Search results for: support vector machine classification

Authors: Israa Sh. Tawfic, Sema Koc Kayhan

Abstract:

In this paper, first, we propose least support orthogonal matching pursuit (LS-OMP) algorithm to improve the performance, of the OMP (orthogonal matching pursuit) algorithm. LS-OMP algorithm adaptively chooses optimum L (least part of support), at each iteration. This modification helps to reduce the computational complexity significantly and performs better than OMP algorithm. Second, we give the procedure for the invisible image watermarking in the presence of compressive sampling. The image reconstruction based on a set of watermarked measurements is performed using LS-OMP.

Keywords: compressed sensing, orthogonal matching pursuit, restricted isometry property, signal reconstruction, least support orthogonal matching pursuit, watermark

Procedia PDF Downloads 327

Authors: Guoliang Lu, Changhou Lu, Xueyong Li

Abstract:

In action recognition, previous studies have demonstrated the effectiveness of using multiple features to improve the recognition performance. We focus on two practical issues: i) most studies use a direct way of concatenating/accumulating multi features to evaluate the similarity between two actions. This way could be too strong since each kind of feature can include different dimensions, quantities, etc; ii) in many studies, the employed classification methods lack of a flexible and effective mechanism to add new feature(s) into classification. In this paper, we explore an unified scheme based on recently-proposed multi-dimensional dynamic time warping (MD-DTW). Experiments demonstrated the scheme's effectiveness of combining multi-feature and the flexibility of adding new feature(s) to increase the recognition performance. In addition, the explored scheme also provides us an open architecture for using new advanced classification methods in the future to enhance action recognition.

Keywords: action recognition, multi features, dynamic time warping, feature combination

Procedia PDF Downloads 425

Authors: Hamid Havasi, Mohamad Reza Gholami Dehbalaei, Hamed Khorami, Shahram Karimi, Hamdi Abdi

Abstract:

Doubly-fed induction generator (DFIG) equipped with a power converter is an efficient tool for converting mechanical energy of a variable speed system to a fixed-frequency electrical grid. Since electrical energy sources faces with production problems such as harmonics caused by nonlinear loads, so in this paper, compensation performance of DPC and FOC method on harmonics reduction of a DFIG wind turbine connected to a nonlinear load in MATLAB Simulink model has been simulated and effect of each method on nonlinear load harmonic elimination has been compared. Results of the two mentioned control methods shows the advantage of the FOC method on DPC method for harmonic compensation. Also, the fifth and seventh harmonic components of the network and THD greatly reduced.

Keywords: DFIG machine, energy conversion, nonlinear load, THD, DPC, FOC

Procedia PDF Downloads 574

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 49

Authors: Julianne Macmullen

Abstract:

Due to advances in technology and early detection and treatment of cancer, many cancer patients are surviving longer than five years post-diagnosis. Most cancer patients suffer from depression, anxiety, and post-traumatic stress disorder (PTSD) at some point during diagnosis, treatment, and survivorship. A subgroup of patients will continue to suffer from depression and PTSD and require early intervention. Support groups provide patients with the emotional and informational support they require while also giving survivors a sense of community, friendship, and purpose. This type of support is recognized by researchers to improve the quality of life while also decreasing depression and PTSD symptoms. The gaps in the literature include cultural diversity, minorities, and support groups involving cancer types other than breast cancer. Another gap in the literature includes the perceptions of cancer patients as well as longitudinal studies to determine the relationships between support groups and decreased depression and PTSD rates over time. Future research is required to fill the gaps in the literature mentioned previously. Future research is also needed to analyze the difference in age groups and different types of support groups such as professionally-led, peer-led, and online. Implications for practice involve providers assessing for the symptoms of depression and PTSD in order to offer prompt treatment and support services to those patients. In conclusion, social support by way of support groups improves the quality of life, gives survivors a sense of purpose to help others while also gaining the support they need, and reduces the rate of depressive episodes related to PTSD.

Keywords: cancer survivor, survivorship, post-traumatic stress disorder (PTSD), depression, support groups

Procedia PDF Downloads 159

Authors: D. López-Mancilla, J. M. Roblero-Villa

Abstract:

Since 1990, the research on chaotic dynamics has received considerable attention, particularly in light of potential applications of this phenomenon in secure communications. Data encryption using chaotic systems was reported in the 90's as a new approach for signal encoding that differs from the conventional methods that use numerical algorithms as the encryption key. The algorithms for image encryption have received a lot of attention because of the need to find security on image transmission in real time over the internet and wireless networks. Known algorithms for image encryption, like the standard of data encryption (DES), have the drawback of low level of efficiency when the image is large. The encrypting based on chaos proposes a new and efficient way to get a fast and highly secure image encryption. In this work, a user interface for image encryption and a novel and easiest way to encrypt images using chaos are presented. The main idea is to reshape any image into a n-dimensional vector and combine it with vector extracted from a chaotic system, in such a way that the vector image can be hidden within the chaotic vector. Once this is done, an array is formed with the original dimensions of the image and turns again. An analysis of the security of encryption from the images using statistical analysis is made and is used a stage of optimization for image encryption security and, at the same time, the image can be accurately recovered. The user interface uses the algorithms designed for the encryption of images, allowing you to read an image from the hard drive or another external device. The user interface, encrypt the image allowing three modes of encryption. These modes are given by three different chaotic systems that the user can choose. Once encrypted image, is possible to observe the safety analysis and save it on the hard disk. The main results of this study show that this simple method of encryption, using the optimization stage, allows an encryption security, competitive with complicated encryption methods used in other works. In addition, the user interface allows encrypting image with chaos, and to submit it through any public communication channel, including internet.

Keywords: image encryption, chaos, secure communications, user interface

Procedia PDF Downloads 471

Authors: Sri Widati, Ira Nurmala

Abstract:

The Se’i Tradition was considered to contribute highly to the high maternal mortality rate in South Amanuban, East Nusa Tenggara. This tradition is still preserved due to the social support that has influenced the decision to carry out the Se’i to pregnant women and post-partum women. The purpose of this study is to analyze this social support towards the Se’i Tradition on pregnant women in East Nusa Tenggara. This research was an explorative study with in-depth interviews, observations, and focus group discussions (FGD) in collecting the data. This study showed that emotional support towards Se’i was commonly given by families, specifically by the mother-in laws. Instrumental support was shown by the husbands and the traditional midwives who helped delivered the babies. Informational support was found on the pregnant women and their mother-in laws. Appraisal support was given by all the neighbors and relatives of the pregnant women by telling how comfortable it was to go through this tradition which eventually affected those women to carry it out themselves. The Se’i Tradition is still carried out and mostly supported by the relatives of the pregnant women. The first recommendation of this study is to suggest people to only follow the suggestions from the local health staff to give birth in the local health centers and not to do the tradition anymore. The second recommendation is to urge the government to give support in the form of transportation facilities for pregnant women to reach the local health staff.

Keywords: the Se’i tradition, social support, pregnant women, maternal mortality, post-partum women

Procedia PDF Downloads 519

Authors: I. Khutsishvili, G. Sirbiladze, B. Ghvaberidze

Abstract:

This work proposes a fuzzy methodology to support the investment decisions. While choosing among competitive investment projects, the methodology makes ranking of projects using the new aggregation OWA operator – AsPOWA, presented in the environment of possibility uncertainty. For numerical evaluation of the weighting vector associated with the AsPOWA operator the mathematical programming problem is constructed. On the basis of the AsPOWA operator the projects’ group ranking maximum criteria is constructed. The methodology also allows making the most profitable investments into several of the project using the method developed by the authors for discrete possibilistic bicriteria problems. The article provides an example of the investment decision-making that explains the work of the proposed methodology.

Keywords: expert evaluations, investment decision making, OWA operator, possibility uncertainty

Procedia PDF Downloads 541

Authors: Gor Muradyan

Abstract:

The paper is about friction and wear, including mechanisms, modeling, characterization, measurement and testing case in Bangladesh. Bangladesh is a country under development, A lot of people live here, approximately 145 million. The territory of this country is very small. Therefore buildings are very close to each other. As the pipe lines are very old, and people get almost dirty water, there are a lot of ongoing projects under ADB. In those projects the contractors using HDD machines (Horizontal Directional Drilling ) and grundoburst. These machines are working underground. As ground in Bangladesh is very sludge, machine can't work relevant because of big friction in the soil. When drilling works are finished machine is pulling the pipe underground. Very often the pulling of the pipes becomes very complicated because of the friction. Therefore long section of the pipe laying can’t be done because of a big friction. In that case, additional problems rise, as well as additional work must be done. As we mentioned above it is not possible to do big section of the pipe laying because of big friction in the soil, Because of this it is coming out that contractors must do more joints, more pressure test. It is always connected with additional expenditure and losing time. This machine can pull in 75 mm to 500 mm pipes connected with the soil condition. Length is possible till 500m related how much friction it will had on the puller. As less as much it can pull. Another machine grundoburst is not working at this soil condition at all. The machine is working with air compressor. This machine are using for the smaller diameter pipes, 20 mm to 63 mm. Most of the cases these machines are being used for the installing of the house connection pipes, for making service connection. To make a friction less contractors using bigger pulling had then the pipe. It is taking down the friction, But the problem of this machine is that it can't work at sludge. Because of mentioned reasons the friction has a big mining during this kind of works. There are a lot of ways to reduce the friction. In this paper we'll introduce the ways that we have researched during our practice in Bangladesh.

Keywords: Bangladesh, friction and wear, HDD machines, reducing friction

Procedia PDF Downloads 293

Authors: Yujiang Wu

Abstract:

As electrical machine (e-machine) power density re-querulents become more stringent in vehicle electrification, mounting a temperature sensor for e-machine stator windings becomes increasingly difficult. This can lead to higher manufacturing costs, complicated harnesses, and reduced reliability. In this paper, we propose a deep-learning method for predicting electric machine winding temperature, which can either replace the sensor entirely or serve as a backup to the existing sensor. We compare the performance of our method, the stateful long short-term memory networks (LSTM) with truncated backpropagation through time (TBTT), with that of linear regression, as well as stateless LSTM with/without residual connection. Our results demonstrate the strength of combining stateful LSTM and TBTT in tackling nonlinear time series prediction problems with long sequence lengths. Additionally, in industrial applications, high-temperature region prediction accuracy is more important because winding temperature sensing is typically used for derating machine power when the temperature is high. To evaluate the performance of our algorithm, we developed a temperature-stratified MSE. We propose a simple but effective data preprocessing trick to improve the high-temperature region prediction accuracy. Our experimental results demonstrate the effectiveness of our proposed method in accurately predicting winding temperature, particularly in high-temperature regions, while also reducing manufacturing costs and improving reliability.

Keywords: deep learning, electrical machine, functional safety, long short-term memory networks (LSTM), thermal management, time series prediction

Procedia PDF Downloads 80

Authors: Ehsan Tuzcuoğlu, Muhammed Emin Çoban, Songül Byraktar

Abstract:

One of the main targets of the washing machine is to remove any dirt and stains from the clothes. Especially, the stain removal is significantly important in the Far East market, where the high percentage of the consumers use the top load washing machines as washing appliance. They use all pretreatment methods (i.e. soaking, prewash, and heavy functions) to eliminate the stains from their clothes. Therefore, with this study it is aimed to study experimentally the stain removal performance of 3 different Top-Loading washing machines of the Far East market with 24 different types of stains which are mostly related to Far East culture. In the meanwhile, the mechanical damge on laundry is examined for each machine to see the mechanical effect of the related stain programs on the textile load of the machines. The test machines vary according to have a heater, moving part(s)on their impeller, and to be in different height/width ratio of the drum. The results indicate that decreasing the water level inside the washing machine might result in better soil removal as well as less textile damage. Beside this, the experimental results reveal that heating has the main effect on stain removal. Two-step (or delayed) heating and a lower amount of water can also be considered as the further parameters

Keywords: laundry, washing machine, top load washing machine, stain removal, textile damage, mechanical textile damage

Procedia PDF Downloads 110

Authors: Anukriti Kumar, Tanmay Singh, Dinesh Kumar Vishwakarma

Abstract:

Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.

Keywords: multiclass classification, convolution neural network, OpenCV

Procedia PDF Downloads 158

Authors: Ebtehal Aljedaani, Maha Aljohani

Abstract:

Privacy and security patterns are both important for developing software that protects users' data and privacy. Privacy patterns are designed to address common privacy problems, such as unauthorized data collection and disclosure. Security patterns are designed to protect software from attack and ensure reliability and trustworthiness. Using privacy and security patterns, software engineers can implement security and privacy by design principles, which means that security and privacy are considered throughout the software development process. These patterns are available to translate "security & privacy-by-design" into practical advice for software engineering. Previous research on privacy and security patterns has typically focused on one category of patterns at a time. This paper aims to bridge this gap by merging the two categories and identifying their similarities and differences. To do this, the authors conducted a systematic literature review of 25 research papers on privacy and security patterns. The papers were analysed based on the category of the pattern, the classification of the pattern, and the security requirements that the pattern addresses. This paper presents the results of a comprehensive review of privacy and security design patterns. The review is intended to help future IT designers understand the relationship between the two types of patterns and how to use them to design secure and privacy-preserving software. The paper provides a clear classification of privacy and security design patterns, along with examples of each type. The authors found that there is only one widely accepted classification of privacy design patterns, while there are several competing classifications of security design patterns. Three types of security design patterns were found to be the most commonly used.

Keywords: design patterns, security, privacy, classification of patterns, security patterns, privacy patterns

Procedia PDF Downloads 108

Authors: Benjamas Penboon, Zachary Zimmer, Aree Jampaklay

Abstract:

Cambodia is a country where labor migration has been consistently high. Coupled with advancing labor opportunities in urban areas, a function partly of globalization, this is resulting in massive migration out of rural areas. This is particularly true in Cambodia where there are high migration and a very large proportion of adult children living some distant from their parents. This paper explores characteristics associated with migrant providing support to parents in rural Cambodia. With reference to perspectives of family altruism and solidarity, this analysis particularly focusses on how a series of variables representing family integration and residential location associates with intergenerational monetary and instrumental support from migrants. The study hypothesizes that migrants are more likely to provide support when parents are in need, and there are no alternative means of support. Data come from The Rural Household Survey (N=3,713), part of the 2011 Cambodian Rural Urban Migration Project (CRUMP). Multilevel multinomial models indicate international migrants are likely to give money, while internal migrants are likely to provide both money and instrumental support, especially when migrants have no sibling and their parent in poor health status. In addition, employed migrants are two times providing monetary compared to those unemployed. Findings elucidate the decision to which and why support occurs more often when no other source of support exists and also depends on the ability to provide of migrants themselves.

Keywords: migration, left-behind parent, intergenerational relations, support, rural, Cambodia

Procedia PDF Downloads 151

Authors: Umamaheswari Shanmugam, Silvia Ronchi

Abstract:

Software, artificial intelligence, and machine learning can improve healthcare through innovative and advanced technologies that can use the large amount and variety of data generated during healthcare services every day; one of the significant advantages of these new technologies is the ability to get experience and knowledge from real-world use and to improve their performance continuously. Healthcare systems and institutions can significantly benefit because the use of advanced technologies improves the efficiency and efficacy of healthcare. Software-defined as a medical device, is stand-alone software that is intended to be used for patients for one or more of these specific medical intended uses: - diagnosis, prevention, monitoring, prediction, prognosis, treatment or alleviation of a disease, any other health conditions, replacing or modifying any part of a physiological or pathological process–manage the received information from in vitro specimens derived from the human samples (body) and without principal main action of its principal intended use by pharmacological, immunological or metabolic definition. Software qualified as medical devices must comply with the general safety and performance requirements applicable to medical devices. These requirements are necessary to ensure high performance and quality and protect patients' safety. The evolution and the continuous improvement of software used in healthcare must consider the increase in regulatory requirements, which are becoming more complex in each market. The gap between these advanced technologies and the new regulations is the biggest challenge for medical device manufacturers. Regulatory requirements can be considered a market barrier, as they can delay or obstacle the device's approval. Still, they are necessary to ensure performance, quality, and safety. At the same time, they can be a business opportunity if the manufacturer can define the appropriate regulatory strategy in advance. The abstract will provide an overview of the current regulatory framework, the evolution of the international requirements, and the standards applicable to medical device software in the potential market all over the world.

Keywords: artificial intelligence, machine learning, SaMD, regulatory, clinical evaluation, classification, international requirements, MDR, 510k, PMA, IMDRF, cyber security, health care systems

Procedia PDF Downloads 76

Authors: H. Yazdani, K. Ghorbanian

Abstract:

This paper deals with modeling and simulation of the plasma actuator with OpenFOAM. Plasma actuator is one of the newest devices in flow control techniques which can delay separation by inducing external momentum to the boundary layer of the flow. The effects of the plasma actuators on the external flow are incorporated into Navier-Stokes computations as a body force vector which is obtained as a product of the net charge density and the electric field. In order to compute this body force vector, the model solves two equations: One for the electric field due to the applied AC voltage at the electrodes and the other for the charge density representing the ionized air. The simulation result is compared to the experimental and typical values which confirms the validity of the modeling.

Keywords: active flow control, flow-field, OpenFOAM, plasma actuator

Procedia PDF Downloads 294

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 108

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 114

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 349

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 29

Authors: Manpreet Kaur

Abstract:

When legitimate credit card users are mistakenly labelled as fraudulent in numerous financial delated applications, there are numerous ethical problems. The innovative machine learning approach we have suggested in this research outperforms the current models and shows how to model a data set for credit card fraud detection while minimizing false positives. As a result, we advise using random forests as the best machine learning method for predicting and identifying credit card transaction fraud. The majority of victims of these fraudulent transactions were discovered to be credit card users over the age of 60, with a higher percentage of fraudulent transactions taking place between the specific hours.

Keywords: automated fraud detection, isolation forest method, local outlier factor, ML algorithm, credit card

Procedia PDF Downloads 90

Authors: Darwin Junnior Sabino Diego, Brando Burgos Guerrero, Diego Arroyo Villanueva

Abstract:

Additive manufacturing, commonly known as 3D printing, has revolutionized modern manufacturing by enabling the agile creation of complex objects. However, challenges persist in the consistency and quality of printed parts, particularly in their mechanical properties. This study focuses on addressing these challenges through the optimization of printing parameters in FDM technology, using Machine Learning techniques. Our aim is to improve the mechanical properties of printed objects by optimizing parameters such as speed, temperature, and orientation. We implement a methodology that combines experimental data collection with Machine Learning algorithms to identify relationships between printing parameters and mechanical properties. The results demonstrate the potential of this methodology to enhance the quality and consistency of 3D printed products, with significant applications across various industrial fields. This research not only advances understanding of additive manufacturing but also opens new avenues for practical implementation in industrial settings.

Keywords: 3D printing, additive manufacturing, machine learning, mechanical properties

Procedia PDF Downloads 30

Authors: Dhruba Das

Abstract:

In this paper, a method has been developed to construct the membership surfaces of row and column vectors and arithmetic operations of imprecise matrix. A matrix with imprecise elements would be called an imprecise matrix. The membership surface of imprecise vector has been already shown based on Randomness-Impreciseness Consistency Principle. The Randomness- Impreciseness Consistency Principle leads to defining a normal law of impreciseness using two different laws of randomness. In this paper, the author has shown row and column membership surfaces and arithmetic operations of imprecise matrix and demonstrated with the help of numerical example.

Keywords: imprecise number, imprecise vector, membership surface, imprecise matrix

Procedia PDF Downloads 374

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 161

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

Abstract:

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

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

Procedia PDF Downloads 29

Authors: Alaa Alrakaf, Sk. Md. Mizanur Rahman

Abstract:

Since the last two decades’ Arabic natural language processing (ANLP) has become increasingly much more important. One of the key issues related to ANLP is ambiguity. In Arabic language different pronunciation of one word may have a different meaning. Furthermore, ambiguity also has an impact on the effectiveness and efficiency of Machine Translation (MT). The issue of ambiguity has limited the usefulness and accuracy of the translation from Arabic to English. The lack of Arabic resources makes ambiguity problem more complicated. Additionally, the orthographic level of representation cannot specify the exact meaning of the word. This paper looked at the diacritics of Arabic language and used them to disambiguate a word. The proposed approach of word sense disambiguation used Diacritizer application to Diacritize Arabic text then found the most accurate sense of an ambiguous word using Naïve Bayes Classifier. Our Experimental study proves that using Arabic Diacritics with Naïve Bayes Classifier enhances the accuracy of choosing the appropriate sense by 23% and also decreases the ambiguity in machine translation.

Keywords: Arabic natural language processing, machine learning, machine translation, Naive bayes classifier, word sense disambiguation

Procedia PDF Downloads 340

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 339

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 232

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 237

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 192