Search results for: one-class classification method
19608 Evaluation of Gesture-Based Password: User Behavioral Features Using Machine Learning Algorithms
Authors: Lakshmidevi Sreeramareddy, Komalpreet Kaur, Nane Pothier
Abstract:
Graphical-based passwords have existed for decades. Their major advantage is that they are easier to remember than an alphanumeric password. However, their disadvantage (especially recognition-based passwords) is the smaller password space, making them more vulnerable to brute force attacks. Graphical passwords are also highly susceptible to the shoulder-surfing effect. The gesture-based password method that we developed is a grid-free, template-free method. In this study, we evaluated the gesture-based passwords for usability and vulnerability. The results of the study are significant. We developed a gesture-based password application for data collection. Two modes of data collection were used: Creation mode and Replication mode. In creation mode (Session 1), users were asked to create six different passwords and reenter each password five times. In replication mode, users saw a password image created by some other user for a fixed duration of time. Three different duration timers, such as 5 seconds (Session 2), 10 seconds (Session 3), and 15 seconds (Session 4), were used to mimic the shoulder-surfing attack. After the timer expired, the password image was removed, and users were asked to replicate the password. There were 74, 57, 50, and 44 users participated in Session 1, Session 2, Session 3, and Session 4 respectfully. In this study, the machine learning algorithms have been applied to determine whether the person is a genuine user or an imposter based on the password entered. Five different machine learning algorithms were deployed to compare the performance in user authentication: namely, Decision Trees, Linear Discriminant Analysis, Naive Bayes Classifier, Support Vector Machines (SVMs) with Gaussian Radial Basis Kernel function, and K-Nearest Neighbor. Gesture-based password features vary from one entry to the next. It is difficult to distinguish between a creator and an intruder for authentication. For each password entered by the user, four features were extracted: password score, password length, password speed, and password size. All four features were normalized before being fed to a classifier. Three different classifiers were trained using data from all four sessions. Classifiers A, B, and C were trained and tested using data from the password creation session and the password replication with a timer of 5 seconds, 10 seconds, and 15 seconds, respectively. The classification accuracies for Classifier A using five ML algorithms are 72.5%, 71.3%, 71.9%, 74.4%, and 72.9%, respectively. The classification accuracies for Classifier B using five ML algorithms are 69.7%, 67.9%, 70.2%, 73.8%, and 71.2%, respectively. The classification accuracies for Classifier C using five ML algorithms are 68.1%, 64.9%, 68.4%, 71.5%, and 69.8%, respectively. SVMs with Gaussian Radial Basis Kernel outperform other ML algorithms for gesture-based password authentication. Results confirm that the shorter the duration of the shoulder-surfing attack, the higher the authentication accuracy. In conclusion, behavioral features extracted from the gesture-based passwords lead to less vulnerable user authentication.Keywords: authentication, gesture-based passwords, machine learning algorithms, shoulder-surfing attacks, usability
Procedia PDF Downloads 9519607 Improving University Operations with Data Mining: Predicting Student Performance
Authors: Mladen Dragičević, Mirjana Pejić Bach, Vanja Šimičević
Abstract:
The purpose of this paper is to develop models that would enable predicting student success. These models could improve allocation of students among colleges and optimize the newly introduced model of government subsidies for higher education. For the purpose of collecting data, an anonymous survey was carried out in the last year of undergraduate degree student population using random sampling method. Decision trees were created of which two have been chosen that were most successful in predicting student success based on two criteria: Grade Point Average (GPA) and time that a student needs to finish the undergraduate program (time-to-degree). Decision trees have been shown as a good method of classification student success and they could be even more improved by increasing survey sample and developing specialized decision trees for each type of college. These types of methods have a big potential for use in decision support systems.Keywords: data mining, knowledge discovery in databases, prediction models, student success
Procedia PDF Downloads 40319606 A Machine Learning Approach for Detecting and Locating Hardware Trojans
Authors: Kaiwen Zheng, Wanting Zhou, Nan Tang, Lei Li, Yuanhang He
Abstract:
The integrated circuit industry has become a cornerstone of the information society, finding widespread application in areas such as industry, communication, medicine, and aerospace. However, with the increasing complexity of integrated circuits, Hardware Trojans (HTs) implanted by attackers have become a significant threat to their security. In this paper, we proposed a hardware trojan detection method for large-scale circuits. As HTs introduce physical characteristic changes such as structure, area, and power consumption as additional redundant circuits, we proposed a machine-learning-based hardware trojan detection method based on the physical characteristics of gate-level netlists. This method transforms the hardware trojan detection problem into a machine-learning binary classification problem based on physical characteristics, greatly improving detection speed. To address the problem of imbalanced data, where the number of pure circuit samples is far less than that of HTs circuit samples, we used the SMOTETomek algorithm to expand the dataset and further improve the performance of the classifier. We used three machine learning algorithms, K-Nearest Neighbors, Random Forest, and Support Vector Machine, to train and validate benchmark circuits on Trust-Hub, and all achieved good results. In our case studies based on AES encryption circuits provided by trust-hub, the test results showed the effectiveness of the proposed method. To further validate the method’s effectiveness for detecting variant HTs, we designed variant HTs using open-source HTs. The proposed method can guarantee robust detection accuracy in the millisecond level detection time for IC, and FPGA design flows and has good detection performance for library variant HTs.Keywords: hardware trojans, physical properties, machine learning, hardware security
Procedia PDF Downloads 13919605 Study on Optimization Design of Pressure Hull for Underwater Vehicle
Authors: Qasim Idrees, Gao Liangtian, Liu Bo, Miao Yiran
Abstract:
In order to improve the efficiency and accuracy of the pressure hull structure, optimization of underwater vehicle based on response surface methodology, a method for optimizing the design of pressure hull structure was studied. To determine the pressure shell of five dimensions as a design variable, the application of thin shell theory and the Chinese Classification Society (CCS) specification was carried on the preliminary design. In order to optimize variables of the feasible region, different methods were studied and implemented such as Opt LHD method (to determine the design test sample points in the feasible domain space), parametric ABAQUS solution for each sample point response, and the two-order polynomial response for the surface model of the limit load of structures. Based on the ultimate load of the structure and the quality of the shell, the two-generation genetic algorithm was used to solve the response surface, and the Pareto optimal solution set was obtained. The final optimization result was 41.68% higher than that of the initial design, and the shell quality was reduced by about 27.26%. The parametric method can ensure the accuracy of the test and improve the efficiency of optimization.Keywords: parameterization, response surface, structure optimization, pressure hull
Procedia PDF Downloads 22919604 Comprehensive Feature Extraction for Optimized Condition Assessment of Fuel Pumps
Authors: Ugochukwu Ejike Akpudo, Jank-Wook Hur
Abstract:
The increasing demand for improved productivity, maintainability, and reliability has prompted rapidly increasing research studies on the emerging condition-based maintenance concept- Prognostics and health management (PHM). Varieties of fuel pumps serve critical functions in several hydraulic systems; hence, their failure can have daunting effects on productivity, safety, etc. The need for condition monitoring and assessment of these pumps cannot be overemphasized, and this has led to the uproar in research studies on standard feature extraction techniques for optimized condition assessment of fuel pumps. By extracting time-based, frequency-based and the more robust time-frequency based features from these vibrational signals, a more comprehensive feature assessment (and selection) can be achieved for a more accurate and reliable condition assessment of these pumps. With the aid of emerging deep classification and regression algorithms like the locally linear embedding (LLE), we propose a method for comprehensive condition assessment of electromagnetic fuel pumps (EMFPs). Results show that the LLE as a comprehensive feature extraction technique yields better feature fusion/dimensionality reduction results for condition assessment of EMFPs against the use of single features. Also, unlike other feature fusion techniques, its capabilities as a fault classification technique were explored, and the results show an acceptable accuracy level using standard performance metrics for evaluation.Keywords: electromagnetic fuel pumps, comprehensive feature extraction, condition assessment, locally linear embedding, feature fusion
Procedia PDF Downloads 11119603 A Pattern Recognition Neural Network Model for Detection and Classification of SQL Injection Attacks
Authors: Naghmeh Moradpoor Sheykhkanloo
Abstract:
Structured Query Language Injection (SQLI) attack is a code injection technique in which malicious SQL statements are inserted into a given SQL database by simply using a web browser. Losing data, disclosing confidential information or even changing the value of data are the severe damages that SQLI attack can cause on a given database. SQLI attack has also been rated as the number-one attack among top ten web application threats on Open Web Application Security Project (OWASP). OWASP is an open community dedicated to enabling organisations to consider, develop, obtain, function, and preserve applications that can be trusted. In this paper, we propose an effective pattern recognition neural network model for detection and classification of SQLI attacks. The proposed model is built from three main elements of: a Uniform Resource Locator (URL) generator in order to generate thousands of malicious and benign URLs, a URL classifier in order to: 1) classify each generated URL to either a benign URL or a malicious URL and 2) classify the malicious URLs into different SQLI attack categories, and an NN model in order to: 1) detect either a given URL is a malicious URL or a benign URL and 2) identify the type of SQLI attack for each malicious URL. The model is first trained and then evaluated by employing thousands of benign and malicious URLs. The results of the experiments are presented in order to demonstrate the effectiveness of the proposed approach.Keywords: neural networks, pattern recognition, SQL injection attacks, SQL injection attack classification, SQL injection attack detection
Procedia PDF Downloads 45819602 Audio Information Retrieval in Mobile Environment with Fast Audio Classifier
Authors: Bruno T. Gomes, José A. Menezes, Giordano Cabral
Abstract:
With the popularity of smartphones, mobile apps emerge to meet the diverse needs, however the resources at the disposal are limited, either by the hardware, due to the low computing power, or the software, that does not have the same robustness of desktop environment. For example, in automatic audio classification (AC) tasks, musical information retrieval (MIR) subarea, is required a fast processing and a good success rate. However the mobile platform has limited computing power and the best AC tools are only available for desktop. To solve these problems the fast classifier suits, to mobile environments, the most widespread MIR technologies, seeking a balance in terms of speed and robustness. At the end we found that it is possible to enjoy the best of MIR for mobile environments. This paper presents the results obtained and the difficulties encountered.Keywords: audio classification, audio extraction, environment mobile, musical information retrieval
Procedia PDF Downloads 53919601 Development of a Classification Model for Value-Added and Non-Value-Added Operations in Retail Logistics: Insights from a Supermarket Case Study
Authors: Helena Macedo, Larissa Tomaz, Levi Guimarães, Luís Cerqueira-Pinto, José Dinis-Carvalho
Abstract:
In the context of retail logistics, the pursuit of operational efficiency and cost optimization involves a rigorous distinction between value-added and non-value-added activities. In today's competitive market, optimizing efficiency and reducing operational costs are paramount for retail businesses. This research paper focuses on the development of a classification model adapted to the retail sector, specifically examining internal logistics processes. Based on a comprehensive analysis conducted in a retail supermarket located in the north of Portugal, which covered various aspects of internal retail logistics, this study questions the concept of value and the definition of wastes traditionally applied in a manufacturing context and proposes a new way to assess activities in the context of internal logistics. This study combines quantitative data analysis with qualitative evaluations. The proposed classification model offers a systematic approach to categorize operations within the retail logistics chain, providing actionable insights for decision-makers to streamline processes, enhance productivity, and allocate resources more effectively. This model contributes not only to academic discourse but also serves as a practical tool for retail businesses, aiding in the enhancement of their internal logistics dynamics.Keywords: lean retail, lean logisitcs, retail logistics, value-added and non-value-added
Procedia PDF Downloads 5019600 Using Closed Frequent Itemsets for Hierarchical Document Clustering
Authors: Cheng-Jhe Lee, Chiun-Chieh Hsu
Abstract:
Due to the rapid development of the Internet and the increased availability of digital documents, the excessive information on the Internet has led to information overflow problem. In order to solve these problems for effective information retrieval, document clustering in text mining becomes a popular research topic. Clustering is the unsupervised classification of data items into groups without the need of training data. Many conventional document clustering methods perform inefficiently for large document collections because they were originally designed for relational database. Therefore they are impractical in real-world document clustering and require special handling for high dimensionality and high volume. We propose the FIHC (Frequent Itemset-based Hierarchical Clustering) method, which is a hierarchical clustering method developed for document clustering, where the intuition of FIHC is that there exist some common words for each cluster. FIHC uses such words to cluster documents and builds hierarchical topic tree. In this paper, we combine FIHC algorithm with ontology to solve the semantic problem and mine the meaning behind the words in documents. Furthermore, we use the closed frequent itemsets instead of only use frequent itemsets, which increases efficiency and scalability. The experimental results show that our method is more accurate than those of well-known document clustering algorithms.Keywords: FIHC, documents clustering, ontology, closed frequent itemset
Procedia PDF Downloads 38919599 Maxillofacial Trauma: A Case of Diacapitular Condylar Fracture
Authors: Krishna Prasad Regmi, Jun-Bo Tu, Cheng-Qun Hou, Li-Feng Li
Abstract:
Maxillofacial trauma in a pediatric group of patients is particularly challenging, as these patients have significant differences from adults as far as the facial skeleton is concerned. Mandibular condylar fractures are common presentations to hospitals across the globe and remain the most important cause of temporomandibular joint (TMJ) ankylosis. The etiology and epidemiology of pediatric trauma involving the diacapitular condylar fractures (DFs) have been reported in a large series of patients. Nevertheless, little is known about treatment protocols for DFs in children. Accordingly, the treatment modalities for the management of pediatric fractures also differ. We suggest following the PDA and intracapsular ABC classification of condylar fracture to increase the overall postoperative satisfaction level that bypasses the change of subjective feelings of patients’ from preoperative to the postoperative condition. At the same time, use of 3-D technology and surgical navigation may also increase treatment accuracy.Keywords: maxillofacial trauma, diacapitular fracture, condylar fracture, PDA classification
Procedia PDF Downloads 26619598 [Keynote Talk]: sEMG Interface Design for Locomotion Identification
Authors: Rohit Gupta, Ravinder Agarwal
Abstract:
Surface electromyographic (sEMG) signal has the potential to identify the human activities and intention. This potential is further exploited to control the artificial limbs using the sEMG signal from residual limbs of amputees. The paper deals with the development of multichannel cost efficient sEMG signal interface for research application, along with evaluation of proposed class dependent statistical approach of the feature selection method. The sEMG signal acquisition interface was developed using ADS1298 of Texas Instruments, which is a front-end interface integrated circuit for ECG application. Further, the sEMG signal is recorded from two lower limb muscles for three locomotions namely: Plane Walk (PW), Stair Ascending (SA), Stair Descending (SD). A class dependent statistical approach is proposed for feature selection and also its performance is compared with 12 preexisting feature vectors. To make the study more extensive, performance of five different types of classifiers are compared. The outcome of the current piece of work proves the suitability of the proposed feature selection algorithm for locomotion recognition, as compared to other existing feature vectors. The SVM Classifier is found as the outperformed classifier among compared classifiers with an average recognition accuracy of 97.40%. Feature vector selection emerges as the most dominant factor affecting the classification performance as it holds 51.51% of the total variance in classification accuracy. The results demonstrate the potentials of the developed sEMG signal acquisition interface along with the proposed feature selection algorithm.Keywords: classifiers, feature selection, locomotion, sEMG
Procedia PDF Downloads 28819597 Heritage Tree Expert Assessment and Classification: Malaysian Perspective
Authors: B.-Y.-S. Lau, Y.-C.-T. Jonathan, M.-S. Alias
Abstract:
Heritage trees are natural large, individual trees with exceptionally value due to association with age or event or distinguished people. In Malaysia, there is an abundance of tropical heritage trees throughout the country. It is essential to set up a repository of heritage trees to prevent valuable trees from being cut down. In this cross domain study, a web-based online expert system namely the Heritage Tree Expert Assessment and Classification (HTEAC) is developed and deployed for public to nominate potential heritage trees. Based on the nomination, tree care experts or arborists would evaluate and verify the nominated trees as heritage trees. The expert system automatically rates the approved heritage trees according to pre-defined grades via Delphi technique. Features and usability test of the expert system are presented. Preliminary result is promising for the system to be used as a full scale public system.Keywords: arboriculture, Delphi, expert system, heritage tree, urban forestry
Procedia PDF Downloads 30519596 Automatic Detection and Classification of Diabetic Retinopathy Using Retinal Fundus Images
Authors: A. Biran, P. Sobhe Bidari, A. Almazroe, V. Lakshminarayanan, K. Raahemifar
Abstract:
Diabetic Retinopathy (DR) is a severe retinal disease which is caused by diabetes mellitus. It leads to blindness when it progress to proliferative level. Early indications of DR are the appearance of microaneurysms, hemorrhages and hard exudates. In this paper, an automatic algorithm for detection of DR has been proposed. The algorithm is based on combination of several image processing techniques including Circular Hough Transform (CHT), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gabor filter and thresholding. Also, Support Vector Machine (SVM) Classifier is used to classify retinal images to normal or abnormal cases including non-proliferative or proliferative DR. The proposed method has been tested on images selected from Structured Analysis of the Retinal (STARE) database using MATLAB code. The method is perfectly able to detect DR. The sensitivity specificity and accuracy of this approach are 90%, 87.5%, and 91.4% respectively.Keywords: diabetic retinopathy, fundus images, STARE, Gabor filter, support vector machine
Procedia PDF Downloads 28719595 Time Series Regression with Meta-Clusters
Authors: Monika Chuchro
Abstract:
This paper presents a preliminary attempt to apply classification of time series using meta-clusters in order to improve the quality of regression models. In this case, clustering was performed as a method to obtain a subgroups of time series data with normal distribution from inflow into waste water treatment plant data which Composed of several groups differing by mean value. Two simple algorithms: K-mean and EM were chosen as a clustering method. The rand index was used to measure the similarity. After simple meta-clustering, regression model was performed for each subgroups. The final model was a sum of subgroups models. The quality of obtained model was compared with the regression model made using the same explanatory variables but with no clustering of data. Results were compared by determination coefficient (R2), measure of prediction accuracy mean absolute percentage error (MAPE) and comparison on linear chart. Preliminary results allows to foresee the potential of the presented technique.Keywords: clustering, data analysis, data mining, predictive models
Procedia PDF Downloads 46219594 Non-Targeted Adversarial Image Classification Attack-Region Modification Methods
Authors: Bandar Alahmadi, Lethia Jackson
Abstract:
Machine Learning model is used today in many real-life applications. The safety and security of such model is important, so the results of the model are as accurate as possible. One challenge of machine learning model security is the adversarial examples attack. Adversarial examples are designed by the attacker to cause the machine learning model to misclassify the input. We propose a method to generate adversarial examples to attack image classifiers. We are modifying the successfully classified images, so a classifier misclassifies them after the modification. In our method, we do not update the whole image, but instead we detect the important region, modify it, place it back to the original image, and then run it through a classifier. The algorithm modifies the detected region using two methods. First, it will add abstract image matrix on back of the detected image matrix. Then, it will perform a rotation attack to rotate the detected region around its axes, and embed the trace of image in image background. Finally, the attacked region is placed in its original position, from where it was removed, and a smoothing filter is applied to smooth the background with foreground. We test our method in cascade classifier, and the algorithm is efficient, the classifier confident has dropped to almost zero. We also try it in CNN (Convolutional neural network) with higher setting and the algorithm was successfully worked.Keywords: adversarial examples, attack, computer vision, image processing
Procedia PDF Downloads 33319593 Human Gait Recognition Using Moment with Fuzzy
Authors: Jyoti Bharti, Navneet Manjhi, M. K.Gupta, Bimi Jain
Abstract:
A reliable gait features are required to extract the gait sequences from an images. In this paper suggested a simple method for gait identification which is based on moments. Moment values are extracted on different number of frames of gray scale and silhouette images of CASIA database. These moment values are considered as feature values. Fuzzy logic and nearest neighbour classifier are used for classification. Both achieved higher recognition.Keywords: gait, fuzzy logic, nearest neighbour, recognition rate, moments
Procedia PDF Downloads 75219592 Adapted Intersection over Union: A Generalized Metric for Evaluating Unsupervised Classification Models
Authors: Prajwal Prakash Vasisht, Sharath Rajamurthy, Nishanth Dara
Abstract:
In a supervised machine learning approach, metrics such as precision, accuracy, and coverage can be calculated using ground truth labels to help in model tuning, evaluation, and selection. In an unsupervised setting, however, where the data has no ground truth, there are few interpretable metrics that can guide us to do the same. Our approach creates a framework to adapt the Intersection over Union metric, referred to as Adapted IoU, usually used to evaluate supervised learning models, into the unsupervised domain, which solves the problem by factoring in subject matter expertise and intuition about the ideal output from the model. This metric essentially provides a scale that allows us to compare the performance across numerous unsupervised models or tune hyper-parameters and compare different versions of the same model.Keywords: general metric, unsupervised learning, classification, intersection over union
Procedia PDF Downloads 3719591 Supervised Learning for Cyber Threat Intelligence
Authors: Jihen Bennaceur, Wissem Zouaghi, Ali Mabrouk
Abstract:
The major aim of cyber threat intelligence (CTI) is to provide sophisticated knowledge about cybersecurity threats to ensure internal and external safeguards against modern cyberattacks. Inaccurate, incomplete, outdated, and invaluable threat intelligence is the main problem. Therefore, data analysis based on AI algorithms is one of the emergent solutions to overcome the threat of information-sharing issues. In this paper, we propose a supervised machine learning-based algorithm to improve threat information sharing by providing a sophisticated classification of cyber threats and data. Extensive simulations investigate the accuracy, precision, recall, f1-score, and support overall to validate the designed algorithm and to compare it with several supervised machine learning algorithms.Keywords: threat information sharing, supervised learning, data classification, performance evaluation
Procedia PDF Downloads 14219590 Low Cost Webcam Camera and GNSS Integration for Updating Home Data Using AI Principles
Authors: Mohkammad Nur Cahyadi, Hepi Hapsari Handayani, Agus Budi Raharjo, Ronny Mardianto, Daud Wahyu Imani, Arizal Bawazir, Luki Adi Triawan
Abstract:
PDAM (local water company) determines customer charges by considering the customer's building or house. Charges determination significantly affects PDAM income and customer costs because the PDAM applies a subsidy policy for customers classified as small households. Periodic updates are needed so that pricing is in line with the target. A thorough customer survey in Surabaya is needed to update customer building data. However, the survey that has been carried out so far has been by deploying officers to conduct one-by-one surveys for each PDAM customer. Surveys with this method require a lot of effort and cost. For this reason, this research offers a technology called moblie mapping, a mapping method that is more efficient in terms of time and cost. The use of this tool is also quite simple, where the device will be installed in the car so that it can record the surrounding buildings while the car is running. Mobile mapping technology generally uses lidar sensors equipped with GNSS, but this technology requires high costs. In overcoming this problem, this research develops low-cost mobile mapping technology using a webcam camera sensor added to the GNSS and IMU sensors. The camera used has specifications of 3MP with a resolution of 720 and a diagonal field of view of 78⁰. The principle of this invention is to integrate four camera sensors, a GNSS webcam, and GPS to acquire photo data, which is equipped with location data (latitude, longitude) and IMU (roll, pitch, yaw). This device is also equipped with a tripod and a vacuum cleaner to attach to the car's roof so it doesn't fall off while running. The output data from this technology will be analyzed with artificial intelligence to reduce similar data (Cosine Similarity) and then classify building types. Data reduction is used to eliminate similar data and maintain the image that displays the complete house so that it can be processed for later classification of buildings. The AI method used is transfer learning by utilizing a trained model named VGG-16. From the analysis of similarity data, it was found that the data reduction reached 50%. Then georeferencing is done using the Google Maps API to get address information according to the coordinates in the data. After that, geographic join is done to link survey data with customer data already owned by PDAM Surya Sembada Surabaya.Keywords: mobile mapping, GNSS, IMU, similarity, classification
Procedia PDF Downloads 7619589 Using Scale Invariant Feature Transform Features to Recognize Characters in Natural Scene Images
Authors: Belaynesh Chekol, Numan Çelebi
Abstract:
The main purpose of this work is to recognize individual characters extracted from natural scene images using scale invariant feature transform (SIFT) features as an input to K-nearest neighbor (KNN); a classification learner algorithm. For this task, 1,068 and 78 images of English alphabet characters taken from Chars74k data set is used to train and test the classifier respectively. For each character image, We have generated describing features by using SIFT algorithm. This set of features is fed to the learner so that it can recognize and label new images of English characters. Two types of KNN (fine KNN and weighted KNN) were trained and the resulted classification accuracy is 56.9% and 56.5% respectively. The training time taken was the same for both fine and weighted KNN.Keywords: character recognition, KNN, natural scene image, SIFT
Procedia PDF Downloads 27519588 Determination of the Botanical Origin of Honey by the Artificial Neural Network Processing of PARAFAC Scores of Fluorescence Data
Authors: Lea Lenhardt, Ivana Zeković, Tatjana Dramićanin, Miroslav D. Dramićanin
Abstract:
Fluorescence spectroscopy coupled with parallel factor analysis (PARAFAC) and artificial neural networks (ANN) were used for characterization and classification of honey. Excitation emission spectra were obtained for 95 honey samples of different botanical origin (acacia, sunflower, linden, meadow, and fake honey) by recording emission from 270 to 640 nm with excitation in the range of 240-500 nm. Fluorescence spectra were described with a six-component PARAFAC model, and PARAFAC scores were further processed with two types of ANN’s (feed-forward network and self-organizing maps) to obtain algorithms for classification of honey on the basis of their botanical origin. Both ANN’s detected fake honey samples with 100% sensitivity and specificity.Keywords: honey, fluorescence, PARAFAC, artificial neural networks
Procedia PDF Downloads 94819587 Classification of Barley Varieties by Artificial Neural Networks
Authors: Alper Taner, Yesim Benal Oztekin, Huseyin Duran
Abstract:
In this study, an Artificial Neural Network (ANN) was developed in order to classify barley varieties. For this purpose, physical properties of barley varieties were determined and ANN techniques were used. The physical properties of 8 barley varieties grown in Turkey, namely thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and colour parameters of grain, were determined and it was found that these properties were statistically significant with respect to varieties. As ANN model, three models, N-l, N-2 and N-3 were constructed. The performances of these models were compared. It was determined that the best-fit model was N-1. In the N-1 model, the structure of the model was designed to be 11 input layers, 2 hidden layers and 1 output layer. Thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and colour parameters of grain were used as input parameter; and varieties as output parameter. R2, Root Mean Square Error and Mean Error for the N-l model were found as 99.99%, 0.00074 and 0.009%, respectively. All results obtained by the N-l model were observed to have been quite consistent with real data. By this model, it would be possible to construct automation systems for classification and cleaning in flourmills.Keywords: physical properties, artificial neural networks, barley, classification
Procedia PDF Downloads 17519586 Speech Emotion Recognition: A DNN and LSTM Comparison in Single and Multiple Feature Application
Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior
Abstract:
Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks
Procedia PDF Downloads 15819585 Traffic Light Detection Using Image Segmentation
Authors: Vaishnavi Shivde, Shrishti Sinha, Trapti Mishra
Abstract:
Traffic light detection from a moving vehicle is an important technology both for driver safety assistance functions as well as for autonomous driving in the city. This paper proposed a deep-learning-based traffic light recognition method that consists of a pixel-wise image segmentation technique and a fully convolutional network i.e., UNET architecture. This paper has used a method for detecting the position and recognizing the state of the traffic lights in video sequences is presented and evaluated using Traffic Light Dataset which contains masked traffic light image data. The first stage is the detection, which is accomplished through image processing (image segmentation) techniques such as image cropping, color transformation, segmentation of possible traffic lights. The second stage is the recognition, which means identifying the color of the traffic light or knowing the state of traffic light which is achieved by using a Convolutional Neural Network (UNET architecture).Keywords: traffic light detection, image segmentation, machine learning, classification, convolutional neural networks
Procedia PDF Downloads 16519584 Safeguarding Product Quality through Pre-Qualification of Material Manufacturers: A Ship and Offshore Classification Society's Perspective
Authors: Sastry Y. Kandukuri, Isak Andersen
Abstract:
Despite recent advances in the manufacturing sector, quality issues remain a frequent occurrence, and can result in fatal accidents, equipment downtime, and loss of life. Adequate quality is of high importance in high-risk industries such as sea-going vessels and offshore installations in which third party quality assurance and product control play an important essential role in ensuring manufacturing quality of critical components. Classification societies play a vital role in mitigating risk in these industries by making sure that all the stakeholders i.e. manufacturers, builders, and end users are provided with adequate rules and standards that effectively ensures components produced at a high level of quality based on the area of application and risk of its failure. Quality issues have also been linked to the lack of competence or negligence of stakeholders in supply value chain. However, continued actions and regulatory reforms through modernization of rules and requirements has provided additional tools for purchasers and manufacturers to confront these issues. Included among these tools are updated ‘approval of manufacturer class programs’ aimed at developing and implementing a set of standardized manufacturing quality metrics for use by the manufacturer and verified by the classification society. The establishment and collection of manufacturing and testing requirements described in these programs could provide various stakeholders – from industry to vessel owners – with greater insight into the state of quality at a given manufacturing facility, and allow stakeholders to anticipate better and address quality issues while simultaneously reducing unnecessary failures that are costly to the industry. The publication introduces, explains and discusses critical manufacturing and testing requirements set in a leading class society’s approval of manufacturer regime and its rationale and some case studies.Keywords: classification society, manufacturing, materials processing, materials testing, quality control
Procedia PDF Downloads 34819583 Factors Associated with Weight Loss Maintenance after an Intervention Program
Authors: Filipa Cortez, Vanessa Pereira
Abstract:
Introduction: The main challenge of obesity treatment is long-term weight loss maintenance. The 3 phases method is a weight loss program that combines a low carb and moderately high-protein diet, food supplements and a weekly one-to-one consultation with a certified nutritionist. Sustained weight control is the ultimate goal of phase 3. Success criterion was the minimum loss of 10% of initial weight and its maintenance after 12 months. Objective: The aim of this study was to identify factors associated with successful weight loss maintenance after 12 months at the end of 3 phases method. Methods: The study included 199 subjects that achieved their weight loss goal (phase 3). Weight and body mass index (BMI) were obtained at the baseline and every week until the end of the program. Therapeutic adherence was measured weekly on a Likert scale from 1 to 5. Subjects were considered in compliance with nutritional recommendation and supplementation when their classification was ≥ 4. After 12 months of the method, the current weight and number of previous weight-loss attempts were collected by telephone interview. The statistical significance was assumed at p-values < 0.05. Statistical analyses were performed using SPSS TM software v.21. Results: 65.3% of subjects met the success criterion. The factors which displayed a significant weight loss maintenance prediction were: greater initial percentage weight loss (OR=1.44) during the weight loss intervention and a higher number of consultations in phase 3 (OR=1.10). Conclusion: These findings suggest that the percentage weight loss during the weight loss intervention and the number of consultations in phase 3 may facilitate maintenance of weight loss after the 3 phases method.Keywords: obesity, weight maintenance, low-carbohydrate diet, dietary supplements
Procedia PDF Downloads 14519582 Hybrid Approach for Software Defect Prediction Using Machine Learning with Optimization Technique
Authors: C. Manjula, Lilly Florence
Abstract:
Software technology is developing rapidly which leads to the growth of various industries. Now-a-days, software-based applications have been adopted widely for business purposes. For any software industry, development of reliable software is becoming a challenging task because a faulty software module may be harmful for the growth of industry and business. Hence there is a need to develop techniques which can be used for early prediction of software defects. Due to complexities in manual prediction, automated software defect prediction techniques have been introduced. These techniques are based on the pattern learning from the previous software versions and finding the defects in the current version. These techniques have attracted researchers due to their significant impact on industrial growth by identifying the bugs in software. Based on this, several researches have been carried out but achieving desirable defect prediction performance is still a challenging task. To address this issue, here we present a machine learning based hybrid technique for software defect prediction. First of all, Genetic Algorithm (GA) is presented where an improved fitness function is used for better optimization of features in data sets. Later, these features are processed through Decision Tree (DT) classification model. Finally, an experimental study is presented where results from the proposed GA-DT based hybrid approach is compared with those from the DT classification technique. The results show that the proposed hybrid approach achieves better classification accuracy.Keywords: decision tree, genetic algorithm, machine learning, software defect prediction
Procedia PDF Downloads 32619581 Identity Verification Using k-NN Classifiers and Autistic Genetic Data
Authors: Fuad M. Alkoot
Abstract:
DNA data have been used in forensics for decades. However, current research looks at using the DNA as a biometric identity verification modality. The goal is to improve the speed of identification. We aim at using gene data that was initially used for autism detection to find if and how accurate is this data for identification applications. Mainly our goal is to find if our data preprocessing technique yields data useful as a biometric identification tool. We experiment with using the nearest neighbor classifier to identify subjects. Results show that optimal classification rate is achieved when the test set is corrupted by normally distributed noise with zero mean and standard deviation of 1. The classification rate is close to optimal at higher noise standard deviation reaching 3. This shows that the data can be used for identity verification with high accuracy using a simple classifier such as the k-nearest neighbor (k-NN).Keywords: biometrics, genetic data, identity verification, k nearest neighbor
Procedia PDF Downloads 24819580 Time-Series Load Data Analysis for User Power Profiling
Authors: Mahdi Daghmhehci Firoozjaei, Minchang Kim, Dima Alhadidi
Abstract:
In this paper, we present a power profiling model for smart grid consumers based on real time load data acquired smart meters. It profiles consumers’ power consumption behaviour using the dynamic time warping (DTW) clustering algorithm. Due to the invariability of signal warping of this algorithm, time-disordered load data can be profiled and consumption features be extracted. Two load types are defined and the related load patterns are extracted for classifying consumption behaviour by DTW. The classification methodology is discussed in detail. To evaluate the performance of the method, we analyze the time-series load data measured by a smart meter in a real case. The results verify the effectiveness of the proposed profiling method with 90.91% true positive rate for load type clustering in the best case.Keywords: power profiling, user privacy, dynamic time warping, smart grid
Procedia PDF Downloads 14219579 Semantic Indexing Improvement for Textual Documents: Contribution of Classification by Fuzzy Association Rules
Authors: Mohsen Maraoui
Abstract:
In the aim of natural language processing applications improvement, such as information retrieval, machine translation, lexical disambiguation, we focus on statistical approach to semantic indexing for multilingual text documents based on conceptual network formalism. We propose to use this formalism as an indexing language to represent the descriptive concepts and their weighting. These concepts represent the content of the document. Our contribution is based on two steps. In the first step, we propose the extraction of index terms using the multilingual lexical resource Euro WordNet (EWN). In the second step, we pass from the representation of index terms to the representation of index concepts through conceptual network formalism. This network is generated using the EWN resource and pass by a classification step based on association rules model (in attempt to discover the non-taxonomic relations or contextual relations between the concepts of a document). These relations are latent relations buried in the text and carried by the semantic context of the co-occurrence of concepts in the document. Our proposed indexing approach can be applied to text documents in various languages because it is based on a linguistic method adapted to the language through a multilingual thesaurus. Next, we apply the same statistical process regardless of the language in order to extract the significant concepts and their associated weights. We prove that the proposed indexing approach provides encouraging results.Keywords: concept extraction, conceptual network formalism, fuzzy association rules, multilingual thesaurus, semantic indexing
Procedia PDF Downloads 133