to the best of authors knowledge there have been no studies on the application of ergonomic principles in dental practice in Georgia. This study focused on evaluating the ergonomic conditions of dental practice in Georgia and determining how common musculoskeletal disorders are among them. The survey was conducted using a random sampling method in selected dental clinics. A tailored questionnaire consisting of 40 questions, created using insights from international practices, was utilized for the study. Two hundred ninety-one filled questionnaires were used for the analysis. Most respondents reported that their workplaces adhered to ergonomic standards. However, 53.6% experienced frequent back pain, with 50.9% suffering from neck pain, 47.9% from shoulder pain, and 47.1% from lower back pain. Many noted that pain had caused them to reduce their working hours. Nearly all respondents expressed a desire to enhance their knowledge about ergonomics and the prevention of occupational diseases. They indicated a preference for participating in continuous professional development programs (61.5%), receiving information through leaflets (12.0%), and attending online webinars (26.6%). Integrating ergonomic principles into the dental practice is crucial for preventing work-related musculoskeletal disorders. It is essential to offer continuous professional development programs and provide information to dentists, via leaflets, thematic online or hybrid webinars.

Keywords: dental practice, ergonomic risks, musculoskeletal disorders, occupational health

Procedia PDF Downloads 27

Authors: Amrita Anil Agashe, Sumant Tapas, Ajay Verma Yogesh Sonavane, Sourabh Yeravar

Abstract:

Due to advancement in MEMS technology today wireless sensors network has gained a lot of importance. The wide range of its applications includes environmental and habitat monitoring, object localization, target tracking, security surveillance etc. Wireless sensor networks consist of tiny sensor devices called as motes. The constrained computation power, battery power, storage capacity and communication bandwidth of the tiny motes pose challenging problems in the design and deployment of such systems. In this paper, we propose a ubiquitous framework for Real-Time Tracking, Sensing and Management System using IITH motes. Also, we explain the algorithm that we have developed for location management in wireless sensor networks with the aspect of mobility. Our developed framework and algorithm can be used to detect emergency events and safety threats and provides warning signals to handle the emergency.

Keywords: mobility management, motes, multihop, wireless sensor networks

Procedia PDF Downloads 418

Authors: Xiaofei Hu, Zhiyu Cai, Weian Yao

Abstract:

V-notch problem under dynamic loading condition is considered in this paper. In the time domain, the precise time domain expanding algorithm is employed, in which a self-adaptive technique is carried out to improve computing accuracy. By expanding variables in each time interval, the recursive finite element formulas are derived. In the space domain, a Symplectic Analytical Singular Element (SASE) for V-notch problem is constructed addressing the stress singularity of the notch tip. Combining with the conventional finite elements, the proposed SASE can be used to solve the dynamic stress intensity factors (DSIFs) in a simple way. Numerical results show that the proposed SASE for V-notch problem subjected to dynamic loading condition is effective and efficient.

Keywords: V-notch, dynamic stress intensity factor, finite element method, precise time domain expanding algorithm

Procedia PDF Downloads 172

Authors: Wajih Abbassi, Zouhaier Ben Khelifa

Abstract:

The present research points towards the empirical validation of three options valuation models, the ad-hoc Black-Scholes model as proposed by Berkowitz (2001), the constant elasticity of variance model of Cox and Ross (1976) and the Kou jump-diffusion model (2002). Our empirical analysis has been conducted on a sample of 26,974 options written on three indexes, the S&P 500, Nasdaq 100 and the Russell 2000 that were negotiated during the year 2007 just before the sub-prime crisis. We start by presenting the theoretical foundations of the models of interest. Then we use the technique of trust-region-reflective algorithm to estimate the structural parameters of these models from cross-section of option prices. The empirical analysis shows the superiority of the Kou jump-diffusion model. This superiority arises from the ability of this model to portray the behavior of market participants and to be closest to the true distribution that characterizes the evolution of these indices. Indeed the double-exponential distribution covers three interesting properties that are: the leptokurtic feature, the memory less property and the psychological aspect of market participants. Numerous empirical studies have shown that markets tend to have both overreaction and under reaction over good and bad news respectively. Despite of these advantages there are not many empirical studies based on this model partly because probability distribution and option valuation formula are rather complicated. This paper is the first to have used the technique of nonlinear curve-fitting through the trust-region-reflective algorithm and cross-section options to estimate the structural parameters of the Kou jump-diffusion model.

Keywords: jump-diffusion process, Kou model, Leptokurtic feature, trust-region-reflective algorithm, US index options

Procedia PDF Downloads 429

Authors: Efrain Rodriguez, Sergio Pertuz, Cristhian Riano

Abstract:

Tool-path generation is an essential step in the FFF (Fused Filament Fabrication)-based Additive Manufacturing (AM) process planning. In the manufacture of a mechanical part by using additive processes, high resource consumption and prolonged production times are inherent drawbacks of these processes mainly due to non-optimized tool-path generation. In this work, we propose a heuristic-search intelligent algorithm-based approach for optimized tool-path generation for FFF-based AM. The main benefit of this approach is a significant reduction of travels without material deposition when the AM machine performs moves without any extrusion. The optimization method used reduces the number of travels without extrusion in comparison with commercial software as Slic3r or Cura Engine, which means a reduction of production time.

Keywords: additive manufacturing, tool-path optimization, fused filament fabrication, process planning

Procedia PDF Downloads 443

Authors: V. Tabrizi, A. Vali, R. GHasemi, V. Behnamgol

Abstract:

In this article, a nonlinear model of an under actuated six degrees of freedom (6 DOF) quadrotor UAV is derived on the basis of the Newton-Euler formula. The derivation comprises determining equations of the motion of the quadrotor in three dimensions and approximating the actuation forces through the modeling of aerodynamic coefficients and electric motor dynamics. The robust nonlinear control strategy includes a smooth second order non-singular terminal sliding mode control which is applied to stabilizing this model. The control method is on the basis of super twisting algorithm for removing the chattering and producing smooth control signal. Also, nonsingular terminal sliding mode idea is used for introducing a nonlinear sliding variable that guarantees the finite time convergence in sliding phase. Simulation results show that the proposed algorithm is robust against uncertainty or disturbance and guarantees a fast and precise control signal.

Keywords: quadrotor UAV, nonsingular terminal sliding mode, second order sliding mode t, electronics, control, signal processing

Procedia PDF Downloads 440

Authors: Sanaz Kavianpour, Zuraini Ismail, Bharanidharan Shanmugam

Abstract:

Social Network Sites (SNSs) can be served as an invaluable platform to transfer the information across a large number of individuals. A substantial component of communicating and managing information is to identify which individual will influence others in propagating information and also whether dissemination of information in the absence of social signals about that information will be occurred or not. Classifying the final audience of social data is difficult as controlling the social contexts which transfers among individuals are not completely possible. Hence, undesirable information diffusion to an unauthorized individual on SNSs can threaten individuals’ privacy. This paper highlights the information diffusion in SNSs and moreover it emphasizes the most significant privacy issues to individuals of SNSs. The goal of this paper is to propose a privacy-preserving model that has urgent regards with individuals’ data in order to control availability of data and improve privacy by providing access to the data for an appropriate third parties without compromising the advantages of information sharing through SNSs.

Keywords: anonymization algorithm, classification algorithm, information diffusion, privacy, social network sites

Procedia PDF Downloads 321

Authors: Nizar Tayem, AbuMuhammad Moinuddeen, Ahmed A. Hussain, Redha M. Radaydeh

Abstract:

This research paper introduces an approach for estimating the direction of arrival (DOA) of multiple RF noncoherent sources in a uniform linear array (ULA). The proposed method utilizes a Capon-like estimation algorithm and incorporates LU decomposition to enhance the accuracy of DOA estimation while significantly reducing computational complexity compared to existing methods like the Capon method. Notably, the proposed method does not require prior knowledge of the number of sources. To validate its effectiveness, the proposed method undergoes validation through both software simulations and practical experimentation on a prototype testbed constructed using a software-defined radio (SDR) platform and GNU Radio software. The results obtained from MATLAB simulations and real-time experiments provide compelling evidence of the proposed method's efficacy.

Keywords: DOA estimation, real-time validation, software defined radio, computational complexity, Capon's method, GNU radio

Procedia PDF Downloads 75

Authors: Soumyajit Koley, Kuladeep Rajamudili, Supriyo Ganguly

Abstract:

In recent years, iron-based shape-memory alloys have been emerging as an inexpensive alternative to costly Ni-Ti alloy and thus considered suitable for many different applications in civil structures. Fe-17Mn-10Cr-5Si-4Ni-0.5V-0.5C alloy contains 37 wt.% of total solute elements. Such complex multi-component metallurgical system often leads to severe solute segregation and solidification cracking. Wire-arc additive manufacturing (WAAM) of Fe-17Mn-10Cr-5Si-4Ni-0.5V-0.5C alloy was attempted using a cold-wire fed plasma arc torch attached to a 6-axis robot. Self-standing walls were manufactured. However, multiple vertical cracks were observed after deposition of around 15 layers. Microstructural characterization revealed open surfaces of dendrites inside the crack, confirming these cracks as solidification cracks. Machine hammer peening (MHP) process was adopted on each layer to cold work the newly deposited alloy. Effect of MHP traverse speed were varied systematically to attain a window of operation where cracking was completely stopped. Microstructural and textural analysis were carried out further to correlate the peening process to microstructure.MHP helped in many ways. Firstly, a compressive residual stress was induced on each layer which countered the tensile residual stress evolved from solidification process; thus, reducing net tensile stress on the wall along its length. Secondly, significant local plastic deformation from MHP followed by the thermal cycle induced by deposition of next layer resulted into a recovered and recrystallized equiaxed microstructure instead of long columnar grains along the vertical direction. This microstructural change increased the total crack propagation length and thus, the overall toughness. Thirdly, the inter-layer peening significantly reduced the strong cubic {001} crystallographic texture formed along the build direction. Cubic {001} texture promotes easy separation of planes and easy crack propagation. Thus reduction of cubic texture alleviates the chance of cracking.

Keywords: Iron-based shape-memory alloy, wire-arc additive manufacturing, solidification cracking, inter-layer cold working, machine hammer peening

Procedia PDF Downloads 72

Authors: Yosep Chong, Yejin Kim, Jingyun Choi, Hwanjo Yu, Eun Jung Lee, Chang Suk Kang

Abstract:

For the past decades, immunohistochemistry (IHC) has been playing an important role in the diagnosis of human neoplasms, by helping pathologists to make a clearer decision on differential diagnosis, subtyping, personalized treatment plan, and finally prognosis prediction. However, the IHC performed in various tumors of daily practice often shows conflicting and very challenging results to interpret. Even comprehensive diagnosis synthesizing clinical, histologic and immunohistochemical findings can be helpless in some twisted cases. Another important issue is that the IHC data is increasing exponentially and more and more information have to be taken into account. For this reason, we reached an idea to develop an expert supporting system to help pathologists to make a better decision in diagnosing human neoplasms with IHC results. We gave probabilistic decision tree algorithm and tested the algorithm with real case data of lymphoid neoplasms, in which the IHC profile is more important to make a proper diagnosis than other human neoplasms. We designed probabilistic decision tree based on Bayesian theorem, program computational process using MATLAB (The MathWorks, Inc., USA) and prepared IHC profile database (about 104 disease category and 88 IHC antibodies) based on WHO classification by reviewing the literature. The initial probability of each neoplasm was set with the epidemiologic data of lymphoid neoplasm in Korea. With the IHC results of 131 patients sequentially selected, top three presumptive diagnoses for each case were made and compared with the original diagnoses. After the review of the data, 124 out of 131 were used for final analysis. As a result, the presumptive diagnoses were concordant with the original diagnoses in 118 cases (93.7%). The major reason of discordant cases was that the similarity of the IHC profile between two or three different neoplasms. The expert supporting system algorithm presented in this study is in its elementary stage and need more optimization using more advanced technology such as deep-learning with data of real cases, especially in differentiating T-cell lymphomas. Although it needs more refinement, it may be used to aid pathological decision making in future. A further application to determine IHC antibodies for a certain subset of differential diagnoses might be possible in near future.

Keywords: database, expert supporting system, immunohistochemistry, probabilistic decision tree

Procedia PDF Downloads 224

Authors: Zaki Ahmad Khan, Jamshed Siddiqui, Abdus Samad

Abstract:

The Scheduling and mapping of tasks on a set of processors is considered as a critical problem in parallel and distributed computing system. This paper deals with the problem of dynamic scheduling on a special type of multiprocessor architecture known as Linear Crossed Cube (LCQ) network. This proposed multiprocessor is a hybrid network which combines the features of both linear type of architectures as well as cube based architectures. Two standard dynamic scheduling schemes namely Minimum Distance Scheduling (MDS) and Two Round Scheduling (TRS) schemes are implemented on the LCQ network. Parallel tasks are mapped and the imbalance of load is evaluated on different set of processors in LCQ network. The simulations results are evaluated and effort is made by means of through analysis of the results to obtain the best solution for the given network in term of load imbalance left and execution time. The other performance matrices like speedup and efficiency are also evaluated with the given dynamic algorithms.

Keywords: dynamic algorithm, load imbalance, mapping, task scheduling

Procedia PDF Downloads 450

Authors: A. Elsariti, T. Evans

Abstract:

The propagation mechanisms in the trabecular bone are poorly understood and have been the subject of extended debate; also, steel wool has been evaluated as a potential bone mimic, Its advantages are ready availability, low cost and a wide range of sizes. In this study, both distilled and tap water were used to estimate the ultrasonic attenuation in coarse steel wool. It is clear from the results that the attenuation of coarse steel wool increased as the distance between the transducers decreased, and it is higher in tap water than distilled water. At 9cm distance between the transducers the attenuation was approximately 0.97 and 4.7 dB in distilled and tap water respectively. While it is 6.97 and 12.2 dB in distilled and tap water respectively at distance 4cm. This change in the attenuation between both distilled and tap water is probably due to gas bubbles in the tap water.

Keywords: bone mimic, porosity, tap water, distilled water, ultrasonic attenuation

Procedia PDF Downloads 528

Authors: Mohammadhadi Mirmohammadi, Reza Safian, Hossein Haddad

Abstract:

This paper presents an innovative solution for complex multi-objective optimization problem which is a part of efforts toward maximizing rolling mill throughput and minimizing processing costs in tandem cold rolling. This computational intelligence based optimization has been applied to the rolling schedules of tandem cold rolling mill. This method involves the combination of two derivative-free optimization procedures in the form of nested loops. The first optimization loop is based on Improving Hit and Run method which focus on balance of power, force and reduction distribution in rolling schedules. The second loop is a real-coded genetic algorithm based optimization procedure which optimizes energy consumption and productivity. An experimental result of application to five stand tandem cold rolling mill is presented.

Keywords: derivative-free optimization, Improving Hit and Run method, real-coded genetic algorithm, rolling schedules of tandem cold rolling mill

Procedia PDF Downloads 696

Authors: Teja Sai Puligadda

Abstract:

Satellite images in detail can serve an important role in the geographic study. Quantitative and qualitative information provided by the satellite and remote sensing images minimizes the complexity of work and time. Data/images are captured at regular intervals by satellite remote sensing systems, and the amount of data collected is often enormous, and it expands rapidly as technology develops. Interpreting remote sensing images, geographic data mining, and researching distinct vegetation types such as agricultural and forests are all part of satellite image categorization. One of the biggest challenge data scientists faces while classifying satellite images is finding the best suitable classification algorithms based on the available that could able to classify images with utmost accuracy. In order to categorize satellite images, which is difficult due to the sheer volume of data, many academics are turning to deep learning machine algorithms. As, the CNN algorithm gives high accuracy in image recognition problems and automatically detects the important features without any human supervision and the ANN algorithm stores information on the entire network (Abhishek Gupta., 2020), these two deep learning algorithms have been used for satellite image classification. This project focuses on remote sensing through Deep Neural Networks i.e., ANN and CNN with Deep Sat (SAT-4) Airborne dataset for classifying images. Thus, in this project of classifying satellite images, the algorithms ANN and CNN are implemented, evaluated & compared and the performance is analyzed through evaluation metrics such as Accuracy and Loss. Additionally, the Neural Network algorithm which gives the lowest bias and lowest variance in solving multi-class satellite image classification is analyzed.

Keywords: artificial neural network, convolutional neural network, remote sensing, accuracy, loss

Procedia PDF Downloads 159

Authors: Shengyong Zhang, Mike Mikulich

Abstract:

Vibration is a crucial limiting consideration in the analysis and design of airplane wing structures to avoid disastrous failures due to the propagation of existing cracks in the material. In this paper, we build CAD models of aircraft wings to capture the design intent with configurations. Subsequent FEA vibration analysis is performed to study the natural vibration properties and impulsive responses of the resulting user-defined wing models. This study reveals the variations of the wing’s vibration characteristics with respect to changes in its structural configurations. Integrating CAD modelling and FEA vibration analysis enables designers to improve wing architectures for implementing design requirements in the preliminary design stage.

Keywords: aircraft wing, CAD modelling, FEA, vibration analysis

Procedia PDF Downloads 165

Authors: A. Bere, H. G. Sithuba, K. Kyei, C. Sigauke

Abstract:

We employ a discrete logit survival model to investigate the risk factors for early alcohol intake among students at two tertiary institutions in Thohoyandou, South Africa. Data were collected from a sample of 744 students using a self-administered questionnaire. Significant covariates were arrived at through a regularization algorithm implemented using the glmmLasso package. The tuning parameter was determined using a five-fold cross-validation algorithm. The baseline hazard was modelled as a smooth function of time through the use of spline functions. The results show that the hazard of initial alcohol intake peaks at the age of about 16 years and that at any given time, being of a male gender, prior use of other drugs, having drinking peers, having experienced negative life events and physical abuse are associated with a higher risk of alcohol intake debut.

Keywords: cross-validation, discrete hazard model, LASSO, smooth baseline hazard

Procedia PDF Downloads 192

Authors: J. K. Kavitha, D. Manjula, U. Kanimozhi

Abstract:

Mining frequent and high utility item sets have gained much significance in the recent years. When the data arrives sporadically, incremental and interactive rule mining and utility mining approaches can be adopted to handle user’s dynamic environmental needs and avoid redundancies, using previous data structures, and mining results. The dependence on recommendation systems has exponentially risen since the advent of search engines. This paper proposes a model for building a recommendation system that suggests frequent and high utility item sets over dynamic datasets for a cluster based location prediction strategy to predict user’s trajectories using the Efficient Incremental Rule Mining (EIRM) algorithm and the Fast Update Utility Pattern Tree (FUUP) algorithm. Through comprehensive evaluations by experiments, this scheme has shown to deliver excellent performance.

Keywords: data sets, recommendation system, utility item sets, frequent item sets mining

Procedia PDF Downloads 293

Authors: Emad Askar, Eldesoky Elsoaly, Mohamed Kamel, Hisham Kamel

Abstract:

The objective of this article is to improve the passive vibration damping of solar array (SA) used in space structures, by the effective application of numerical optimization. A case study of a SA is used for demonstration. A finite element (FE) model was created and verified by experimental testing. Optimization was then conducted by implementing the FE model with the genetic algorithm, to find the optimal placement of aluminum circular patches, to suppress the first two bending mode shapes. The results were verified using experimental testing. Finally, a parametric study was conducted using the FE model where patch locations, material type, and shape were varied one at a time, and the results were compared with the optimal ones. The results clearly show that through the proper application of FE modeling and numerical optimization, passive vibration damping of space structures has been successfully achieved.

Keywords: damping optimization, genetic algorithm optimization, passive vibration damping, solar array vibration damping

Procedia PDF Downloads 450

Authors: Salah Al-Din I. Badran, Samad Ahmadi, Ismail Shahin

Abstract:

A blind source separation method is proposed; in this method we use a non-uniform filter bank and a novel normalisation. This method provides a reduced computational complexity and increased convergence speed comparing to the full-band algorithm. Recently, adaptive sub-band scheme has been recommended to solve two problems: reduction of computational complexity and increase the convergence speed of the adaptive algorithm for correlated input signals. In this work the reduction in computational complexity is achieved with the use of adaptive filters of orders less than the full-band adaptive filters, which operate at a sampling rate lower than the sampling rate of the input signal. The decomposed signals by analysis bank filter are less correlated in each sub-band than the input signal at full bandwidth, and can promote better rates of convergence.

Keywords: blind source separation, computational complexity, subband, convergence speed, mixture

Procedia PDF Downloads 555

Authors: Bello Yusuf Idi

Abstract:

The Gongola arm of the Upper Banue Trough, Northeastern Nigeria is predominantly covered by the outcrops of Limestone-bearing rocks in form of Sandstone with intercalation of carbonate clay, shale, basaltic, felsphatic and migmatide rocks at subpixel dimension. In this work, subpixel classification algorithm was used to classify the data acquired from landsat 7 Enhance Thematic Mapper (ETM+) satellite system with the aim of producing fractional distribution image for three most economically important solid minerals of the area: Limestone, Basalt and Migmatide. Linear Spectral Unmixing (LSU) algorithm was used to produce fractional distribution image of abundance of the three mineral resources within a 100Km2 portion of the area. The results show that the minerals occur at different proportion all over the area. The fractional map could therefore serve as a guide to the ongoing reconnaissance for the economic potentiality of the formation.

Keywords: linear spectral un-mixing, upper benue trough, gongola arm, geological engineering

Procedia PDF Downloads 374

Authors: Gong Zhilin, Jing Yang, Jian Yin

Abstract:

The purpose of this paper is to develop a novel system for credit card fraud detection based on sequential modeling of data using hybrid deep learning models. The projected model encapsulates five major phases are pre-processing, imbalance-data handling, feature extraction, optimal feature selection, and fraud detection with an ensemble classifier. The collected raw data (input) is pre-processed to enhance the quality of the data through alleviation of the missing data, noisy data as well as null values. The pre-processed data are class imbalanced in nature, and therefore they are handled effectively with the K-means clustering-based SMOTE model. From the balanced class data, the most relevant features like improved Principal Component Analysis (PCA), statistical features (mean, median, standard deviation) and higher-order statistical features (skewness and kurtosis). Among the extracted features, the most optimal features are selected with the Self-improved Arithmetic Optimization Algorithm (SI-AOA). This SI-AOA model is the conceptual improvement of the standard Arithmetic Optimization Algorithm. The deep learning models like Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and optimized Quantum Deep Neural Network (QDNN). The LSTM and CNN are trained with the extracted optimal features. The outcomes from LSTM and CNN will enter as input to optimized QDNN that provides the final detection outcome. Since the QDNN is the ultimate detector, its weight function is fine-tuned with the Self-improved Arithmetic Optimization Algorithm (SI-AOA).

Keywords: credit card, data mining, fraud detection, money transactions

Procedia PDF Downloads 131

Authors: Rodrigo S. Fonseca, Antônio C. P. Veiga

Abstract:

Aiming at helping people with some movement limitation that makes typing and communication difficult, there is a need to customize an assistive tool with a learning environment that helps the user in order to optimize text input, identifying the error and providing the correction and possibilities of choice in the Portuguese language. The work presents an Orthographic and Grammatical System that can be incorporated into writing environments, improving and facilitating the use of an alphanumeric keyboard, using a prototype built using a genetic algorithm in addition to carrying out the prediction, which can occur based on the quantity and position of the inserted letters and even placement in the sentence, ensuring the sequence of ideas using a Long Short Term Memory (LSTM) neural network. The prototype optimizes data entry, being a component of assistive technology for the textual formulation, detecting errors, seeking solutions and informing the user of accurate predictions quickly and effectively through machine learning.

Keywords: genetic algorithm, neural networks, word prediction, machine learning

Procedia PDF Downloads 194

Authors: Mahdi Daghmhehci Firoozjaei, Minchang Kim, Dima Alhadidi

Abstract:

In this paper, we present a power profiling model for smart grid consumers based on real time load data acquired smart meters. It profiles consumers’ power consumption behaviour using the dynamic time warping (DTW) clustering algorithm. Due to the invariability of signal warping of this algorithm, time-disordered load data can be profiled and consumption features be extracted. Two load types are defined and the related load patterns are extracted for classifying consumption behaviour by DTW. The classification methodology is discussed in detail. To evaluate the performance of the method, we analyze the time-series load data measured by a smart meter in a real case. The results verify the effectiveness of the proposed profiling method with 90.91% true positive rate for load type clustering in the best case.

Keywords: power profiling, user privacy, dynamic time warping, smart grid

Procedia PDF Downloads 148

Authors: Thanh Nguyen, Andrei Doncescu, Pierre Siegel

Abstract:

Classification is an important data mining technique and could be used as data filtering in artificial intelligence. The broad application of classification for all kind of data leads to be used in nearly every field of our modern life. Classification helps us to put together different items according to the feature items decided as interesting and useful. In this paper, we compare two classification methods Naïve Bayes and ADTree use to detect spam e-mail. This choice is motivated by the fact that Naive Bayes algorithm is based on probability calculus while ADTree algorithm is based on decision tree. The parameter settings of the above classifiers use the maximization of true positive rate and minimization of false positive rate. The experiment results present classification accuracy and cost analysis in view of optimal classifier choice for Spam Detection. It is point out the number of attributes to obtain a tradeoff between number of them and the classification accuracy.

Keywords: classification, data mining, spam filtering, naive bayes, decision tree

Procedia PDF Downloads 411

Authors: Jocelyn Li, Xiangyang Li

Abstract:

We have employed THINC-it® to study the acute effects of Spravato on the cognitive function of patients with severe major depression disorder (MDD). The scores of the four tasks (Spotter, Symbol Check, Code Breaker, Trails) found in THINC-it® were used to measure cognitive function throughout treatment. The patients who participated in this study have tried more than 3 antidepressants without significant improvement before they began Spravato treatment. All patients received 3 doses of 28 mg Spravato 5 minutes apart (84 mg total per treatment) during this study with THINC-it®. The data were collected before the first Spravato administration (T0), 1 hour after the first Spravato administration (T1), and 2 hours after the first Spravato administration (T2) during each treatment. The following data were from 13 patients, with a total of 226 trials in a 2-3 month period. Spravato at 84 mg reduced the scores of Trails, Code Breaker, Symbol Check, and Spotter at T1 by 10-20% in all patients with one exception for a minority of patients in Spotter. At T2, the scores of Trails, Symbol Check, and Spotter were back to 97% of T0 while the score of Code Breaker was back to 92%. Interestingly, we found that the score of Spotter was consistently increased by 17% at T1 in the same 30% of patients in each treatment. We called this change reverse response while the pattern of the other patients, a decline (T1) and then recovery (T2), was called non-reverse response. We also compared the scores at T0 between the first visit and the fifth visit. The T0 scores of all four tasks were improved at visit 5 when compared to visit 1. The scores of Trails, Code Breaker, and Symbol Check at T0 were increased by 14%, 33%, and 14% respectively at visit 5. The score of Code Breaker, which had two trends, improved by 9% in reverse response patients compared to a 27% improvement in non-reverse response patients. To our knowledge, this is the first study done on the impact of Spravato on cognitive function change in major depression patients at this time frame. Whether we can predict future responses to Spravato with THINC-it® merits further study.

Keywords: Spravato, THINC-it, major depressive disorder, cognitive function

Procedia PDF Downloads 116

Authors: Sara Rejeb, Catherine Duveau, Tabea Rebafka

Abstract:

To monitor the production process of turbofan aircraft engines, multiple measurements of various geometrical parameters are systematically recorded on manufactured parts. Engine parts are subject to extremely high standards as they can impact the performance of the engine. Therefore, it is essential to analyze these databases to better understand the influence of the different parameters on the engine's performance. Self-organizing maps are unsupervised neural networks which achieve two tasks simultaneously: they visualize high-dimensional data by projection onto a 2-dimensional map and provide clustering of the data. This technique has become very popular for data exploration since it provides easily interpretable results and a meaningful global view of the data. As such, self-organizing maps are usually applied to aircraft engine condition monitoring. As databases in this field are huge and complex, they naturally contain multiple missing entries for various reasons. The classical Kohonen algorithm to compute self-organizing maps is conceived for complete data only. A naive approach to deal with partially observed data consists in deleting items or variables with missing entries. However, this requires a sufficient number of complete individuals to be fairly representative of the population; otherwise, deletion leads to a considerable loss of information. Moreover, deletion can also induce bias in the analysis results. Alternatively, one can first apply a common imputation method to create a complete dataset and then apply the Kohonen algorithm. However, the choice of the imputation method may have a strong impact on the resulting self-organizing map. Our approach is to address simultaneously the two problems of computing a self-organizing map and imputing missing values, as these tasks are not independent. In this work, we propose an extension of self-organizing maps for partially observed data, referred to as missSOM. First, we introduce a criterion to be optimized, that aims at defining simultaneously the best self-organizing map and the best imputations for the missing entries. As such, missSOM is also an imputation method for missing values. To minimize the criterion, we propose an iterative algorithm that alternates the learning of a self-organizing map and the imputation of missing values. Moreover, we develop an accelerated version of the algorithm by entwining the iterations of the Kohonen algorithm with the updates of the imputed values. This method is efficiently implemented in R and will soon be released on CRAN. Compared to the standard Kohonen algorithm, it does not come with any additional cost in terms of computing time. Numerical experiments illustrate that missSOM performs well in terms of both clustering and imputation compared to the state of the art. In particular, it turns out that missSOM is robust to the missingness mechanism, which is in contrast to many imputation methods that are appropriate for only a single mechanism. This is an important property of missSOM as, in practice, the missingness mechanism is often unknown. An application to measurements on one type of part is also provided and shows the practical interest of missSOM.

Keywords: imputation method of missing data, partially observed data, robustness to missingness mechanism, self-organizing maps

Procedia PDF Downloads 151

Authors: Rung-Shiang Cheng, Wei-Jun Hong, Jheng-Syun Wang, Kawuu W. Lin

Abstract:

Users rely increasingly on Location-Based Services (LBS) and automated navigation/guidance systems nowadays. However, while such services are easily implemented in outdoor environments using Global Positioning System (GPS) technology, a requirement still exists for accurate localization and guidance schemes in indoor settings. Accordingly, the present study presents a methodology based on GPS, Bluetooth Low Energy (BLE) beacons, and Near Field Communication (NFC) technology. Through establishing graphic information and the design of algorithm, this study develops a guidance system for indoor and outdoor on smartphones, with aim to provide users a smart life through this system. The presented system is implemented on a smartphone and evaluated on a student campus environment. The experimental results confirm the ability of the presented app to switch automatically from an outdoor mode to an indoor mode and to guide the user to the requested target destination via the shortest possible route.

Keywords: beacon, indoor, BLE, Dijkstra algorithm

Procedia PDF Downloads 302