Search results for: computer assisted classification

Authors: Yeshona Sewsynker

Abstract:

This study presents three microwave-assisted alkalic salt pretreatments to enhance delignification and enzymatic saccharification of corn cobs. The effects of process parameters of salt concentration (0-15%), microwave power intensity (0-800 W) and pretreatment time (2-8 min) on reducing sugar yield from corn cobs were investigated. Pretreatment models were developed with the high coefficient of determination values (R2>0.85). Optimization gave a maximum reducing sugar yield of 0.76 g/g. Scanning electron microscopy (SEM) and Fourier Transform Infrared analysis (FTIR) showed major changes in the lignocellulosic structure after pretreatment. A 7-fold increase in the sugar yield was observed compared to previous reports on the same substrate. The developed pretreatment strategy was effective for enhancing enzymatic saccharification from lignocellulosic wastes for microbial biofuel production processes and value-added products.

Keywords: pretreatment, lignocellulosic biomass, enzymatic hydrolysis, delignification

Procedia PDF Downloads 499

Authors: Bishoy Abouelsoud Saad Amin

Abstract:

This paper examines the use of computer and its related health hazard among computer users in South-Western zone of Nigeria. Two hundred and eighteen (218) computer users constituted the population used to evaluate association between posture, extensive computer use and related health hazard. The instruments for the study are a questionnaire on demographics, lifestyle, body features and work ability index while mean rating, standard deviation and t test were used for data analysis. Identified health related hazard include damages to the eyesight, bad posture, arthritis, musculoskeletal disorders, headache, stress and so on. The results showed that factors such as work demand, posture, closeness to computer screen and excessive working hours on computers constitute health hazards in both old and young computer users of various gender. It is therefore recommended that total number of hours spent with computer should be monitored and controlled.

Keywords: computer game, metaphor, middle school students, virtual environments computer auditing, risk, measures to prevent, information management computer-related health hazard, musculoskeletal disorders, computer usage, work ability index

Procedia PDF Downloads 68

Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan

Abstract:

This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.

Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal

Procedia PDF Downloads 113

Authors: Roukia Hammoudi, Chabrouk Farid, Dehak Karima, Mahfoud Hadj Mahammed, Mohamed Didi Ouldelhadj

Abstract:

The objective of this study was to optimise the extraction conditions for phenolic compounds from Deverra scoparia Coss and Dur. Apiaceae plant by ultrasound assisted extraction (UAE). The effects of solvent type (acetone, ethanol and methanol), solvent concentration (%), extraction time (mins) and extraction temperature (°C) on total phenolic content (TPC) were determined. The optimum extraction conditions were found to be acetone concentration of 80%, extraction time of 25 min and extraction temperature of 25°C. Under the optimized conditions, the value for TPC was 9.68 ± 1.05 mg GAE/g of extract. The study of the antioxidant power of these oils was performed by the method of DPPH. The results showed that antioxidant activity of the Deverra scoparia essential oil was more effective as compared to ascorbic acid and trolox.

Keywords: Deverra scoparia, phenolic compounds, ultrasound assisted extraction, total phenolic content, antioxidant activity

Procedia PDF Downloads 603

Authors: Roukia Hammoudi, Dehak Karima, Chabrouk Farid, Mahfoud Hadj Mahammed, Mohamed Didi Ouldelhadj

Abstract:

The objective of this study was to optimise the extraction conditions for phenolic compounds from Deverra scoparia Coss and Dur. Apiaceae plant by ultrasound assisted extraction (UAE). The effects of solvent type (Acetone, Ethanol and methanol), solvent concentration (%), extraction time (mins) and extraction temperature (°C) on total phenolic content (TPC) were determined. the optimum extraction conditions were found to be acetone concentration of 80%, extraction time of 25 min and extraction temperature of 25°C. Under the optimized conditions, the value for TPC was 9.68 ± 1.05 mg GAE/g of extract. The study of the antioxidant power of these oils was performed by the method of DPPH. The results showed that antioxidant activity of the Deverra scoparia essential oil was more effective as compared to ascorbic acid and trolox.

Keywords: Deverra scoparia, phenolic compounds, ultrasound assisted extraction, total phenolic content, antioxidant activity

Procedia PDF Downloads 595

Authors: Dasom Kim, William Xiu Shun Wong, Yoonjin Hyun, Donghoon Lee, Minji Paek, Sungho Byun, Namgyu Kim

Abstract:

There have been many researches on document classification for classifying voluminous documents automatically. Through document classification, we can assign a specific category to each unlabeled document on the basis of various machine learning algorithms. However, providing labeled documents manually requires considerable time and effort. To overcome the limitations, the semi-supervised learning which uses unlabeled document as well as labeled documents has been invented. However, traditional document classifiers, regardless of supervised or semi-supervised ones, cannot sufficiently explain the reason or the process of the classification. Thus, in this paper, we proposed a methodology to visualize major topics and class components of each document. We believe that our methodology for visualizing topics and classes of each document can enhance the reliability and explanatory power of document classifiers.

Keywords: data mining, document classifier, text mining, topic modeling

Procedia PDF Downloads 402

Authors: Kwangmin Joo

Abstract:

Automatic detection of lumbar vertebrae and classification method is proposed for evaluating the degree of disc narrowing. Prior to classification, deep learning based segmentation is applied to detect individual lumbar vertebra. M-net is applied to segment five lumbar vertebrae and fine-tuning segmentation is employed to improve the accuracy of segmentation. Using the features extracted from previous step, clustering technique, k-means clustering, is applied to estimate the degree of disc space narrowing under four grade scoring system. As preliminary study, techniques proposed in this research could help building an automatic scoring system to diagnose the severity of disc narrowing from X-ray images.

Keywords: Disc space narrowing, Degenerative disc disorders, Deep learning based segmentation, Clustering technique

Procedia PDF Downloads 125

Authors: Sikiru Oluwarotimi Ismail, Hom Nath Dhakal, Anish Roy, Dong Wang, Ivan Popov

Abstract:

The ultrasonically-assisted drilling (UAD) is a non-traditional technique which involves the superimposition of a high frequency and low amplitude vibration, usually greater than 18kHz and less than 20µm respectively, on a drill bit along the feed direction. UAD has remarkable advantages over the conventional drilling (CD), especially the high drilling-force reduction. Force reduction improves the quality of the drilled holes, reduces power consumption rate and cost of production. Nevertheless, in addition to the setbacks of UAD including expensiveness of set-up, unpredicted results and chipping effects, this paper presents the problems of insignificant force reduction and poor surface quality during UAD of hemp fibre-reinforced composites (HFRCs), a natural composite, with polycaprolactone (PCL) matrix. The experimental results obtained depict that HFRCs/PCL samples have more burnt chip-materials attached on the drilled holes during UAD than CD. This effect produced a very high surface roughness (Ra), up to 13µm. In a bid to reduce these challenges, different drilling parameters (feed rates and cutting speeds, frequencies and amplitudes for UAD), conditions (dry machining and airflow cooling) and diameters of drill bits (3mm and 6mm of high speed steel), as well as HFRCs/PCL samples of various fibre aspect ratios, including 0 (neat), 19, 26, 30 and 38 have been used. However, the setbacks still persisted. Evidently, the benefits of UAD are not obtainable for the drilling of the HFRCs/PCL laminates. These problems occurred due to the 60 °C melting temperature of PCL, quite lower than 56-90.2 °C and 265–290.8 °C composite-tool interface temperature during CD and UAD respectively.

Keywords: force reduction, hemp fibre-reinforced composites, ultrasonically-assisted drilling, surface quality

Procedia PDF Downloads 438

Authors: Hsin-Yang Wang, K. M. A. Salam, Ying-Jia Lin, Daniel Tan, Tzu-Hsuan Chou, Hung-Yu Kao

Abstract:

Detecting user intent from natural language expression has a wide variety of use cases in different natural language processing applications. Recently few-shot training has a spike of usage on commercial domains. Due to the lack of significant sample features, the downstream task performance has been limited or leads to an unstable result across different domains. As a state-of-the-art method, the pre-trained BERT model gathering the sentence-level information from a large text corpus shows improvement on several NLP benchmarks. In this research, we are proposing a method to change multi-class classification tasks into binary classification tasks, then use the confidence score to rank the results. As a language model, BERT performs well on sequence data. In our experiment, we change the objective from predicting labels into finding the relations between words in sequence data. Our proposed method achieved 71.0% accuracy in the internal intent detection dataset and 63.9% accuracy in the HuffPost dataset. Acknowledgment: This work was supported by NCKU-B109-K003, which is the collaboration between National Cheng Kung University, Taiwan, and SoftBank Corp., Tokyo.

Keywords: OSML, BERT, text classification, one shot

Procedia PDF Downloads 101

Authors: Nooraneda Mutalip Laidey

Abstract:

Computer Crimes Act 1997 (CCA 1997) was conceded by Malaysia’s legislative body in 1997 and the Act was enforced in June 2000. The purpose of CCA 1997 is to provide for offences related to misuse of computers such as hacking, cracking and phishing. CCA 1997 was modelled after United Kingdom’s Computer Misuses Act 1990 as a response to the emerging computer crimes. This legislation is divided into three parts and 12 Sections. The first part outlines preliminary matters that include short title and relevant definitions, second part provides for the offenses related to misuse of computers and specifies penalties for each offences, and the last part deals with ancillary provisions such as jurisdictional and investigational issues of cybercrime. The main objective of this paper is to discuss the development of computer crimes and its deterrence in Malaysia. Specific sections of CCA 1997 will be analysed in details and detail assessment on the prevention and prosecution of computer crimes in Malaysia will be accessed to determine whether CCA 1997 is so far adequate in preventing computer crimes in Malaysia.

Keywords: computer, computer crimes, CCA 1997, circumvention, deterrence

Procedia PDF Downloads 344

Authors: Dimiter M. Dimitrov, Abdullah Sadaawi

Abstract:

The National Assessment for Schools (NAFS) in Saudi Arabia consists of standardized tests in Mathematics, Reading, and Science for school grade levels 3, 6, and 9. One main goal is to classify students into four categories of NAFS performance (minimal, basic, proficient, and advanced) by schools and the entire national sample. The NAFS scoring and equating is performed on a bounded scale (D-scale: ranging from 0 to 1) in the framework of the recently developed “D-scoring method of measurement.” The specificity of the NAFS measurement framework and data complexity presented both challenges and opportunities to (a) the estimation of score reliability for schools, (b) setting cut-scores for the classification of students into categories of performance, and (c) generating plausible values for distributions of student performance on the D-scale. The estimation of score reliability at the school level was performed in the framework of generalizability theory (GT), with students “nested” within schools and test items “nested” within test forms. The GT design was executed via a multilevel modeling syntax code in R. Cut-scores (on the D-scale) for the classification of students into performance categories was derived via a recently developed method of standard setting, referred to as “Response Vector for Mastery” (RVM) method. For each school, the classification of students into categories of NAFS performance was based on distributions of plausible values for the students’ scores on NAFS tests by grade level (3, 6, and 9) and subject (Mathematics, Reading, and Science). Plausible values (on the D-scale) for each individual student were generated via random selection from a statistical logit-normal distribution with parameters derived from the student’s D-score and its conditional standard error, SE(D). All procedures related to D-scoring, equating, generating plausible values, and classification of students into performance levels were executed via a computer program in R developed for the purpose of NAFS data analysis.

Keywords: large-scale assessment, reliability, generalizability theory, plausible values

Procedia PDF Downloads 18

Authors: Spoorthi Sripad

Abstract:

Remote sensing is a powerful tool for acquiring information about the Earth's surface without direct contact, relying on the interaction of electromagnetic radiation with various materials and features. This paper explores the fundamental principle of "Interaction with Earth's Surface" in remote sensing, shedding light on the intricate processes that occur when electromagnetic waves encounter different surfaces. The absorption, reflection, and transmission of radiation generate distinct spectral signatures, allowing for the identification and classification of surface materials. The paper delves into the significance of the visible, infrared, and thermal infrared regions of the electromagnetic spectrum, highlighting how their unique interactions contribute to a wealth of applications, from land cover classification to environmental monitoring. The discussion encompasses the types of sensors and platforms used to capture these interactions, including multispectral and hyperspectral imaging systems. By examining real-world applications, such as land cover classification and environmental monitoring, the paper underscores the critical role of understanding the interaction with the Earth's surface for accurate and meaningful interpretation of remote sensing data.

Keywords: remote sensing, earth's surface interaction, electromagnetic radiation, spectral signatures, land cover classification, archeology and cultural heritage preservation

Procedia PDF Downloads 59

Authors: Mohammad Hadi Khorashadi Zadeh, Amin Karkon, Seyd Mohammad Reza Mashhoori ‎

Abstract:

the technology of Computer audit played a major role in the progress and ‎prospects of a proper application to improve the quality and efficiency of audit ‎work. But due to the technical complexity and the specific risks of computer ‎audit, it should be shown effective in audit and preventive action. Mainly through ‎research in this paper, we proposes the causes of audit risk in a computer ‎environment and the risk of further proposals for measures to control, to some ‎extent reduce the risk of computer audit and improve the audit quality.‎

Keywords: computer auditing, risk, measures to prevent, information technology

Procedia PDF Downloads 489

Authors: Roza Dzierzak, Waldemar Wojcik, Piotr Kacejko

Abstract:

Analysis of the texture of medical images consists of determining the parameters and characteristics of the examined tissue. The main goal is to assign the analyzed area to one of two basic groups: as a healthy tissue or a tissue with pathological changes. The CT images of the thoracic lumbar spine from 15 healthy patients and 15 with confirmed osteoporosis were used for the analysis. As a result, 120 samples with dimensions of 50x50 pixels were obtained. The set of features has been obtained based on the histogram, gradient, run-length matrix, co-occurrence matrix, autoregressive model, and Haar wavelet. As a result of the image analysis, 290 descriptors of textural features were obtained. The dimension of the space of features was reduced by the use of three selection methods: Fisher coefficient (FC), mutual information (MI), minimization of the classification error probability and average correlation coefficients between the chosen features minimization of classification error probability (POE) and average correlation coefficients (ACC). Each of them returned ten features occupying the initial place in the ranking devised according to its own coefficient. As a result of the Fisher coefficient and mutual information selections, the same features arranged in a different order were obtained. In both rankings, the 50% percentile (Perc.50%) was found in the first place. The next selected features come from the co-occurrence matrix. The sets of features selected in the selection process were evaluated using six classification tree methods. These were: decision stump (DS), Hoeffding tree (HT), logistic model trees (LMT), random forest (RF), random tree (RT) and reduced error pruning tree (REPT). In order to assess the accuracy of classifiers, the following parameters were used: overall classification accuracy (ACC), true positive rate (TPR, classification sensitivity), true negative rate (TNR, classification specificity), positive predictive value (PPV) and negative predictive value (NPV). Taking into account the classification results, it should be stated that the best results were obtained for the Hoeffding tree and logistic model trees classifiers, using the set of features selected by the POE + ACC method. In the case of the Hoeffding tree classifier, the highest values of three parameters were obtained: ACC = 90%, TPR = 93.3% and PPV = 93.3%. Additionally, the values of the other two parameters, i.e., TNR = 86.7% and NPV = 86.6% were close to the maximum values obtained for the LMT classifier. In the case of logistic model trees classifier, the same ACC value was obtained ACC=90% and the highest values for TNR=88.3% and NPV= 88.3%. The values of the other two parameters remained at a level close to the highest TPR = 91.7% and PPV = 91.6%. The results obtained in the experiment show that the use of classification trees is an effective method of classification of texture features. This allows identifying the conditions of the spongy tissue for healthy cases and those with the porosis.

Keywords: classification, feature selection, texture analysis, tree algorithms

Procedia PDF Downloads 178

Authors: Fariba Tadayon, Nika Gharahgolooyan, Ateke Tadayon, Mostafa Jafarian

Abstract:

Carotenoid pigments are a various group of lipophilic compounds that generate the yellow to red colors of many plants, foods and flowers. A well-known type of carotenoids which is pro-vitamin A is β-carotene. Due to the color of citrus fruit’s peel, the peel can be a good source of different carotenoids. Ostrich oil is one of the most valuable foundations in many branches of industry, medicine, cosmetics and nutrition. The animal-based ostrich oil could be considered as an alternative and green solvent. Following this study, wastes of citrus peel will recycle by a simple method and extracted carotenoids can increase properties of ostrich oil. In this work, a simple and efficient method for extraction of carotenoids from tangerine peel was designed. Ultrasound-assisted extraction (UAE) showed significant effect on the extraction rate by increasing the mass transfer rate. Ostrich oil can be used as a green solvent in many studies to eliminate petroleum-based solvents. Since tangerine peel is a complex source of different carotenoids separation and determination was performed by high-performance liquid chromatography (HPLC). In addition, the ability of ostrich oil and sunflower oil in carotenoid extraction from tangerine peel and carrot was compared. The highest yield of β-carotene extracted from tangerine peel using sunflower oil and ostrich oil were 75.741 and 88.110 (mg/L), respectively. Optimization of the process was achieved by response surface methodology (RSM) and the optimal extraction conditions were tangerine peel powder particle size of 0.180 mm, ultrasonic intensity of 19 W/cm2 and sonication time of 30 minutes.

Keywords: β-carotene, carotenoids, citrus peel, ostrich oil, response surface methodology, ultrasound-assisted extraction

Procedia PDF Downloads 316

Authors: Muhammad Saqlain, Nazar Abbas Saqib, Muazzam A. Khan

Abstract:

Heart Failure (HF) has become the major health problem in our society. The prevalence of HF has increased as the patient’s ages and it is the major cause of the high mortality rate in adults. A successful identification and progression of HF can be helpful to reduce the individual and social burden from this syndrome. In this study, we use a real data set of cardiac patients to propose a classification model for the identification and progression of HF. The data set has divided into three age groups, namely young, adult, and old and then each age group have further classified into four classes according to patient’s current physical condition. Contemporary Data Mining classification algorithms have been applied to each individual class of every age group to identify the HF. Decision Tree (DT) gives the highest accuracy of 90% and outperform all other algorithms. Our model accurately diagnoses different stages of HF for each age group and it can be very useful for the early prediction of HF.

Keywords: decision tree, heart failure, data mining, classification model

Procedia PDF Downloads 402

Authors: Seyed Mehdi Ghezi, Hesam Hasanpoor

Abstract:

This scientific article explores enhancement methods for ensemble learning with the aim of improving the performance of classifiers in the analysis and classification of brain signals. The research approach in this field consists of two main parts, each with its own strengths and weaknesses. The choice of approach depends on the specific research question and available resources. By combining these approaches and leveraging their respective strengths, researchers can enhance the accuracy and reliability of classification results, consequently advancing our understanding of the brain and its functions. The first approach focuses on utilizing machine learning methods to identify the best features among the vast array of features present in brain signals. The selection of features varies depending on the research objective, and different techniques have been employed for this purpose. For instance, the genetic algorithm has been used in some studies to identify the best features, while optimization methods have been utilized in others to identify the most influential features. Additionally, machine learning techniques have been applied to determine the influential electrodes in classification. Ensemble learning plays a crucial role in identifying the best features that contribute to learning, thereby improving the overall results. The second approach concentrates on designing and implementing methods for selecting the best classifier or utilizing meta-classifiers to enhance the final results in ensemble learning. In a different section of the research, a single classifier is used instead of multiple classifiers, employing different sets of features to improve the results. The article provides an in-depth examination of each technique, highlighting their advantages and limitations. By integrating these techniques, researchers can enhance the performance of classifiers in the analysis and classification of brain signals. This advancement in ensemble learning methodologies contributes to a better understanding of the brain and its functions, ultimately leading to improved accuracy and reliability in brain signal analysis and classification.

Keywords: ensemble learning, brain signals, classification, feature selection, machine learning, genetic algorithm, optimization methods, influential features, influential electrodes, meta-classifiers

Procedia PDF Downloads 75

Authors: Ashwini Mohan, Haris Batley

Abstract:

An orthodontic index is used to rate or categorise an individual’s occlusion using a numeric or alphanumeric score. Indexing of malocclusions and their correction is important in epidemiology, diagnosis, communication between clinicians as well as their patients and assessing treatment outcomes. Many useful indices have been put forward, but to the author’s best knowledge, no one method to this day appears to be equally suitable for the use of epidemiologists, public health program planners and clinicians. This article describes the common clinical orthodontic indices and classifications used in United Kingdom.

Keywords: classification, indices, orthodontics, validity

Procedia PDF Downloads 151

Authors: Sheldon McCall, Miao Yu, Liyun Gong, Shigang Yue, Stefanos Kollias

Abstract:

Falls are a significant health concern for older adults globally, and prompt identification is critical to providing necessary healthcare support. Our study proposes a new fall detection method using computer vision based on modern deep learning techniques. Our approach involves training a trans- former model on a large 2D pose dataset for general action recognition, followed by transfer learning. Specifically, we freeze the first few layers of the trained transformer model and train only the last two layers for fall detection. Our experimental results demonstrate that our proposed method outperforms both classical machine learning and deep learning approaches in fall/non-fall classification. Overall, our study suggests that our proposed methodology could be a valuable tool for identifying falls.

Keywords: healthcare, fall detection, transformer, transfer learning

Procedia PDF Downloads 146

Authors: Naser Safdarian, Nader Jafarnia Dabanloo

Abstract:

In this paper we used four features i.e. Q-wave integral, QRS complex integral, T-wave integral and total integral as extracted feature from normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our research we focused on detection and localization of MI in standard ECG. We use the Q-wave integral and T-wave integral because this feature is important impression in detection of MI. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI. Because these methods have good accuracy for classification of normal and abnormal signals. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 80% for accuracy in test data for localization and over 95% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve accuracy of classification by adding more features in this method. A simple method based on using only four features which extracted from standard ECG is presented which has good accuracy in MI localization.

Keywords: ECG signal processing, myocardial infarction, features extraction, pattern recognition

Procedia PDF Downloads 456

Authors: Nkechinyere Joy Olawuyi, Babajide Samuel Afolabi, Bola Ibitoye

Abstract:

This study collected a preprocessed dataset of chest radiographs and formulated a deep neural network model for detecting abnormalities. It also evaluated the performance of the formulated model and implemented a prototype of the formulated model. This was with the view to developing a deep neural network model to automatically classify abnormalities in chest radiographs. In order to achieve the overall purpose of this research, a large set of chest x-ray images were sourced for and collected from the CheXpert dataset, which is an online repository of annotated chest radiographs compiled by the Machine Learning Research Group, Stanford University. The chest radiographs were preprocessed into a format that can be fed into a deep neural network. The preprocessing techniques used were standardization and normalization. The classification problem was formulated as a multi-label binary classification model, which used convolutional neural network architecture to make a decision on whether an abnormality was present or not in the chest radiographs. The classification model was evaluated using specificity, sensitivity, and Area Under Curve (AUC) score as the parameter. A prototype of the classification model was implemented using Keras Open source deep learning framework in Python Programming Language. The AUC ROC curve of the model was able to classify Atelestasis, Support devices, Pleural effusion, Pneumonia, A normal CXR (no finding), Pneumothorax, and Consolidation. However, Lung opacity and Cardiomegaly had a probability of less than 0.5 and thus were classified as absent. Precision, recall, and F1 score values were 0.78; this implies that the number of False Positive and False Negative is the same, revealing some measure of label imbalance in the dataset. The study concluded that the developed model is sufficient to classify abnormalities present in chest radiographs into present or absent.

Keywords: transfer learning, convolutional neural network, radiograph, classification, multi-label

Procedia PDF Downloads 129

Authors: Djamel Fawzi Hadj Sadok, Marrone Silvério Melo Dantas Pedro Henrique Dreyer, Gabriel Fonseca Reis de Souza, Daniel Bezerra, Ricardo Souza, Silvia Lins, Judith Kelner

Abstract:

A radio base station (RBS), part of the radio access network, is a particular type of equipment that supports the connection between a wide range of cellular user devices and an operator network access infrastructure. Nowadays, most of the RBS maintenance is carried out manually, resulting in a time consuming and costly task. A suitable candidate for RBS maintenance automation is repairing faulty links between devices caused by missing or unplugged connectors. A suitable candidate for RBS maintenance automation is repairing faulty links between devices caused by missing or unplugged connectors. This paper proposes and compares two deep learning solutions to identify attached RJ45 connectors on network ports. We named connector detection, the solution based on object detection, and connector classification, the one based on object classification. With the connector detection, we get an accuracy of 0:934, mean average precision 0:903. Connector classification, get a maximum accuracy of 0:981 and an AUC of 0:989. Although connector detection was outperformed in this study, this should not be viewed as an overall result as connector detection is more flexible for scenarios where there is no precise information about the environment and the possible devices. At the same time, the connector classification requires that information to be well-defined.

Keywords: radio base station, maintenance, classification, detection, deep learning, automation

Procedia PDF Downloads 201

Authors: K. P. Sandesh, M. H. Suman

Abstract:

Text processing plays an important role in information retrieval, data-mining, and web search. Measuring the similarity between the documents is an important operation in the text processing field. In this project, a new similarity measure is proposed. To compute the similarity between two documents with respect to a feature the proposed measure takes the following three cases into account: (1) The feature appears in both documents; (2) The feature appears in only one document and; (3) The feature appears in none of the documents. The proposed measure is extended to gauge the similarity between two sets of documents. The effectiveness of our measure is evaluated on several real-world data sets for text classification and clustering problems, especially in banking and health sectors. The results show that the performance obtained by the proposed measure is better than that achieved by the other measures.

Keywords: document classification, document clustering, entropy, accuracy, classifiers, clustering algorithms

Procedia PDF Downloads 518

Authors: Rafael Marinho de Andrade, Elcio Hideti Shiguemori, Rafael Duarte Coelho dos Santos

Abstract:

Relying on computer vision, many clever things are possible in order to make the world safer and optimized on resource management, especially considering time and attention as manageable resources, once the modern world is very abundant in cameras from inside our pockets to above our heads while crossing the streets. Thus, automated solutions based on computer vision techniques to detect, react, or even prevent relevant events such as robbery, car crashes and traffic jams can be accomplished and implemented for the sake of both logistical and surveillance improvements. In this paper, we present an approach for vehicles’ abnormal behaviors detection from highway footages, in which the vectorial data of the vehicles’ displacement are extracted directly from surveillance cameras footage through object detection and tracking with a deep convolutional neural network and inserted into a long-short term memory neural network for behavior classification. The results show that the classifications of behaviors are consistent and the same principles may be applied to other trackable objects and scenarios as well.

Keywords: artificial intelligence, behavior detection, computer vision, convolutional neural networks, LSTM, highway footage

Procedia PDF Downloads 166

Authors: Liane Marcia Freitas Silva, Fernando Augusto Silva Marins, Maria Silene Alexandre Leite

Abstract:

The adoption of a network structure, like in the supply chains, favors the increase of dependence between companies and, by consequence, their vulnerability. Environment disasters, sociopolitical and economical events, and the dynamics of supply chains elevate the uncertainty of their operation, favoring the occurrence of events that can generate break up in the operations and other undesired consequences. Thus, supply chains are exposed to various risks that can influence the profitability of companies involved, and there are several previous studies that have proposed risk classification models in order to categorize the risks and to manage them. The objective of this paper is to analyze and discuss thirty of these risk classification models by means a theoretical survey. The research method adopted for analyzing and discussion includes three phases: The identification of the types of risks proposed in each one of the thirty models, the grouping of them considering equivalent concepts associated to their definitions, and, the analysis of these risks groups, evaluating their similarities and differences. After these analyses, it was possible to conclude that, in fact, there is more than thirty risks types identified in the literature of Supply Chains, but some of them are identical despite of be used distinct terms to characterize them, because different criteria for risk classification are adopted by researchers. In short, it is observed that some types of risks are identified as risk source for supply chains, such as, demand risk, environmental risk and safety risk. On the other hand, other types of risks are identified by the consequences that they can generate for the supply chains, such as, the reputation risk, the asset depreciation risk and the competitive risk. These results are consequence of the disagreements between researchers on risk classification, mainly about what is risk event and about what is the consequence of risk occurrence. An additional study is in developing in order to clarify how the risks can be generated, and which are the characteristics of the components in a Supply Chain that leads to occurrence of risk.

Keywords: sisks classification, survey, supply chain management, theoretical discussion

Procedia PDF Downloads 633

Authors: Mehran Asadi, Afrand Agah

Abstract:

In data mining, partitioning is used as a fundamental tool for classification. With the help of partitioning, we study the structure of data, which allows us to envision decision rules, which can be applied to classification trees. In this research, we used online social network dataset and all of its attributes (e.g., Node features, labels, etc.) to determine what constitutes an above average chance of being a divergent node. We used the R statistical computing language to conduct the analyses in this report. The data were found on the UC Irvine Machine Learning Repository. This research introduces the basic concepts of classification in online social networks. In this work, we utilize overfitting and describe different approaches for evaluation and performance comparison of different classification methods. In classification, the main objective is to categorize different items and assign them into different groups based on their properties and similarities. In data mining, recursive partitioning is being utilized to probe the structure of a data set, which allow us to envision decision rules and apply them to classify data into several groups. Estimating densities is hard, especially in high dimensions, with limited data. Of course, we do not know the densities, but we could estimate them using classical techniques. First, we calculated the correlation matrix of the dataset to see if any predictors are highly correlated with one another. By calculating the correlation coefficients for the predictor variables, we see that density is strongly correlated with transitivity. We initialized a data frame to easily compare the quality of the result classification methods and utilized decision trees (with k-fold cross validation to prune the tree). The method performed on this dataset is decision trees. Decision tree is a non-parametric classification method, which uses a set of rules to predict that each observation belongs to the most commonly occurring class label of the training data. Our method aggregates many decision trees to create an optimized model that is not susceptible to overfitting. When using a decision tree, however, it is important to use cross-validation to prune the tree in order to narrow it down to the most important variables.

Keywords: online social networks, data mining, social cloud computing, interaction and collaboration

Procedia PDF Downloads 157

Authors: Subham Kharel, Sudha Ravindranath, A. Vidya, B. Chandrasekaran, K. Ganesha Raj, T. Shesadri

Abstract:

Digitization of urban features is a tedious and time-consuming process when done manually. In addition to this problem, Indian cities have complex habitat patterns and convoluted clustering patterns, which make it even more difficult to map features. This paper makes an attempt to classify urban objects in the satellite image using object-oriented classification techniques in which various classes such as vegetation, water bodies, buildings, and shadows adjacent to the buildings were mapped semi-automatically. Building layer obtained as a result of object-oriented classification along with already available building layers was used. The main focus, however, lay in the extraction of high-rise buildings using spatial technology, digital image processing, and modeling, which would otherwise be a very difficult task to carry out manually. Results indicated a considerable rise in the total number of buildings in the city. High-rise buildings were successfully mapped using satellite imagery, spatial technology along with logical reasoning and mathematical considerations. The results clearly depict the ability of Remote Sensing and GIS to solve complex problems in urban scenarios like studying urban sprawl and identification of more complex features in an urban area like high-rise buildings and multi-dwelling units. Object-Oriented Technique has been proven to be effective and has yielded an overall efficiency of 80 percent in the classification of high-rise buildings.

Keywords: object oriented classification, shadow extraction, high-rise buildings, satellite imagery, spatial technology

Procedia PDF Downloads 155

Authors: Kumar Shashvat, Amol P. Bhondekar

Abstract:

In the midst of the five senses, odor is the most reminiscent and least understood. Odor testing has been mysterious and odor data fabled to most practitioners. The delinquent of recognition and classification of odor is important to achieve. The facility to smell and predict whether the artifact is of further use or it has become undesirable for consumption; the imitation of this problem hooked on a model is of consideration. The general industrial standard for this classification is color based anyhow; odor can be improved classifier than color based classification and if incorporated in machine will be awfully constructive. For cataloging of odor for peas, trees and cashews various discriminative approaches have been used Discriminative approaches offer good prognostic performance and have been widely used in many applications but are incapable to make effectual use of the unlabeled information. In such scenarios, generative approaches have better applicability, as they are able to knob glitches, such as in set-ups where variability in the series of possible input vectors is enormous. Generative models are integrated in machine learning for either modeling data directly or as a transitional step to form an indeterminate probability density function. The algorithms or models Linear Discriminant Analysis and Naive Bayes Classifier have been used for classification of the odor of cashews. Linear Discriminant Analysis is a method used in data classification, pattern recognition, and machine learning to discover a linear combination of features that typifies or divides two or more classes of objects or procedures. The Naive Bayes algorithm is a classification approach base on Bayes rule and a set of qualified independence theory. Naive Bayes classifiers are highly scalable, requiring a number of restraints linear in the number of variables (features/predictors) in a learning predicament. The main recompenses of using the generative models are generally a Generative Models make stronger assumptions about the data, specifically, about the distribution of predictors given the response variables. The Electronic instrument which is used for artificial odor sensing and classification is an electronic nose. This device is designed to imitate the anthropological sense of odor by providing an analysis of individual chemicals or chemical mixtures. The experimental results have been evaluated in the form of the performance measures i.e. are accuracy, precision and recall. The investigational results have proven that the overall performance of the Linear Discriminant Analysis was better in assessment to the Naive Bayes Classifier on cashew dataset.

Keywords: odor classification, generative models, naive bayes, linear discriminant analysis

Procedia PDF Downloads 387

Authors: Raana Babadi Fathipour

Abstract:

Tea, a beverage widely cherished across the globe, has captured the interest of scholars with its recent acknowledgement for possessing noteworthy health advantages. Of particular significance is its proven ability to ward off ailments such as cancer and cardiovascular afflictions. Moreover, within the realm of culinary creations, lipid oxidation poses a significant challenge for food product development. In light of these aforementioned concerns, this present discourse turns its attention towards exploring diverse methodologies employed in extracting polyphenols from various types of tea leaves and examining their utility within the vast landscape of the ever-evolving food industry. Based on the discoveries unearthed in this comprehensive investigation, it has been determined that the fundamental constituents of tea are polyphenols possessed of intrinsic health-enhancing properties. This includes an assortment of catechins, namely epicatechin, epigallocatechin, epicatechin gallate, and epigallocatechin gallate. Moreover, gallic acid, flavonoids, flavonols and theaphlavins have also been detected within this aromatic beverage. Of these myriad components examined vigorously in this study's analysis, catechin emerges as particularly beneficial. Multiple techniques have emerged over time to successfully extract key compounds from tea plants, including solvent-based extraction methodologies, microwave-assisted water extraction approaches and ultrasound-assisted extraction techniques. In particular, consideration is given to microwave-assisted water extraction method as a viable scheme which effectively procures valuable polyphenols from tea extracts. This methodology appears adaptable for implementation within sectors such as dairy production along with meat and oil industries alike.

Keywords: camellia sinensis, extraction, food application, shelf life, tea

Procedia PDF Downloads 70

Authors: Preshanthan Moodley, E. B. Gueguim-Kana

Abstract:

The objective of this study was to develop a method to pretreat sugarcane leaf waste using microwave-assisted (MA) inorganic salt. The effects of process parameters of salt concentration, microwave power intensity and pretreatment time on reducing sugar yield from enzymatically hydrolysed sugarcane leaf waste were investigated. Pretreatment models based on MA-NaCl, MA-ZnCl2 and MA-FeCl3 were developed. Maximum reducing sugar yield of 0.406 g/g was obtained with 2 M FeCl3 at 700W for 3.5 min. Scanning electron microscopy (SEM) and Fourier Transform Infrared analysis (FTIR) showed major changes in lignocellulosic structure after MA-FeCl3 pretreatment with 71.5 % hemicellulose solubilization. This pretreatment was further assessed on sorghum leaves and Napier grass under optimal MA-FeCl3 conditions. A 2 fold and 3.1-fold increase in sugar yield respectively were observed compared to previous reports. This pretreatment was highly effective for enhancing enzymatic saccharification of lignocellulosic biomass.

Keywords: acid, pretreatment, salt, sugarcane leaves

Procedia PDF Downloads 453