Search results for: objects detection
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 4199

Search results for: objects detection

2729 Enhanced Test Scheme based on Programmable Write Time for Future Computer Memories

Authors: Nor Zaidi Haron, Fauziyah Salehuddin, Norsuhaidah Arshad, Sani Irwan Salim

Abstract:

Resistive random access memories (RRAMs) are one of the main candidates for future computer memories. However, due to their tiny size and immature device technology, the quality of the outgoing RRAM chips is seen as a serious issue. Defective RRAM cells might behave differently than existing semiconductor memories (Dynamic RAM, Static RAM, and Flash), meaning that they are difficult to be detected using existing test schemes. This paper presents an enhanced test scheme, referred to as Programmable Short Write Time (PSWT) that is able to improve the detection of faulty RRAM cells. It is developed by applying multiple weak write operations, each with different time durations. The test circuit embedded in the RRAM chip is made programmable in order to supply different weak write times during testing. The RRAM electrical model is described using Verilog-AMS language and is simulated using HSPICE simulation tools. Simulation results show that the proposed test scheme offers better open-resistive fault detection compared to existing test schemes.

Keywords: memory fault, memory test, design-for-testability, resistive random access memory

Procedia PDF Downloads 383
2728 Denoising of Motor Unit Action Potential Based on Tunable Band-Pass Filter

Authors: Khalida S. Rijab, Mohammed E. Safi, Ayad A. Ibrahim

Abstract:

When electrical electrodes are mounted on the skin surface of the muscle, a signal is detected when a skeletal muscle undergoes contraction; the signal is known as surface electromyographic signal (EMG). This signal has a noise-like interference pattern resulting from the temporal and spatial summation of action potentials (AP) of all active motor units (MU) near electrode detection. By appropriate processing (Decomposition), the surface EMG signal may be used to give an estimate of motor unit action potential. In this work, a denoising technique is applied to the MUAP signals extracted from the spatial filter (IB2). A set of signals from a non-invasive two-dimensional grid of 16 electrodes from different types of subjects, muscles, and sex are recorded. These signals will acquire noise during recording and detection. A digital fourth order band- pass Butterworth filter is used for denoising, with a tuned band-pass frequency of suitable choice of cutoff frequencies is investigated, with the aim of obtaining a suitable band pass frequency. Results show an improvement of (1-3 dB) in the signal to noise ratio (SNR) have been achieved, relative to the raw spatial filter output signals for all cases that were under investigation. Furthermore, the research’s goal included also estimation and reconstruction of the mean shape of the MUAP.

Keywords: EMG, Motor Unit, Digital Filter, Denoising

Procedia PDF Downloads 398
2727 Emotions in Health Tweets: Analysis of American Government Official Accounts

Authors: García López

Abstract:

The Government Departments of Health have the task of informing and educating citizens about public health issues. For this, they use channels like Twitter, key in the search for health information and the propagation of content. The tweets, important in the virality of the content, may contain emotions that influence the contagion and exchange of knowledge. The goal of this study is to perform an analysis of the emotional projection of health information shared on Twitter by official American accounts: the disease control account CDCgov, National Institutes of Health, NIH, the government agency HHSGov, and the professional organization PublicHealth. For this, we used Tone Analyzer, an International Business Machines Corporation (IBM) tool specialized in emotion detection in text, corresponding to the categorical model of emotion representation. For 15 days, all tweets from these accounts were analyzed with the emotional analysis tool in text. The results showed that their tweets contain an important emotional load, a determining factor in the success of their communications. This exposes that official accounts also use subjective language and contain emotions. The predominance of emotion joy over sadness and the strong presence of emotions in their tweets stimulate the virality of content, a key in the work of informing that government health departments have.

Keywords: emotions in tweets, emotion detection in the text, health information on Twitter, American health official accounts, emotions on Twitter, emotions and content

Procedia PDF Downloads 135
2726 Early Detection of Instability in Emulsions via Diffusing Wave Spectroscopy

Authors: Coline Bretz, Andrea Vaccaro, Dario Leumann

Abstract:

The food, personal care, and cosmetic industries are seeing increased consumer demand for more sustainable and innovative ingredients. When developing new formulations incorporating such ingredients, stability is one of the first criteria that must be assessed, and it is thus of great importance to have a method that can detect instabilities early and quickly. Diffusing Wave Spectroscopy (DWS) is a light scattering technique that probes the motion,i.e., the mean square displacement (MSD), of colloids, such as nanoparticles in a suspension or droplets in emulsions. From the MSD, the rheological properties of the surrounding medium can be determined via the so-called microrheology approach. In the case of purely viscous media, it is also possible to obtain information about particle size. DWS can thus be used to monitor the size evolution of particles, droplets, or bubbles in aging dispersions, emulsions, or foams. In the context of early instability detection in emulsions, DWS offers considerable advantages, as the samples are measured in a contact-free manner, using only small quantities of samples loaded in a sealable cuvette. The sensitivity and rapidity of the technique are key to detecting and following the ageing of emulsions reliably. We present applications of DWS focused on the characterization of emulsions. In particular, we demonstrate the ability to record very subtle changes in the structural properties early on. We also discuss the various mechanisms at play in the destabilization of emulsions, such as coalescence or Ostwald ripening, and how to identify them through this technique.

Keywords: instrumentation, emulsions, stability, DWS

Procedia PDF Downloads 61
2725 Detection of Mustard Traces in Food by an Official Food Safety Laboratory

Authors: Clara Tramuta, Lucia Decastelli, Elisa Barcucci, Sandra Fragassi, Samantha Lupi, Enrico Arletti, Melissa Bizzarri, Daniela Manila Bianchi

Abstract:

Introdution: Food allergies occurs, in the Western World, 2% of adults and up to 8% of children. The protection of allergic consumers is guaranted, in Eurrope, by Regulation (EU) No 1169/2011 of the European Parliament which governs the consumer's right to information and identifies 14 food allergens to be mandatory indicated on the label. Among these, mustard is a popular spice added to enhance the flavour and taste of foods. It is frequently present as an ingredient in spice blends, marinades, salad dressings, sausages, and other products. Hypersensitivity to mustard is a public health problem since the ingestion of even low amounts can trigger severe allergic reactions. In order to protect the allergic consumer, high performance methods are required for the detection of allergenic ingredients. Food safety laboratories rely on validated methods that detect hidden allergens in food to ensure the safety and health of allergic consumers. Here we present the test results for the validation and accreditation of a Real time PCR assay (RT-PCR: SPECIALfinder MC Mustard, Generon), for the detection of mustard traces in food. Materials and Methods. The method was tested on five classes of food matrices: bakery and pastry products (chocolate cookies), meats (ragù), ready-to-eat (mixed salad), dairy products (yogurt), grains, and milling products (rice and barley flour). Blank samples were spiked starting with the mustard samples (Sinapis Alba), lyophilized and stored at -18 °C, at a concentration of 1000 ppm. Serial dilutions were then prepared to a final concentration of 0.5 ppm, using the DNA extracted by ION Force FAST (Generon) from the blank samples. The Real Time PCR reaction was performed by RT-PCR SPECIALfinder MC Mustard (Generon), using CFX96 System (BioRad). Results. Real Time PCR showed a limit of detection (LOD) of 0.5 ppm in grains and milling products, ready-to-eat, meats, bakery, pastry products, and dairy products (range Ct 25-34). To determine the exclusivity parameter of the method, the ragù matrix was contaminated with Prunus dulcis (almonds), peanut (Arachis hypogaea), Glycine max (soy), Apium graveolens (celery), Allium cepa (onion), Pisum sativum (peas), Daucus carota (carrots), and Theobroma cacao (cocoa) and no cross-reactions were observed. Discussion. In terms of sensitivity, the Real Time PCR confirmed, even in complex matrix, a LOD of 0.5 ppm in five classes of food matrices tested; these values are compatible with the current regulatory situation that does not consider, at international level, to establish a quantitative criterion for the allergen considered in this study. The Real Time PCR SPECIALfinder kit for the detection of mustard proved to be easy to use and particularly appreciated for the rapid response times considering that the amplification and detection phase has a duration of less than 50 minutes. Method accuracy was rated satisfactory for sensitivity (100%) and specificity (100%) and was fully validated and accreditated. It was found adequate for the needs of the laboratory as it met the purpose for which it was applied. This study was funded in part within a project of the Italian Ministry of Health (IZS PLV 02/19 RC).

Keywords: allergens, food, mustard, real time PCR

Procedia PDF Downloads 163
2724 Theoretical Approaches to Graphic and Formal Generation from Evolutionary Genetics

Authors: Luz Estrada

Abstract:

The currents of evolutionary materialistic thought have argued that knowledge about an object is not obtained through the abstractive method. That is, the object cannot come to be understood if founded upon itself, nor does it take place by the encounter between form and matter. According to this affirmation, the research presented here identified as a problematic situation the absence of comprehension of the formal creation as a generative operation. This has been referred to as a recurrent lack in the production of objects and corresponds to the need to conceive the configurative process from the reality of its genesis. In this case, it is of interest to explore ways of creation that consider the object as if it were a living organism, as well as responding to the object’s experience as embodied in the designer since it unfolds its genesis simultaneously to the ways of existence of those who are involved in the generative experience.

Keywords: architecture, theoretical graphics, evolutionary genetics, formal perception

Procedia PDF Downloads 112
2723 Artificial Neural Network Based Model for Detecting Attacks in Smart Grid Cloud

Authors: Sandeep Mehmi, Harsh Verma, A. L. Sangal

Abstract:

Ever since the idea of using computing services as commodity that can be delivered like other utilities e.g. electric and telephone has been floated, the scientific fraternity has diverted their research towards a new area called utility computing. New paradigms like cluster computing and grid computing came into existence while edging closer to utility computing. With the advent of internet the demand of anytime, anywhere access of the resources that could be provisioned dynamically as a service, gave rise to the next generation computing paradigm known as cloud computing. Today, cloud computing has become one of the most aggressively growing computer paradigm, resulting in growing rate of applications in area of IT outsourcing. Besides catering the computational and storage demands, cloud computing has economically benefitted almost all the fields, education, research, entertainment, medical, banking, military operations, weather forecasting, business and finance to name a few. Smart grid is another discipline that direly needs to be benefitted from the cloud computing advantages. Smart grid system is a new technology that has revolutionized the power sector by automating the transmission and distribution system and integration of smart devices. Cloud based smart grid can fulfill the storage requirement of unstructured and uncorrelated data generated by smart sensors as well as computational needs for self-healing, load balancing and demand response features. But, security issues such as confidentiality, integrity, availability, accountability and privacy need to be resolved for the development of smart grid cloud. In recent years, a number of intrusion prevention techniques have been proposed in the cloud, but hackers/intruders still manage to bypass the security of the cloud. Therefore, precise intrusion detection systems need to be developed in order to secure the critical information infrastructure like smart grid cloud. Considering the success of artificial neural networks in building robust intrusion detection, this research proposes an artificial neural network based model for detecting attacks in smart grid cloud.

Keywords: artificial neural networks, cloud computing, intrusion detection systems, security issues, smart grid

Procedia PDF Downloads 315
2722 Preparation of Indium Tin Oxide Nanoparticle-Modified 3-Aminopropyltrimethoxysilane-Functionalized Indium Tin Oxide Electrode for Electrochemical Sulfide Detection

Authors: Md. Abdul Aziz

Abstract:

Sulfide ion is water soluble, highly corrosive, toxic and harmful to the human beings. As a result, knowing the exact concentration of sulfide in water is very important. However, the existing detection and quantification methods have several shortcomings, such as high cost, low sensitivity, and massive instrumentation. Consequently, the development of novel sulfide sensor is relevant. Nevertheless, electrochemical methods gained enormous popularity due to a vast improvement in the technique and instrumentation, portability, low cost, rapid analysis and simplicity of design. Successful field application of electrochemical devices still requires vast improvement, which depends on the physical, chemical and electrochemical aspects of the working electrode. The working electrode made of bulk gold (Au) and platinum (Pt) are quite common, being very robust and endowed with good electrocatalytic properties. High cost, and electrode poisoning, however, have so far hindered their practical application in many industries. To overcome these obstacles, we developed a sulfide sensor based on an indium tin oxide nanoparticle (ITONP)-modified ITO electrode. To prepare ITONP-modified ITO, various methods were tested. Drop-drying of ITONPs (aq.) on aminopropyltrimethoxysilane-functionalized ITO (APTMS/ITO) was found to be the best method on the basis of voltammetric analysis of the sulfide ion. ITONP-modified APTMS/ITO (ITONP/APTMS/ITO) yielded much better electrocatalytic properties toward sulfide electro-οxidation than did bare or APTMS/ITO electrodes. The ITONPs and ITONP-modified ITO were also characterized using transmission electron microscopy and field emission scanning electron microscopy, respectively. Optimization of the type of inert electrolyte and pH yielded an ITONP/APTMS/ITO detector whose amperometrically and chronocoulοmetrically determined limits of detection for sulfide in aqueous solution were 3.0 µM and 0.90 µM, respectively. ITONP/APTMS/ITO electrodes which displayed reproducible performances were highly stable and were not susceptible to interference by common contaminants. Thus, the developed electrode can be considered as a promising tool for sensing sulfide.

Keywords: amperometry, chronocoulometry, electrocatalytic properties, ITO-nanoparticle-modified ITO, sulfide sensor

Procedia PDF Downloads 126
2721 Current-Based Multiple Faults Detection in Electrical Motors

Authors: Moftah BinHasan

Abstract:

Induction motors (IM) are vital components in industrial processes whose failure may yield to an unexpected interruption at the industrial plant, with highly incurred consequences in costs, product quality, and safety. Among different detection approaches proposed in the literature, that based on stator current monitoring termed as Motor Current Signature Analysis (MCSA) is the most preferred. MCSA is advantageous due to its non-invasive properties. The popularity of motor current signature analysis comes from being that the current consists of motor harmonics, around the supply frequency, which show some properties related to different situations of healthy and faulty conditions. One of the techniques used with machine line current resorts to spectrum analysis. Besides discussing the fundamentals of MCSA and its applications in the condition monitoring arena, this paper shows a summary of the most frequent faults and their consequence signatures on the stator current spectrum of an induction motor. In addition, this article presents different case studies of induction motor fault diagnosis. These faults were seeded in the machine which was run for more than an hour for each test before the results were recorded for the faulty situations. These results are then compared with those for the healthy cases that were recorded earlier.

Keywords: induction motor, condition monitoring, fault diagnosis, MCSA, rotor, stator, bearing, eccentricity

Procedia PDF Downloads 455
2720 Context Aware Anomaly Behavior Analysis for Smart Home Systems

Authors: Zhiwen Pan, Jesus Pacheco, Salim Hariri, Yiqiang Chen, Bozhi Liu

Abstract:

The Internet of Things (IoT) will lead to the development of advanced Smart Home services that are pervasive, cost-effective, and can be accessed by home occupants from anywhere and at any time. However, advanced smart home applications will introduce grand security challenges due to the increase in the attack surface. Current approaches do not handle cybersecurity from a holistic point of view; hence, a systematic cybersecurity mechanism needs to be adopted when designing smart home applications. In this paper, we present a generic intrusion detection methodology to detect and mitigate the anomaly behaviors happened in Smart Home Systems (SHS). By utilizing our Smart Home Context Data Structure, the heterogeneous information and services acquired from SHS are mapped in context attributes which can describe the context of smart home operation precisely and accurately. Runtime models for describing usage patterns of home assets are developed based on characterization functions. A threat-aware action management methodology, used to efficiently mitigate anomaly behaviors, is proposed at the end. Our preliminary experimental results show that our methodology can be used to detect and mitigate known and unknown threats, as well as to protect SHS premises and services.

Keywords: Internet of Things, network security, context awareness, intrusion detection

Procedia PDF Downloads 186
2719 Development of Technologies for Biotransformation of Aquatic Biological Resources for the Production of Functional, Specialized, Therapeutic, Preventive, and Microbiological Products

Authors: Kira Rysakova, Vitaly Novikov

Abstract:

An improved method of obtaining enzymatic collagen hydrolysate from the tissues of marine hydrobionts is proposed, which allows to obtain hydrolysate without pre-isolation of pure collagen. The method can be used to isolate enzymatic collagen hydrolysate from the waste of industrial processing of Red King crab and non-traditional objects - marine holothurias. Comparative analysis of collagen hydrolysates has shown the possibility of their use in a number of nutrient media, but this requires additional optimization of their composition and biological tests on wide sets of test strains of microorganisms.

Keywords: collagen hydrolysate, marine hydrobionts, red king crab, marine holothurias, enzymes, exclusive HPLC

Procedia PDF Downloads 165
2718 Molecular Study of P53- and Rb-Tumor Suppressor Genes in Human Papilloma Virus-Infected Breast Cancers

Authors: Shakir H. Mohammed Al-Alwany, Saad Hasan M. Ali, Ibrahim Mohammed S. Shnawa

Abstract:

The study was aimed to define the percentage of detection of high-oncogenic risk types of HPV and their genotyping in archival tissue specimens that ranged from apparently healthy tissue to invasive breast cancer by using one of the recent versions of In Situ Hybridization(ISH) 0.2. To find out rational significance of such genotypes as well as over expressed products of mutants P53 and RB genes on the severity of underlying breast cancers. The DNA of HPV was detected in 46.5 % of tissues from breast cancers while HPV DNA in the tissues from benign breast tumours was detected in 12.5%. No HPV positive–ISH reaction was detected in healthy breast tissues of the control group. HPV DNA of genotypes (16, 18, 31 and 33) was detected in malignant group in frequency of 25.6%, 27.1%, 30.2% and 12.4%, respectively. Over expression of p53 was detected by IHC in 51.2% breast cancer cases and in 50% benign breast tumour group, while none of control group showed P53- over expression. Retinoblastoma protein was detected by IHC test in 49.7% of malignant breast tumours, 54.2% of benign breast tumours but no signal was reported in the tissues of control group. The significance prevalence of expression of mutated p53 & Rb genes as well as detection of high-oncogenic HPV genotypes in patients with breast cancer supports the hypothesis of an etiologic role for the virus in breast cancer development.

Keywords: human papilloma virus, P53, RB, breast cancer

Procedia PDF Downloads 475
2717 Radar Cross Section Modelling of Lossy Dielectrics

Authors: Ciara Pienaar, J. W. Odendaal, J. Joubert, J. C. Smit

Abstract:

Radar cross section (RCS) of dielectric objects play an important role in many applications, such as low observability technology development, drone detection, and monitoring as well as coastal surveillance. Various materials are used to construct the targets of interest such as metal, wood, composite materials, radar absorbent materials, and other dielectrics. Since simulated datasets are increasingly being used to supplement infield measurements, as it is more cost effective and a larger variety of targets can be simulated, it is important to have a high level of confidence in the predicted results. Confidence can be attained through validation. Various computational electromagnetic (CEM) methods are capable of predicting the RCS of dielectric targets. This study will extend previous studies by validating full-wave and asymptotic RCS simulations of dielectric targets with measured data. The paper will provide measured RCS data of a number of canonical dielectric targets exhibiting different material properties. As stated previously, these measurements are used to validate numerous CEM methods. The dielectric properties are accurately characterized to reduce the uncertainties in the simulations. Finally, an analysis of the sensitivity of oblique and normal incidence scattering predictions to material characteristics is also presented. In this paper, the ability of several CEM methods, including method of moments (MoM), and physical optics (PO), to calculate the RCS of dielectrics were validated with measured data. A few dielectrics, exhibiting different material properties, were selected and several canonical targets, such as flat plates and cylinders, were manufactured. The RCS of these dielectric targets were measured in a compact range at the University of Pretoria, South Africa, over a frequency range of 2 to 18 GHz and a 360° azimuth angle sweep. This study also investigated the effect of slight variations in the material properties on the calculated RCS results, by varying the material properties within a realistic tolerance range and comparing the calculated RCS results. Interesting measured and simulated results have been obtained. Large discrepancies were observed between the different methods as well as the measured data. It was also observed that the accuracy of the RCS data of the dielectrics can be frequency and angle dependent. The simulated RCS for some of these materials also exhibit high sensitivity to variations in the material properties. Comparison graphs between the measured and simulation RCS datasets will be presented and the validation thereof will be discussed. Finally, the effect that small tolerances in the material properties have on the calculated RCS results will be shown. Thus the importance of accurate dielectric material properties for validation purposes will be discussed.

Keywords: asymptotic, CEM, dielectric scattering, full-wave, measurements, radar cross section, validation

Procedia PDF Downloads 230
2716 Determination of Bisphenol A and Uric Acid by Modified Single-Walled Carbon Nanotube with Magnesium Layered Hydroxide 3-(4-Methoxyphenyl)Propionic Acid Nanocomposite

Authors: Illyas Md Isa, Maryam Musfirah Che Sobry, Mohamad Syahrizal Ahmad, Nurashikin Abd Azis

Abstract:

A single-walled carbon nanotube (SWCNT) that has been modified with magnesium layered hydroxide 3-(4-methoxyphenyl)propionic acid nanocomposite was proposed for the determination of uric acid and bisphenol A by square wave voltammetry. The results obtained denote that MLH-MPP nanocomposites enhance the sensitivity of the voltammetry detection responses. The best performance is shown by the modified carbon nanotube paste electrode (CNTPE) with the composition of single-walled carbon nanotube: magnesium layered hydroxide 3-(4-methoxyphenyl)propionic acid nanocomposite at 100:15 (% w/w). The linear range where the sensor works well is within the concentration 1.0 10-7 – 1.0 10-4 and 3.0 10-7 – 1.0 10-4 for uric acid and bisphenol A respectively with the limit of detection of 1.0 10-7 M for both organics. The interferences of uric acid and bisphenol A with other organic were studied and most of them did not interfere. The results shown for each experimental parameter on the proposed CNTPE showed that it has high sensitivity, good selectivity, repeatability and reproducibility. Therefore, the modified CNTPE can be used for the determination of uric acid and bisphenol A in real samples such as blood, plastic bottles and foods.

Keywords: bisphenol A, magnesium layered hydroxide 3-(4-methoxyphenyl)propionic acid nanocomposite, Nanocomposite, uric acid

Procedia PDF Downloads 209
2715 A Single-Channel BSS-Based Method for Structural Health Monitoring of Civil Infrastructure under Environmental Variations

Authors: Yanjie Zhu, André Jesus, Irwanda Laory

Abstract:

Structural Health Monitoring (SHM), involving data acquisition, data interpretation and decision-making system aim to continuously monitor the structural performance of civil infrastructures under various in-service circumstances. The main value and purpose of SHM is identifying damages through data interpretation system. Research on SHM has been expanded in the last decades and a large volume of data is recorded every day owing to the dramatic development in sensor techniques and certain progress in signal processing techniques. However, efficient and reliable data interpretation for damage detection under environmental variations is still a big challenge. Structural damages might be masked because variations in measured data can be the result of environmental variations. This research reports a novel method based on single-channel Blind Signal Separation (BSS), which extracts environmental effects from measured data directly without any prior knowledge of the structure loading and environmental conditions. Despite the successful application in audio processing and bio-medical research fields, BSS has never been used to detect damage under varying environmental conditions. This proposed method optimizes and combines Ensemble Empirical Mode Decomposition (EEMD), Principal Component Analysis (PCA) and Independent Component Analysis (ICA) together to separate structural responses due to different loading conditions respectively from a single channel input signal. The ICA is applying on dimension-reduced output of EEMD. Numerical simulation of a truss bridge, inspired from New Joban Line Arakawa Railway Bridge, is used to validate this method. All results demonstrate that the single-channel BSS-based method can recover temperature effects from mixed structural response recorded by a single sensor with a convincing accuracy. This will be the foundation of further research on direct damage detection under varying environment.

Keywords: damage detection, ensemble empirical mode decomposition (EEMD), environmental variations, independent component analysis (ICA), principal component analysis (PCA), structural health monitoring (SHM)

Procedia PDF Downloads 302
2714 'Coping with Workplace Violence' Workshop: A Commendable Addition to the Curriculum for BA in Nursing

Authors: Ilana Margalith, Adaya Meirowitz, Sigalit Cohavi

Abstract:

Violence against health professionals by patients and their families have recently become a disturbing phenomenon worldwide, exacting psychological as well as economic tolls. Health workplaces in Israel (e.g. hospitals and H.M.O clinics) provide workshops for their employees, supplying them with coping strategies. However, these workshops do not focus on nursing students, who are also subjected to this violence. Their learning environment is no longer as protective as it used to be. Furthermore, coping with violence was not part of the curriculum for Israeli nursing students. Thus, based on human aggression theories which depict the pivotal role of the professional's correct response in preventing the onset of an aggressive response or the escalation of violence, a workshop was developed for undergraduate nursing students at the Clalit Nursing Academy, Rabin Campus (Dina), Israel. The workshop aimed at reducing students' anxiety vis a vis the aggressive patient or family in addition to strengthening their ability to cope with such situations. The students practiced interpersonal skills, especially relevant to early detection of potential violence, as well as ‘a correct response’ reaction to the violence, thus developing the necessary steps to be implemented when encountering violence in the workplace. In order to assess the efficiency of the workshop, the participants filled out a questionnaire comprising knowledge and self-efficacy scales. Moreover, the replies of the 23 participants in this workshop were compared with those of 24 students who attended a standard course on interpersonal communication. Students' self-efficacy and knowledge were measured in both groups before and after the course. A statistically significant interaction was found between group (workshop/standard course) and time (before/after) as to the influence on students' self-efficacy (p=0.004) and knowledge (p=0.007). Nursing students, who participated in this ‘coping with workplace violence’ workshop, gained knowledge, confidence and a sense of self-efficacy with regard to workplace violence. Early detection of signs of imminent violence amongst patients or families and the prevention of its escalation, as well as the ability to manage the threatening situation when occurring, are acquired skills. Encouraging nursing students to learn and practice these skills may enhance their ability to cope with these unfortunate occurrences.

Keywords: early detection of violence, nursing students, patient aggression, self-efficacy, workplace violence

Procedia PDF Downloads 133
2713 Sustainable Concepts Applied in the Pre-Columbian Andean Architecture in Southern Ecuador

Authors: Diego Espinoza-Piedra, David Duran

Abstract:

All architectural and land use processes are framed in a cultural, social and geographical context. The present study analyzes the Andean culture before the Spanish conquest in southern Ecuador, in the province of Azuay. This area has been habited for more than 10.000 years. The Canari and the Inca cultures occupied Azuay close to the arrival of the Spanish conquers. The Inca culture was settled in the Andes Mountains. The Canari culture was established in the south of Ecuador, on the actual provinces of Azuay and Canar. In contrast with history and archeology, to the best of our knowledge, their architecture has not yet been studied in this area because of the lack of architectural structures. Consequently, the present research reviewed the land use and culture for architectonic interpretations. The two main architectural objects in these cultures were dwellings and public buildings. In the first case, housing was conceived as temporary. It had to stand as long as its inhabitants lived. Therefore, houses were built when a couple got married. The whole community started the construction through the so-called ‘minga’ or collective work. The construction materials were tree branches, reeds, agave, ground, and straw. So that when their owners aged and then died, this house was easily disarmed and overthrown. Their materials become part of the land for agriculture. Finally, this cycle was repeated indefinitely. In the second case, the buildings, which we can call public, have presented erroneous interpretations. They have been defined as temples. But according to our conclusions, they were places for temporary accommodation, storage of objects and products, and in some special cases, even astronomical observatories. These public buildings were settled along the important road system called ‘Capac-Nam’, currently declared by UNESCO as World Cultural Heritage. The buildings had different scales at regular distances. Also, they were established in special or strategic places, which constituted a system of observatories. These observatories allowed to determine the cycles or calendars (solar or lunar) necessary for the agricultural production, as well as other natural phenomena. Most of the current minimal existence of physical structures in quantity and state of conservation is at the level of foundations or pieces of walls. Therefore, this study was realized after the identification of the history and culture of the inhabitants of this Andean region.

Keywords: Andean, pre-Colombian architecture, Southern Ecuador, sustainable

Procedia PDF Downloads 124
2712 Speed Breaker/Pothole Detection Using Hidden Markov Models: A Deep Learning Approach

Authors: Surajit Chakrabarty, Piyush Chauhan, Subhasis Panda, Sujoy Bhattacharya

Abstract:

A large proportion of roads in India are not well maintained as per the laid down public safety guidelines leading to loss of direction control and fatal accidents. We propose a technique to detect speed breakers and potholes using mobile sensor data captured from multiple vehicles and provide a profile of the road. This would, in turn, help in monitoring roads and revolutionize digital maps. Incorporating randomness in the model formulation for detection of speed breakers and potholes is crucial due to substantial heterogeneity observed in data obtained using a mobile application from multiple vehicles driven by different drivers. This is accomplished with Hidden Markov Models, whose hidden state sequence is found for each time step given the observables sequence, and are then fed as input to LSTM network with peephole connections. A precision score of 0.96 and 0.63 is obtained for classifying bumps and potholes, respectively, a significant improvement from the machine learning based models. Further visualization of bumps/potholes is done by converting time series to images using Markov Transition Fields where a significant demarcation among bump/potholes is observed.

Keywords: deep learning, hidden Markov model, pothole, speed breaker

Procedia PDF Downloads 140
2711 Electrochemical Impedance Spectroscopy Based Label-Free Detection of TSG101 by Electric Field Lysis of Immobilized Exosomes from Human Serum

Authors: Nusrat Praween, Krishna Thej Pammi Guru, Palash Kumar Basu

Abstract:

Designing non-invasive biosensors for cancer diagnosis is essential for developing an affordable and specific tool to measure cancer-related exosome biomarkers. Exosomes, released by healthy as well as cancer cells, contain valuable information about the biomarkers of various diseases, including cancer. Despite the availability of various isolation techniques, ultracentrifugation is the standard technique that is being employed. Post isolation, exosomes are traditionally exposed to detergents for extracting their proteins, which can often lead to protein degradation. Further to this, it is very essential to develop a sensing platform for the quantification of clinically relevant proteins in a wider range to ensure practicality. In this study, exosomes were immobilized on the Au Screen Printed Electrode (SPE) using EDC/NHS chemistry to facilitate binding. After immobilizing the exosomes on the screen-printed electrode (SPE), we investigated the impact of the electric field by applying various voltages to induce exosome lysis and release their contents. The lysed solution was used for sensing TSG101, a crucial biomarker associated with various cancers, using both faradaic and non-faradaic electrochemical impedance spectroscopy (EIS) methods. The results of non-faradaic and faradaic EIS were comparable and showed good consistency, indicating that non-faradaic sensing can be a reliable alternative. Hence, the non-faradaic sensing technique was used for label-free quantification of the TSG101 biomarker. The results were validated using ELISA. Our electrochemical immunosensor demonstrated a consistent response of TSG101 from 125 pg/mL to 8000 pg/mL, with a detection limit of 0.125 pg/mL at room temperature. Additionally, since non-faradic sensing is label-free, the ease of usage and cost of the final sensor developed can be reduced. The proposed immunosensor is capable of detecting the TSG101 protein at low levels in healthy serum with good sensitivity and specificity, making it a promising platform for biomarker detection.

Keywords: biosensor, exosomes isolation on SPE, electric field lysis of exosome, EIS sensing of TSG101

Procedia PDF Downloads 40
2710 Performance Analysis of Traffic Classification with Machine Learning

Authors: Htay Htay Yi, Zin May Aye

Abstract:

Network security is role of the ICT environment because malicious users are continually growing that realm of education, business, and then related with ICT. The network security contravention is typically described and examined centrally based on a security event management system. The firewalls, Intrusion Detection System (IDS), and Intrusion Prevention System are becoming essential to monitor or prevent of potential violations, incidents attack, and imminent threats. In this system, the firewall rules are set only for where the system policies are needed. Dataset deployed in this system are derived from the testbed environment. The traffic as in DoS and PortScan traffics are applied in the testbed with firewall and IDS implementation. The network traffics are classified as normal or attacks in the existing testbed environment based on six machine learning classification methods applied in the system. It is required to be tested to get datasets and applied for DoS and PortScan. The dataset is based on CICIDS2017 and some features have been added. This system tested 26 features from the applied dataset. The system is to reduce false positive rates and to improve accuracy in the implemented testbed design. The system also proves good performance by selecting important features and comparing existing a dataset by machine learning classifiers.

Keywords: false negative rate, intrusion detection system, machine learning methods, performance

Procedia PDF Downloads 115
2709 UV-Enhanced Room-Temperature Gas-Sensing Properties of ZnO-SnO2 Nanocomposites Obtained by Hydrothermal Treatment

Authors: Luís F. da Silva, Ariadne C. Catto, Osmando F. Lopes, Khalifa Aguir, Valmor R. Mastelaro, Caue Ribeiro, Elson Longo

Abstract:

Gas detection is important for controlling industrial, and vehicle emissions, agricultural residues, and environmental control. In last decades, several semiconducting oxides have been used to detect dangerous or toxic gases. The excellent gas-sensing performance of these devices have been observed at high temperatures (~250 °C), which forbids the use for the detection of flammable and explosive gases. In this way, ultraviolet light activated gas sensors have been a simple and promising alternative to achieve room temperature sensitivity. Among the semiconductor oxides which exhibit a good performance as gas sensor, the zinc oxide (ZnO) and tin oxide (SnO2) have been highlighted. Nevertheless, their poor selectivity is the main disadvantage for application as gas sensor devices. Recently, heterostructures combining these two semiconductors (ZnO-SnO2) have been studied as an alternative way to enhance the gas sensor performance (sensitivity, selectivity, and stability). In this work, we investigated the influence of mass ratio Zn:Sn on the properties of ZnO-SnO2 nanocomposites prepared by hydrothermal treatment for 4 hours at 200 °C. The crystalline phase, surface, and morphological features were characterized by X-ray diffraction (XRD), high-resolution transmission electron (HR-TEM), and X-ray photoelectron spectroscopy (XPS) measurements. The gas sensor measurements were carried out at room-temperature under ultraviolet (UV) light irradiation using different ozone levels (0.06 to 0.61 ppm). The XRD measurements indicate the presence of ZnO and SnO2 crystalline phases, without the evidence of solid solution formation. HR-TEM analysis revealed that a good contact between the SnO2 nanoparticles and the ZnO nanorods, which are very important since interface characteristics between nanostructures are considered as challenge to development new and efficient heterostructures. Electrical measurements proved that the best ozone gas-sensing performance is obtained for ZnO:SnO2 (50:50) nanocomposite under UV light irradiation. Its sensitivity was around 6 times higher when compared to SnO2 pure, a traditional ozone gas sensor. These results demonstrate the potential of ZnO-SnO2 heterojunctions for the detection of ozone gas at room-temperature when irradiated with UV light irradiation.

Keywords: hydrothermal, zno-sno2, ozone sensor, uv-activation, room-temperature

Procedia PDF Downloads 280
2708 Development and Validation of a HPLC Method for 6-Gingerol and 6-Shogaol in Joint Pain Relief Gel Containing Ginger (Zingiber officinale)

Authors: Tanwarat Kajsongkram, Saowalux Rotamporn, Sirinat Limbunruang, Sirinan Thubthimthed.

Abstract:

High-Performance Liquid Chromatography (HPLC) method was developed and validated for simultaneous estimation of 6-Gingerol(6G) and 6-Shogaol(6S) in joint pain relief gel containing ginger extract. The chromatographic separation was achieved by using C18 column, 150 x 4.6mm i.d., 5μ Luna, mobile phase containing acetonitrile and water (gradient elution). The flow rate was 1.0 ml/min and the absorbance was monitored at 282 nm. The proposed method was validated in terms of the analytical parameters such as specificity, accuracy, precision, linearity, range, limit of detection (LOD), limit of quantification (LOQ), and determined based on the International Conference on Harmonization (ICH) guidelines. The linearity ranges of 6G and 6S were obtained over 20-60 and 6-18 µg/ml respectively. Good linearity was observed over the above-mentioned range with linear regression equation Y= 11016x- 23778 for 6G and Y = 19276x-19604 for 6S (x is concentration of analytes in μg/ml and Y is peak area). The value of correlation coefficient was found to be 0.9994 for both markers. The limit of detection (LOD) and limit of quantification (LOQ) for 6G were 0.8567 and 2.8555 µg/ml and for 6S were 0.3672 and 1.2238 µg/ml respectively. The recovery range for 6G and 6S were found to be 91.57 to 102.36 % and 84.73 to 92.85 % for all three spiked levels. The RSD values from repeated extractions for 6G and 6S were 3.43 and 3.09% respectively. The validation of developed method on precision, accuracy, specificity, linearity, and range were also performed with well-accepted results.

Keywords: ginger, 6-gingerol, HPLC, 6-shogaol

Procedia PDF Downloads 437
2707 Computational Pipeline for Lynch Syndrome Detection: Integrating Alignment, Variant Calling, and Annotations

Authors: Rofida Gamal, Mostafa Mohammed, Mariam Adel, Marwa Gamal, Marwa kamal, Ayat Saber, Maha Mamdouh, Amira Emad, Mai Ramadan

Abstract:

Lynch Syndrome is an inherited genetic condition associated with an increased risk of colorectal and other cancers. Detecting Lynch Syndrome in individuals is crucial for early intervention and preventive measures. This study proposes a computational pipeline for Lynch Syndrome detection by integrating alignment, variant calling, and annotation. The pipeline leverages popular tools such as FastQC, Trimmomatic, BWA, bcftools, and ANNOVAR to process the input FASTQ file, perform quality trimming, align reads to the reference genome, call variants, and annotate them. It is believed that the computational pipeline was applied to a dataset of Lynch Syndrome cases, and its performance was evaluated. It is believed that the quality check step ensured the integrity of the sequencing data, while the trimming process is thought to have removed low-quality bases and adaptors. In the alignment step, it is believed that the reads were accurately mapped to the reference genome, and the subsequent variant calling step is believed to have identified potential genetic variants. The annotation step is believed to have provided functional insights into the detected variants, including their effects on known Lynch Syndrome-associated genes. The results obtained from the pipeline revealed Lynch Syndrome-related positions in the genome, providing valuable information for further investigation and clinical decision-making. The pipeline's effectiveness was demonstrated through its ability to streamline the analysis workflow and identify potential genetic markers associated with Lynch Syndrome. It is believed that the computational pipeline presents a comprehensive and efficient approach to Lynch Syndrome detection, contributing to early diagnosis and intervention. The modularity and flexibility of the pipeline are believed to enable customization and adaptation to various datasets and research settings. Further optimization and validation are believed to be necessary to enhance performance and applicability across diverse populations.

Keywords: Lynch Syndrome, computational pipeline, alignment, variant calling, annotation, genetic markers

Procedia PDF Downloads 67
2706 A Detailed Study of Sexism in Mizo Language

Authors: H. C. Laltleipuii, Lalruatdiki Siakeng

Abstract:

Mizo is a language spoken by the natives of Mizoram in North-East India. The Mizo society is a patriarchal society and hence is encumbered with trails of sexism in its language. Sexist language expresses discrimination on the basis of gender. While women are primarily affected, it is not however limited to just the female gender. This paper focuses on the sexist language that reflects the discrimination of women in the male-dominated, male-centered society of the Mizo. The main purpose of this paper is to emphasize with details, sexism that can be found in three aspects of language: in the naming of animate and inanimate objects or words in general, in the idioms and phrases and proverbs. This study will also take into account the gender neutral terms that are in use in the language.

Keywords: gender, Mizo, patriarchy, sexism

Procedia PDF Downloads 407
2705 A Differential Detection Method for Chip-Scale Spin-Exchange Relaxation Free Atomic Magnetometer

Authors: Yi Zhang, Yuan Tian, Jiehua Chen, Sihong Gu

Abstract:

Chip-scale spin-exchange relaxation free (SERF) atomic magnetometer makes use of millimeter-scale vapor cells micro-fabricated by Micro-electromechanical Systems (MEMS) technique and SERF mechanism, resulting in the characteristics of high spatial resolution and high sensitivity. It is useful for biomagnetic imaging including magnetoencephalography and magnetocardiography. In a prevailing scheme, circularly polarized on-resonance laser beam is adapted for both pumping and probing the atomic polarization. And the magnetic-field-sensitive signal is extracted by transmission laser intensity enhancement as a result of atomic polarization increase on zero field level crossing resonance. The scheme is very suitable for integration, however, the laser amplitude modulation (AM) noise and laser frequency modulation to amplitude modulation (FM-AM) noise is superimposed on the photon shot noise reducing the signal to noise ratio (SNR). To suppress AM and FM-AM noise the paper puts forward a novel scheme which adopts circularly polarized on-resonance light pumping and linearly polarized frequency-detuning laser probing. The transmission beam is divided into transmission and reflection beams by a polarization analyzer, the angle between the analyzer's transmission polarization axis and frequency-detuning laser polarization direction is set to 45°. The magnetic-field-sensitive signal is extracted by polarization rotation enhancement of frequency-detuning laser which induces two beams intensity difference increase as the atomic polarization increases. Therefore, AM and FM-AM noise in two beams are common-mode and can be almost entirely canceled by differential detection. We have carried out an experiment to study our scheme. The experiment reveals that the noise in the differential signal is obviously smaller than that in each beam. The scheme is promising to be applied for developing more sensitive chip-scale magnetometer.

Keywords: atomic magnetometer, chip scale, differential detection, spin-exchange relaxation free

Procedia PDF Downloads 165
2704 Molecular Detection of Leishmania from the Phlebotomus Genus: Tendency towards Leishmaniasis Regression in Constantine, North-East of Algeria

Authors: K. Frahtia, I. Mihoubi, S. Picot

Abstract:

Leishmaniasis is a group of parasitic disease with a varied clinical expression caused by flagellate protozoa of the Leishmania genus. These diseases are transmitted to humans and animals by the sting of a vector insect, the female sandfly. Among the groups of dipteral disease vectors, Phlebotominae occupy a prime position and play a significant role in human pathology, such as leishmaniasis that affects nearly 350 million people worldwide. The vector control operation launched by health services throughout the country proves to be effective since despite the prevalence of the disease remains high especially in rural areas, leishmaniasis appears to be declining in Algeria. In this context, this study mainly concerns molecular detection of Leishmania from the vector. Furthermore, a molecular diagnosis has also been made on skin samples taken from patients in the region of Constantine, located in the North-East of Algeria. Concerning the vector, 5858 sandflies were captured, including 4360 males and 1498 females. Male specimens were identified based on their morphological. The morphological identification highlighted the presence of the Phlebotomus genus with a prevalence of 93% against 7% represented by the Sergentomyia genus. About the identified species, P. perniciosus is the most abundant with 59.4% of the male identified population followed by P. longicuspis with 24.7% of the workforce. P. perfiliewi is poorly represented by 6.7% of specimens followed by P. papatasi with 2.2% and 1.5% S. dreyfussi. Concerning skin samples, 45/79 (56.96%) collected samples were found positive by real-time PCR. This rate appears to be in sharp decline compared to previous years (alert peak of 30,227 cases in 2005). Concerning the detection of Leishmania from sandflies by RT-PCR, the results show that 3/60 PCR performed genus are positive with melting temperatures corresponding to that of the reference strain (84.1 +/- 0.4 ° C for L. infantum). This proves that the vectors were parasitized. On the other side, identification by RT-PCR species did not give any results. This could be explained by the presence of an insufficient amount of leishmanian DNA in the vector, and therefore support the hypothesis of the regression of leishmaniasis in Constantine.

Keywords: Algeria, molecular diagnostic, phlebotomus, real time PCR

Procedia PDF Downloads 268
2703 Understanding Jordanian Women's Values and Beliefs Related to Prevention and Early Detection of Breast Cancer

Authors: Khlood F. Salman, Richard Zoucha, Hani Nawafleh

Abstract:

Introduction: Jordan ranks the fourth highest breast cancer prevalence after Lebanon, Bahrain, and Kuwait. Considerable evidence showed that cultural, ethnic, and economic differences influence a woman’s practice to early detection and prevention of breast cancer. Objectives: To understand women’s health beliefs and values in relation to early detection of breast cancer; and to explore the impact of these beliefs on their decisions regarding reluctance or acceptance of early detection measures such as mammogram screening. Design: A qualitative focused ethnography was used to collect data for this study. Settings: The study was conducted in the second largest city surrounded by a large rural area in Ma’an- Jordan. Participants: A total of twenty seven women, with no history of breast cancer, between the ages of 18 and older, who had prior health experience with health providers, and were willing to share elements of personal health beliefs related to breast health within the larger cultural context. The participants were recruited using the snowball method and words of mouth. Data collection and analysis: A short questionnaire was designed to collect data related to socio demographic status (SDQ) from all participants. A Semi-structured interviews guide was used to elicit data through interviews with the informants. Nvivo10 a data manager was utilized to assist with data analysis. Leininger’s four phases of qualitative data analysis was used as a guide for the data analysis. The phases used to analyze the data included: 1) Collecting and documenting raw data, 2) Identifying of descriptors and categories according to the domains of inquiry and research questions. Emic and etic data is coded for similarities and differences, 3) Identifying patterns and contextual analysis, discover saturation of ideas and recurrent patterns, and 4) Identifying themes and theoretical formulations and recommendations. Findings: Three major themes were emerged within the cultural and religious context; 1. Fear, denial, embarrassment and lack of knowledge were common perceptions of Ma’anis’ women regarding breast health and screening mammography, 2. Health care professionals in Jordan were not quick to offer information and education about breast cancer and screening, and 3. Willingness to learn about breast health and cancer prevention. Conclusion: The study indicated the disparities between the infrastructure and resourcing in rural and urban areas of Jordan, knowledge deficit related to breast cancer, and lack of education about breast health may impact women’s decision to go for a mammogram screening. Cultural beliefs, fear, embarrassments as well as providers lack of focus on breast health were significant contributors against practicing breast health. Health providers and policy makers should provide resources for the establishment health education programs regarding breast cancer early detection and mammography screening. Nurses should play a major role in delivering health education about breast health in general and breast cancer in particular. A culturally appropriate health awareness messages can be used in creating educational programs which can be employed at the national levels.

Keywords: breast health, beliefs, cultural context, ethnography, mammogram screening

Procedia PDF Downloads 294
2702 Development of Sulfite Biosensor Based on Sulfite Oxidase Immobilized on 3-Aminoproplytriethoxysilane Modified Indium Tin Oxide Electrode

Authors: Pawasuth Saengdee, Chamras Promptmas, Ting Zeng, Silke Leimkühler, Ulla Wollenberger

Abstract:

Sulfite has been used as a versatile preservative to limit the microbial growth and to control the taste in some food and beverage. However, it has been reported to cause a wide spectrum of severe adverse reactions. Therefore, it is important to determine the amount of sulfite in food and beverage to ensure consumer safety. An efficient electrocatalytic biosensor for sulfite detection was developed by immobilizing of human sulfite oxidase (hSO) on 3-aminoproplytriethoxysilane (APTES) modified indium tin oxide (ITO) electrode. Cyclic voltammetry was employed to investigate the electrochemical characteristics of the hSO modified ITO electrode for various pretreatment and binding conditions. Amperometry was also utilized to demonstrate the current responses of the sulfite sensor toward sodium sulfite in an aqueous solution at a potential of 0 V (vs. Ag/AgCl 1 M KCl). The proposed sulfite sensor has a linear range between 0.5 to 2 mM with a correlation coefficient 0.972. Then, the additional polymer layer of PVA was introduced to extend the linear range of sulfite sensor and protect the enzyme. The linear range of sulfite sensor with 5% coverage increases from 2.8 to 20 mM at a correlation coefficient of 0.983. In addition, the stability of sulfite sensor with 5% PVA coverage increases until 14 days when kept in 0.5 mM Tris-buffer, pH 7.0 at 4 8C. Therefore, this sensor could be applied for the detection of sulfite in the real sample, especially in food and beverage.

Keywords: sulfite oxidase, bioelectrocatalytsis, indium tin oxide, direct electrochemistry, sulfite sensor

Procedia PDF Downloads 227
2701 A Machine Learning Approach for Anomaly Detection in Environmental IoT-Driven Wastewater Purification Systems

Authors: Giovanni Cicceri, Roberta Maisano, Nathalie Morey, Salvatore Distefano

Abstract:

The main goal of this paper is to present a solution for a water purification system based on an Environmental Internet of Things (EIoT) platform to monitor and control water quality and machine learning (ML) models to support decision making and speed up the processes of purification of water. A real case study has been implemented by deploying an EIoT platform and a network of devices, called Gramb meters and belonging to the Gramb project, on wastewater purification systems located in Calabria, south of Italy. The data thus collected are used to control the wastewater quality, detect anomalies and predict the behaviour of the purification system. To this extent, three different statistical and machine learning models have been adopted and thus compared: Autoregressive Integrated Moving Average (ARIMA), Long Short Term Memory (LSTM) autoencoder, and Facebook Prophet (FP). The results demonstrated that the ML solution (LSTM) out-perform classical statistical approaches (ARIMA, FP), in terms of both accuracy, efficiency and effectiveness in monitoring and controlling the wastewater purification processes.

Keywords: environmental internet of things, EIoT, machine learning, anomaly detection, environment monitoring

Procedia PDF Downloads 145
2700 Non-Targeted Adversarial Object Detection Attack: Fast Gradient Sign Method

Authors: Bandar Alahmadi, Manohar Mareboyana, Lethia Jackson

Abstract:

Today, there are many applications that are using computer vision models, such as face recognition, image classification, and object detection. The accuracy of these models is very important for the performance of these applications. One challenge that facing the computer vision models is the adversarial examples attack. In computer vision, the adversarial example is an image that is intentionally designed to cause the machine learning model to misclassify it. One of very well-known method that is used to attack the Convolution Neural Network (CNN) is Fast Gradient Sign Method (FGSM). The goal of this method is to find the perturbation that can fool the CNN using the gradient of the cost function of CNN. In this paper, we introduce a novel model that can attack Regional-Convolution Neural Network (R-CNN) that use FGSM. We first extract the regions that are detected by R-CNN, and then we resize these regions into the size of regular images. Then, we find the best perturbation of the regions that can fool CNN using FGSM. Next, we add the resulted perturbation to the attacked region to get a new region image that looks similar to the original image to human eyes. Finally, we placed the regions back to the original image and test the R-CNN with the attacked images. Our model could drop the accuracy of the R-CNN when we tested with Pascal VOC 2012 dataset.

Keywords: adversarial examples, attack, computer vision, image processing

Procedia PDF Downloads 188