Search results for: fault detection and classification

Authors: M. V. Chidananda Murthy, M. Z. Kurian, H. S. Guruprasad

Abstract:

Image restoration in the process of communication is one of the emerging fields in the image processing. The motion analysis processing is the simplest case to detect motion in an image. Applications of motion analysis widely spread in many areas such as surveillance, remote sensing, film industry, navigation of autonomous vehicles, etc. The scene may contain multiple moving objects, by using motion analysis techniques the blur caused by the movement of the objects can be enhanced by filling-in occluded regions and reconstruction of transparent objects, and it also removes the motion blurring. This paper presents the design and comparison of various motion detection and enhancement filters. Median filter, Linear image deconvolution, Inverse filter, Pseudoinverse filter, Wiener filter, Lucy Richardson filter and Blind deconvolution filters are used to remove the blur. In this work, we have considered different types and different amount of blur for the analysis. Mean Square Error (MSE) and Peak Signal to Noise Ration (PSNR) are used to evaluate the performance of the filters. The designed system has been implemented in Matlab software and tested for synthetic and real-time images.

Keywords: image enhancement, motion analysis, motion detection, motion estimation

Procedia PDF Downloads 288

Authors: Hamed Alqahtani, Manolya Kavakli-Thorne

Abstract:

The large pose discrepancy is one of the critical challenges in face recognition during video surveillance. Due to the entanglement of pose attributes with identity information, the conventional approaches for pose-independent representation lack in providing quality results in recognizing largely posed faces. In this paper, we propose a practical approach to disentangle the pose attribute from the identity information followed by synthesis of a face using a classifier network in latent space. The proposed approach employs a modified generative adversarial network framework consisting of an encoder-decoder structure embedded with a classifier in manifold space for carrying out factorization on the latent encoding. It can be further generalized to other face and non-face attributes for real-life video frames containing faces with significant attribute variations. Experimental results and comparison with state of the art in the field prove that the learned representation of the proposed approach synthesizes more compelling perceptual images through a combination of adversarial and classification losses.

Keywords: disentanglement, face detection, generative adversarial networks, video surveillance

Procedia PDF Downloads 129

Authors: A. J. Babajanyan, T. A. Abrahamyan, H. A. Minasyan, K. V. Nerkararyan

Abstract:

Optical radiation emitted from a metal-coated fiber tip apex at liquid-air interface was measured. The intensity of the output radiation was strongly depending on the relative position of the tip to a liquid-air interface and varied with surface fluctuations. This phenomenon permits in-situ real-time investigation of nano-metric vibrations of the liquid surface and provides a basis for development of various origin ultrasensitive vibration detecting sensors. The described method can be used for detection of week seismic vibrations.

Keywords: fiber-tip, liquid-air interface, nano vibration, opto-mechanical sensor

Procedia PDF Downloads 484

Authors: Yaojun Wang, Yaoqing Wang

Abstract:

Stock selection is an important decision-making problem. Many machine learning and data mining technologies are employed to build automatic stock-selection system. A profitable stock-selection system should consider the stock’s investment value and the market timing. In this paper, we present a hybrid system including both engage for stock selection. This system uses a case-based reasoning (CBR) model to execute the stock classification, uses a decision-tree model to help with market timing and stock selection. The experiments show that the performance of this hybrid system is better than that of other techniques regarding to the classification accuracy, the average return and the Sharpe ratio.

Keywords: case-based reasoning, decision tree, stock selection, machine learning

Procedia PDF Downloads 420

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 187

Authors: Mahsa Mousavi, Hamid Reza Pourshaghaghi, Mohammad Tahghighi, Henk Corporaal

Abstract:

Recently, Statistic Random-Access Memory-based (SRAM-based) Field-Programmable Gate Arrays (FPGAs) are widely used in aeronautics and space systems where high dependability is demanded and considered as a mandatory requirement. Since design’s circuit is stored in configuration memory in SRAM-based FPGAs; they are very sensitive to Single Event Upsets (SEUs). In addition, the adverse effects of SEUs on the electronics used in space are much higher than in the Earth. Thus, developing fault tolerant techniques play crucial roles for the use of SRAM-based FPGAs in space. However, fault tolerance techniques introduce additional penalties in system parameters, e.g., area, power, performance and design time. In this paper, an accurate estimation of configuration memory vulnerability to SEUs is proposed for approximate-tolerant applications. This vulnerability estimation is highly required for compromising between the overhead introduced by fault tolerance techniques and system robustness. In this paper, we study applications in which the exact final output value is not necessarily always a concern meaning that some of the SEU-induced changes in output values are negligible. We therefore define and propose Approximate-based Configuration Memory Vulnerability Factor (ACMVF) estimation to avoid overestimating configuration memory vulnerability to SEUs. In this paper, we assess the vulnerability of configuration memory by injecting SEUs in configuration memory bits and comparing the output values of a given circuit in presence of SEUs with expected correct output. In spite of conventional vulnerability factor calculation methods, which accounts any deviations from the expected value as failures, in our proposed method a threshold margin is considered depending on user-case applications. Given the proposed threshold margin in our model, a failure occurs only when the difference between the erroneous output value and the expected output value is more than this margin. The ACMVF is subsequently calculated by acquiring the ratio of failures with respect to the total number of SEU injections. In our paper, a test-bench for emulating SEUs and calculating ACMVF is implemented on Zynq-7000 FPGA platform. This system makes use of the Single Event Mitigation (SEM) IP core to inject SEUs into configuration memory bits of the target design implemented in Zynq-7000 FPGA. Experimental results for 32-bit adder show that, when 1% to 10% deviation from correct output is considered, the counted failures number is reduced 41% to 59% compared with the failures number counted by conventional vulnerability factor calculation. It means that estimation accuracy of the configuration memory vulnerability to SEUs is improved up to 58% in the case that 10% deviation is acceptable in output results. Note that less than 10% deviation in addition result is reasonably tolerable for many applications in approximate computing domain such as Convolutional Neural Network (CNN).

Keywords: fault tolerance, FPGA, single event upset, approximate computing

Procedia PDF Downloads 198

Authors: Kenneth Fon Mbah, Arash Habibi Lashkari, Ali A. Ghorbani

Abstract:

Phishing e-mails are a security issue that not only annoys online users, but has also resulted in significant financial losses for businesses. Phishing advertisements and pornographic e-mails are difficult to detect as attackers have been becoming increasingly intelligent and professional. Attackers track users and adjust their attacks based on users’ attractions and hot topics that can be extracted from community news and journals. This research focuses on deceptive Phishing attacks and their variants such as attacks through advertisements and pornographic e-mails. We propose a framework called Phishing Alerting System (PHAS) to accurately classify e-mails as Phishing, advertisements or as pornographic. PHAS has the ability to detect and alert users for all types of deceptive e-mails to help users in decision making. A well-known email dataset has been used for these experiments and based on previously extracted features, 93.11% detection accuracy is obtainable by using J48 and KNN machine learning techniques. Our proposed framework achieved approximately the same accuracy as the benchmark while using this dataset.

Keywords: phishing e-mail, phishing detection, anti phishing, alarm system, machine learning

Procedia PDF Downloads 341

Authors: Andrea Bellucci, Martina Tofi

Abstract:

The aim of paper is to analyze business models of bancassurance in Italy for life business. The life insurance business is very developed in the Italian market and banks branches have 80% of the market share. Given its maturity, the life insurance market needs to consolidate its organizational form to allow for the development of non-life business, which nowadays collects few premiums but represents a great opportunity to enlarge the market share of bancassurance using its strength in the distribution channel while the market share of independent agents is decreasing. Starting with the main business model of bancassurance for life business, this paper will analyze the performances of life companies in the Italian market by balance sheet indicators and by main discriminant variables of business models. The study will observe trends from 2013 to 2015 for the Italian market by exploiting a database managed by Associazione Nazionale delle Imprese di Assicurazione (ANIA). The applied approach is based on a bottom-up analysis starting with variables and indicators to define business models’ classification. The statistical classification algorithm proposed by Ward is employed to design business models’ profiles. Results from the analysis will be a representation of the main business models built by their profile related to indicators. In that way, an unsupervised analysis is developed that has the limit of its judgmental dimension based on research opinion, but it is possible to obtain a design of effective business models.

Keywords: bancassurance, business model, non life bancassurance, insurance business value drivers

Procedia PDF Downloads 299

Authors: Afsal Mohammed Kadavilpparampu, Haider A. J. Al Lawati, Fakhr Eldin O. Suliman, Salma M. Z. Al Kindy

Abstract:

In this work, we evaluated the appropriateness of various oxidants that can be used potentially with Ru(bipy)32+ CL system while performing CL detection in a microfluidic device using eight common active pharmaceutical ingredients- ciprofloxacin, hydrochlorothiazide, norfloxacin, buspirone, fexofenadine, cetirizine, codeine, and dextromethorphan. This is because, microfludics have very small channel volume and the residence time is also very short. Hence, a highly efficient oxidant is required for on-chip CL detection to obtain analytically acceptable CL emission. Three common oxidants were evaluated, lead dioxide, cerium ammonium sulphate and ammonium peroxydisulphate. Results obtained showed that ammonium peroxydisulphate is the most appropriate oxidant which can be used in microfluidic setup and all the tested analyte give strong CL emission while using this oxidant. We also found that Ru(bipy)33+ generated off-line by oxidizing [Ru(bipy)3]Cl2.6H2O in acetonitrile under acidic condition with lead dioxide was stable for more than 72 hrs. A highly sensitive microbore HPLC- CL method using ammonium peroxydisulphate as an oxidant in a microfluidic on-chip CL detection has been developed for the analyses of fixed-dose combinations of pseudoephedrine (PSE), fexofenadine (FEX) and cetirizine (CIT) in biological fluids and pharmaceutical formulations with minimum sample pre-treatment.

Keywords: oxidants, microbore High Performance Liquid Chromatography, chemiluminescence, microfluidics

Procedia PDF Downloads 449

Authors: Sai Snehitha Yadavalli, K. Sruthi, Swati Ghosh Acharyya

Abstract:

Heavy metal ions are toxic to humans and all living species when exposed in large quantities or for long durations. Though Fe acts as a nutrient, when intake is in large quantities, it becomes toxic. These toxic heavy metal ions, when consumed through water, will cause many disorders and are harmful to all flora and fauna through biomagnification. Specifically, humans are prone to innumerable diseases ranging from skin to gastrointestinal, neurological, etc. In higher quantities, they even cause cancer in humans. Detection of these toxic heavy metal ions in water is thus important. Traditionally, the detection of heavy metal ions in water has been done by techniques like Inductively Coupled Plasma Mass Spectroscopy (ICPMS) and Atomic Absorption Spectroscopy (AAS). Though these methods offer accurate quantitative analysis, they require expensive equipment and cannot be used for on-site measurements. Anodic Stripping Voltammetry is a good alternative as the equipment is affordable, and measurements can be made at the river basins or lakes. In the current study, Square Wave Anodic Stripping Voltammetry (SWASV) was used to detect the heavy metal ions in water. Literature reports various electrodes on which deposition of heavy metal ions was carried out like Bismuth, Polymers, etc. The working electrode used in this study is a polyvinyl chloride (PVC) modified glassy carbon electrode (GCE). Ag/AgCl reference electrode and Platinum counter electrode were used. Biologic Potentiostat SP 300 was used for conducting the experiments. Through this work of simultaneous detection, four heavy metal ions were successfully detected at a time. The influence of modifying GCE with PVC was studied in comparison with unmodified GCE. The simultaneous detection of Cd⁺², Fe⁺², Co⁺², Pb⁺² heavy metal ions was done using PVC modified GCE by drop casting 1 wt.% of PVC dissolved in Tetra Hydro Furan (THF) solvent onto GCE. The concentration of all heavy metal ions was 0.2 mg/L, as shown in the figure. The scan rate was 0.1 V/s. Detection parameters like pH, scan rate, temperature, time of deposition, etc., were optimized. It was clearly understood that PVC helped in increasing the sensitivity and selectivity of detection as the current values are higher for PVC-modified GCE compared to unmodified GCE. The peaks were well defined when PVC-modified GCE was used.

Keywords: cadmium, cobalt, electrochemical sensing, glassy carbon electrodes, heavy metal Ions, Iron, lead, polyvinyl chloride, potentiostat, square wave anodic stripping voltammetry

Procedia PDF Downloads 103

Authors: Endrick Barnacin, Jean-Luc Henry, Jimmy Nagau, Jack Molinie

Abstract:

Palynology is a field of interest in many disciplines due to its multiple applications: chronological dating, climatology, allergy treatment, and honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time consuming task that requires the intervention of experts in the field, which are becoming increasingly rare due to economic and social conditions. That is why the need for automation of this task is urgent. A lot of studies have investigated the subject using different standard image processing descriptors and sometimes hand-crafted ones.In this work, we make a comparative study between classical feature extraction methods (Shape, GLCM, LBP, and others) and Deep Learning (CNN, Autoencoders, Transfer Learning) to perform a recognition task over 80 regional pollen species. It has been found that the use of Transfer Learning seems to be more precise than the other approaches

Keywords: pollens identification, features extraction, pollens classification, automated palynology

Procedia PDF Downloads 136

Authors: Meysam Jamali, Ebrahim Moghimi, Zean Alabden Jafarpour

Abstract:

Karst term is the determiner of a variety of areas or landforms and unique perspectives that have been formed in result of the ingredients dissolution of rocks constituter by natural waters. Shiraz area with an area of 5322km2 is located in the simple folded belt in the southern part of Zagros Mountain of Fars, and is surrounded with Limestone Mountains (Asmari formation). Shiraz area is located in Calcareous areas. The Infrastructure of this city is lime and absorbing wells that the city has, can influence on the Limestone dissolution and those accelerate its rate and increases the cavitation below the surface. Dasht-e Arjan is a graben, which has been created as the result of activity of two normal faults in its east and west sides. It is a complete sample of Karst plains (Polje) which has been created with the help of tectonic forces (fault) and dissolution process of water in Asmari limestone formation. It is located 60km. off south west of Shiraz (on Kazeroon-Shiraz road). In 1971, UNESCO has recognized this plain as a reserve of biosphere. It is considered as one of the world’s most beautiful geological phenomena, so that most of the world’s geologists are interested in visiting this place. The purpose of this paper is to identify and introduce landscapes of Karst features shiraz city and Dasht-e Arjan including Karst dissolution features (Lapiez, Karst springs, dolines, caves, underground caves, ponors, and Karst valleys), anticlines and synclines, and Arjan Lake, which are studied in this paper.

Keywords: Dasht-eArjan, fault, Karst features, polje, Shiraz city, Zagros

Procedia PDF Downloads 420

Authors: Yan Zhang

Abstract:

Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. Analytics-driven predictive maintenance is gaining increasing attention in many industries such as manufacturing, utilities, aerospace, etc., along with the emerging demand of Internet of Things (IoT) applications and the maturity of technologies that support Big Data storage and processing. This study aims to build an end-to-end analytics solution that includes both real-time machine condition monitoring and machine learning based predictive analytics capabilities. The goal is to showcase a general predictive maintenance solution architecture, which suggests how the data generated from field machines can be collected, transmitted, stored, and analyzed. We use a publicly available aircraft engine run-to-failure dataset to illustrate the streaming analytics component and the batch failure prediction component. We outline the contributions of this study from four aspects. First, we compare the predictive maintenance problems from the view of the traditional reliability centered maintenance field, and from the view of the IoT applications. When evolving to the IoT era, predictive maintenance has shifted its focus from ensuring reliable machine operations to improve production/maintenance efficiency via any maintenance related tasks. It covers a variety of topics, including but not limited to: failure prediction, fault forecasting, failure detection and diagnosis, and recommendation of maintenance actions after failure. Second, we review the state-of-art technologies that enable a machine/device to transmit data all the way through the Cloud for storage and advanced analytics. These technologies vary drastically mainly based on the power source and functionality of the devices. For example, a consumer machine such as an elevator uses completely different data transmission protocols comparing to the sensor units in an environmental sensor network. The former may transfer data into the Cloud via WiFi directly. The latter usually uses radio communication inherent the network, and the data is stored in a staging data node before it can be transmitted into the Cloud when necessary. Third, we illustrate show to formulate a machine learning problem to predict machine fault/failures. By showing a step-by-step process of data labeling, feature engineering, model construction and evaluation, we share following experiences: (1) what are the specific data quality issues that have crucial impact on predictive maintenance use cases; (2) how to train and evaluate a model when training data contains inter-dependent records. Four, we review the tools available to build such a data pipeline that digests the data and produce insights. We show the tools we use including data injection, streaming data processing, machine learning model training, and the tool that coordinates/schedules different jobs. In addition, we show the visualization tool that creates rich data visualizations for both real-time insights and prediction results. To conclude, there are two key takeaways from this study. (1) It summarizes the landscape and challenges of predictive maintenance applications. (2) It takes an example in aerospace with publicly available data to illustrate each component in the proposed data pipeline and showcases how the solution can be deployed as a live demo.

Keywords: Internet of Things, machine learning, predictive maintenance, streaming data

Procedia PDF Downloads 386

Authors: Ashlesha Khanapure, Harsh Kashyap, Abhinav Anand, Sanjana Habib, Anupama Bidargaddi

Abstract:

Technologies that are developing quickly are being developed daily in a variety of disciplines, particularly the medical field. For the purpose of detecting bone fractures in X-ray pictures of different body segments, our work compares the ResNet-50 and MobileNetV3 architectures. It evaluates accuracy and computing efficiency with X-rays of the elbow, hand, and shoulder from the MURA dataset. Through training and validation, the models are evaluated on normal and fractured images. While ResNet-50 showcases superior accuracy in fracture identification, MobileNetV3 showcases superior speed and resource optimization. Despite ResNet-50’s accuracy, MobileNetV3’s swifter inference makes it a viable choice for real-time clinical applications, emphasizing the importance of balancing computational efficiency and accuracy in medical imaging. We created a graphical user interface (GUI) for MobileNet V3 model bone fracture detection. This research underscores MobileNetV3’s potential to streamline bone fracture diagnoses, potentially revolutionizing orthopedic medical procedures and enhancing patient care.

Keywords: CNN, MobileNet V3, ResNet-50, healthcare, MURA, X-ray, fracture detection

Procedia PDF Downloads 65

Authors: Mohammed Al Sulaimani, Hamad Al Manhi

Abstract:

With the development of Remote Sensing technology, the resolution of optical Remote Sensing images has greatly improved, and images have become largely available. Numerous detectors have been developed for detecting different types of objects. In the past few years, Remote Sensing has benefited a lot from deep learning, particularly Deep Convolution Neural Networks (CNNs). Deep learning holds great promise to fulfill the challenging needs of Remote Sensing and solving various problems within different fields and applications. The use of Unmanned Aerial Systems in acquiring Aerial Photos has become highly used and preferred by most organizations to support their activities because of their high resolution and accuracy, which make the identification and detection of very small features much easier than Satellite Images. And this has opened an extreme era of Deep Learning in different applications not only in feature extraction and prediction but also in analysis. This work addresses the capacity of Machine Learning and Deep Learning in detecting and extracting Oil Leaks from Flowlines (Onshore) using High-Resolution Aerial Photos which have been acquired by UAS fixed with RGB Sensor to support early detection of these leaks and prevent the company from the leak’s losses and the most important thing environmental damage. Here, there are two different approaches and different methods of DL have been demonstrated. The first approach focuses on detecting the Oil Leaks from the RAW Aerial Photos (not processed) using a Deep Learning called Single Shoot Detector (SSD). The model draws bounding boxes around the leaks, and the results were extremely good. The second approach focuses on detecting the Oil Leaks from the Ortho-mosaiced Images (Georeferenced Images) by developing three Deep Learning Models using (MaskRCNN, U-Net and PSP-Net Classifier). Then, post-processing is performed to combine the results of these three Deep Learning Models to achieve a better detection result and improved accuracy. Although there is a relatively small amount of datasets available for training purposes, the Trained DL Models have shown good results in extracting the extent of the Oil Leaks and obtaining excellent and accurate detection.

Keywords: GIS, remote sensing, oil leak detection, machine learning, aerial photos, unmanned aerial systems

Procedia PDF Downloads 34

Authors: Ismayanti Magfirah, Sartohadi Junun, Samodra Guruh

Abstract:

Landslides are one of the most frequent and devastating natural disasters in Indonesia. Many studies have been conducted regarding this phenomenon. However, there is a lack of attention in the landslide inventory mapping. The natural condition (dense forest area) and the limited human and economic resources are some of the major problems in building landslide inventory in Indonesia. Considering the importance of landslide inventory data in susceptibility, hazard, and risk analysis, it is essential to generate landslide inventory based on available resources. In order to achieve this, the first thing we have to do is identify the landslides' location. The presence of Sentinel-1A and Sentinel-2A data gives new insights into land monitoring investigation. The free access, high spatial resolution, and short revisit time, make the data become one of the most trending open sources data used in landslide mapping. Sentinel-1A and Sentinel-2A data have been used broadly for landslide detection and landuse/landcover mapping. This study aims to generate landslide map by integrating Sentinel-1A and Sentinel-2A data use change detection method. The result will be validated by field investigation to make preliminary landslide inventory in the study area.

Keywords: change detection method, landslide inventory mapping, Sentinel-1A, Sentinel-2A

Procedia PDF Downloads 171

Authors: Aly Elshafei, Daniela Romano

Abstract:

With the development of autonomous vehicles, a human-machine interaction (HMI) system is needed for a safe transition of control when a takeover request (TOR) is required. An important part of the HMI system is the ability to monitor the level of situational awareness (SA) of any driver in real-time, in different scenarios, and without any pre-calibration. Presenting state-of-the-art machine learning models used to measure SA is the purpose of this systematic review. Investigating the limitations of each type of sensor, the gaps, and the most suited sensor and computational model that can be used in driving applications. To the author’s best knowledge this is the first literature review identifying online and offline classification methods used to measure SA, explaining which measurements are subject or session-specific, and how many classifications can be done with each classification model. This information can be very useful for researchers measuring SA to identify the most suited model to measure SA for different applications.

Keywords: situational awareness, autonomous driving, gaze metrics, EEG, ECG

Procedia PDF Downloads 119

Authors: Ki Hyun Park, Hye Min Park, Jeong Ho Kim, Chan Jong Park, Koan Sik Joo

Abstract:

In the modern days, the use of radioactive substances is on the rise in the areas like chemical weaponry, industrial usage, and power plants. Although there are various technologies available to detect and monitor radioactive substances in the air, the technologies to detect underwater radioactive substances are scarce. In this study, computer simulation of the underwater detection system measuring beta-ray, a radioactive substance, has been done through MCNP. CaF₂, YAP(Ce) and YAG(Ce) have been used in the computer simulation to detect beta-ray as scintillator. Also, the source used in the computer simulation is Sr-90 and Y-90, both of them emitting only pure beta-ray. The distance between the source and the detector was shifted from 1mm to 10mm by 1 mm in the computer simulation. The result indicated that Sr-90 was impossible to measure below 1 mm since its emission energy is low while Y-90 was able to be measured up to 10mm underwater. In addition, the detector designed with CaF₂ had the highest efficiency among 3 scintillators used in the computer simulation. Since it was possible to verify the detectable range and the detection efficiency according to modeling through MCNP simulation, it is expected that such result will reduce the time and cost in building the actual beta-ray detector and evaluating its performances, thereby contributing the research and development.

Keywords: Beta-ray, CaF₂, detector, MCNP simulation, scintillator

Procedia PDF Downloads 510

Authors: Benhammadi Hocine, Djamel Boubaya, Chaffai Hicham

Abstract:

Meskiana Area is characterized by a semi-arid climate where the water supply for irrigation and industry is not sufficient as the priority goes for domestic use. To meet the increasing population growth and development, the authorities have considered building a new water retaining structure on some major temporary water streams. For this purpose Chebabta site on Oued Meskiana was chosen as the future dam site. It is large enough to store the desired volume of water. This study comes to investigate the conditions of the site and the adequacy of the ground as a foundation for the projected dam. The conditions of the site include the geological structure and mainly the presence of discontinuities in the formation on which the dam will be built, the nature of the lithologies under the foundation and the future lake, and the presence of any hazard. This site characterization is usually carried out using different methods in order to highlight any underground buried problematic structure. In this context, the different geophysical technics remain the most used ones. Three geophysical methods were used in the case of the Chebabta dam site, namely, electric survey, seismic refraction, and tomography. The choice of the technics and the location of the scan line was made on the basis of the available geological data. In this sense, profiles have been established on both banks of Oued Meskiana. The obtained results have allowed a better characterization of the geological structure, defining the limit between the surface cover and the bedrock, which is, in other words, the limit between the weathered zone and the bedrock. Their respective thicknesses were also determined by seismic refraction and electrical resistivity sounding. However, the tomography imaging technic has succeeded in positioning a fault structure passing through the right bank of the wadi.

Keywords: dam site, fault, geophysic, investigation, Meskiana

Procedia PDF Downloads 88

Authors: Hongmei Chi

Abstract:

The Blockchain has become a necessity for many different societal industries and ordinary lives including cryptocurrency technology, supply chain, health care, public safety, education, etc. Therefore, training our future blockchain developers to know blockchain programming vulnerability and I.T. students' cyber security is in high demand. In this work, we propose a framework including learning modules and hands-on labs to guide future I.T. professionals towards developing secure blockchain programming habits and mitigating source code vulnerabilities at the early stages of the software development lifecycle following the concept of Secure Software Development Life Cycle (SSDLC). In this research, our goal is to make blockchain programmers and I.T. students aware of the vulnerabilities of blockchains. In summary, we develop a framework that will (1) improve students' skills and awareness of blockchain source code vulnerabilities, detection tools, and mitigation techniques (2) integrate concepts of blockchain vulnerabilities for IT students, (3) improve future IT workers’ ability to master the concepts of blockchain attacks.

Keywords: software vulnerability detection, hands-on lab, static analysis tools, vulnerabilities, blockchain, active learning

Procedia PDF Downloads 99

Authors: Nicholas Mavrogiannis, Francesca Crivellari, Zachary Gagnon

Abstract:

Development of low-cost, rapid, sensitive and portable biosensing systems are important for the detection and prevention of disease in developing countries, biowarfare/antiterrorism applications, environmental monitoring, point-of-care diagnostic testing and for basic biological research. Currently, the most established commercially available and widespread assays for portable point of care detection and disease testing are paper-based dipstick and lateral flow test strips. These paper-based devices are often small, cheap and simple to operate. The last three decades in particular have seen an emergence in these assays in diagnostic settings for detection of pregnancy, HIV/AIDS, blood glucose, Influenza, urinary protein, cardiovascular disease, respiratory infections and blood chemistries. Such assays are widely available largely because they are inexpensive, lightweight, and portable, are simple to operate, and a few platforms are capable of multiplexed detection for a small number of sample targets. However, there is a critical need for sensitive, quantitative and multiplexed detection capabilities for point-of-care diagnostics and for the detection and prevention of disease in the developing world that cannot be satisfied by current state-of-the-art paper-based assays. For example, applications including the detection of cardiac and cancer biomarkers and biothreat applications require sensitive multiplexed detection of analytes in the nM and pM range, and cannot currently be satisfied with current inexpensive portable platforms due to their lack of sensitivity, quantitative capabilities and often unreliable performance. In this talk, inexpensive label-free biomolecular detection at liquid interfaces using a newly discovered electrokinetic phenomenon known as fluidic dielectrophoresis (fDEP) is demonstrated. The electrokinetic approach involves exploiting the electrical mismatches between two aqueous liquid streams forced to flow side-by-side in a microfluidic T-channel. In this system, one fluid stream is engineered to have a higher conductivity relative to its neighbor which has a higher permittivity. When a “low” frequency (< 1 MHz) alternating current (AC) electrical field is applied normal to this fluidic electrical interface the fluid stream with high conductivity displaces into the low conductive stream. Conversely, when a “high” frequency (20MHz) AC electric field is applied, the high permittivity stream deflects across the microfluidic channel. There is, however, a critical frequency sensitive to the electrical differences between each fluid phase – the fDEP crossover frequency – between these two events where no fluid deflection is observed, and the interface remains fixed when exposed to an external field. To perform biomolecular detection, two streams flow side-by-side in a microfluidic T-channel: one fluid stream with an analyte of choice and an adjacent stream with a specific receptor to the chosen target. The two fluid streams merge and the fDEP crossover frequency is measured at different axial positions down the resulting liquid

Keywords: biodetection, fluidic dielectrophoresis, interfacial polarization, liquid interface

Procedia PDF Downloads 446

Authors: Ghada A. Alfattni

Abstract:

Analysing unbalanced datasets is one of the challenges that practitioners in machine learning field face. However, many researches have been carried out to determine the effectiveness of the use of the synthetic minority over-sampling technique (SMOTE) to address this issue. The aim of this study was therefore to compare the effectiveness of the SMOTE over different models on unbalanced datasets. Three classification models (Logistic Regression, Support Vector Machine and Nearest Neighbour) were tested with multiple datasets, then the same datasets were oversampled by using SMOTE and applied again to the three models to compare the differences in the performances. Results of experiments show that the highest number of nearest neighbours gives lower values of error rates. 

Keywords: imbalanced datasets, SMOTE, machine learning, logistic regression, support vector machine, nearest neighbour

Procedia PDF Downloads 350

Authors: Hamid Kazemi, Abbasali Sadeghi

Abstract:

Assessment of seismic behavior of frame structures is just done for evaluating life and financial damages or lost. The new structural seismic behavior assessment methods have been proposed, so it is necessary to define a formulation as a damage index, which the damage amount has been quantified and qualified. In this paper, four new steel moment-resisting frames with intermediate ductility and different height (2, 5, 8, and 12-story) with regular geometry and simple rectangular plan were supposed and designed. The three existing groups’ damage indices were studied, each group consisting of local index (Drift, Maximum Roof Displacement, Banon Failure, Kinematic, Banon Normalized Cumulative Rotation, Cumulative Plastic Rotation and Ductility), global index (Roufaiel and Meyer, Papadopoulos, Sozen, Rosenblueth, Ductility and Base Shear), and story (Banon Failure and Inter-story Rotation). The necessary parameters for these damage indices have been calculated under the effect of far-fault ground motion records by Non-linear Dynamic Time History Analysis. Finally, prioritization of damage indices is defined based on more conservative values in terms of more damageability rate. The results show that the selected damage index has an important effect on estimation of the damage state. Also, failure, drift, and Rosenblueth damage indices are more conservative indices respectively for local, story and global damage indices.

Keywords: damage index, far-fault ground motion records, non-linear time history analysis, SeismoStruct software, steel moment-resisting frame

Procedia PDF Downloads 292

Authors: Mohamed Fathy Heweage, Xiao Wen, Ayman Mokhtar, Ahmed Eldamarawy

Abstract:

In this paper, we are interested in modeling, simulation, and measurement of the laser spot position with a quadrant detector. We enhance detection and tracking of semi-laser weapon decoding system based on microcontroller. The system receives the reflected pulse through quadrant detector and processes the laser pulses through a processing circuit, a microcontroller decoding laser pulse reflected by the target. The seeker accuracy will be enhanced by the decoding system, the laser detection time based on the receiving pulses number is reduced, a gate is used to limit the laser pulse width. The model is implemented based on Pulse Repetition Frequency (PRF) technique with two microcontroller units (MCU). MCU1 generates laser pulses with different codes. MCU2 decodes the laser code and locks the system at the specific code. The codes EW selected based on the two selector switches. The system is implemented and tested in Proteus ISIS software. The implementation of the full position determination circuit with the detector is produced. General system for the spot position determination was performed with the laser PRF for incident radiation and the mechanical system for adjusting system at different angles. The system test results show that the system can detect the laser code with only three received pulses based on the narrow gate signal, and good agreement between simulation and measured system performance is obtained.

Keywords: four quadrant detector, pulse code detection, laser guided weapons, pulse repetition frequency (PRF), Atmega 32 microcontrollers

Procedia PDF Downloads 390

Authors: S. Agheb, G. Ledwich, G.Walker, Z.Tong

Abstract:

Frequency control has become more of concern for reliable operation of interconnected power systems due to the integration of low inertia renewable energy sources to the grid and their volatility. Also, in case of a sudden fault, the system has less time to recover before widespread blackouts. Electric Vehicles (EV)s have the potential to cooperate in the Emergency Frequency Regulation (EFR) by a nonlinear control of the power system in case of large disturbances. The time is not adequate to communicate with each individual EV on emergency cases, and thus, an aggregate model is necessary for a quick response to prevent from much frequency deviation and the occurrence of any blackout. In this work, an aggregate of EVs is modelled as a big virtual battery in each area considering various aspects of uncertainty such as the number of connected EVs and their initial State of Charge (SOC) as stochastic variables. A control law was proposed and applied to the aggregate model using Lyapunov energy function to maximize the rate of reduction of total kinetic energy in a two-area network after the occurrence of a fault. The control methods are primarily based on the charging/ discharging control of available EVs as shunt capacity in the distribution system. Three different cases were studied considering the locational aspect of the model with the virtual EV either in the center of the two areas or in the corners. The simulation results showed that EVs could help the generator lose its kinetic energy in a short time after a contingency. Earlier estimation of possible contributions of EVs can help the supervisory control level to transmit a prompt control signal to the subsystems such as the aggregator agents and the grid. Thus, the percentage of EVs contribution for EFR will be characterized in the future as the goal of this study.

Keywords: emergency frequency regulation, electric vehicle, EV, aggregation, Lyapunov energy function

Procedia PDF Downloads 100

Authors: S. Thomet, S. De-Paoli, F. Ghaffari, J. M. Daveau, P. Roche, O. Romain

Abstract:

In this paper, we present a hardware module dedicated to understanding the fail reason of a System on Chip (SoC) exposed to a particle beam. Impact of Single-Event Effects (SEE) on processor-based SoCs is a concern that has increased in the past decade, particularly for terrestrial applications with automotive safety increasing requirements, as well as consumer and industrial domains. The SEE created by the impact of a particle on an SoC may have consequences that can end to instability or crashes. Specific hardening techniques for hardware and software have been developed to make such systems more reliable. SoC is then qualified using cosmic ray Accelerated Soft-Error Rate (ASER) to ensure the Soft-Error Rate (SER) remains in mission profiles. Understanding where errors are occurring is another challenge because of the complexity of operations performed in an SoC. Common techniques to monitor an SoC running under a beam are based on non-intrusive debug, consisting of recording the program counter and doing some consistency checking on the fly. To detect and understand SEE, we have developed a module embedded within the SoC that provide support for recording probes, hardware watchpoints, and a memory mapped register bank dedicated to software usage. To identify CPU failure modes and the most important resources to probe, we have carried out a fault injection campaign on the RTL model of the SoC. Probes are placed on generic CPU registers and bus accesses. They highlight the propagation of errors and allow identifying the failure modes. Typical resulting errors are bit-flips in resources creating bad addresses, illegal instructions, longer than expected loops, or incorrect bus accesses. Although our module is processor agnostic, it has been interfaced to a RISC-V by probing some of the processor registers. Probes are then recorded in a ring buffer. Associated hardware watchpoints are allowing to do some control, such as start or stop event recording or halt the processor. Finally, the module is also providing a bank of registers where the firmware running on the SoC can log information. Typical usage is for operating system context switch recording. The module is connected to a dedicated debug bus and is interfaced to a remote controller via a debugger link. Thus, a remote controller can interact with the monitoring module without any intrusiveness on the SoC. Moreover, in case of CPU unresponsiveness, or system-bus stall, the recorded information can still be recovered, providing the fail reason. A preliminary version of the module has been integrated into a test chip currently being manufactured at ST in 28-nm FDSOI technology. The module has been triplicated to provide reliable information on the SoC behavior. As the primary application domain is automotive and safety, the efficiency of the module will be evaluated by exposing the test chip under a fast-neutron beam by the end of the year. In the meantime, it will be tested with alpha particles and electromagnetic fault injection (EMFI). We will report in the paper on fault-injection results as well as irradiation results.

Keywords: fault injection, SoC fail reason, SoC soft error rate, terrestrial application

Procedia PDF Downloads 229

Authors: Chongya Song, Kang Yen, Alexander Pons, Jin Liu

Abstract:

In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.

Keywords: consensus, curse of correlation, imbalance classification, rank-based chain-mode ensemble

Procedia PDF Downloads 138

Authors: Afaf Alharbi, Qianni Zhang

Abstract:

The identification of malignant tissue in histopathological slides holds significant importance in both clinical settings and pathology research. This paper introduces a methodology aimed at automatically categorizing cancerous tissue through the utilization of a multiple-instance learning framework. This framework is specifically developed to acquire knowledge of the Bernoulli distribution of the bag label probability by employing neural networks. Furthermore, we put forward a neural network based permutation-invariant aggregation operator, equivalent to attention mechanisms, which is applied to the multi-instance learning network. Through empirical evaluation of an openly available colon cancer histopathology dataset, we provide evidence that our approach surpasses various conventional deep learning methods.

Keywords: attention multiple instance learning, MIL and transfer learning, histopathological slides, cancer tissue classification

Procedia PDF Downloads 110

Authors: M. Shemis, O. Maher, G. Casterou, F. Gauffre

Abstract:

Hepatitis C virus (HCV) is a major cause of chronic liver disease with a global 170 million chronic carriers at risk of developing liver cirrhosis and/or liver cancer. Egypt reports the highest prevalence of HCV worldwide. Currently, two classes of assays are used in the diagnosis and management of HCV infection. Despite the high sensitivity and specificity of the available diagnostic assays, they are time-consuming, labor-intensive, expensive, and require specialized equipment and highly qualified personal. It is therefore important for clinical and economic terms to develop a low-tech assay for the direct detection of HCV RNA with acceptable sensitivity and specificity, short turnaround time, and cost-effectiveness. Such an assay would be critical to control HCV in developing countries with limited resources and high infection rates, such as Egypt. The unique optical and physical properties of gold nanoparticles (AuNPs) have allowed the use of these nanoparticles in developing simple and rapid colorimetric assays for clinical diagnosis offering higher sensitivity and specificity than current detection techniques. The current research aims to develop a detection assay for HCV RNA using gold nanoparticles (AuNPs). Methods: 200 anti-HCV positive samples and 50 anti-HCV negative plasma samples were collected from Egyptian patients. HCV viral load was quantified using m2000rt (Abbott Molecular Inc., Des Plaines, IL). HCV genotypes were determined using multiplex nested RT- PCR. The assay is based on the aggregation of AuNPs in presence of the target RNA. Aggregation of AuNPs causes a color shift from red to blue. AuNPs were synthesized using citrate reduction method. Different sets of probes within the 5’ UTR conserved region of the HCV genome were designed, grafted on AuNPs and optimized for the efficient detection of HCV RNA. Results: The nano-gold assay could colorimetrically detect HCV RNA down to 125 IU/ml with sensitivity and specificity of 91.1% and 93.8% respectively. The turnaround time of the assay is < 30 min. Conclusions: The assay allows sensitive and rapid detection of HCV RNA and represents an inexpensive and simple point-of-care assay for resource-limited settings.

Keywords: HCV, gold nanoparticles, point of care, viral load

Procedia PDF Downloads 206

Authors: Vipulkumar Jagodana

Abstract:

Recently the use of renewable sources has increased, these sources include fuel cell, photo voltaic, and wind turbine. Islanding occurs when one portion of grid is isolated from remaining grid. Use of the renewable sources can provide continuous power to isolated portion in islanding condition. One of the common renewable sources is wind generation using wind turbine. The efficiency of wind generation can be increased in combination with conventional sources. When islanding occurs, few parameters change which may be frequency, voltage, active power, and harmonics. According to large change in one of these parameters islanding is detected. In this paper, two passive methods Rate of Change of Frequency (ROCOF) and Rate of change of Power (ROCOP) have been implemented for islanding detection of small wind-turbine. Islanding detection of both methods have been simulated in PSCAD. Simulation results show at different islanding inception angle response of ROCOF and ROCOP.

Keywords: islanding, adopted methods, PSCAD simulation, comparison

Procedia PDF Downloads 225