scholarly journals Potential advantages and limitations of using information fusion in media forensics—a discussion on the example of detecting face morphing attacks

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Christian Kraetzer ◽  
Andrey Makrushin ◽  
Jana Dittmann ◽  
Mario Hildebrandt
Keyword(s):  
Information Fusion ◽  
Classification Accuracy ◽  
Negative Impact ◽  
Field Application ◽  
Attack Detection ◽  
Majority Voting ◽  
Forensic Sciences ◽  
List Type ◽  
Media Forensics ◽  
Shafer Theory

AbstractInformation fusion, i.e., the combination of expert systems, has a huge potential to improve the accuracy of pattern recognition systems. During the last decades, various application fields started to use different fusion concepts extensively. The forensic sciences are still hesitant if it comes to blindly applying information fusion. Here, a potentially negative impact on the classification accuracy, if wrongly used or parameterized, as well as the increased complexity (and the inherently higher costs for plausibility validation) of fusion is in conflict with the fundamental requirements for forensics.The goals of this paper are to explain the reasons for this reluctance to accept such a potentially very beneficial technique and to illustrate the practical issues arising when applying fusion. For those practical discussions the exemplary application scenario of morphing attack detection (MAD) is selected with the goal to facilitate the understanding between the media forensics community and forensic practitioners.As general contributions, it is illustrated why the naive assumption that fusion would make the detection more reliable can fail in practice, i.e., why fusion behaves in a field application sometimes differently than in the lab. As a result, the constraints and limitations of the application of fusion are discussed and its impact to (media) forensics is reflected upon.As technical contributions, the current state of the art of MAD is expanded by: The introduction of the likelihood-based fusion and an fusion ensemble composition experiment to extend the set of methods (majority voting, sum-rule, and Dempster-Shafer Theory of evidence) used previously The direct comparison of the two evaluation scenarios “MAD in document issuing” and “MAD in identity verification” using a realistic and some less restrictive evaluation setups A thorough analysis and discussion of the detection performance issues and the reasons why fusion in a majority of the test cases discussed here leads to worse classification accuracy than the best individual classifier

scholarly journals Investigating the Impact of Noneffortful Responses on Individual-Level Scores: Can the Effort-Moderated IRT Model Serve as a Solution?

2021 ◽  
pp. 014662162110138
Author(s):  
Joseph A. Rios ◽  
James Soland
Keyword(s):  
Classification Accuracy ◽  
Negative Impact ◽  
Parameter Recovery ◽  
Individual Level ◽  
Irt Model ◽  
Ability Estimates ◽  
Misclassification Rates ◽  
Individual Scores ◽  
3Pl Model ◽  
The Impact

Suboptimal effort is a major threat to valid score-based inferences. While the effects of such behavior have been frequently examined in the context of mean group comparisons, minimal research has considered its effects on individual score use (e.g., identifying students for remediation). Focusing on the latter context, this study addressed two related questions via simulation and applied analyses. First, we investigated how much including noneffortful responses in scoring using a three-parameter logistic (3PL) model affects person parameter recovery and classification accuracy for noneffortful responders. Second, we explored whether improvements in these individual-level inferences were observed when employing the Effort Moderated IRT (EM-IRT) model under conditions in which its assumptions were met and violated. Results demonstrated that including 10% noneffortful responses in scoring led to average bias in ability estimates and misclassification rates by as much as 0.15 SDs and 7%, respectively. These results were mitigated when employing the EM-IRT model, particularly when model assumptions were met. However, once model assumptions were violated, the EM-IRT model’s performance deteriorated, though still outperforming the 3PL model. Thus, findings from this study show that (a) including noneffortful responses when using individual scores can lead to potential unfounded inferences and potential score misuse, and (b) the negative impact that noneffortful responding has on person ability estimates and classification accuracy can be mitigated by employing the EM-IRT model, particularly when its assumptions are met.

Tobacco Leaf Grading Based on Deep Convolutional Neural Networks and Machine Vision

2021 ◽  
Vol 65 (1) ◽  
pp. 11-22
Author(s):  
Mengyao Lu ◽  
Shuwen Jiang ◽  
Cong Wang ◽  
Dong Chen ◽  
Tian’en Chen
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Classification Accuracy ◽  
Classification Model ◽  
List Type ◽  
Tobacco Leaves ◽  
Tobacco Leaf ◽  
Grading Model

HighlightsA classification model for the front and back sides of tobacco leaves was developed for application in industry.A tobacco leaf grading method that combines a CNN with double-branch integration was proposed.The A-ResNet network was proposed and compared with other classic CNN networks.The grading accuracy of eight different grades was 91.30% and the testing time was 82.180 ms, showing a relatively high classification accuracy and efficiency.Abstract. Flue-cured tobacco leaf grading is a key step in the production and processing of Chinese-style cigarette raw materials, directly affecting cigarette blend and quality stability. At present, manual grading of tobacco leaves is dominant in China, resulting in unsatisfactory grading quality and consuming considerable material and financial resources. In this study, for fast, accurate, and non-destructive tobacco leaf grading, 2,791 flue-cured tobacco leaves of eight different grades in south Anhui Province, China, were chosen as the study sample, and a tobacco leaf grading method that combines convolutional neural networks and double-branch integration was proposed. First, a classification model for the front and back sides of tobacco leaves was trained by transfer learning. Second, two processing methods (equal-scaled resizing and cropping) were used to obtain global images and local patches from the front sides of tobacco leaves. A global image-based tobacco leaf grading model was then developed using the proposed A-ResNet-65 network, and a local patch-based tobacco leaf grading model was developed using the ResNet-34 network. These two networks were compared with classic deep learning networks, such as VGGNet, GoogLeNet-V3, and ResNet. Finally, the grading results of the two grading models were integrated to realize tobacco leaf grading. The tobacco leaf classification accuracy of the final model, for eight different grades, was 91.30%, and grading of a single tobacco leaf required 82.180 ms. The proposed method achieved a relatively high grading accuracy and efficiency. It provides a method for industrial implementation of the tobacco leaf grading and offers a new approach for the quality grading of other agricultural products. Keywords: Convolutional neural network, Deep learning, Image classification, Transfer learning, Tobacco leaf grading

scholarly journals Exposure to auditory feedback delay while speaking induces perceptual habituation but does not mitigate the disruptive effect of delay on speech auditory-motor learning

2020 ◽  
Author(s):  
Douglas M. Shiller ◽  
Takashi Mitsuya ◽  
Ludo Max
Keyword(s):  
Motor Learning ◽  
Visual Feedback ◽  
Auditory Feedback ◽  
Detrimental Effect ◽  
Negative Impact ◽  
Motor Adaptation ◽  
List Type ◽  
Disruptive Effect ◽  
Feedback Delay ◽  
Spectral Perturbation

ABSTRACTPerceiving the sensory consequences of our actions with a delay alters the interpretation of these afferent signals and impacts motor learning. For reaching movements, delayed visual feedback of hand position reduces the rate and extent of visuomotor adaptation, but substantial adaptation still occurs. Moreover, the detrimental effect of visual feedback delay on reach motor learning—selectively affecting its implicit component—can be mitigated by prior habituation to the delay. Auditory-motor learning for speech has been reported to be more sensitive to feedback delay, and it remains unknown whether habituation to auditory delay reduces its negative impact on learning. We investigated whether 30 minutes of exposure to auditory delay during speaking (a) affects the subjective perception of delay, and (b) mitigates its disruptive effect on speech auditory-motor learning. During a speech adaptation task with real-time perturbation of vowel spectral properties, participants heard this frequency-shifted feedback with no delay, 75 ms delay, or 115 ms delay. In the delay groups, 50% of participants had been exposed to the delay throughout a preceding 30-minute block of speaking whereas the remaining participants completed this block without delay. Although habituation minimized awareness of the delay, no improvement in adaptation to the spectral perturbation was observed. Thus, short-term habituation to auditory feedback delays is not effective in reducing the negative impact of delay on speech auditory-motor adaptation. Combined with previous findings, the strong negative effect of delay and the absence of an influence of delay awareness suggest the involvement of predominantly implicit learning mechanisms in speech.HIGHLIGHTSSpeech auditory-motor adaptation to a spectral perturbation was reduced by ~50% when feedback was delayed by 75 or 115 ms.Thirty minutes of prior delay exposure without perturbation effectively reduced participants’ awareness of the delay.However, habituation was ineffective in remediating the detrimental effect of delay on speech auditory-motor adaptation.The dissociation of delay awareness and adaptation suggests that speech auditory-motor learning is mostly implicit.

scholarly journals Leaf shape is a predictor of fruit quality and cultivar performance in tomato

2019 ◽  
Author(s):  
Steven D. Rowland ◽  
Kristina Zumstein ◽  
Hokuto Nakayama ◽  
Zizhang Cheng ◽  
Amber M. Flores ◽  
...  
Keyword(s):  
Fruit Quality ◽  
Leaf Morphology ◽  
Negative Impact ◽  
Positive Impact ◽  
Leaf Shape ◽  
Sugar Content ◽  
Crop Improvement ◽  
List Type ◽  
Vegetable Crops ◽  
Tomato Crop

SummaryCommercial tomato (Solanum lycopersicum) is one of the most widely grown vegetable crops worldwide. Heirloom tomatoes retain extensive genetic diversity and a considerable range of fruit quality and leaf morphological traits.Here the role of leaf morphology was investigated for its impact on fruit quality. Heirloom cultivars were grown in field conditions and BRIX by Yield (BY) and other traits measured over a fourteen-week period. The complex relationships among these morphological and physiological traits were evaluated using PLS-Path Modeling, and a consensus model developed.Photosynthesis contributed strongly to vegetative biomass and sugar content of fruits but had a negative impact on yield. Conversely leaf shape, specifically rounder leaves, had a strong positive impact on both fruit sugar content and yield. Cultivars such as Stupice and Glacier, with very round leaves, had the highest performance in both fruit sugar and yield. Our model accurately predicted BY for two commercial cultivars using leaf shape data as input.This study revealed the importance of leaf shape to fruit quality in tomato, with rounder leaves having significantly improved fruit quality. This correlation was maintained across a range of diverse genetic backgrounds and shows the importance of leaf morphology in tomato crop improvement.

scholarly journals Cyber-Physical Attack Detection and Recovery based on RNN in Automotive Brake Systems

2018 ◽  
Author(s):  
Jongho Shin ◽  
Youngmi Baek ◽  
Jaeseong Lee ◽  
Seonghun Lee
Keyword(s):  
Classification Accuracy ◽  
Weighted Average ◽  
Data Integrity ◽  
Wheel Speed ◽  
Attack Detection ◽  
Cyber Attacks ◽  
Speed Estimation ◽  
Vehicle Speed ◽  
Detection And Identification ◽  
Fault Detection And Identification

The violation of data integrity in automotive Cyber-Physical Systems (CPS) may lead to dangerous situations for drivers and pedestrians in terms of safety. In particular, cyber-attacks on the sensor could easily degrade data accuracy and consistency over any other attack, we investigate attack detection and identification based on a deep learning technology on wheel speed sensors of automotive CPS. For faster recovery of a physical system with detection of the cyber-attacks, estimation of a specific value is conducted to substitute false data. To the best of our knowledge, there has not been a case of joining sensor attack detection and vehicle speed estimation in existing literatures. In this work, we design a novel method to combine attack detection and identification, vehicle speed estimation of wheel speed sensors to improve the safety of CPS even under the attacks. First, we define states of the sensors based on the cases of attacks that can occur in the sensors. Second, Recurrent Neural Network (RNN) is applied to detect and identify wheel speed sensor attacks. Third, in order to estimate the vehicle speeds accurately, we employ Weighted Average (WA), as one of the fusion algorithms, in order to assign a different weight to each sensor. Since environment uncertainty while driving has an impact on different characteristics of vehicles and cause performance degradation, the recovery mechanism needs the ability adaptive to changing environments. Therefore, we estimate the vehicle speeds after assigning a different weight to each sensor depending on driving situations classified by analyzing driving data. Experiments including training, validation, and test are carried out with actual measurements obtained while driving on the real road. In case of the fault detection and identification, classification accuracy is evaluated. Mean Squared Error (MSE) is calculated to verify that the speed is estimated accurately. The classification accuracy about test additive attack data is 99.4978%. MSE of our proposed speed estimation algorithm is 1.7786. It is about 0.2 lower than MSEs of other algorithms. We demonstrate that our system maintains data integrity well and is safe relatively in comparison with systems which apply other algorithms.

scholarly journals Object-Based Change Detection of Very High Resolution Images by Fusing Pixel-Based Change Detection Results Using Weighted Dempster–Shafer Theory

2020 ◽  
Vol 12 (6) ◽  
pp. 983 ◽  
Author(s):  
Youkyung Han ◽  
Aisha Javed ◽  
Sejung Jung ◽  
Sicong Liu
Keyword(s):  
High Resolution ◽  
Change Detection ◽  
Principal Component ◽  
Geographic Area ◽  
Majority Voting ◽  
Dempster Shafer Theory ◽  
Object Based ◽  
Intensity Images ◽  
Shafer Theory ◽  
Very High

Change detection (CD), one of the primary applications of multi-temporal satellite images, is the process of identifying changes in the Earth’s surface occurring over a period of time using images of the same geographic area on different dates. CD is divided into pixel-based change detection (PBCD) and object-based change detection (OBCD). Although PBCD is more popular due to its simple algorithms and relatively easy quantitative analysis, applying this method in very high resolution (VHR) images often results in misdetection or noise. Because of this, researchers have focused on extending the PBCD results to the OBCD map in VHR images. In this paper, we present a proposed weighted Dempster-Shafer theory (wDST) fusion method to generate the OBCD by combining multiple PBCD results. The proposed wDST approach automatically calculates and assigns a certainty weight for each object of the PBCD result while considering the stability of the object. Moreover, the proposed wDST method can minimize the tendency of the number of changed objects to decrease or increase based on the ratio of changed pixels to the total pixels in the image when the PBCD result is extended to the OBCD result. First, we performed co-registration between the VHR multitemporal images to minimize the geometric dissimilarity. Then, we conducted the image segmentation of the co-registered pair of multitemporal VHR imagery. Three change intensity images were generated using change vector analysis (CVA), iteratively reweighted-multivariate alteration detection (IRMAD), and principal component analysis (PCA). These three intensity images were exploited to generate different binary PBCD maps, after which the maps were fused with the segmented image using the wDST to generate the OBCD map. Finally, the accuracy of the proposed CD technique was assessed by using a manually digitized map. Two VHR multitemporal datasets were used to test the proposed approach. Experimental results confirmed the superiority of the proposed method by comparing the existing PBCD methods and the OBCD method using the majority voting technique.

Brain tissue segmentation based on spatial information fusion by Dempster-Shafer theory

2012 ◽  
Vol 13 (7) ◽  
pp. 520-533 ◽  
Author(s):  
Jamal Ghasemi ◽  
Mohammad Reza Karami Mollaei ◽  
Reza Ghaderi ◽  
Ali Hojjatoleslami
Keyword(s):  
Brain Tissue ◽  
Information Fusion ◽  
Spatial Information ◽  
Tissue Segmentation ◽  
Dempster Shafer Theory ◽  
Brain Tissue Segmentation ◽  
Shafer Theory

scholarly journals Mental Health During COVID-19: A Qualitative Study with Ethnically Diverse Healthcare Workers in the United Kingdom

2021 ◽  
Author(s):  
Irtiza Qureshi ◽  
Mayuri Gogoi ◽  
Amani Al-Oraibi ◽  
Fatimah Wobi ◽  
Jonathan Chaloner ◽  
...  
Keyword(s):  
Mental Health ◽  
United Kingdom ◽  
Ethnic Minority ◽  
Healthcare Workers ◽  
Negative Impact ◽  
Ethnically Diverse ◽  
Working Hours ◽  
Severe Illness ◽  
List Type ◽  
The United Kingdom

ABSTRACTIntroductionHealthcare workers are experiencing deterioration in their mental health due to COVID-19. Ethnic minority populations in the United Kingdom are disproportionately affected by COVID-19, with a higher death rate and poorer physical and mental health outcomes. It is important that healthcare organisations consider the specific context and mental, as well as physical, health needs of an ethnically diverse healthcare workforce in order to better support them during, and after, the COVID-19 pandemic.MethodsWe undertook a qualitative work package as part of the United Kingdom Research study into Ethnicity and COVID-19 outcomes among healthcare workers (UK-REACH). As part of the qualitative research, we conducted focus group discussions with healthcare workers between December 2020 and July 2021, and covered topics such as their experiences, fears and concerns, and perceptions about safety and protection, while working during the pandemic. The purposive sample included ancillary health workers, doctors, nurses, midwives and allied health professionals from diverse ethnic backgrounds. We conducted discussions using Microsoft Teams. Recordings were transcribed and thematically analysed.FindingsWe carried out 16 focus groups with a total of 61 participants. Several factors were identified which contributed to, and potentially exacerbated, the poor mental health of ethnic minority healthcare workers during this period including anxiety (due to inconsistent protocols and policy); fear (of infection); trauma (due to increased exposure to severe illness and death); guilt (of potentially infecting loved ones); and stress (due to longer working hours and increased workload).ConclusionCOVID-19 has affected the mental health of healthcare workers. We identified a number of factors which may be contributing to a deterioration in mental health across diverse ethnic groups. Healthcare organisations should consider developing strategies to counter the negative impact of these factors. This paper will help employers of healthcare workers and other relevant policy makers better understand the wider implications and potential risks of COVID-19 and assist in developing strategies to safeguard the mental health of these healthcare workers going forward, and reduce ethnic disparities.Key messagesWhat is already known about this subjectHealthcare Workers (HCWs) are experiencing deterioration of their mental health due to COVID-19Ethnic minority populations and HCWs are disproportionately affected by COVID-19More research is needed on the specific factors influencing the mental health of ethnically diverse healthcare workforcesWhat are the new findingsProminent factors influencing the mental health and emotional wellbeing of this population include:anxiety (due to inconsistent protocols and policy)fear (of infection)trauma (due to increased exposure to severe illness and death)guilt (of potentially infecting loved ones)stress (due to longer working hours and increased workload)How might this impact on policy or clinical practice in the foreseeable futureHealthcare organisations should consider the specific circumstances of these staff and develop strategies to counter the negative impact of these factors and help safeguard the mental health of their staff

Sign in / Sign up

Export Citation Format

Share Document