Search results for: deep machine learning

Authors: Carlos Gordon, Patricio Encalada, Henry Lema, Diego Leon, Dennis Chicaiza

Abstract:

The following work presents a proposal of autonomous navigation of mobile robots implemented in an omnidirectional robot Kuka Youbot. We have been able to perform the integration of robotic operative system (ROS) and machine learning algorithms. ROS mainly provides two distributions; ROS hydro and ROS Kinect. ROS hydro allows managing the nodes of odometry, kinematics, and path planning with statistical and probabilistic, global and local algorithms based on Adaptive Monte Carlo Localization (AMCL) and Dijkstra. Meanwhile, ROS Kinect is responsible for the detection block of dynamic objects which can be in the points of the planned trajectory obstructing the path of Kuka Youbot. The detection is managed by artificial vision module under a trained neural network based on the single shot multibox detector system (SSD), where the main dynamic objects for detection are human beings and domestic animals among other objects. When the objects are detected, the system modifies the trajectory or wait for the decision of the dynamic obstacle. Finally, the obstacles are skipped from the planned trajectory, and the Kuka Youbot can reach its goal thanks to the machine learning algorithms.

Keywords: autonomous navigation, machine learning, path planning, robotic operative system, open source computer vision library

Procedia PDF Downloads 156

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 122

Authors: A. M. Byrne, E. Bonfiglio, C. Rigby, N. Edelstyn

Abstract:

Introduction: Neuromarketing employs numerous methodologies when investigating products and advertisement effectiveness. Electroencephalography (EEG), a non-invasive measure of electrical activity from the brain, is commonly used in neuromarketing. EEG data can be considered using time-frequency (TF) analysis, where changes in the frequency of brainwaves are calculated to infer participant’s mental states, or event-related potential (ERP) analysis, where changes in amplitude are observed in direct response to a stimulus. This presentation discusses the findings of a systematic review of EEG measures in neuromarketing. A systematic review summarises evidence on a research question, using explicit measures to identify, select, and critically appraise relevant research papers. Thissystematic review identifies which EEG measures are the most robust predictor of customer preference and purchase intention. Methods: Search terms identified174 papers that used EEG in combination with marketing-related stimuli. Publications were excluded if they were written in a language other than English or were not published as journal articles (e.g., book chapters). The review investigated which TF effect (e.g., theta-band power) and ERP component (e.g., N400) most consistently reflected preference and purchase intention. Machine-learning prediction was also investigated, along with the use of EEG combined with physiological measures such as eye-tracking. Results: Frontal alpha asymmetry was the most reliable TF signal, where an increase in activity over the left side of the frontal lobe indexed a positive response to marketing stimuli, while an increase in activity over the right side indexed a negative response. The late positive potential, a positive amplitude increase around 600 ms after stimulus presentation, was the most reliable ERP component, reflecting the conscious emotional evaluation of marketing stimuli. However, each measure showed mixed results when related to preference and purchase behaviour. Predictive accuracy was greatly improved through machine-learning algorithms such as deep neural networks, especially when combined with eye-tracking or facial expression analyses. Discussion: This systematic review provides a novel catalogue of the most effective use of each EEG measure commonly used in neuromarketing. Exciting findings to emerge are the identification of the frontal alpha asymmetry and late positive potential as markers of preferential responses to marketing stimuli. Predictive accuracy using machine-learning algorithms achieved predictive accuracies as high as 97%, and future research should therefore focus on machine-learning prediction when using EEG measures in neuromarketing.

Keywords: EEG, ERP, neuromarketing, machine-learning, systematic review, time-frequency

Procedia PDF Downloads 97

Authors: Delphine Vendryes, Dushyanth Sekhar, Baojia Tong, Matthew Theisen, Chester Curme

Abstract:

Much of the data that inform the decisions of governments, corporations and individuals are harvested from unstructured documents. Data extraction is defined here as a process that turns non-machine-readable information into a machine-readable format that can be stored, for instance, in a database. In financial services, introducing more automation in data extraction pipelines is a major challenge. Information sought by financial data consumers is often buried within vast bodies of unstructured documents, which have historically required thorough manual extraction. Automated solutions provide faster access to non-machine-readable datasets, in a context where untimely information quickly becomes irrelevant. Data quality standards cannot be compromised, so automation requires high data integrity. This multifaceted task is broken down into smaller steps: ingestion, table parsing (detection and structure recognition), text analysis (entity detection and disambiguation), schema-based record extraction, user feedback incorporation. Selected intermediary steps are phrased as machine learning problems. Solutions leveraging cutting-edge approaches from the fields of computer vision (e.g. table detection) and natural language processing (e.g. entity detection and disambiguation) are proposed.

Keywords: computer vision, entity recognition, finance, information retrieval, machine learning, natural language processing

Procedia PDF Downloads 93

Authors: Dua Hişam, Serhat İkizoğlu

Abstract:

Identifying the problem behind balance disorder is one of the most interesting topics in the medical literature. This study has considerably enhanced the development of artificial intelligence (AI) algorithms applying multiple machine learning (ML) models to sensory data on gait collected from humans to classify between normal people and those suffering from Vestibular System (VS) problems. Although AI is widely utilized as a diagnostic tool in medicine, AI models have not been used to perform feature extraction and identify VS disorders through training on raw data. In this study, three machine learning (ML) models, the Random Forest Classifier (RF), Extreme Gradient Boosting (XGB), and K-Nearest Neighbor (KNN), have been trained to detect VS disorder, and the performance comparison of the algorithms has been made using accuracy, recall, precision, and f1-score. With an accuracy of 95.28 %, Random Forest Classifier (RF) was the most accurate model.

Keywords: vestibular disorder, machine learning, random forest classifier, k-nearest neighbor, extreme gradient boosting

Procedia PDF Downloads 53

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: deep learning, field programmable gate array, FPGA, hardware accelerator, convolutional neural networks, CNN

Procedia PDF Downloads 105

Authors: Maha Wiss, Wael Khreich

Abstract:

Animals, objects, foods, plants, and other non-human terms are commonly used as a source of metaphors to describe females in formal and slang language. Comparing women to non-human items not only reflects cultural views that might conceptualize women as subordinates or in a lower position than humans, yet it conveys this degradation to the listeners. Moreover, the dehumanizing representation of females in the language normalizes the derogation and even encourages sexism and aggressiveness against women. Although dehumanization has been a popular research topic for decades, according to our knowledge, no studies have linked women's dehumanizing language to the machine learning field. Therefore, we introduce our research work as one of the first attempts to create a tool for the automated detection of the dehumanizing depiction of females in English texts. We also present the first labeled dataset on the charted topic, which is used for training supervised machine learning algorithms to build an accurate classification model. The importance of this work is that it accomplishes the first step toward mitigating dehumanizing language against females.

Keywords: gender bias, machine learning, NLP, women dehumanization

Procedia PDF Downloads 65

Authors: Carlos Theran, Yohn Parra Bautista, Victor Adankai, Richard Alo, Jimwi Liu, Clement G. Yedjou

Abstract:

Alzheimer's disease (AD) is a neurodegenerative disorder primarily characterized by deteriorating cognitive functions. AD has gained relevant attention in the last decade. An estimated 24 million people worldwide suffered from this disease by 2011. In 2016 an estimated 40 million were diagnosed with AD, and for 2050 is expected to reach 131 million people affected by AD. Therefore, detecting and confirming AD at its different stages is a priority for medical practices to provide adequate and accurate treatments. Recently, Machine Learning (ML) models have been used to study AD's stages handling missing values in multiclass, focusing on the delineation of Early Mild Cognitive Impairment (EMCI), Late Mild Cognitive Impairment (LMCI), and normal cognitive (CN). But, to our best knowledge, robust performance information of these models and the missing data analysis has not been presented in the literature. In this paper, we propose studying the performance of five different machine learning models for AD's stages multiclass prediction in terms of accuracy, precision, and F1-score. Also, the analysis of three imputation methods to handle the missing value problem is presented. A framework that integrates ML model for AD's stages multiclass prediction is proposed, performing an average accuracy of 84%.

Keywords: alzheimer's disease, missing value, machine learning, performance evaluation

Procedia PDF Downloads 216

Authors: Adam Beaunoyer, Cory Beaunoyer, Mohammed Elmorsy, Hanan Saleh

Abstract:

This research aims to create a reinforcement learning agent capable of racing in challenging simulated environments with a low collision count. We present a reinforcement learning agent that can navigate challenging tracks using both a Deep Q-Network (DQN) and a Soft Actor-Critic (SAC) method. A challenging track includes curves, jumps, and varying road widths throughout. Using open-source code on Github, the environment used in this research is based on the 1995 racing game WipeOut. The proposed reinforcement learning agent can navigate challenging tracks rapidly while maintaining low racing completion time and collision count. The results show that the SAC model outperforms the DQN model by a large margin. We also propose an alternative multiple-car model that can navigate the track without colliding with other vehicles on the track. The SAC model is the basis for the multiple-car model, where it can complete the laps quicker than the single-car model but has a higher collision rate with the track wall.

Keywords: reinforcement learning, soft actor-critic, deep q-network, self-driving cars, artificial intelligence, gaming

Procedia PDF Downloads 23

Authors: Yakubu Bala Mohammed, Nadire Chavus, Mohammed Bulama

Abstract:

Generative Pre-trained Transformer (ChatGPT) represents an artificial intelligence (AI) tool capable of swiftly generating comprehensive responses to prompts and follow-up inquiries. This emerging AI tool was introduced in November 2022 by OpenAI firm, an American AI research laboratory, utilizing substantial language models. This present study aims to delve into the potential future consequences of ChatGPT usage in education using AI-based algorithms. The paper will bring forth the likely potential risks of ChatGBT utilization, such as academic integrity concerns, unfair learning assessments, excessive reliance on AI, and dissemination of inaccurate information using four machine learning algorithms: eXtreme-Gradient Boosting (XGBoost), Support vector machine (SVM), Emotional artificial neural network (EANN), and Random forest (RF) would be used to analyze the study collected data due to their robustness. Finally, the findings of the study will assist education stakeholders in understanding the future implications of ChatGPT usage in education and propose solutions and directions for upcoming studies.

Keywords: machine learning, ChatGPT, education, learning, implications

Procedia PDF Downloads 205

Authors: James Purnama, Riri Fitri Sari

Abstract:

We investigate the machine learning algorithm selection problem in the term of a depth image based eye gaze estimation, with respect to its essential difficulty in reducing the number of required training samples and duration time of training. Statistics based prediction accuracy are increasingly used to assess and evaluate prediction or estimation in gaze estimation. This article evaluates Root Mean Squared Error (RMSE) and R-Squared statistical analysis to assess machine learning methods on depth camera data for gaze estimation. There are 4 machines learning methods have been evaluated: Random Forest Regression, Regression Tree, Support Vector Machine (SVM), and Linear Regression. The experiment results show that the Random Forest Regression has the lowest RMSE and the highest R-Squared, which means that it is the best among other methods.

Keywords: gaze estimation, gaze tracking, eye tracking, kinect, regression model, orange python

Procedia PDF Downloads 523

Authors: Hamdi Beji, Toufik Kanit, Tanguy Messager

Abstract:

This study aims to construct a predictive model proficient in foreseeing the linear elastic and thermal characteristics of composite materials, drawing on a multitude of influencing parameters. These parameters encompass the shape of inclusions (circular, elliptical, square, triangle), their spatial coordinates within the matrix, orientation, volume fraction (ranging from 0.05 to 0.4), and variations in contrast (spanning from 10 to 200). A variety of machine learning techniques are deployed, including decision trees, random forests, support vector machines, k-nearest neighbors, and an artificial neural network (ANN), to facilitate this predictive model. Moreover, this research goes beyond the predictive aspect by delving into an inverse analysis using genetic algorithms. The intent is to unveil the intrinsic characteristics of composite materials by evaluating their thermomechanical responses. The foundation of this research lies in the establishment of a comprehensive database that accounts for the array of input parameters mentioned earlier. This database, enriched with this diversity of input variables, serves as a bedrock for the creation of machine learning and genetic algorithm-based models. These models are meticulously trained to not only predict but also elucidate the mechanical and thermal conduct of composite materials. Remarkably, the coupling of machine learning and genetic algorithms has proven highly effective, yielding predictions with remarkable accuracy, boasting scores ranging between 0.97 and 0.99. This achievement marks a significant breakthrough, demonstrating the potential of this innovative approach in the field of materials engineering.

Keywords: machine learning, composite materials, genetic algorithms, mechanical and thermal proprieties

Procedia PDF Downloads 44

Authors: Tokihiko Akita, Seiichi Mita

Abstract:

A millimeter-wave radar is the most robust against adverse environments, making it an essential environment recognition sensor for automated driving. However, the reflection signal is sparse and unstable, so it is difficult to obtain the high recognition accuracy. Deep learning provides high accuracy even for them in recognition, but requires large scale datasets with ground truth. Specially, it takes a lot of cost to annotate for a millimeter-wave radar. For the solution, utilizing a simulator that can generate an annotated huge dataset is effective. Simulation of the radar is more difficult to match with real world data than camera image, and recognition by deep learning with higher-order features using the simulator causes further deviation. We have challenged to improve the accuracy of traffic participant classification by fusing simulator and real-world data with domain adaptation technique. Experimental results with the domain adaptation network created by us show that classification accuracy can be improved even with a few real-world data.

Keywords: millimeter-wave radar, object classification, deep learning, simulation, domain adaptation

Procedia PDF Downloads 74

Authors: Madhawa Basnayaka, Jouni Paltakari

Abstract:

Fully passive backscattering chipless RFID tags are an emerging wireless technology with low cost, higher reading distance, and fast automatic identification without human interference, unlike already available technologies like optical barcodes. The design optimization of chipless RFID tags is crucial as it requires replacing integrated chips found in conventional RFID tags with printed geometric designs. These designs enable data encoding and decoding through backscattered electromagnetic (EM) signatures. The applications of chipless RFID tags have been limited due to the constraints of data encoding capacity and the ability to design accurate yet efficient configurations. The traditional approach to accomplishing design parameters for a desired EM response involves iterative adjustment of design parameters and simulating until the desired EM spectrum is achieved. However, traditional numerical simulation methods encounter limitations in optimizing design parameters efficiently due to the speed and resource consumption. In this work, a deep learning neural network (DNN) is utilized to establish a correlation between the EM spectrum and the dimensional parameters of nested centric rings, specifically square and octagonal. The proposed bi-directional DNN has two simultaneously running neural networks, namely spectrum prediction and design parameters prediction. First, spectrum prediction DNN was trained to minimize mean square error (MSE). After the training process was completed, the spectrum prediction DNN was able to accurately predict the EM spectrum according to the input design parameters within a few seconds. Then, the trained spectrum prediction DNN was connected to the design parameters prediction DNN and trained two networks simultaneously. For the first time in chipless tag design, design parameters were predicted accurately after training bi-directional DNN for a desired EM spectrum. The model was evaluated using a randomly generated spectrum and the tag was manufactured using the predicted geometrical parameters. The manufactured tags were successfully tested in the laboratory. The amount of iterative computer simulations has been significantly decreased by this approach. Therefore, highly efficient but ultrafast bi-directional DNN models allow rapid and complicated chipless RFID tag designs.

Keywords: artificial intelligence, chipless RFID, deep learning, machine learning

Procedia PDF Downloads 28

Authors: Rikson Gultom

Abstract:

Hate Speech and Abusive language on social media is difficult to detect, usually, it is detected after it becomes viral in cyberspace, of course, it is too late for prevention. An early detection system that has a fairly good accuracy is needed so that it can reduce conflicts that occur in society caused by postings on social media that attack individuals, groups, and governments in Indonesia. The purpose of this study is to find an early detection model on Twitter social media using machine learning that has high accuracy from several machine learning methods studied. In this study, the support vector machine (SVM), Naïve Bayes (NB), and Random Forest Decision Tree (RFDT) methods were compared with the Support Vector machine with genetic algorithm (SVM-GA), Nave Bayes with genetic algorithm (NB-GA), and Random Forest Decision Tree with Genetic Algorithm (RFDT-GA). The study produced a comparison table for the accuracy of the hate speech and abusive language detection model, and presented it in the form of a graph of the accuracy of the six algorithms developed based on the Indonesian-language Twitter dataset, and concluded the best model with the highest accuracy.

Keywords: abusive language, hate speech, machine learning, optimization, social media

Procedia PDF Downloads 112

Authors: Kashika P. H.

Abstract:

The development of computer vision systems has been greatly aided by the efficient and precise detection of images and videos. Although the ability to recognize and comprehend images is a strength of the human brain, employing technology to tackle this issue is exceedingly challenging. In the past few years, the use of Deep Learning algorithms to treat object detection has dramatically expanded. One of the key issues in the realm of image recognition is the recognition and detection of certain notable people from randomly acquired photographs. Face recognition uses a way to identify, assess, and compare faces for a variety of purposes, including user identification, user counting, and classification. With the aid of an accessible deep learning-based API, this article intends to recognize various faces of people and their facial descriptors more accurately. The purpose of this study is to locate suitable individuals and deliver accurate information about them by using the Amazon Rekognition system to identify a specific human from a vast image dataset. We have chosen the Amazon Rekognition system, which allows for more accurate face analysis, face comparison, and face search, to tackle this difficulty.

Keywords: Amazon rekognition, API, deep learning, computer vision, face detection, text detection

Procedia PDF Downloads 92

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 186

Authors: Thewodros K. Geberemariam

Abstract:

The rapid physical expansion of urbanization coupled with aging infrastructure presents a unique decision and management challenges for many big city municipalities. Cities must therefore upgrade and maintain the existing aging urban drainage infrastructure systems to keep up with the demands. Given the overall contribution of assets to municipal revenue and the importance of infrastructure to the success of a livable city, many municipalities are currently looking for a robust and smart urban drainage infrastructure asset management solution that combines management, financial, engineering and technical practices. This robust decision-making shall rely on sound, complete, current and relevant data that enables asset valuation, impairment testing, lifecycle modeling, and forecasting across the multiple asset portfolios. On this paper, predictive computational intelligence (CI) and multi-class machine learning (ML) coupled with online, offline, and historical record data that are collected from an array of multi-parameter sensors are used for the extraction of different operational and non-conforming patterns hidden in structured and unstructured data to determine and produce actionable insight on the current and future states of the network. This paper aims to improve the strategic decision-making process by identifying all possible alternatives; evaluate the risk of each alternative, and choose the alternative most likely to attain the required goal in a cost-effective manner using historical and near real-time urban drainage infrastructure data for urban drainage infrastructures assets that have previously not benefited from computational intelligence and machine learning advancements.

Keywords: computational intelligence, machine learning, urban drainage infrastructure, machine learning, classification, prediction, asset management space

Procedia PDF Downloads 139

Authors: Shariful Islam, Sharun Akter Khushbu, S. M. Shaqib, Shahriar Sultan Ramit

Abstract:

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwear. The suggested method precisely locates these safety items by using the YOLO v7 (You Only Look Once) object detection algorithm. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a [email protected] score of 87.7%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research contributes to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry.

Keywords: deep learning, safety equipment detection, YOLOv7, computer vision, workplace safety

Procedia PDF Downloads 54

Authors: David F. Nettleton, Christian Wasiak, Jonas Dorissen, David Gillen, Alexandr Tretyak, Elodie Bugnicourt, Alejandro Rosales

Abstract:

In this work, preliminary results are given for the modeling and calibration of two inline processes, pultrusion, and laser ablation, using machine learning techniques. The end product of the processes is the core of a medical guidewire, manufactured to comply with a user specification of diameter and flexibility. An ensemble approach is followed which requires training several models. Two state of the art machine learning algorithms are benchmarked: Kernel Recursive Least Squares (KRLS) and Support Vector Regression (SVR). The final objective is to build a precise digital model of the pultrusion and laser ablation process in order to calibrate the resulting diameter and flexibility of a medical guidewire, which is the end product while taking into account the friction on the forming die. The result is an ensemble of models, whose output is within a strict required tolerance and which covers the required range of diameter and flexibility of the guidewire end product. The modeling and automatic calibration of complex in-line industrial processes is a key aspect of the Industry 4.0 movement for cyber-physical systems.

Keywords: calibration, data modeling, industrial processes, machine learning

Procedia PDF Downloads 273

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 415

Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez

Abstract:

Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.

Keywords: deep-learning, image classification, image identification, industrial engineering.

Procedia PDF Downloads 142

Authors: Diego Aguirre, Olac Fuentes

Abstract:

In this paper, we present a taxonomy of weight initialization schemes used in deep learning. We survey the most representative techniques in each class and compare them in terms of overhead cost, convergence rate, and applicability. We also introduce a new weight initialization scheme. In this technique, we perform an initial feedforward pass through the network using an initialization mini-batch. Using statistics obtained from this pass, we initialize the weights of the network, so the following properties are met: 1) weight matrices are orthogonal; 2) ReLU layers produce a predetermined number of non-zero activations; 3) the output produced by each internal layer has a unit variance; 4) weights in the last layer are chosen to minimize the error in the initial mini-batch. We evaluate our method on three popular architectures, and a faster converge rates are achieved on the MNIST, CIFAR-10/100, and ImageNet datasets when compared to state-of-the-art initialization techniques.

Keywords: deep learning, image classification, supervised learning, weight initialization

Procedia PDF Downloads 116

Authors: Ágoston Nagy

Abstract:

This paper introduces a method of using unsupervised machine learning to visualize the feature space of a dataset in 2D, in order to find most characteristic segments in the set. After dimension reduction, users can select clusters by manual drawing. Selected clusters are recorded into a data model that is used for later predictions, based on realtime data. Predictions are made with supervised learning, using Gesture Recognition Toolkit. The paper introduces two example applications: a semantic audio organizer for analyzing incoming sounds, and a gesture database organizer where gestural data (recorded by a Leap motion) is visualized for further manipulation.

Keywords: gesture recognition, machine learning, real-time interaction, visualization

Procedia PDF Downloads 330

Authors: Radoslav Židek, Veronika Šidlová, Radovan Kasarda, Birgit Fuerst-Waltl

Abstract:

Machine learning represents a set of topics dealing with the creation and evaluation of algorithms that facilitate pattern recognition, classification, and prediction, based on models derived from existing data. The data can present identification patterns which are used to classify into groups. The result of the analysis is the pattern which can be used for identification of data set without the need to obtain input data used for creation of this pattern. An important requirement in this process is careful data preparation validation of model used and its suitable interpretation. For breeders, it is important to know the origin of animals from the point of the genetic diversity. In case of missing pedigree information, other methods can be used for traceability of animal´s origin. Genetic diversity written in genetic data is holding relatively useful information to identify animals originated from individual countries. We can conclude that the application of data mining for molecular genetic data using supervised learning is an appropriate tool for hypothesis testing and identifying an individual.

Keywords: genetic data, Pinzgau cattle, supervised learning, machine learning

Procedia PDF Downloads 532

Authors: Halimatu S. Abdullahi, Ray E. Sheriff, Fatima Mahieddine

Abstract:

Agriculture is essential to the continuous existence of human life as they directly depend on it for the production of food. The exponential rise in population calls for a rapid increase in food with the application of technology to reduce the laborious work and maximize production. Technology can aid/improve agriculture in several ways through pre-planning and post-harvest by the use of computer vision technology through image processing to determine the soil nutrient composition, right amount, right time, right place application of farm input resources like fertilizers, herbicides, water, weed detection, early detection of pest and diseases etc. This is precision agriculture which is thought to be solution required to achieve our goals. There has been significant improvement in the area of image processing and data processing which has being a major challenge. A database of images is collected through remote sensing, analyzed and a model is developed to determine the right treatment plans for different crop types and different regions. Features of images from vegetations need to be extracted, classified, segmented and finally fed into the model. Different techniques have been applied to the processes from the use of neural network, support vector machine, fuzzy logic approach and recently, the most effective approach generating excellent results using the deep learning approach of convolution neural network for image classifications. Deep Convolution neural network is used to determine soil nutrients required in a plantation for maximum production. The experimental results on the developed model yielded results with an average accuracy of 99.58%.

Keywords: convolution, feature extraction, image analysis, validation, precision agriculture

Procedia PDF Downloads 296

Authors: Sudha T., Naveen C.

Abstract:

Dengue is a serious public health issue that causes significant annual economic and welfare burdens on nations. However, enhanced optimization techniques and quantitative modeling approaches can predict the incidence of dengue. By advocating for a data-driven approach, public health officials can make informed decisions, thereby improving the overall effectiveness of sudden disease outbreak control efforts. The National Oceanic and Atmospheric Administration and the Centers for Disease Control and Prevention are two of the U.S. Federal Government agencies from which this study uses environmental data. Based on environmental data that describe changes in temperature, precipitation, vegetation, and other factors known to affect dengue incidence, many predictive models are constructed that use different machine learning methods to estimate weekly dengue cases. The first step involves preparing the data, which includes handling outliers and missing values to make sure the data is prepared for subsequent processing and the creation of an accurate forecasting model. In the second phase, multiple feature selection procedures are applied using various machine learning models and optimization techniques. During the third phase of the research, machine learning models like the Huber Regressor, Support Vector Machine, Gradient Boosting Regressor (GBR), and Support Vector Regressor (SVR) are compared with several optimization techniques for feature selection, such as Harmony Search and Genetic Algorithm. In the fourth stage, the model's performance is evaluated using Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) as assistance. Selecting an optimization strategy with the least number of errors, lowest price, biggest productivity, or maximum potential results is the goal. In a variety of industries, including engineering, science, management, mathematics, finance, and medicine, optimization is widely employed. An effective optimization method based on harmony search and an integrated genetic algorithm is introduced for input feature selection, and it shows an important improvement in the model's predictive accuracy. The predictive models with Huber Regressor as the foundation perform the best for optimization and also prediction.

Keywords: deep learning model, dengue fever, prediction, optimization

Procedia PDF Downloads 38

Authors: Ruchika Malhotra, Megha Khanna

Abstract:

The development of change prediction models can help the software practitioners in planning testing and inspection resources at early phases of software development. However, a major challenge faced during the training process of any classification model is the imbalanced nature of the software quality data. A data with very few minority outcome categories leads to inefficient learning process and a classification model developed from the imbalanced data generally does not predict these minority categories correctly. Thus, for a given dataset, a minority of classes may be change prone whereas a majority of classes may be non-change prone. This study explores various alternatives for adeptly handling the imbalanced software quality data using different sampling methods and effective MetaCost learners. The study also analyzes and justifies the use of different performance metrics while dealing with the imbalanced data. In order to empirically validate different alternatives, the study uses change data from three application packages of open-source Android data set and evaluates the performance of six different machine learning techniques. The results of the study indicate extensive improvement in the performance of the classification models when using resampling method and robust performance measures.

Keywords: change proneness, empirical validation, imbalanced learning, machine learning techniques, object-oriented metrics

Procedia PDF Downloads 401

Authors: Çiğdem Bakır, Mecit Yüzkat

Abstract:

With the increasing emphasis on water quality worldwide, the search for and expanding the market for new and intelligent monitoring systems has increased. The current method is the laboratory process, where samples are taken from bodies of water, and tests are carried out in laboratories. This method is time-consuming, a waste of manpower, and uneconomical. To solve this problem, we used machine learning methods to detect water pollution in our study. We created decision trees with the Orange3 software we used in our study and tried to determine all the factors that cause water pollution. An automatic prediction model based on water quality was developed by taking many model inputs such as water temperature, pH, transparency, conductivity, dissolved oxygen, and ammonia nitrogen with machine learning methods. The proposed approach consists of three stages: preprocessing of the data used, feature detection, and classification. We tried to determine the success of our study with different accuracy metrics and the results. We presented it comparatively. In addition, we achieved approximately 98% success with the decision tree.

Keywords: decision tree, water quality, water pollution, machine learning

Procedia PDF Downloads 69

Authors: Skyler Kim

Abstract:

An early diagnosis of leukemia has always been a challenge to doctors and hematologists. On a worldwide basis, it was reported that there were approximately 350,000 new cases in 2012, and diagnosing leukemia was time-consuming and inefficient because of an endemic shortage of flow cytometry equipment in current clinical practice. As the number of medical diagnosis tools increased and a large volume of high-quality data was produced, there was an urgent need for more advanced data analysis methods. One of these methods was the AI approach. This approach has become a major trend in recent years, and several research groups have been working on developing these diagnostic models. However, designing and implementing a leukemia diagnostic system in real clinical environments based on a deep learning approach with larger sets remains complex. Leukemia is a major hematological malignancy that results in mortality and morbidity throughout different ages. We decided to select acute lymphocytic leukemia to develop our diagnostic system since acute lymphocytic leukemia is the most common type of leukemia, accounting for 74% of all children diagnosed with leukemia. The results from this development work can be applied to all other types of leukemia. To develop our model, the Kaggle dataset was used, which consists of 15135 total images, 8491 of these are images of abnormal cells, and 5398 images are normal. In this paper, we design and implement a leukemia diagnostic system in a real clinical environment based on deep learning approaches with larger sets. The proposed diagnostic system has the function of detecting and classifying leukemia. Different from other AI approaches, we explore hybrid architectures to improve the current performance. First, we developed two independent convolutional neural network models: VGG19 and ResNet50. Then, using both VGG19 and ResNet50, we developed a hybrid deep learning architecture employing transfer learning techniques to extract features from each input image. In our approach, fusing the features from specific abstraction layers can be deemed as auxiliary features and lead to further improvement of the classification accuracy. In this approach, features extracted from the lower levels are combined into higher dimension feature maps to help improve the discriminative capability of intermediate features and also overcome the problem of network gradient vanishing or exploding. By comparing VGG19 and ResNet50 and the proposed hybrid model, we concluded that the hybrid model had a significant advantage in accuracy. The detailed results of each model’s performance and their pros and cons will be presented in the conference.

Keywords: acute lymphoblastic leukemia, hybrid model, leukemia diagnostic system, machine learning

Procedia PDF Downloads 175