Search results for: closed-loop model identification

Authors: J. K. Visser, H. T. Malan

Abstract:

A need exists to identify the sources of risks associated with the process automation systems within petrochemical companies or similar energy related industries. These companies use many different process automation technologies in its value chain. A crucial part of the process automation system is the information technology component featuring in the supervisory control layer. The ever-changing technology within the process automation layers and the rate at which it advances pose a risk to safe and predictable automation system performance. The age of the automation equipment also provides challenges to the operations and maintenance managers of the plant due to obsolescence and unavailability of spare parts. The main objective of this research was to determine the risk sources associated with the equipment that is part of the process automation systems. A secondary objective was to establish whether technology managers and technicians were aware of the risks and share the same viewpoint on the importance of the risks associated with automation systems. A conceptual model for risk sources of automation systems was formulated from models and frameworks in literature. This model comprised six categories of risk which forms the basis for identifying specific risks. This model was used to develop a questionnaire that was sent to 172 instrument technicians and technology managers in the company to obtain primary data. 75 completed and useful responses were received. These responses were analyzed statistically to determine the highest risk sources and to determine whether there was difference in opinion between technology managers and technicians. The most important risks that were revealed in this study are: 1) the lack of skilled technicians, 2) integration capability of third-party system software, 3) reliability of the process automation hardware, 4) excessive costs pertaining to performing maintenance and migrations on process automation systems, and 5) requirements of having third-party communication interfacing compatibility as well as real-time communication networks.

Keywords: distributed control system, identification of risks, information technology, process automation system

Procedia PDF Downloads 107

Authors: Entisar A. Elgmati

Abstract:

Recurrent infant diarrhea is studied using daily data collected in Salvador, Brazil over one year and three months. A logistic regression model is fitted instead of Aalen's additive model using the same covariates that were used in the analysis with the additive model. The model gives reasonably similar results to that using additive regression model. In addition, the problem with the estimated conditional probabilities not being constrained between zero and one in additive model is solved here. Also martingale residuals that have been used to judge the goodness of fit for the additive model are shown to be useful for judging the goodness of fit of the logistic model.

Keywords: additive model, cumulative probabilities, infant diarrhoea, recurrent event

Procedia PDF Downloads 608

Authors: Young Ik Suh, Taewook Chung, Glaucio Scremin, Tywan Martin

Abstract:

In May of 2016, the Philadelphia 76ers announced that StubHub, the ticket resale company, will have advertising on the team’s jerseys beginning in the 2017-18 season. The 76ers and National Basketball Association (NBA) became the first team and league which embraced jersey sponsorships in the four major U.S. professional sports. Even though many professional teams and leagues in Europe, Asia, Africa, and South America have adopted jersey sponsorship actively, this phenomenon is relatively new in America. While the jersey sponsorship provides economic gains for the professional leagues and franchises, sport fans can have different points of view for the phenomenon of jersey sponsorship. For instance, since many sport fans in U.S. are not familiar with ads on jerseys, this movement can possibly cause negative reaction such as the decrease in ticket and merchandise sales. They also concern the small size of ads on jersey become bigger ads, like in the English Premier League (EPL). However, some sport fans seem they do not mind too much about jersey sponsorship because the ads on jersey will not affect their loyalty and fanship. Therefore, the assumption of this study was that the sport fans’ reaction about jersey sponsorship can be possibly different, especially based on different levels of the sport fans’ team identification and various sizes of ads on jersey. Unlike general sponsorship in sport industry, jersey sponsorship has received little attention regarding its potential impact on sport fans attitudes and buying intentions. Thus, the current study sought to identify how the various levels of team identification influence brand attitude and buying intention in terms of jersey sponsorship. In particular, this study examined the effect of team identification on brand attitude and buying intention when there are no ads, small size ads, and large size ads on jersey. 3 (large, small, and no ads) X 3 (Team Identification: high, moderate, low) between subject factorial design was conducted on attitude toward the brand and buying intention of jersey sponsorship. The ads on Philadelphia 76ers jersey were used. The sample of this study was selected from message board users provided by different sports websites (i.e., forums.realgm.com and phillysportscentral.com). A total of 275 respondents participated in this study by responding to an online survey questionnaire. The results showed that there were significant differences between fans with high identification and fans with low identification. The findings of this study are expected to have many theoretical and practical contributions and implications by extending the research and literature pertaining to the relationship between team identification and brand strategy based upon different levels of team identification.

Keywords: brand attitude, buying intention, Jersey sponsorship, team identification

Procedia PDF Downloads 220

Authors: Muhammad Sheeraz, Mehwish Ejaz

Abstract:

This study endeavors to enhance the understanding of the determinants of oppositional brand loyalty, particularly within the context of fans of a sports brand. The primary focus is on investigating how oppositional brand loyalty fosters rivalry among the fans and exploring the interplay between various variables, namely self-congruence, consumer brand identification, consumer brand engagement, and narcissism, in influencing the likelihood of endorsing a rival team. The research adopts a cross-sectional survey methodology, employing a structured questionnaire distributed both online and onsite to gather responses from a representative sample of 460 PSL fans in Pakistan. The data collection process involved obtaining responses from diverse settings, including universities, shopping malls, and other public spaces frequented by PSL enthusiasts. Participants were prompted to indicate their allegiance to a specific PSL team and subsequently respond to the questionnaire based on their preferences. The findings of the study reveal that narcissism, as a moderating factor, exhibits no significant influence on consumer brand identification, consumer brand engagement, and oppositional brand loyalty. However, it does emerge as a significant moderator in the relationship between self-congruence and consumer brand identification. Particularly, consumers express brand identification through self-congruence, elucidating the existence of oppositional sentiments among PSL fans and their counterparts supporting rival teams. The implications of these results underscore the importance for marketers to establish a brand identity that resonates with consumers on a personal level. Such an approach fosters a strong sense of identification with the brand, prompting consumers to vigorously defend and support their favored brands, even in the face of opposition from rival teams. Marketers are encouraged to focus on cultivating long-term consumer loyalty, as it proves pivotal in maintaining a competitive advantage over industry counterparts.

Keywords: oppositional brand loyalty, consumer brand identification, consumer brand engagement, narcissism, self-congruence

Procedia PDF Downloads 35

Authors: Kishor Chandra Kandpal, Amit Kumar

Abstract:

The Indian Himalaya region harbours approximately 1748 plants of medicinal importance, and as per International Union for Conservation of Nature (IUCN), the 112 plant species among these are threatened and endangered. To ease the pressure on these plants, the government of India is encouraging its in-situ cultivation. The Saussurea costus, Valeriana jatamansi, and Picrorhiza kurroa have also been prioritized for large scale cultivation owing to their market demand, conservation value and medicinal properties. These species are found from 1000 m to 4000 m elevation ranges in the Indian Himalaya. Identification of these plants in the field requires taxonomic skills, which is one of the major bottleneck in the conservation and management of these plants. In recent years, Hyperspectral remote sensing techniques have been precisely used for the discrimination of plant species with the help of their unique spectral signatures. In this background, a spectral library of the above 03 medicinal plants was prepared by collecting the spectral data using a handheld spectroradiometer (325 to 1075 nm) from farmer’s fields of Himachal Pradesh and Uttarakhand states of Indian Himalaya. The Random forest (RF) model was implied on the spectral data for the classification of the medicinal plants. The 80:20 standard split ratio was followed for training and validation of the RF model, which resulted in training accuracy of 84.39 % (kappa coefficient = 0.72) and testing accuracy of 85.29 % (kappa coefficient = 0.77). This RF classifier has identified green (555 to 598 nm), red (605 nm), and near-infrared (725 to 840 nm) wavelength regions suitable for the discrimination of these species. The findings of this study have provided a technique for rapid and onsite identification of the above medicinal plants in the field. This will also be a key input for the classification of hyperspectral remote sensing images for mapping of these species in farmer’s field on a regional scale. This is a pioneer study in the Indian Himalaya region for medicinal plants in which the applicability of hyperspectral remote sensing has been explored.

Keywords: himalaya, hyperspectral remote sensing, machine learning; medicinal plants, random forests

Procedia PDF Downloads 175

Authors: Nastaran Moosavi, Mohammad Mokhtari

Abstract:

Seismic inversion is a technique which has been in use for years and its main goal is to estimate and to model physical characteristics of rocks and fluids. Generally, it is a combination of seismic and well-log data. Seismic inversion can be carried out through different methods; we have conducted and compared post-stack and pre- stack seismic inversion methods on real data in one of the fields in the Persian Gulf. Pre-stack seismic inversion can transform seismic data to rock physics such as P-impedance, S-impedance and density. While post- stack seismic inversion can just estimate P-impedance. Then these parameters can be used in reservoir identification. Based on the results of inverting seismic data, a gas reservoir was detected in one of Hydrocarbon oil fields in south of Iran (Persian Gulf). By comparing post stack and pre-stack seismic inversion it can be concluded that the pre-stack seismic inversion provides a more reliable and detailed information for identification and prediction of hydrocarbon reservoirs.

Keywords: density, p-impedance, s-impedance, post-stack seismic inversion, pre-stack seismic inversion

Procedia PDF Downloads 295

Authors: Sarah Aldhalaan, Tanzila Saba

Abstract:

Healthcare sectors are increasing rapidly to fulfill patient’s needs across the world. A patient identification is considered as the main aspect for a patient to be served in healthcare institutes. Nowadays, people are presenting their insurance card along with their identification card in order to get the needed treatment in hospitals however, this process lack security preferences. The aim of this research paper is to reveal a solution to introduce and use biometrics in healthcare hospitals. The findings show that the people know biometrics since they are interacting with them through different channels and that the need for biometrics techniques to identify patients is essential. Also, the survey relevant questions are used to analyze and add insights on what is are the suitable biometrics to be used in such cases. Moreover, results are presented to exhibit the effectiveness of the used methodology and in analyzing usage of biometrics in hospitals in an enhancing way. Finally, an interesting conclusion of overall work is presented at the end of paper.

Keywords: biometrics, healthcare, fingerprint, Saudi Arabia

Procedia PDF Downloads 217

Authors: Sundus Mona, Atif Adnan, Babar Ali, Fareeha Arshad, Allah Rakha

Abstract:

Molecular diversity is the variation in the abundance of species. Forensic entomology is a neglected field in Pakistan. Insects collected from the crime scene should be handled by forensic entomologists who are currently virtually non-existent in Pakistan. Correct identification of insect specimen along with knowledge of their biodiversity can aid in solving many problems related to complicated forensic cases. Inadequate morphological identification and insufficient thermal biological studies limit the entomological utility in Forensic Medicine. Recently molecular identification of entomological evidence has gained attention globally. DNA barcoding is the latest and established method for species identification. Only proper identification can provide a precise estimation of postmortem intervals. Arthropods are known to be the first tourists scavenging on decomposing dead matter. The objective of the proposed study was to identify species by molecular techniques and analyze their phylogenetic importance with barcoded necrophagous insect species of early succession on human cadavers. Based upon this identification, the study outcomes will be the utilization of established DNA bar codes to identify carrion feeding insect species for concordant estimation of post mortem interval. A molecular identification method involving sequencing of a 658bp ‘barcode’ fragment of the mitochondrial cytochrome oxidase subunit 1 (CO1) gene from collected specimens of unknown dipteral species from cadavers of Lahore was evaluated. Nucleotide sequence divergences were calculated using MEGA 7 and Arlequin, and a neighbor-joining phylogenetic tree was generated. Three species were identified, Chrysomya megacephala, Chrysomya saffranea, and Chrysomya rufifacies with low genetic diversity. The fixation index was 0.83992 that suggests a need for further studies to identify and classify forensically relevant insects in Pakistan. There is an exigency demand for further research especially when immature forms of arthropods are recovered from the crime scene.

Keywords: molecular diversity, DNA barcoding, species identification, forensically relevant

Procedia PDF Downloads 118

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

Abstract:

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

Keywords: healthcare, fall detection, transformer, transfer learning

Procedia PDF Downloads 100

Authors: Radoslav Židek, Veronika Šidlová, Radovan Kasarda, Birgit Fuerst-Waltl

Abstract:

Machine learning represents a set of topics dealing with the creation and evaluation of algorithms that facilitate pattern recognition, classification, and prediction, based on models derived from existing data. The data can present identification patterns which are used to classify into groups. The result of the analysis is the pattern which can be used for identification of data set without the need to obtain input data used for creation of this pattern. An important requirement in this process is careful data preparation validation of model used and its suitable interpretation. For breeders, it is important to know the origin of animals from the point of the genetic diversity. In case of missing pedigree information, other methods can be used for traceability of animal´s origin. Genetic diversity written in genetic data is holding relatively useful information to identify animals originated from individual countries. We can conclude that the application of data mining for molecular genetic data using supervised learning is an appropriate tool for hypothesis testing and identifying an individual.

Keywords: genetic data, Pinzgau cattle, supervised learning, machine learning

Procedia PDF Downloads 518

Authors: Nitin Shravan, Sudarsun Santhiappan, B. Sivaselvan

Abstract:

Subsection identification, in the context of Electronic Health Records (EHRs), is identifying the important sections for down-stream tasks like auto-coding. In this work, we classify the text present in EHRs according to their information, using machine learning and deep learning techniques. We initially describe briefly about the problem and formulate it as a text classification problem. Then, we discuss upon the methods from the literature. We try two approaches - traditional feature extraction based machine learning methods and deep learning methods. Through experiments on a private dataset, we establish that the deep learning methods perform better than the feature extraction based Machine Learning Models.

Keywords: deep learning, machine learning, semantic clinical classification, subsection identification, text classification

Procedia PDF Downloads 182

Authors: Rashini Maduka, C. R. Wijesinghe, A. R. Weerasinghe

Abstract:

Drug-drug interactions (DDIs) can happen when two or more drugs are taken together. Today DDIs have become a serious health issue due to adverse drug effects. In vivo and in vitro methods for identifying DDIs are time-consuming and costly. Therefore, in-silico-based approaches are preferred in DDI identification. Most machine learning models for DDI prediction are used chemical and biological drug properties as features. However, some drug features are not available and costly to extract. Therefore, it is better to make automatic feature engineering. Furthermore, people who have diabetes already suffer from other diseases and take more than one medicine together. Then adverse drug effects may happen to diabetic patients and cause unpleasant reactions in the body. In this study, we present a model with a graph convolutional autoencoder and a graph decoder using a dataset from DrugBank version 5.1.3. The main objective of the model is to identify unknown interactions between antidiabetic drugs and the drugs taken by diabetic patients for other diseases. We considered automatic feature engineering and used Known DDIs only as the input for the model. Our model has achieved 0.86 in AUC and 0.86 in AP.

Keywords: drug-drug interaction prediction, graph embedding, graph convolutional networks, adverse drug effects

Procedia PDF Downloads 70

Authors: Ravindra B. Patil, P. Krishnamoorthy, Shriram Sethuraman

Abstract:

This work proposes a novel Gaussian Mixture Model (GMM) based approach for accurate tracking of the arterial wall and subsequent computation of the distension waveform using Radio Frequency (RF) ultrasound signal. The approach was evaluated on ultrasound RF data acquired using a prototype ultrasound system from an artery mimicking flow phantom. The effectiveness of the proposed algorithm is demonstrated by comparing with existing wall tracking algorithms. The experimental results show that the proposed method provides 20% reduction in the error margin compared to the existing approaches in tracking the arterial wall movement. This approach coupled with ultrasound system can be used to estimate the arterial compliance parameters required for screening of cardiovascular related disorders.

Keywords: distension waveform, Gaussian Mixture Model, RF ultrasound, arterial wall movement

Procedia PDF Downloads 475

Authors: Fuad M. Alkoot

Abstract:

DNA data have been used in forensics for decades. However, current research looks at using the DNA as a biometric identity verification modality. The goal is to improve the speed of identification. We aim at using gene data that was initially used for autism detection to find if and how accurate is this data for identification applications. Mainly our goal is to find if our data preprocessing technique yields data useful as a biometric identification tool. We experiment with using the nearest neighbor classifier to identify subjects. Results show that optimal classification rate is achieved when the test set is corrupted by normally distributed noise with zero mean and standard deviation of 1. The classification rate is close to optimal at higher noise standard deviation reaching 3. This shows that the data can be used for identity verification with high accuracy using a simple classifier such as the k-nearest neighbor (k-NN). 

Keywords: biometrics, genetic data, identity verification, k nearest neighbor

Procedia PDF Downloads 227

Authors: Victor Toom

Abstract:

Albeit it is never possible to anticipate the full range of difficulties after a catastrophe, efforts to identify victims of mass casualty events have become institutionalized and standardized with the aim of effectively and efficiently addressing the many challenges and contingencies. Such ‘disaster victim identification’ (DVI) practices are dependent on the forensic sciences, are subject of national legislation, and are reliant on technical and organizational protocols to mitigate the many complexities in the wake of catastrophe. Apart from such technological, legal and bureaucratic elements constituting a DVI operation, victims’ families and their emotions are also part and parcel of any effort to identify casualties of mass human fatality incidents. Take for example the fact that forensic experts require (antemortem) information from the group of relatives to make identification possible. An identified body or body part is also repatriated to kin. Relatives are thus main stakeholders in DVI operations. Much has been achieved in years past regarding facilitating victims’ families’ issues and their emotions. Yet, how families are dealt with by experts and authorities is still considered a difficult topic. Due to sensitivities and required emphatic interaction with families on the one hand, and the rationalized DVI efforts, on the other hand, there is still scope for improving communication, providing information and meaningful inclusion of relatives in the DVI effort. This paper aims to bridge the standardized world of DVI efforts and families’ experienced realities and makes suggestions to further improve DVI efforts through inclusion of victims’ families. Based on qualitative interviews, the paper narrates involvement and experiences of inter alia DVI practitioners, victims’ families, advocates and clergy in the wake of the 1995 Srebrenica genocide which killed approximately 8,000 men, and the 9/11 in New York City with 2,750 victims. The paper shows that there are several models of including victims’ families into a DVI operation, and it argues for a model of where victims’ families become a partner in DVI operations.

Keywords: disaster victim identification (DVI), victims’ families, social science (qualitative), 9/11 attacks, Srebrenica genocide

Procedia PDF Downloads 205

Authors: Davide Fuscà, Kanan Rahimli, Roberto Leuzzi

Abstract:

Preventing abuse and illegal activities in a given area of the sea is a very difficult and expensive task. Artificial intelligence offers the possibility to implement new methods to identify the vessel class type from the kinematic features of the vessel itself. The task strictly depends on the quality of the data. This paper explores the application of a deep, long short-term memory model by using AIS flow only with a relatively low quality. The proposed model reaches high accuracy on detecting nine vessel classes representing the most common vessel types in the Ionian-Adriatic Sea. The model has been applied during the Adriatic-Ionian trial period of the international EU ANDROMEDA H2020 project to identify vessels performing behaviors far from the expected one depending on the declared type.

Keywords: maritime surveillance, artificial intelligence, behavior analysis, LSTM

Procedia PDF Downloads 203

Authors: Yu Qin

Abstract:

In order to tackle the ever-growing problem of the lack of parking space, this paper presents the design and implementation of a smart unmanned parking system that is based on RFID (radio frequency identification) technology and Wireless communication technology. This system uses RFID technology to achieve the identification function (transmitted by 2.4 G wireless module) and is equipped with an STM32L053 micro controller as the main control chip of the smart vehicle. This chip can accomplish automatic parking (in/out), charging and other functions. On this basis, it can also help users easily query the information that is stored in the database through the Internet. Experimental tests have shown that the system has the features of low power consumption and stable operation, among others. It can effectively improve the level of automation control of the parking lot management system and has enormous application prospects.

Keywords: RFID, embedded system, unmanned, parking management

Procedia PDF Downloads 301

Authors: J. Tamosaitiene

Abstract:

The article focuses on the identification and classification of key risk management criteria that represent the most important sustainability aspects of the construction industry. The construction sector is one of the most important sectors in Lithuania. Nowadays, the assessment of the risk level of a construction project is especially important for the quality of construction projects, the growth of enterprises and the sector. To establish the most important criteria for successful growth of the sector, a questionnaire for experts was developed. The analytic hierarchy process (AHP), the expert judgement method and other multicriteria decision making (MCDM) methods were used to develop the hybrid model. The results were used to develop an integrated knowledge system for the measurement of a risk level particular to construction projects. The article presents a practical case that details the developed system, sustainable aspects, and risk assessment.

Keywords: risk, system, model, construction

Procedia PDF Downloads 138

Authors: Megha Gupta, Nupur Prakash

Abstract:

Identification of plant diseases has been performed using machine learning and deep learning models on the datasets containing images of healthy and diseased plant leaves. The current study carries out an evaluation of some of the deep learning models based on convolutional neural network (CNN) architectures for identification of plant diseases. For this purpose, the publicly available New Plant Diseases Dataset, an augmented version of PlantVillage dataset, available on Kaggle platform, containing 87,900 images has been used. The dataset contained images of 26 diseases of 14 different plants and images of 12 healthy plants. The CNN models selected for the study presented in this paper are AlexNet, ZFNet, VGGNet (four models), GoogLeNet, and ResNet (three models). The selected models are trained using PyTorch, an open-source machine learning library, on Google Colaboratory. A comparative study has been carried out to analyze the high degree of accuracy achieved using these models. The highest test accuracy and F1-score of 99.59% and 0.996, respectively, were achieved by using GoogLeNet with Mini-batch momentum based gradient descent learning algorithm.

Keywords: comparative analysis, convolutional neural networks, deep learning, plant disease identification

Procedia PDF Downloads 166

Authors: Elham Allahmoradi, Bahman Allahmoradi, Ali Bonyadi Naeini

Abstract:

Complex systems have many aspects. A variety of methods have been developed to analyze these systems. The most efficient of these methods should not only be simple, but also provide useful and comprehensive information about many aspects of the system. Matrix methods are considered the most commonly methods used to analyze and design systems. Each matrix method can examine a particular aspect of the system. If these methods are combined, managers can access to more comprehensive and broader information about the system. This study was conducted in four steps. In the first step, a process model of a real project has been extracted through IDEF3. In the second step, activity levels have been attained by writing a process model in the form of a design structure matrix (DSM) and sorting it through triangulation algorithm (TA). In the third step, sub-processes have been obtained by writing the process model in the form of an interface structure matrix (ISM) and clustering it through cluster identification algorithm (CIA). In the fourth step, a mixed model has been developed to provide a unified picture of the project structure through the simultaneous presentation of activities and sub-processes. Finally, the paper is completed with a conclusion.

Keywords: integrated definition for process description capture (IDEF3) method, design structure matrix (DSM), interface structure matrix (ism), mixed matrix model, activity level, sub-process

Procedia PDF Downloads 470

Authors: Chia-Chun Wu, Yu-Hsien Sung

Abstract:

This study aims to examine the consistency between students’ predictions and their actual observations on the bullying prevalence rate among different types of high-risk victims, thereby clarifying the reliability of students’ reports on the identification of bullying. A total of 1,732 Taiwanese students (734 males and 998 females) participated in this study. A Rasch model was adopted for data analysis. The results showed that students with “personality or behavioral issues” are more likely to be bullied in schools, based on both students’ predictions and actual observations. Moreover, the results differed significantly between genders and between various educational levels in students’ predictions and their actual observations on the bullying prevalence rate of different types of high-risk victims. To summarize, this study not only suggests that students’ reports on the identification of bullying are accurate and could be a valuable reference in terms of recognizing a bullying incident, but it also argues that more attention should be paid to students’ gender and educational level when taking their perspectives into consideration when it comes to identifying bullying behaviors.

Keywords: school bullying, student, bullying recognition, high-risk victims

Procedia PDF Downloads 62

Authors: Chih Hung Shih

Abstract:

Eyewitness identification is one of the efficient information to identify suspects during criminal investigation. However eyewitness identification is improved frequently, inaccurate and plays vital roles in wrongful convictions. Most eyewitness misidentifications are made during police criminal investigation stage and then accepted by juries. Four failure investigation case studies in Taiwan are conduct to demonstrate how misidentifications are caused during the police investigation context. The result shows that there are several common grounds among these cases: (1) investigators lacked for knowledge about eyewitness memory so that they couldn’t evaluate the validity of the eyewitnesses’ accounts and identifications, (2) eyewitnesses were always asked to filter out several suspects during the investigation, and received investigation information which contaminated the eyewitnesses’ memory, (3) one to one live individual identifications were made in most of cases, (4) eyewitness identifications were always used to support the hypotheses of investigators, and exaggerated theirs powers when conform with the investigation lines, (5) the eyewitnesses’ confidence didn’t t reflect the validity of their identifications , but always influence the investigators’ beliefs for the identifications, (6) the investigators overestimated the power of the eyewitness identifications and ignore the inconsistency with other evidence. Recommendations have been proposed for future academic research and police practice of eyewitness identification in Taiwan.

Keywords: criminal investigation, eyewitness identification, investigative bias, investigative failures

Procedia PDF Downloads 219

Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez

Abstract:

Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.

Keywords: deep-learning, image classification, image identification, industrial engineering.

Procedia PDF Downloads 133

Authors: Virender Singh, Mathew Rees, Simon Hampton, Sivaram Annadurai

Abstract:

Plant identification is a challenging task that aims to identify the family, genus, and species according to plant morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users narrow down the possibilities. However, numerous morphological similarities between and within species render correct classification difficult. In this paper, we tested custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88,000 provided by the Royal Horticultural Society (RHS) and a smaller dataset of 16,000 images from the PlantClef 2015 dataset for classifying plants at genus and species levels, respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420 and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. For classifying plants at the species level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success. In conclusion, these results could help end users, professionals and the general public alike in identifying plants quicker and with improved accuracy.

Keywords: plant identification, CNN, image processing, vision transformer, classification

Procedia PDF Downloads 66

Authors: Zongyan Li, Matt Best

Abstract:

This paper presents an optimization method for reducing the number of input channels and the complexity of the feed-forward NARX neural network (NN) without compromising the accuracy of the NN model. By utilizing the correlation analysis method, the most significant regressors are selected to form the input layer of the NN structure. An application of vehicle dynamic model identification is also presented in this paper to demonstrate the optimization technique and the optimal input layer structure and the optimal number of neurons for the neural network is investigated.

Keywords: correlation analysis, F-ratio, levenberg-marquardt, MSE, NARX, neural network, optimisation

Procedia PDF Downloads 343

Authors: M. Chňapek, M. Tomka, R. Peroutková, Z. Gálová

Abstract:

Processes of plant breeding, testing and licensing of new varieties, patent protection in seed production, relations in trade and protection of copyright are dependent on identification, differentiation and characterization of plant genotypes. Therefore, we focused our research on utilization of wheat storage proteins as genetic markers suitable not only for differentiation of individual genotypes, but also for identification and characterization of their considerable properties. We analyzed a collection of 102 genotypes of bread wheat (Triticum aestivum L.), 41 genotypes of spelt wheat (Triticum spelta L.), and 35 genotypes of durum wheat (Triticum durum Desf.), in this study. Our results show, that genotypes of bread wheat and durum wheat were homogenous and single line, but spelt wheat genotypes were heterogenous. We observed variability of HMW-GS composition according to environmental factors and level of breeding and predict technological quality on the basis of Glu-score calculation.

Keywords: genotype identification, HMW-GS, wheat quality, polymorphism

Procedia PDF Downloads 434

Authors: Daudi S. Simbeye, Mbazingwa E. Mkiramweni

Abstract:

Plant diseases have the potential to drastically diminish the quantity and quality of agricultural products. Guava (Psidium guajava), sometimes known as the apple of the tropics, is one of the most widely cultivated fruits in tropical regions. Monitoring plant health and diagnosing illnesses is an essential matter for sustainable agriculture, requiring the inspection of visually evident patterns on plant leaves and fruits. Due to minor variations in the symptoms of various guava illnesses, a professional opinion is required for disease diagnosis. Due to improper pesticide application by farmers, erroneous diagnoses may result in economic losses. This study proposes a method that uses artificial intelligence (AI) to detect and classify the most widespread guava plant by comparing images of its leaves and fruits to datasets. ESP32 CAM is responsible for data collection, which includes images of guava leaves and fruits. By comparing the datasets, these image formats are used as datasets to help in the diagnosis of plant diseases through the leaves and fruits, which is vital for the development of an effective automated agricultural system. The system test yielded the most accurate identification findings (99 percent accuracy in differentiating four guava fruit diseases (Canker, Mummification, Dot, and Rust) from healthy fruit). The proposed model has been interfaced with a mobile application to be used by smartphones to make a quick and responsible judgment, which can help the farmers instantly detect and prevent future production losses by enabling them to take precautions beforehand.

Keywords: early identification, guava plants, fruit diseases, deep learning

Procedia PDF Downloads 47

Authors: Merih Şimşek, Recep Keşli, Özgül Çetinkaya, Cengiz Demir, Adem Aslan

Abstract:

Bacteremia is a clinical entity with high morbidity and mortality rates when immediate diagnose, or treatment cannot be achieved. Microorganisms which can cause sepsis or bacteremia are easily isolated from blood cultures. Fifty-five positive blood cultures were included in this study. Microorganisms in 55 blood cultures were isolated by conventional microbiological methods; afterwards, microorganisms were defined in terms of the phenotypic aspects by the Vitek-2 system. The same microorganisms in all blood culture samples were defined in terms of genotypic aspects again by Multiplex-PCR DNA Low-Density Microarray System. At the end of the identification process, the DNA microarray system’s success in identification was evaluated based on the Vitek-2 system. The Vitek-2 system and DNA Microarray system were able to identify the same microorganisms in 53 samples; on the other hand, different microorganisms were identified in the 2 blood cultures by DNA Microarray system. The microorganisms identified by Vitek-2 system were found to be identical to 96.4 % of microorganisms identified by DNA Microarrays system. In addition to bacteria identified by Vitek-2, the presence of a second bacterium has been detected in 5 blood cultures by the DNA Microarray system. It was identified 18 of 55 positive blood culture as E.coli strains with both Vitek 2 and DNA microarray systems. The same identification numbers were found 6 and 8 for Acinetobacter baumanii, 10 and 10 for K.pneumoniae, 5 and 5 for S.aureus, 7 and 11 for Enterococcus spp, 5 and 5 for P.aeruginosa, 2 and 2 for C.albicans respectively. According to these results, DNA Microarray system requires both a technical device and experienced staff support; besides, it requires more expensive kits than Vitek-2. However, this method should be used in conjunction with conventional microbiological methods. Thus, large microbiology laboratories will produce faster, more sensitive and more successful results in the identification of cultured microorganisms.

Keywords: microarray, Vitek-2, blood culture, bacteremia

Procedia PDF Downloads 314

Authors: Bilel Chalghaf, Mathieu Varin

Abstract:

Forest characterization in Quebec, Canada, is usually assessed based on photo-interpretation at the stand level. For species identification, this often results in a lack of precision. Very high spatial resolution imagery, such as DigitalGlobe, and Light Detection and Ranging (LiDAR), have the potential to overcome the limitations of aerial imagery. To date, few studies have used that data to map a large number of species at the tree level using machine learning techniques. The main objective of this study is to map 11 individual high tree species ( > 17m) at the tree level using an object-based approach in the broadleaf forest of Kenauk Nature, Quebec. For the individual tree crown segmentation, three canopy-height models (CHMs) from LiDAR data were assessed: 1) the original, 2) a filtered, and 3) a corrected model. The corrected CHM gave the best accuracy and was then coupled with imagery to refine tree species crown identification. When compared with photo-interpretation, 90% of the objects represented a single species. For modeling, 313 variables were derived from 16-band WorldView-3 imagery and LiDAR data, using radiance, reflectance, pixel, and object-based calculation techniques. Variable selection procedures were employed to reduce their number from 313 to 16, using only 11 bands to aid reproducibility. For classification, a global approach using all 11 species was compared to a semi-hierarchical hybrid classification approach at two levels: (1) tree type (broadleaf/conifer) and (2) individual broadleaf (five) and conifer (six) species. Five different model techniques were used: (1) support vector machine (SVM), (2) classification and regression tree (CART), (3) random forest (RF), (4) k-nearest neighbors (k-NN), and (5) linear discriminant analysis (LDA). Each model was tuned separately for all approaches and levels. For the global approach, the best model was the SVM using eight variables (overall accuracy (OA): 80%, Kappa: 0.77). With the semi-hierarchical hybrid approach, at the tree type level, the best model was the k-NN using six variables (OA: 100% and Kappa: 1.00). At the level of identifying broadleaf and conifer species, the best model was the SVM, with OA of 80% and 97% and Kappa values of 0.74 and 0.97, respectively, using seven variables for both models. This paper demonstrates that a hybrid classification approach gives better results and that using 16-band WorldView-3 with LiDAR data leads to more precise predictions for tree segmentation and classification, especially when the number of tree species is large.

Keywords: tree species, object-based, classification, multispectral, machine learning, WorldView-3, LiDAR

Procedia PDF Downloads 107

Authors: Louise H. Gracioso, Marcela P.G. Baltazar, Ingrid R. Avanzi, Bruno Karolski, Luciana J. Gimenes, Claudio O. Nascimento, Elen A. Perpetuo

Abstract:

Introduction: Higher copper concentrations promote a selection pressure on organisms such as plants, fungi and bacteria, which allows surviving only the resistant organisms to the contaminated site. This selective pressure keeps only the organisms most resistant to a specific condition and subsequently increases their bioremediation potential. Despite the bacteria importance for biosphere maintenance, it is estimated that only a small fraction living microbial species has been described and characterized. Due to the molecular biology development, tools based on analysis 16S ribosomal RNA or another specific gene are making a new scenario for the characterization studies and identification of microorganisms in the environment. News identification of microorganisms methods have also emerged like Biotyper (MALDI / TOF), this method mass spectrometry is subject to the recognition of spectroscopic patterns of conserved and features proteins for different microbial species. In view of this, this study aimed to isolate bacteria resistant to copper present in a Copper Processing Area (Sossego Mine, Canaan, PA) and identifies them in two different methods: Recent (spectrometry mass) and conventional. This work aimed to use them for a future bioremediation of this Mining. Material and Methods: Samples were collected at fifteen different sites of five periods of times. Microorganisms were isolated from mining wastes by culture enrichment technique; this procedure was repeated 4 times. The isolates were inoculated into MJS medium containing different concentrations of chloride copper (1mM, 2.5mM, 5mM, 7.5mM and 10 mM) and incubated in plates for 72 h at 28 ºC. These isolates were subjected to mass spectrometry identification methods (Biotyper – MALDI/TOF) and 16S gene sequencing. Results: A total of 105 strains were isolated in this area, bacterial identification by mass spectrometry method (MALDI/TOF) achieved 74% agreement with the conventional identification method (16S), 31% have been unsuccessful in MALDI-TOF and 2% did not obtain identification sequence the 16S. These results show that Biotyper can be a very useful tool in the identification of bacteria isolated from environmental samples, since it has a better value for money (cheap and simple sample preparation and MALDI plates are reusable). Furthermore, this technique is more rentable because it saves time and has a high performance (the mass spectra are compared to the database and it takes less than 2 minutes per sample).

Keywords: copper mining area, bioremediation, microorganisms, identification, MALDI/TOF, RNA 16S

Procedia PDF Downloads 352