Search results for: classification%20quality
910 Introduction to Techno-Sectoral Innovation System Modeling and Functions Formulating
Authors: S. M. Azad, H. Ghodsi Pour, F. Roshannafasa
Abstract:
In recent years ‘technology management and policymaking’ is one of the most important problems in management science. In this field, different generations of innovation and technology management are presented which the earliest one is Innovation System (IS) approach. In a general classification, innovation systems are divided in to 4 approaches: Technical, sectoral, regional, and national. There are many researches in relation to each of these approaches in different academic fields. Every approach has some benefits. If two or more approaches hybrid, their benefits would be combined. In addition, according to the sectoral structure of the governance model in Iran, in many sectors such as information technology, the combination of three other approaches with sectoral approach is essential. Hence, in this paper, combining two IS approaches (technical and sectoral) and using system dynamics, a generic model is presented for a sample of software industry. As a complimentary point, this article is introducing a new hybrid approach called Techno-Sectoral Innovation System. This TSIS model is accomplished by Changing concepts of the ‘functions’ which came from Technological IS literature and using them into sectoral system as measurable indicators.Keywords: innovation system, technology, techno-sectoral system, functional indicators, system dynamics
Procedia PDF Downloads 425909 Plant Leaf Recognition Using Deep Learning
Authors: Aadhya Kaul, Gautam Manocha, Preeti Nagrath
Abstract:
Our environment comprises of a wide variety of plants that are similar to each other and sometimes the similarity between the plants makes the identification process tedious thus increasing the workload of the botanist all over the world. Now all the botanists cannot be accessible all the time for such laborious plant identification; therefore, there is an urge for a quick classification model. Also, along with the identification of the plants, it is also necessary to classify the plant as healthy or not as for a good lifestyle, humans require good food and this food comes from healthy plants. A large number of techniques have been applied to classify the plants as healthy or diseased in order to provide the solution. This paper proposes one such method known as anomaly detection using autoencoders using a set of collections of leaves. In this method, an autoencoder model is built using Keras and then the reconstruction of the original images of the leaves is done and the threshold loss is found in order to classify the plant leaves as healthy or diseased. A dataset of plant leaves is considered to judge the reconstructed performance by convolutional autoencoders and the average accuracy obtained is 71.55% for the purpose.Keywords: convolutional autoencoder, anomaly detection, web application, FLASK
Procedia PDF Downloads 155908 Predicting Machine-Down of Woodworking Industrial Machines
Authors: Matteo Calabrese, Martin Cimmino, Dimos Kapetis, Martina Manfrin, Donato Concilio, Giuseppe Toscano, Giovanni Ciandrini, Giancarlo Paccapeli, Gianluca Giarratana, Marco Siciliano, Andrea Forlani, Alberto Carrotta
Abstract:
In this paper we describe a machine learning methodology for Predictive Maintenance (PdM) applied on woodworking industrial machines. PdM is a prominent strategy consisting of all the operational techniques and actions required to ensure machine availability and to prevent a machine-down failure. One of the challenges with PdM approach is to design and develop of an embedded smart system to enable the health status of the machine. The proposed approach allows screening simultaneously multiple connected machines, thus providing real-time monitoring that can be adopted with maintenance management. This is achieved by applying temporal feature engineering techniques and training an ensemble of classification algorithms to predict Remaining Useful Lifetime of woodworking machines. The effectiveness of the methodology is demonstrated by testing an independent sample of additional woodworking machines without presenting machine down event.Keywords: predictive maintenance, machine learning, connected machines, artificial intelligence
Procedia PDF Downloads 216907 WebAppShield: An Approach Exploiting Machine Learning to Detect SQLi Attacks in an Application Layer in Run-time
Authors: Ahmed Abdulla Ashlam, Atta Badii, Frederic Stahl
Abstract:
In recent years, SQL injection attacks have been identified as being prevalent against web applications. They affect network security and user data, which leads to a considerable loss of money and data every year. This paper presents the use of classification algorithms in machine learning using a method to classify the login data filtering inputs into "SQLi" or "Non-SQLi,” thus increasing the reliability and accuracy of results in terms of deciding whether an operation is an attack or a valid operation. A method Web-App auto-generated twin data structure replication. Shielding against SQLi attacks (WebAppShield) that verifies all users and prevents attackers (SQLi attacks) from entering and or accessing the database, which the machine learning module predicts as "Non-SQLi" has been developed. A special login form has been developed with a special instance of data validation; this verification process secures the web application from its early stages. The system has been tested and validated, up to 99% of SQLi attacks have been prevented.Keywords: SQL injection, attacks, web application, accuracy, database
Procedia PDF Downloads 136906 Prediction of All-Beta Protein Secondary Structure Using Garnier-Osguthorpe-Robson Method
Authors: K. Tejasri, K. Suvarna Vani, S. Prathyusha, S. Ramya
Abstract:
Proteins are chained sequences of amino acids which are brought together by the peptide bonds. Many varying formations of the chains are possible due to multiple combinations of amino acids and rotation in numerous positions along the chain. Protein structure prediction is one of the crucial goals worked towards by the members of bioinformatics and theoretical chemistry backgrounds. Among the four different structure levels in proteins, we emphasize mainly the secondary level structure. Generally, the secondary protein basically comprises alpha-helix and beta-sheets. Multi-class classification problem of data with disparity is truly a challenge to overcome and has to be addressed for the beta strands. Imbalanced data distribution constitutes a couple of the classes of data having very limited training samples collated with other classes. The secondary structure data is extracted from the protein primary sequence, and the beta-strands are predicted using suitable machine learning algorithms.Keywords: proteins, secondary structure elements, beta-sheets, beta-strands, alpha-helices, machine learning algorithms
Procedia PDF Downloads 87905 Hybrid Feature Selection Method for Sentiment Classification of Movie Reviews
Authors: Vishnu Goyal, Basant Agarwal
Abstract:
Sentiment analysis research provides methods for identifying the people’s opinion written in blogs, reviews, social networking websites etc. Sentiment analysis is to understand what opinion people have about any given entity, object or thing. Sentiment analysis research can be broadly categorised into three types of approaches i.e. semantic orientation, machine learning and lexicon based approaches. Feature selection methods improve the performance of the machine learning algorithms by eliminating the irrelevant features. Information gain feature selection method has been considered best method for sentiment analysis; however, it has the drawback of selection of threshold. Therefore, in this paper, we propose a hybrid feature selection methods comprising of information gain and proposed feature selection method. Initially, features are selected using Information Gain (IG) and further more noisy features are eliminated using the proposed feature selection method. Experimental results show the efficiency of the proposed feature selection methods.Keywords: feature selection, sentiment analysis, hybrid feature selection
Procedia PDF Downloads 323904 Hierarchical Piecewise Linear Representation of Time Series Data
Authors: Vineetha Bettaiah, Heggere S. Ranganath
Abstract:
This paper presents a Hierarchical Piecewise Linear Approximation (HPLA) for the representation of time series data in which the time series is treated as a curve in the time-amplitude image space. The curve is partitioned into segments by choosing perceptually important points as break points. Each segment between adjacent break points is recursively partitioned into two segments at the best point or midpoint until the error between the approximating line and the original curve becomes less than a pre-specified threshold. The HPLA representation achieves dimensionality reduction while preserving prominent local features and general shape of time series. The representation permits course-fine processing at different levels of details, allows flexible definition of similarity based on mathematical measures or general time series shape, and supports time series data mining operations including query by content, clustering and classification based on whole or subsequence similarity.Keywords: data mining, dimensionality reduction, piecewise linear representation, time series representation
Procedia PDF Downloads 269903 A Deep Learning Based Approach for Dynamically Selecting Pre-processing Technique for Images
Authors: Revoti Prasad Bora, Nikita Katyal, Saurabh Yadav
Abstract:
Pre-processing plays an important role in various image processing applications. Most of the time due to the similar nature of images, a particular pre-processing or a set of pre-processing steps are sufficient to produce the desired results. However, in the education domain, there is a wide variety of images in various aspects like images with line-based diagrams, chemical formulas, mathematical equations, etc. Hence a single pre-processing or a set of pre-processing steps may not yield good results. Therefore, a Deep Learning based approach for dynamically selecting a relevant pre-processing technique for each image is proposed. The proposed method works as a classifier to detect hidden patterns in the images and predicts the relevant pre-processing technique needed for the image. This approach experimented for an image similarity matching problem but it can be adapted to other use cases too. Experimental results showed significant improvement in average similarity ranking with the proposed method as opposed to static pre-processing techniques.Keywords: deep-learning, classification, pre-processing, computer vision, image processing, educational data mining
Procedia PDF Downloads 147902 Towards Integrating Statistical Color Features for Human Skin Detection
Authors: Mohd Zamri Osman, Mohd Aizaini Maarof, Mohd Foad Rohani
Abstract:
Human skin detection recognized as the primary step in most of the applications such as face detection, illicit image filtering, hand recognition and video surveillance. The performance of any skin detection applications greatly relies on the two components: feature extraction and classification method. Skin color is the most vital information used for skin detection purpose. However, color feature alone sometimes could not handle images with having same color distribution with skin color. A color feature of pixel-based does not eliminate the skin-like color due to the intensity of skin and skin-like color fall under the same distribution. Hence, the statistical color analysis will be exploited such mean and standard deviation as an additional feature to increase the reliability of skin detector. In this paper, we studied the effectiveness of statistical color feature for human skin detection. Furthermore, the paper analyzed the integrated color and texture using eight classifiers with three color spaces of RGB, YCbCr, and HSV. The experimental results show that the integrating statistical feature using Random Forest classifier achieved a significant performance with an F1-score 0.969.Keywords: color space, neural network, random forest, skin detection, statistical feature
Procedia PDF Downloads 452901 Study of the Potential of Raw Sediments and Sediments Treated with Lime or Cement for Use in a Foundation Layer and the Base Layer of a Roadway
Authors: Nor-Edine Abriak, Mahfoud Benzerzour, Mouhamadou Amar, Abdeljalil Zri
Abstract:
In this work, firstly we have studied the potential of raw sediments and sediments treated with lime or cement for use in a foundation layer and the base layer of a roadway. Secondly, we have examined mineral changes caused by the addition of lime or cement in order to explain the mechanical performance of stabilized sediments. After determining the amount of lime and cement required stabilizing the sediments, the compaction characteristics and Immediate Bearing Capacity (IBI) were studied using the Modified Proctor method. Then, the evolution of the three parameters, which are optimum water content, maximum dry density and IBI, were determined. Mechanical performances can be evaluated through resistance to compression, resistance under traction and the elasticity modulus. The resistances of the formulations treated with ROLAC®645 increase with the amount of ROLAC®645. Traction resistance and the elastic modulus were used to evaluate the potential of the formulations as road construction materials using the classification diagram. The results show that all the other formulations with ROLAC®645 can be used in subgrades and foundation layers for roads.Keywords: sediment, lime, cement, roadway
Procedia PDF Downloads 259900 Impact Assessment of Tropical Cyclone Hudhud on Visakhapatnam, Andhra Pradesh
Authors: Vivek Ganesh
Abstract:
Tropical cyclones are some of the most damaging events. They occur in yearly cycles and affect the coastal population with three dangerous effects: heavy rain, strong wind and storm surge. In order to estimate the area and the population affected by a cyclone, all the three types of physical impacts must be taken into account. Storm surge is an abnormal rise of water above the astronomical tides, generated by strong winds and drop in the atmospheric pressure. The main aim of the study is to identify the impact by comparing three different months data. The technique used here is NDVI classification technique for change detection and other techniques like storm surge modelling for finding the tide height. Current study emphasize on recent very severe cyclonic storm Hud Hud of category 3 hurricane which had developed on 8 October 2014 and hit the coast on 12 October 2014 which caused significant changes on land and coast of Visakhapatnam, Andhra Pradesh. In the present study, we have used Remote Sensing and GIS tools for investigating and quantifying the changes in vegetation and settlement.Keywords: inundation map, NDVI map, storm tide map, track map
Procedia PDF Downloads 254899 Machine Learning Driven Analysis of Kepler Objects of Interest to Identify Exoplanets
Authors: Akshat Kumar, Vidushi
Abstract:
This paper identifies 27 KOIs, 26 of which are currently classified as candidates and one as false positives that have a high probability of being confirmed. For this purpose, 11 machine learning algorithms were implemented on the cumulative kepler dataset sourced from the NASA exoplanet archive; it was observed that the best-performing model was HistGradientBoosting and XGBoost with a test accuracy of 93.5%, and the lowest-performing model was Gaussian NB with a test accuracy of 54%, to test model performance F1, cross-validation score and RUC curve was calculated. Based on the learned models, the significant characteristics for confirm exoplanets were identified, putting emphasis on the object’s transit and stellar properties; these characteristics were namely koi_count, koi_prad, koi_period, koi_dor, koi_ror, and koi_smass, which were later considered to filter out the potential KOIs. The paper also calculates the Earth similarity index based on the planetary radius and equilibrium temperature for each KOI identified to aid in their classification.Keywords: Kepler objects of interest, exoplanets, space exploration, machine learning, earth similarity index, transit photometry
Procedia PDF Downloads 53898 PM10 Prediction and Forecasting Using CART: A Case Study for Pleven, Bulgaria
Authors: Snezhana G. Gocheva-Ilieva, Maya P. Stoimenova
Abstract:
Ambient air pollution with fine particulate matter (PM10) is a systematic permanent problem in many countries around the world. The accumulation of a large number of measurements of both the PM10 concentrations and the accompanying atmospheric factors allow for their statistical modeling to detect dependencies and forecast future pollution. This study applies the classification and regression trees (CART) method for building and analyzing PM10 models. In the empirical study, average daily air data for the city of Pleven, Bulgaria for a period of 5 years are used. Predictors in the models are seven meteorological variables, time variables, as well as lagged PM10 variables and some lagged meteorological variables, delayed by 1 or 2 days with respect to the initial time series, respectively. The degree of influence of the predictors in the models is determined. The selected best CART models are used to forecast future PM10 concentrations for two days ahead after the last date in the modeling procedure and show very accurate results.Keywords: cross-validation, decision tree, lagged variables, short-term forecasting
Procedia PDF Downloads 188897 The Functions of “Question” and Its Role in Education Process: Quranic Approach
Authors: Sara Tusian, Zahra Salehi Motaahed, Narges Sajjadie, Nikoo Dialame
Abstract:
One of the methods which have frequently been used in Quran is the “question”. In the Quran, in addition to the content, methods are also important. Using analysis-interpretation method, the present study has investigated Quranic questions, and extracted its functions from educational perspective. In so doing, it has first investigated all the questions in Quran and then taking the three-stage classification of education into account, it has offered question functions. The results obtained from this study suggest that question functions in Quran are presented in three categories: the preparation stage (including preparation of the audience, revising the insights, and internal Evolution); main body (including the granting the insight, and elimination of intellectual negligence and the question of innate and logical axioms, the introducting of the realm of thinking, creating emotional arousal and alleged in the claim) and the third stage as modification and revision (including invitation to move in the framework of tasks using the individual beliefs to reveal the contradictions and, Error detection and contribution to change the function) that each of which has a special role in the education process.Keywords: education, question, Quranic questions, Quran
Procedia PDF Downloads 490896 Roadway Maintenance Management System
Authors: Chika Catherine Ayogu
Abstract:
Rehabilitation plays an important and integral part in the life of roadway rehabilitation management system. It is a systematic method for inspection and rating the roadway condition in a given area. The system performs a cost effective analysis of various maintenance and rehabilitation strategies. Finally the system prioritize and recommend roadway rehabilitation and maintenance to maximize results within a given budget amount. During execution of maintenance activity, the system also tracks labour, materials, equipment and cost for activities performed. The system implements physical assessment field inspection and rating of each street segment which is then entered into a database. The information is analyzed using a software, and provide recommendations and project future conditions. The roadway management system provides a deterioration curve for each segment based on input then assigns the most cost-effective maintenance strategy based on conditions, surface type and functional classification, and available budget. This paper investigates the roadway management system and its capabilities to assist in applying the right treatment to the right roadway at the right time so that expected service life of the roadway is extended as long as possible with acceptable cost.Keywords: effectiveness, rehabilitation, roadway, software system
Procedia PDF Downloads 138895 Parkinson's Disease Gene Identification Using Physicochemical Properties of Amino Acids
Authors: Priya Arora, Ashutosh Mishra
Abstract:
Gene identification, towards the pursuit of mutated genes, leading to Parkinson’s disease, puts forward a challenge towards proactive cure of the disorder itself. Computational analysis is an effective technique for exploring genes in the form of protein sequences, as the theoretical and manual analysis is infeasible. The limitations and effectiveness of a particular computational method are entirely dependent on the previous data that is available for disease identification. The article presents a sequence-based classification method for the identification of genes responsible for Parkinson’s disease. During the initiation phase, the physicochemical properties of amino acids transform protein sequences into a feature vector. The second phase of the method employs Jaccard distances to select negative genes from the candidate population. The third phase involves artificial neural networks for making final predictions. The proposed approach is compared with the state of art methods on the basis of F-measure. The results confirm and estimate the efficiency of the method.Keywords: disease gene identification, Parkinson’s disease, physicochemical properties of amino acid, protein sequences
Procedia PDF Downloads 129894 The Results of the Archaeological Excavations at the Site of Qurh in Al Ula Region
Authors: Ahmad Al Aboudi
Abstract:
The Department of Archaeology at King Saud University conduct a long Term excavations since 2004 at the archaeological site of (Qurh) in Al-Ula area. The history of the site goes back to the eighth century AD. The main aim of the excavations is the training of the students on the archaeological field work associated with the scientific skills of exploring, surveying, classifying, documentations and other necessary in the field archaeology. During the 12th Season of Excavations, an area of 20 × 40 m2 of the site was excavated. The depth of the excavating the site was reached to 2-3 m. Many of the architectural features of a residential area in the northern part of the site were excavated this season. Circular walls made of mud-brick and a brick column drums and tiles made of clay were revealed this season. Additionally, lots of findings such as Gemstones, jars, ceramic plates, metal, glass, and fabric, as well as some jewelers and coins were discovered. This paper will deal with the main results of this field project including the architectural features and phenomena and their interpretations, the classification of excavated material culture remains and stratigraphy.Keywords: Islamic architecture, Islamic art, excavations, early Islamic city
Procedia PDF Downloads 261893 A Topological Approach for Motion Track Discrimination
Authors: Tegan H. Emerson, Colin C. Olson, George Stantchev, Jason A. Edelberg, Michael Wilson
Abstract:
Detecting small targets at range is difficult because there is not enough spatial information present in an image sub-region containing the target to use correlation-based methods to differentiate it from dynamic confusers present in the scene. Moreover, this lack of spatial information also disqualifies the use of most state-of-the-art deep learning image-based classifiers. Here, we use characteristics of target tracks extracted from video sequences as data from which to derive distinguishing topological features that help robustly differentiate targets of interest from confusers. In particular, we calculate persistent homology from time-delayed embeddings of dynamic statistics calculated from motion tracks extracted from a wide field-of-view video stream. In short, we use topological methods to extract features related to target motion dynamics that are useful for classification and disambiguation and show that small targets can be detected at range with high probability.Keywords: motion tracks, persistence images, time-delay embedding, topological data analysis
Procedia PDF Downloads 107892 Profit-Based Artificial Neural Network (ANN) Trained by Migrating Birds Optimization: A Case Study in Credit Card Fraud Detection
Authors: Ashkan Zakaryazad, Ekrem Duman
Abstract:
A typical classification technique ranks the instances in a data set according to the likelihood of belonging to one (positive) class. A credit card (CC) fraud detection model ranks the transactions in terms of probability of being fraud. In fact, this approach is often criticized, because firms do not care about fraud probability but about the profitability or costliness of detecting a fraudulent transaction. The key contribution in this study is to focus on the profit maximization in the model building step. The artificial neural network proposed in this study works based on profit maximization instead of minimizing the error of prediction. Moreover, some studies have shown that the back propagation algorithm, similar to other gradient–based algorithms, usually gets trapped in local optima and swarm-based algorithms are more successful in this respect. In this study, we train our profit maximization ANN using the Migrating Birds optimization (MBO) which is introduced to literature recently.Keywords: neural network, profit-based neural network, sum of squared errors (SSE), MBO, gradient descent
Procedia PDF Downloads 466891 Instability Index Method and Logistic Regression to Assess Landslide Susceptibility in County Route 89, Taiwan
Authors: Y. H. Wu, Ji-Yuan Lin, Yu-Ming Liou
Abstract:
This study aims to set up the landslide susceptibility map of County Route 89 at Ren-Ai Township in Nantou County using the Instability Index Method and Logistic regression. Seven susceptibility factors including Slope Angle, Aspect, Elevation, Distance to fold, Distance to River, Distance to Road and Accumulated Rainfall were obtained by GIS based on the Typhoon Toraji landslide area identified by Industrial Technology Research Institute in 2001. To calculate the landslide percentage of each factor and acquire the weight and grade the grid by means of Instability Index Method. In this study, landslide susceptibility can be classified into four grades: high, medium high, medium low and low, in order to determine the advantages and disadvantages of the two models. The precision of this model is verified by classification error matrix and SRC curve. These results suggest that the logistic regression model is a preferred method than instability index in the assessment of landslide susceptibility. It is suitable for the landslide prediction and precaution in this area in the future.Keywords: instability index method, logistic regression, landslide susceptibility, SRC curve
Procedia PDF Downloads 280890 Syllogistic Reasoning with 108 Inference Rules While Case Quantities Change
Authors: Mikhail Zarechnev, Bora I. Kumova
Abstract:
A syllogism is a deductive inference scheme used to derive a conclusion from a set of premises. In a categorical syllogisms, there are only two premises and every premise and conclusion is given in form of a quantified relationship between two objects. The different order of objects in premises give classification known as figures. We have shown that the ordered combinations of 3 generalized quantifiers with certain figure provide in total of 108 syllogistic moods which can be considered as different inference rules. The classical syllogistic system allows to model human thought and reasoning with syllogistic structures always attracted the attention of cognitive scientists. Since automated reasoning is considered as part of learning subsystem of AI agents, syllogistic system can be applied for this approach. Another application of syllogistic system is related to inference mechanisms on the Semantic Web applications. In this paper we proposed the mathematical model and algorithm for syllogistic reasoning. Also the model of iterative syllogistic reasoning in case of continuous flows of incoming data based on case–based reasoning and possible applications of proposed system were discussed.Keywords: categorical syllogism, case-based reasoning, cognitive architecture, inference on the semantic web, syllogistic reasoning
Procedia PDF Downloads 406889 Sentiment Analysis: An Enhancement of Ontological-Based Features Extraction Techniques and Word Equations
Authors: Mohd Ridzwan Yaakub, Muhammad Iqbal Abu Latiffi
Abstract:
Online business has become popular recently due to the massive amount of information and medium available on the Internet. This has resulted in the huge number of reviews where the consumers share their opinion, criticisms, and satisfaction on the products they have purchased on the websites or the social media such as Facebook and Twitter. However, to analyze customer’s behavior has become very important for organizations to find new market trends and insights. The reviews from the websites or the social media are in structured and unstructured data that need a sentiment analysis approach in analyzing customer’s review. In this article, techniques used in will be defined. Definition of the ontology and description of its possible usage in sentiment analysis will be defined. It will lead to empirical research that related to mobile phones used in research and the ontology used in the experiment. The researcher also will explore the role of preprocessing data and feature selection methodology. As the result, ontology-based approach in sentiment analysis can help in achieving high accuracy for the classification task.Keywords: feature selection, ontology, opinion, preprocessing data, sentiment analysis
Procedia PDF Downloads 189888 Impact of Implementation of 5S and TPM in Industrial Organizations: A Review
Authors: Jamal Ahmed Hama Kareem, Noraini Abu Talib
Abstract:
The purpose of this paper is to explore the literature on 5S and Total Productive Maintenance (TPM) and the benefits that are to be derived from their implementation. It also seeks to highlight the main phases for implementing both the 5S and the TPM successfully, along with highlighting aspects that are needed for successful implementation of these two techniques simultaneously in the contemporary manufacturing scenario. The literature on classification of 5S and TPM has so far been very limited. The paper reviews a large number of papers in this field and presents the overview of several of implementation practices of 5S and TPM, and the benefits that can be achieved by the implementation of 5S and TPM as a one system by industrial organizations globally. The paper systematically categorizes the published literature and reveals important issues that influence the successful implementation of 5S and TPM in organizations to improve production effectiveness for competitiveness. Further, the paper also highlights various phases suggested by researchers and practitioners, which ensure smooth and effective implementation of the 5S and TPM in industrial organizations. In the end, study puts forth propositions based on the model of the study after extensive review of literature. The paper will be useful to researchers, maintenance professionals and other concerned officials with improving the performance of production processes effectiveness in industrial organizations.Keywords: 5S, Total Productive Maintenance (TPM), phases of implementation of 5S and TPM, industrial organizations
Procedia PDF Downloads 610887 Self-Supervised Pretraining on Sequences of Functional Magnetic Resonance Imaging Data for Transfer Learning to Brain Decoding Tasks
Authors: Sean Paulsen, Michael Casey
Abstract:
In this work we present a self-supervised pretraining framework for transformers on functional Magnetic Resonance Imaging (fMRI) data. First, we pretrain our architecture on two self-supervised tasks simultaneously to teach the model a general understanding of the temporal and spatial dynamics of human auditory cortex during music listening. Our pretraining results are the first to suggest a synergistic effect of multitask training on fMRI data. Second, we finetune the pretrained models and train additional fresh models on a supervised fMRI classification task. We observe significantly improved accuracy on held-out runs with the finetuned models, which demonstrates the ability of our pretraining tasks to facilitate transfer learning. This work contributes to the growing body of literature on transformer architectures for pretraining and transfer learning with fMRI data, and serves as a proof of concept for our pretraining tasks and multitask pretraining on fMRI data.Keywords: transfer learning, fMRI, self-supervised, brain decoding, transformer, multitask training
Procedia PDF Downloads 81886 Correlation of Clinical and Sonographic Findings with Cytohistology for Diagnosis of Ovarian Tumours
Authors: Meenakshi Barsaul Chauhan, Aastha Chauhan, Shilpa Hurmade, Rajeev Sen, Jyotsna Sen, Monika Dalal
Abstract:
Introduction: Ovarian masses are common forms of neoplasm in women and represent 2/3rd of gynaecological malignancies. A pre-operative suggestion of malignancy can guide the gynecologist to refer women with suspected pelvic mass to a gynecological oncologist for appropriate therapy and optimized treatment, which can improve survival. In the younger age group preoperative differentiation into benign or malignant pathology can decide for conservative or radical surgery. Imaging modalities have a definite role in establishing the diagnosis. By using International Ovarian Tumor Analysis (IOTA) classification with sonography, costly radiological methods like Magnetic Resonance Imaging (MRI) / computed tomography (CT) scan can be reduced, especially in developing countries like India. Thus, this study is being undertaken to evaluate the role of clinical methods and sonography for diagnosis of the nature of the ovarian tumor. Material And Methods: This prospective observational study was conducted on 40 patients presenting with ovarian masses, in the Department of Obstetrics and Gynaecology, at a tertiary care center in northern India. Functional cysts were excluded. Ultrasonography and color Doppler were performed on all the cases.IOTA rules were applied, which take into account locularity, size, presence of solid components, acoustic shadow, dopper flow etc . Magnetic Resonance Imaging (MRI) / computed tomography (CT) scans abdomen and pelvis were done in cases where sonography was inconclusive. In inoperable cases, Fine needle aspiration cytology (FNAC) was done. The histopathology report after surgery and cytology report after FNAC was correlated statistically with the pre-operative diagnosis made clinically and sonographically using IOTA rules. Statistical Analysis: Descriptive measures were analyzed by using mean and standard deviation and the Student t-test was applied and the proportion was analyzed by applying the chi-square test. Inferential measures were analyzed by sensitivity, specificity, negative predictive value, and positive predictive value. Results: Provisional diagnosis of the benign tumor was made in 16(42.5%) and of the malignant tumor was made in 24(57.5%) patients on the basis of clinical findings. With IOTA simple rules on sonography, 15(37.5%) were found to be benign, while 23 (57.5%) were found to be malignant and findings were inconclusive in 2 patients (5%). FNAC/Histopathology reported that benign ovarian tumors were 14 (35%) and 26(65%) were malignant, which was taken as the gold standard. The clinical finding alone was found to have a sensitivity of 66.6% and a specificity of 90.9%. USG alone had a sensitivity of 86% and a specificity of 80%. When clinical findings and IOTA simple rules of sonography were combined (excluding inconclusive masses), the sensitivity and specificity were 83.3% and 92.3%, respectively. While including inconclusive masses, sensitivity came out to be 91.6% and specificity was 89.2. Conclusion: IOTA's simple sonography rules are highly sensitive and specific in the prediction of ovarian malignancy and also easy to use and easily reproducible. Thus, combining clinical examination with USG will help in the better management of patients in terms of time, cost and better prognosis. This will also avoid the need for costlier modalities like CT, and MRI.Keywords: benign, international ovarian tumor analysis classification, malignant, ovarian tumours, sonography
Procedia PDF Downloads 73885 Occupational Safety in Construction Projects
Authors: Heba Elbibas, Esra Gnijeewa, Zedan Hatush
Abstract:
This paper presents research on occupational safety in construction projects, where the importance of safety management in projects was studied, including the preparation of a safety plan and program for each project and the identification of the responsibilities of each party to the contract. The research consists of two parts: 1-Field visits: which were field visits to three construction projects, including building projects, road projects, and tower installation. The safety level of these projects was evaluated through a checklist that includes the most important safety elements in terms of the application of these items in the projects. 2-Preparation of a questionnaire: which included supervisors and engineers and aimed to determine the level of awareness and commitment of different project categories to safety standards. The results showed the following: i) There is a moderate occupational safety policy. ii) The preparation and storage of maintenance reports are not fully complied with. iii) There is a moderate level of training on occupational safety for project workers. iv) The company does not impose penalties on safety violators permanently. v) There is a moderate policy for equipment and machinery safety. vi) Self-injuries occur due to (fatigue, lack of attention, deliberate error, and emotional factors), with a rate of 82.4%.Keywords: management, safety, occupational safety, classification
Procedia PDF Downloads 93884 Feature-Based Summarizing and Ranking from Customer Reviews
Authors: Dim En Nyaung, Thin Lai Lai Thein
Abstract:
Due to the rapid increase of Internet, web opinion sources dynamically emerge which is useful for both potential customers and product manufacturers for prediction and decision purposes. These are the user generated contents written in natural languages and are unstructured-free-texts scheme. Therefore, opinion mining techniques become popular to automatically process customer reviews for extracting product features and user opinions expressed over them. Since customer reviews may contain both opinionated and factual sentences, a supervised machine learning technique applies for subjectivity classification to improve the mining performance. In this paper, we dedicate our work is the task of opinion summarization. Therefore, product feature and opinion extraction is critical to opinion summarization, because its effectiveness significantly affects the identification of semantic relationships. The polarity and numeric score of all the features are determined by Senti-WordNet Lexicon. The problem of opinion summarization refers how to relate the opinion words with respect to a certain feature. Probabilistic based model of supervised learning will improve the result that is more flexible and effective.Keywords: opinion mining, opinion summarization, sentiment analysis, text mining
Procedia PDF Downloads 321883 Chinese Sentence Level Lip Recognition
Authors: Peng Wang, Tigang Jiang
Abstract:
The computer based lip reading method of different languages cannot be universal. At present, for the research of Chinese lip reading, whether the work on data sets or recognition algorithms, is far from mature. In this paper, we study the Chinese lipreading method based on machine learning, and propose a Chinese Sentence-level lip-reading network (CNLipNet) model which consists of spatio-temporal convolutional neural network(CNN), recurrent neural network(RNN) and Connectionist Temporal Classification (CTC) loss function. This model can map variable-length sequence of video frames to Chinese Pinyin sequence and is trained end-to-end. More over, We create CNLRS, a Chinese Lipreading Dataset, which contains 5948 samples and can be shared through github. The evaluation of CNLipNet on this dataset yielded a 41% word correct rate and a 70.6% character correct rate. This evaluation result is far superior to the professional human lip readers, indicating that CNLipNet performs well in lipreading.Keywords: lipreading, machine learning, spatio-temporal, convolutional neural network, recurrent neural network
Procedia PDF Downloads 116882 Machine Learning Based Gender Identification of Authors of Entry Programs
Authors: Go Woon Kwak, Siyoung Jun, Soyun Maeng, Haeyoung Lee
Abstract:
Entry is an education platform used in South Korea, created to help students learn to program, in which they can learn to code while playing. Using the online version of the entry, teachers can easily assign programming homework to the student and the students can make programs simply by linking programming blocks. However, the programs may be made by others, so that the authors of the programs should be identified. In this paper, as the first step toward author identification of entry programs, we present an artificial neural network based classification approach to identify genders of authors of a program written in an entry. A neural network has been trained from labeled training data that we have collected. Our result in progress, although preliminary, shows that the proposed approach could be feasible to be applied to the online version of entry for gender identification of authors. As future work, we will first use a machine learning technique for age identification of entry programs, which would be the second step toward the author identification.Keywords: artificial intelligence, author identification, deep neural network, gender identification, machine learning
Procedia PDF Downloads 311881 Fast and Accurate Model to Detect Ictal Waveforms in Electroencephalogram Signals
Authors: Piyush Swami, Bijaya Ketan Panigrahi, Sneh Anand, Manvir Bhatia, Tapan Gandhi
Abstract:
Visual inspection of electroencephalogram (EEG) signals to detect epileptic signals is very challenging and time-consuming task even for any expert neurophysiologist. This problem is most challenging in under-developed and developing countries due to shortage of skilled neurophysiologists. In the past, notable research efforts have gone in trying to automate the seizure detection process. However, due to high false alarm detections and complexity of the models developed so far, have vastly delimited their practical implementation. In this paper, we present a novel scheme for epileptic seizure detection using empirical mode decomposition technique. The intrinsic mode functions obtained were then used to calculate the standard deviations. This was followed by probability density based classifier to discriminate between non-ictal and ictal patterns in EEG signals. The model presented here demonstrated very high classification rates ( > 97%) without compromising the statistical performance. The computation timings for each testing phase were also very low ( < 0.029 s) which makes this model ideal for practical applications.Keywords: electroencephalogram (EEG), epilepsy, ictal patterns, empirical mode decomposition
Procedia PDF Downloads 397