Search results for: vehicle classification

Authors: Jens Hagman, Jenny Janhager Stier, Ellen Olausson, Anne Y. Faxer, Ana Magazinius

Abstract:

Sweden has the second highest electric vehicle (plug-in hybrid and battery electric vehicle) sales per capita in Europe but in relation to sales of internal combustion engine electric vehicles sales are still minuscular (< 4%). Much research effort has been placed on various technical and user focused barriers and enablers for adoption of electric vehicles. Less effort has been placed on investigating the retail (dealership-customer) sales process of vehicles in general and electric vehicles in particular. Arguably, no one ought to be better informed about needs and desires of potential electric vehicle buyers than car salesmen, originating from their daily encounters with customers at the dealership. The aim of this paper is to explore the conditions of selling electric vehicle from a car salesmen’s perspective. This includes identifying barriers and enablers for electric vehicle sales originating from internal (dealership and brand) and external (customer, government) sources. In this interview study five car brands (manufacturers) that sell both electric and internal combustion engine vehicles have been investigated. A total of 15 semi-structured interviews have been conducted (three per brand, in rural and urban settings and at different dealerships). Initial analysis reveals several barriers and enablers, experienced by car salesmen, which influence electric vehicle sales. Examples of as reported by car salesmen identified barriers are: -Electric vehicles earn car salesmen less commission on average compared to internal combustion engine vehicles. -It takes more time to sell and deliver an electric vehicle than an internal combustion engine vehicle. -Current leasing contracts entails relatively low second-hand value estimations for electric vehicles and thus a high leasing fee, which negatively affects the attractiveness of electric vehicles for private consumers in particular. -High purchasing price discourages many consumers from considering electric vehicles. -The education and knowledge level of electric vehicles differs between car salesmen, which could affect their self-confidence in meeting well prepared and question prone electric vehicle buyers. Examples of identified enablers are: -Company car tax regulation promotes sales of electric vehicles; in particular, plug-in hybrid electric vehicles are sold extensively to companies (up to 95 % of sales). -Low operating cost of electric vehicles such as fuel and service is an advantage when understood by consumers. -The drive performance of electric vehicles (quick, silent and fun to drive) is attractive to consumers. -Environmental aspects are considered important for certain consumer groups. -Fast technological improvements, such as increased range are opening up a wider market for electric vehicles. -For one of the brands; attractive private lease campaigns have proved effective to promote sales. This paper gives insights of an important but often overlooked aspect for the diffusion of electric vehicles (and durable products in general); the interaction between car salesmen and customers at the critical acquiring moment. Extracted through interviews with multiple car salesmen. The results illuminate untapped potential for sellers (salesmen, dealerships and brands) to mitigating sales barriers and strengthening sales enablers and thus becoming a more important actor in the electric vehicle diffusion process.

Keywords: customer barriers, electric vehicle promotion, sales of electric vehicles, interviews with car salesmen

Procedia PDF Downloads 229

Authors: Doyin Afolabi, Phillip Adewole, Oladipupo Sennaike

Abstract:

Most well-known classifiers, including the decision tree algorithm, can make predictions on balanced datasets efficiently. However, the decision tree algorithm tends to be biased towards imbalanced datasets because of the skewness of the distribution of such datasets. To overcome this problem, this study proposes a weighted decision tree algorithm that aims to remove the bias toward the majority class and prevents the reduction of majority observations in imbalance datasets classification. The proposed weighted decision tree algorithm was tested on three imbalanced datasets- cancer dataset, german credit dataset, and banknote dataset. The specificity, sensitivity, and accuracy metrics were used to evaluate the performance of the proposed decision tree algorithm on the datasets. The evaluation results show that for some of the weights of our proposed decision tree, the specificity, sensitivity, and accuracy metrics gave better results compared to that of the ID3 decision tree and decision tree induced with minority entropy for all three datasets.

Keywords: data mining, decision tree, classification, imbalance dataset

Procedia PDF Downloads 137

Authors: Eiman Kattan

Abstract:

This study aims to evaluate the impact of classifying labelled remote sensing images conventional neural network (CNN) architecture, i.e., AlexNet on different land cover scenarios based on two remotely sensed datasets from different point of views such as the computational time and performance. Thus, a set of experiments were conducted to specify the effectiveness of the selected convolutional neural network using two implementing approaches, named fully trained and fine-tuned. For validation purposes, two remote sensing datasets, AID, and RSSCN7 which are publicly available and have different land covers features were used in the experiments. These datasets have a wide diversity of input data, number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in training, validation, and testing. As a result, the fully trained approach has achieved a trivial result for both of the two data sets, AID and RSSCN7 by 73.346% and 71.857% within 24 min, 1 sec and 8 min, 3 sec respectively. However, dramatic improvement of the classification performance using the fine-tuning approach has been recorded by 92.5% and 91% respectively within 24min, 44 secs and 8 min 41 sec respectively. The represented conclusion opens the opportunities for a better classification performance in various applications such as agriculture and crops remote sensing.

Keywords: conventional neural network, remote sensing, land cover, land use

Procedia PDF Downloads 370

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 55

Authors: Salima Smiti, Ines Gasmi, Makram Soui

Abstract:

Credit risk is the most important issue for financial institutions. Its assessment becomes an important task used to predict defaulter customers and classify customers as good or bad payers. To this objective, numerous techniques have been applied for credit risk assessment. However, to our knowledge, several evaluation techniques are black-box models such as neural networks, SVM, etc. They generate applicants’ classes without any explanation. In this paper, we propose to assess credit risk using rules classification method. Our output is a set of rules which describe and explain the decision. To this end, we will compare seven classification algorithms (JRip, Decision Table, OneR, ZeroR, Fuzzy Rule, PART and Genetic programming (GP)) where the goal is to find the best rules satisfying many criteria: accuracy, sensitivity, and specificity. The obtained results confirm the efficiency of the GP algorithm for German and Australian datasets compared to other rule-based techniques to predict the credit risk.

Keywords: credit risk assessment, classification algorithms, data mining, rule extraction

Procedia PDF Downloads 181

Authors: Vijayendra Anil Menon, Ashwath Narayan Murali

Abstract:

The present day vehicles do not reuse the energy expelled in running the vehicle. The energy used to run the vehicle is expelled immediately.This has remained a constant for many decades. With all the vehicles running on non-renewable resources like fossil fuels, there is an urgent need to improve efficiency of the vehicles until a reliable replacement for fossil fuels is found.Our design is based on the concept of Kinetic energy recovery systems. Though our design lies in principle with the KERS, our design can be used in day-to-day driving. With our design, efficiency of vehicles increases and fuel conservation is possible thereby reducing the carbon footprint.

Keywords: KERS, Battery, Wheels, Efficiency.

Procedia PDF Downloads 393

Authors: Yulong Wang, Yuan Yan Tang, Cuiming Zou, Lina Yang

Abstract:

This paper presents a novel sparse representation method for robust pattern classification. Generalized orthogonal matching pursuit (GOMP) is a recently proposed efficient sparse representation technique. However, GOMP adopts the mean square error (MSE) criterion and assign the same weights to all measurements, including both severely and slightly corrupted ones. To reduce the limitation, we propose an information-theoretic GOMP (ITGOMP) method by exploiting the correntropy induced metric. The results show that ITGOMP can adaptively assign small weights on severely contaminated measurements and large weights on clean ones, respectively. An ITGOMP based classifier is further developed for robust pattern classification. The experiments on public real datasets demonstrate the efficacy of the proposed approach.

Keywords: correntropy induced metric, matching pursuit, pattern classification, sparse representation

Procedia PDF Downloads 355

Authors: Qi Xiu, Hiromu Hota, Yohsuke Ishii, Takuya Oda

Abstract:

Recently, collectable manufacturing data are rapidly increasing. On the other hand, mega recall is getting serious as a social problem. Under such circumstances, there are increasing needs for preventing mega recalls by defect analysis such as root cause analysis and abnormal detection utilizing manufacturing data. However, the time to classify strings in manufacturing data by traditional method is too long to meet requirement of quick defect analysis. Therefore, we present String Length Distribution Classification method (SLDC) to correctly classify strings in a short time. This method learns character features, especially string length distribution from Product ID, Machine ID in BOM and asset list. By applying the proposal to strings in actual manufacturing data, we verified that the classification time of strings can be reduced by 80%. As a result, it can be estimated that the requirement of quick defect analysis can be fulfilled.

Keywords: string classification, data quality, feature selection, probability distribution, string length

Procedia PDF Downloads 318

Authors: Mark Schudeleit, Christian Sieg, Ferit Küçükay

Abstract:

This paper describes how to dimension the electric components of a 48V hybrid system considering real customer use. Furthermore, it provides information about savings in energy and CO2 emissions by a customer-tailored 48V hybrid. Based on measured customer profiles, the electric units such as the electric motor and the energy storage are dimensioned. Furthermore, the CO2 reduction potential in real customer use is determined compared to conventional vehicles. Finally, investigations are carried out to specify the topology design and preliminary considerations in order to hybridize a conventional vehicle with a 48V hybrid system. The emission model results from an empiric approach also taking into account the effects of engine dynamics on emissions. We analyzed transient engine emissions during representative customer driving profiles and created emission meta models. The investigation showed a significant difference in emissions when simulating realistic customer driving profiles using the created verified meta models compared to static approaches which are commonly used for vehicle simulation.

Keywords: customer use, dimensioning, hybrid electric vehicles, vehicle simulation, 48V hybrid system

Procedia PDF Downloads 508

Authors: Jared Oluoch

Abstract:

Connected vehicles are equipped with wireless sensors that aid in Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communication. These vehicles will in the near future provide road safety, improve transport efficiency, and reduce traffic congestion. One of the challenges for connected vehicles is how to ensure that information sent across the network is secure. If security of the network is not guaranteed, several attacks can occur, thereby compromising the robustness, reliability, and efficiency of the network. This paper discusses existing security mechanisms and unique properties of connected vehicles. The methodology employed in this work is exploratory. The paper reviews existing security solutions for connected vehicles. More concretely, it discusses various cryptographic mechanisms available, and suggests areas of improvement. The study proposes a combination of symmetric key encryption and public key cryptography to improve security. The study further proposes message aggregation as a technique to overcome message redundancy. This paper offers a comprehensive overview of connected vehicles technology, its applications, its security mechanisms, open challenges, and potential areas of future research.

Keywords: VANET, connected vehicles, 802.11p, WAVE, DSRC, trust, security, cryptography

Procedia PDF Downloads 312

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 266

Authors: Rami Hashish, Manon Limousis-Gayda, Caitlin McCleery

Abstract:

Introduction: Mild traumatic brain injuries, also referred to as concussions, represent an increasing burden to society. Due to limited objective diagnostic measures, concussions are diagnosed by assessing subjective symptoms, often leading to disputes to their presence. Common biomechanical measures associated with concussion are high linear and/or angular acceleration to the head. With regards to linear acceleration, approximately 80g’s has previously been shown to equate with a 50% probability of concussion. Motor vehicle collisions (MVCs) are a leading cause of concussion, due to high head accelerations experienced. The change in velocity (delta-V) of a vehicle in an MVC is an established metric for impact severity. As acceleration is the rate of delta-V with respect to time, the purpose of this paper is to determine the relation between delta-V (and occupant parameters) with linear head acceleration. Methods: A meta-analysis was conducted for manuscripts collected using the following keywords: head acceleration, concussion, brain injury, head kinematics, delta-V, change in velocity, motor vehicle collision, and rear-end. Ultimately, 280 studies were surveyed, 14 of which fulfilled the inclusion criteria as studies investigating the human response to impacts, reporting head acceleration, and delta-V of the occupant’s vehicle. Statistical analysis was conducted with SPSS and R. The best fit line analysis allowed for an initial understanding of the relation between head acceleration and delta-V. To further investigate the effect of occupant parameters on head acceleration, a quadratic model and a full linear mixed model was developed. Results: From the 14 selected studies, 139 crashes were analyzed with head accelerations and delta-V values ranging from 0.6 to 17.2g and 1.3 to 11.1 km/h, respectively. Initial analysis indicated that the best line of fit (Model 1) was defined as Head Acceleration = 0.465

Keywords: acceleration, brain injury, change in velocity, Delta-V, TBI

Procedia PDF Downloads 233

Authors: Jularat Chumnaul

Abstract:

In forensic science, corpses from various homicides are different; there are both complete and incomplete, depending on causes of death or forms of homicide. For example, some corpses are cut into pieces, some are camouflaged by dumping into the river, some are buried, some are burned to destroy the evidence, and others. If the corpses are incomplete, it can lead to the difficulty of personally identifying because some tissues and bones are destroyed. To specify gender of the corpses from skeletal remains, the most precise method is DNA identification. However, this method is costly and takes longer so that other identification techniques are used instead. The first technique that is widely used is considering the features of bones. In general, an evidence from the corpses such as some pieces of bones, especially the skull and pelvis can be used to identify their gender. To use this technique, forensic scientists are required observation skills in order to classify the difference between male and female bones. Although this technique is uncomplicated, saving time and cost, and the forensic scientists can fairly accurately determine gender by using this technique (apparently an accuracy rate of 90% or more), the crucial disadvantage is there are only some positions of skeleton that can be used to specify gender such as supraorbital ridge, nuchal crest, temporal lobe, mandible, and chin. Therefore, the skeletal remains that will be used have to be complete. The other technique that is widely used for gender specifying in forensic science and archeology is skeletal measurements. The advantage of this method is it can be used in several positions in one piece of bones, and it can be used even if the bones are not complete. In this study, the classification and cluster analysis are applied to this technique, including the Kth Nearest Neighbor Classification, Classification Tree, Ward Linkage Cluster, K-mean Cluster, and Two Step Cluster. The data contains 507 particular individuals and 9 skeletal measurements (diameter measurements), and the performance of five methods are investigated by considering the apparent error rate (APER). The results from this study indicate that the Two Step Cluster and Kth Nearest Neighbor method seem to be suitable to specify gender from human skeletal remains because both yield small apparent error rate of 0.20% and 4.14%, respectively. On the other hand, the Classification Tree, Ward Linkage Cluster, and K-mean Cluster method are not appropriate since they yield large apparent error rate of 10.65%, 10.65%, and 16.37%, respectively. However, there are other ways to evaluate the performance of classification such as an estimate of the error rate using the holdout procedure or misclassification costs, and the difference methods can make the different conclusions.

Keywords: skeletal measurements, classification, cluster, apparent error rate

Procedia PDF Downloads 252

Authors: S. Di Benedetto, M. P. Di Donato, A. Rispoli, S. Cardone, J. Riehmer, J. Steelant, L. Vecchione

Abstract:

Thanks to a coordinated funding by the European Space Agency (ESA) and the European Commission (EC) within the 7th framework program, the High-Speed Experimental Fly Vehicles – International (HEXAFLY-INT) project is aimed at the flight validation of hypersonics technologies enabling future trans-atmospheric flights. The project, which is currently involving partners from Europe, Russian Federation and Australia operating under ESA/ESTEC coordination, will achieve the goal of designing, manufacturing, assembling and flight testing an unpowered high speed vehicle in a glider configuration by 2018. The main technical challenges of the project are specifically related to the design of the vehicle gliding configuration and to the complexity of integrating breakthrough technologies with standard aeronautical technologies, e.g. high temperature protection system and airframe cold structures. Also, the sonic boom impact, which is one of the environmental challenges of the high speed flight, will be assessed. This paper provides a comprehensive and detailed update on all the current projects activities carried out to date on both the vehicle and mission design.

Keywords: design, flight testing, HEXAFLY-INT, hypersonics

Procedia PDF Downloads 468

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

The purpose of this work is to develop a method for classifying hand signals and using the output in a drone control algorithm. To achieve this, methods based on Convolutional Neural Networks (CNN) were applied. CNN's are a subset of deep learning, which allows grid-like inputs to be processed and passed through a neural network to be trained for classification. This type of neural network allows for classification via imaging, which is less intrusive than previous methods using biosensors, such as EMG sensors. Classification CNN's operate purely from the pixel values in an image; therefore they can be used without additional exteroceptive sensors. A development bench was constructed using a desktop computer connected to a high-definition webcam mounted on a scissor arm. This allowed the camera to be pointed downwards at the desk to provide a constant solid background for the dataset and a clear detection area for the user. A MATLAB script was created to automate dataset image capture at the development bench and save the images to the desktop. This allowed the user to create their own dataset of 12,000 images within three hours. These images were evenly distributed among seven classes. The defined classes include forward, backward, left, right, idle, and land. The drone has a popular flip function which was also included as an additional class. To simplify control, the corresponding hand signals chosen were the numerical hand signs for one through five for movements, a fist for land, and the universal “ok” sign for the flip command. Transfer learning with PyTorch (Python) was performed using a pre-trained 18-layer residual learning network (ResNet-18) to retrain the network for custom classification. An algorithm was created to interpret the classification and send encoded messages to a Ryze Tello drone over its 2.4 GHz Wi-Fi connection. The drone’s movements were performed in half-meter distance increments at a constant speed. When combined with the drone control algorithm, the classification performed as desired with negligible latency when compared to the delay in the drone’s movement commands.

Keywords: classification, computer vision, convolutional neural networks, drone control

Procedia PDF Downloads 210

Authors: Javier Alfonso Bonilla-Chávez, Angélica Lozano

Abstract:

In North America, more than 2,000 people annually die in accidents related to railroad tracks. In 2020, collisions at grade crossings were the main cause of deaths related to railway accidents in Mexico. Railway networks have constant interaction with motor transport users, cyclists, and pedestrians, mainly in grade crossings, where is the greatest vulnerability and risk of accidents. Usually, accidents at grade crossings are directly related to risky behavior and non-compliance with regulations by motorists, cyclists, and pedestrians, especially in developing countries. Around the world, countries classify these crossings in different ways. In Mexico, according to their dangerousness (high, medium, or low), types A, B and C have been established, recommending for each one different type of auditive and visual signaling and gates, as well as horizontal and vertical signaling. This classification is based in a weighting, but regrettably, it is not explained how the weight values were obtained. A review of the variables and the current approach for the grade crossing classification is required, since it is inadequate for some crossings. In contrast, North America (USA and Canada) and European countries consider a broader classification so that attention to each crossing is addressed more precisely and equipment costs are adjusted. Lack of a proper classification, could lead to cost overruns in the equipment and a deficient operation. To exemplify the lack of a good classification, six crossings are studied, three located in the rural area of Mexico and three in Mexico City. These cases show the need of: improving the current regulations, improving the existing infrastructure, and implementing technological systems, including informative signals with nomenclature of the involved crossing and direct telephone line for reporting emergencies. This implementation is unaffordable for most municipal governments. Also, an inventory of the most dangerous grade crossings in urban and rural areas must be obtained. Then, an approach for improving the classification of grade crossings is suggested. This approach must be based on criteria design, characteristics of adjacent roads or intersections which can influence traffic flow through the crossing, accidents related to motorized and non-motorized vehicles, land use and land management, type of area, and services and economic activities in the zone where the grade crossings is located. An expanded classification of grade crossing in Mexico could reduce accidents and improve the efficiency of the railroad.

Keywords: accidents, grade crossing, railroad, traffic safety

Procedia PDF Downloads 108

Authors: P. S. Jagadeesh Kumar, Yang Yung, Wenli Hu

Abstract:

Speech emotion classification is a dominant research field in finding a sturdy and profligate classifier appropriate for different real-life applications. This effort accentuates on classifying different emotions from speech signal quarried from the features related to pitch, formants, energy contours, jitter, shimmer, spectral, perceptual and temporal features. Tensor deep stacking neural networks were supported to examine the factors that influence the classification success rate. Facial electromyography signals were composed of several forms of focuses in a controlled atmosphere by means of audio-visual stimuli. Proficient facial electromyography signals were pre-processed using moving average filter, and a set of arithmetical features were excavated. Extracted features were mapped into consistent emotions using bilinear mapping. With facial electromyography signals, a database comprising diverse emotions will be exposed with a suitable fine-tuning of features and training data. A success rate of 92% can be attained deprived of increasing the system connivance and the computation time for sorting diverse emotional states.

Keywords: speech emotion classification, tensor deep stacking neural networks, facial electromyography, bilinear mapping, audio-visual stimuli

Procedia PDF Downloads 254

Authors: Xiao Yihong, Yu Kexin, Burra Venkata Durga Kumar

Abstract:

With the accelerating process of urbanization, the problem of urban road congestion is becoming more and more serious. Intelligent transportation system combining distributed and artificial intelligence has become a research hotspot. As the core development direction of the intelligent transportation system, Cooperative Intelligent Transportation System (C-ITS) integrates advanced information technology and communication methods and realizes the integration of humans, vehicle, roadside infrastructure, and other elements through the multi-agent distributed system. By analyzing the system architecture and technical characteristics of C-ITS, the report proposes a distributed multi-agent C-ITS. The system consists of Roadside Sub-system, Vehicle Sub-system, and Personal Sub-system. At the same time, we explore the scalability of the C-ITS and put forward incorporating local rewards in the centralized training decentralized execution paradigm, hoping to add a scalable value decomposition method. In addition, we also suggest introducing blockchain to improve the safety of the traffic information transmission process. The system is expected to improve vehicle capacity and traffic safety.

Keywords: distributed system, artificial intelligence, multi-agent, cooperative intelligent transportation system

Procedia PDF Downloads 214

Authors: Li Kewen, Su Zhaoxin, Wang Xingmou, Zhu Jian Bing

Abstract:

Conventional reservoir prediction methods ar not sufficient to explore the implicit relation between seismic attributes, and thus data utilization is low. In order to improve the predictive classification accuracy of reservoir lithology, this paper proposes a deep learning lithology prediction method based on ResNet (Residual Neural Network) and SENet (Squeeze-and-Excitation Neural Network). The neural network model is built and trained by using seismic attribute data and lithology data of Shengli oilfield, and the nonlinear mapping relationship between seismic attribute and lithology marker is established. The experimental results show that this method can significantly improve the classification effect of reservoir lithology, and the classification accuracy is close to 70%. This study can effectively predict the lithology of undrilled area and provide support for exploration and development.

Keywords: convolutional neural network, lithology, prediction of reservoir, seismic attributes

Procedia PDF Downloads 177

Authors: Regina Chua

Abstract:

To reduce the costs of re-fielding a large survey, a Random Forest classifier was applied to measure the accuracy of classifying individuals into their assigned segments with the fewest possible questions. Given a long survey, one needed to determine the most predictive ten or fewer questions that would accurately assign new individuals to custom segments. Furthermore, the solution needed to be quick in its classification and usable in non-Python environments. In this paper, a supervised Random Forest classifier was modeled on a dataset with 7,000 individuals, 60 questions, and 254 features. The Random Forest consisted of an iterative collection of individual decision trees that result in a predicted segment with robust precision and recall scores compared to a single tree. A random 70-30 stratified sampling for training the algorithm was used, and accuracy trade-offs at different depths for each segment were identified. Ultimately, the Random Forest classifier performed at 87% accuracy at a depth of 10 with 20 instead of 254 features and 10 instead of 60 questions. With an acceptable accuracy in prioritizing feature selection, new tools were developed for non-Python environments: a worksheet with a formulaic version of the algorithm and an embedded function to predict the segment of an individual in real-time. Random Forest was determined to be an optimal classification model by its feature selection, performance, processing speed, and flexible application in other environments.

Keywords: machine learning, supervised learning, data science, random forest, classification, prediction, predictive modeling

Procedia PDF Downloads 94

Authors: Abolfazl Hosseinpour, Javad Marzbanrad

Abstract:

In this research, the topology and shape optimization of a Macpherson control arm has been accomplished to achieve lighter weight. Present automotive market demands low cost and light weight component to meet the need of fuel efficient and cost effective vehicle. This in turn gives the rise to more effective use of materials for automotive parts which can reduce the mass of vehicle. Since automotive components are under dynamic loads which cause fatigue damage, considering fatigue criteria seems to be essential in designing automotive components. At first, in order to create severe loading condition for control arm, some rough roads are generated through power spectral density. Then, the most critical loading conditions are obtained through multibody dynamics analysis of a full vehicle model. Then, the topology optimization is performed based on fatigue life criterion using HyperMesh software, which resulted to 50 percent mass reduction. In the next step a CAD model is created using CATIA software and shape optimization is performed to achieve accurate dimensions with less mass.

Keywords: topology optimization, shape optimization, fatigue life, MacPherson control arm

Procedia PDF Downloads 316

Authors: José A. Menezes, Giordano Cabral, Bruno T. Gomes

Abstract:

Choosing good features is an essential part of machine learning. Recent techniques aim to automate this process. For instance, feature learning intends to learn the transformation of raw data into a useful representation to machine learning tasks. In automatic audio classification tasks, this is interesting since the audio, usually complex information, needs to be transformed into a computationally convenient input to process. Another technique tries to generate features by searching a feature space. Genetic algorithms, for instance, have being used to generate audio features by combining or modifying them. We find this approach particularly interesting and, despite the undeniable advances of feature learning approaches, we wanted to take a step forward in the use of genetic algorithms to find audio features, combining them with more conventional methods, like PCA, and inserting search control mechanisms, such as constraints over a confusion matrix. This work presents the results obtained on particular audio classification problems.

Keywords: feature generation, feature learning, genetic algorithm, music information retrieval

Procedia PDF Downloads 435

Authors: Nicholas Milburn, Yu Liang, Dalei Wu

Abstract:

Athlete performance scoring within the climbing do-main presents interesting challenges as the sport does not have an objective way to assign skill. Assessing skill levels within any sport is valuable as it can be used to mark progress while training, and it can help an athlete choose appropriate climbs to attempt. Machine learning-based methods are popular for complex problems like this. The dataset available was composed of dynamic force data recorded during climbing; however, this dataset came with challenges such as data scarcity, imbalance, and it was temporally heterogeneous. Investigated solutions to these challenges include data augmentation, temporal normalization, conversion of time series to the spectral domain, and cross validation strategies. The investigated solutions to the classification problem included light weight machine classifiers KNN and SVM as well as the deep learning with CNN. The best performing model had an 80% accuracy. In conclusion, there seems to be enough information within climbing force data to accurately categorize climbers by skill.

Keywords: classification, climbing, data imbalance, data scarcity, machine learning, time sequence

Procedia PDF Downloads 143

Authors: Manish Kumar, Krupa Shah

Abstract:

The usage of renewable energy sources is increased day by day to overcome the dependency on fossil fuels. The wind energy is considered as a prominent source of renewable energy. This paper presents an approach for utilizing wind energy obtained from moving the vehicle for cell-phone charging. The selection of wind turbine, blades, generator, etc. is done to have the most efficient system. The calculation procedure for power generated and drag force is shown to know the effectiveness of the proposal. The location of the turbine is selected such that the system remains symmetric, stable and has the maximum induced wind. The calculation of the generated power at different velocity is presented. The charging is achieved for the speed 30 km/h and the system works well till 60 km/h. The model proposed seems very useful for the people traveling long distances in the absence of mobile electricity. The model is very economical and easy to fabricate. It has very less weight and area that makes it portable and comfortable to carry along. The practical results are shown by implementing the portable wind turbine system on two-wheeler.

Keywords: cell-phone charging, on-board power generation, wind energy, vehicle

Procedia PDF Downloads 295

Authors: Aleksandra Zysk, Pawel Badura

Abstract:

Recognizing and controlling vocal registers during singing is a difficult task for beginner vocalist. It requires among others identifying which part of natural resonators is being used when a sound propagates through the body. Thus, an application has been designed allowing for sound recording, automatic vocal register recognition (VRR), and a graphical user interface providing real-time visualization of the signal and recognition results. Six spectral features are determined for each time frame and passed to the support vector machine classifier yielding a binary decision on the head or chest register assignment of the segment. The classification training and testing data have been recorded by ten professional female singers (soprano, aged 19-29) performing sounds for both chest and head register. The classification accuracy exceeded 93% in each of various validation schemes. Apart from a hard two-class clustering, the support vector classifier returns also information on the distance between particular feature vector and the discrimination hyperplane in a feature space. Such an information reflects the level of certainty of the vocal register classification in a fuzzy way. Thus, the designed recognition and training application is able to assess and visualize the continuous trend in singing in a user-friendly graphical mode providing an easy way to control the vocal emission.

Keywords: classification, singing, spectral analysis, vocal emission, vocal register

Procedia PDF Downloads 304

Authors: Mohamed El Morsy, Gabriela Achtenová

Abstract:

Research on damage of gears and gear pairs using vibration signals remains very attractive, because vibration signals from a gear pair are complex in nature and not easy to interpret. Predicting gear pair defects by analyzing changes in vibration signal of gears pairs in operation is a very reliable method. Therefore, a suitable vibration signal processing technique is necessary to extract defect information generally obscured by the noise from dynamic factors of other gear pairs. This article presents the value of cepstrum analysis in vehicle gearbox fault diagnosis. Cepstrum represents the overall power content of a whole family of harmonics and sidebands when more than one family of sidebands is present at the same time. The concept for the measurement and analysis involved in using the technique are briefly outlined. Cepstrum analysis is used for detection of an artificial pitting defect in a vehicle gearbox loaded with different speeds and torques. The test stand is equipped with three dynamometers; the input dynamometer serves as the internal combustion engine, the output dynamometers introduce the load on the flanges of the output joint shafts. The pitting defect is manufactured on the tooth side of a gear of the fifth speed on the secondary shaft. Also, a method for fault diagnosis of gear faults is presented based on order cepstrum. The procedure is illustrated with the experimental vibration data of the vehicle gearbox. The results show the effectiveness of cepstrum analysis in detection and diagnosis of the gear condition.

Keywords: cepstrum analysis, fault diagnosis, gearbox, vibration signals

Procedia PDF Downloads 379

Authors: Kamal KC, Zhendong Yin, Dasen Li, Zhilu Wu

Abstract:

Intra-plant disease classification based on leaf images is a challenging computer vision task due to similarities in texture, color, and shape of leaves with a slight variation of leaf spot; and external environmental changes such as lighting and background noises. Deep convolutional neural network (DCNN) has proven to be an effective tool for binary classification. In this paper, two methods for binary classification of diseased plant leaves using DCNN are presented; model created from scratch and transfer learning. Our main contribution is a thorough evaluation of 4 networks created from scratch and transfer learning of 5 pre-trained models. Training and testing of these models were performed on a plant leaf images dataset belonging to 16 distinct classes, containing a total of 22,265 images from 8 different plants, consisting of a pair of healthy and diseased leaves. We introduce a deep CNN model, Optimized MobileNet. This model with depthwise separable CNN as a building block attained an average test accuracy of 99.77%. We also present a fine-tuning method by introducing the concept of a convolutional block, which is a collection of different deep neural layers. Fine-tuned models proved to be efficient in terms of accuracy and computational cost. Fine-tuned MobileNet achieved an average test accuracy of 99.89% on 8 pairs of [healthy, diseased] leaf ImageSet.

Keywords: deep convolution neural network, depthwise separable convolution, fine-grained classification, MobileNet, plant disease, transfer learning

Procedia PDF Downloads 186

Authors: Hamidreza Ahmadi, Majid Abbasalizadeh, Ghasem Yazdani, Masoud Ahmadi

Abstract:

In this paper a special kind of aerodynamic system as a spoiler has been designed and tried to show effects of this devise on braking system of vehicle. Moreover, position of this spoiler has been considered in order to find optimum point from safety and highest rate of braking view for spoiler. Fluent software is our main tool to calculate rate of extra force that is produced by spoiler and this article has been tried to use various figures that are showed effects of spoiler at different speeds, angles and also heights. Other major points in this paper are static pressure of vehicle at different speed and statues. Undoubtedly, shape of spoiler would be very important, so in this investigation spoiler has been designed and proposed after a lot of simulation for different shape of spoiler. In the end, there is very important part as validation since these simulations must be validated by experimental way to prove our claims. In this case, a special kind of BMW has been simulated and results have been compared by experimental results that have been presented by BMW Company. Difference between simulation results and experimental results are very little and it could be a suitable validation for this project.

Keywords: drag force, down force, vehicle, spoiler

Procedia PDF Downloads 337

Authors: Onur Kaya, Ilknur Tukenmez

Abstract:

In this study, we consider vehicle routing problems on networks with alternative direct links between nodes, and we analyze a multi-objective problem considering the financial, environmental and social objectives in this context. In real life, there might exist several alternative direct roads between two nodes, and these roads might have differences in terms of their lengths and durations. For example, a road might be shorter than another but might require longer time due to traffic and speed limits. Similarly, some toll roads might be shorter or faster but require additional payment, leading to higher costs. We consider such alternative links in our problem and develop a mixed integer linear programming model that determines which alternative link to use between two nodes, in addition to determining the optimal routes for different vehicles, depending on the model objectives and constraints. We consider the minimum cost routing as the financial objective for the company, minimizing the CO2 emissions and gas usage as the environmental objectives, and optimizing the driver working conditions/working hours, and minimizing the risks of accidents as the social objectives. With these objective functions, we aim to determine which routes, and which alternative links should be used in addition to the speed choices on each link. We discuss the results of the developed vehicle routing models and compare their results depending on the system parameters.

Keywords: vehicle routing, alternative links between nodes, mixed integer linear programming, triple bottom line accounting

Procedia PDF Downloads 407

Authors: Ali Asheibi

Abstract:

The rapid increase in the size of databases required to store power quality monitoring data has demanded new techniques for analysing and understanding the data. One suggested technique to assist in analysis is data mining. Preparing raw data to be ready for data mining exploration take up most of the effort and time spent in the whole data mining process. Clustering is an important technique in data mining and machine learning in which underlying and meaningful groups of data are discovered. Large amounts of harmonic data have been collected from an actual harmonic monitoring system in a distribution system in Australia for three years. This amount of acquired data makes it difficult to identify operational events that significantly impact the harmonics generated on the system. In this paper, harmonic data preparation processes to better understanding of the data have been presented. Underlying classes in this data has then been identified using clustering technique based on the Minimum Message Length (MML) method. The underlying operational information contained within the clusters can be rapidly visualised by the engineers. The C5.0 algorithm was used for classification and interpretation of the generated clusters.

Keywords: data mining, harmonic data, clustering, classification

Procedia PDF Downloads 248