Detection Of Inconsistencies Research Articles

Grading of diabetic retinopathy using a pre-segmenting deep learning classification model: Validation of an automated algorithm.

To validate the performance of autonomous diabetic retinopathy (DR) grading by comparing a human grader and a self-developed deep-learning (DL) algorithm with gold-standard evaluation. We included 500, 6-field retinal images graded by an expert ophthalmologist (gold standard) according to the International Clinical Diabetic Retinopathy Disease Severity Scale as represented with DR levels 0-4 (97, 100, 100, 103, 100, respectively). Weighted kappa was calculated to measure the DR classification agreement for (1) a certified human grader without, and (2) with assistance from a DL algorithm and (3) the DL operating autonomously. Using any DR (level 0 vs. 1-4) as a cutoff, we calculated sensitivity, specificity, as well as positive and negative predictive values (PPV and NPV). Finally, we assessed lesion discrepancies between Model 3 and the gold standard. As compared to the gold standard, weighted kappa for Models 1-3 was 0.88, 0.89 and 0.72, sensitivities were 95%, 94% and 78% and specificities were 82%, 84% and 81%. Extrapolating to a real-world DR prevalence of 23.8%, the PPV were 63%, 64% and 57% and the NPV were 98%, 98% and 92%. Discrepancies between the gold standard and Model 3 were mainly incorrect detection of artefacts (n = 49), missed microaneurysms (n = 26) and inconsistencies between the segmentation and classification (n = 51). While the autonomous DL algorithm for DR classification only performed on par with a human grader for some measures in a high-risk population, extrapolations to a real-world population demonstrated an excellent 92% NPV, which could make it clinically feasible to use autonomously to identify non-DR patients.

Local inconsistency detection using the Kullback–Leibler divergence measure

BackgroundThe standard approach to local inconsistency assessment typically relies on testing the conflict between the direct and indirect evidence in selected treatment comparisons. However, statistical tests for inconsistency have low power and are subject to misinterpreting a p-value above the significance threshold as evidence of consistency.MethodsWe propose a simple framework to interpret local inconsistency based on the average Kullback–Leibler divergence (KLD) from approximating the direct with the corresponding indirect estimate and vice versa. Our framework uses directly the mean and standard error (or posterior mean and standard deviation) of the direct and indirect estimates obtained from a local inconsistency method to calculate the average KLD measure for selected comparisons. The average KLD values are compared with a semi-objective threshold to judge the inconsistency as acceptably low or material. We exemplify our novel interpretation approach using three networks with multiple treatments and multi-arm studies.ResultsAlmost all selected comparisons in the networks were not associated with statistically significant inconsistency at a significance level of 5%. The proposed interpretation framework indicated 14%, 66%, and 75% of the selected comparisons with an acceptably low inconsistency in the corresponding networks. Overall, information loss was more notable when approximating the posterior density of the indirect estimates with that of the direct estimates, attributed to indirect estimates being more imprecise.ConclusionsUsing the concept of information loss between two distributions alongside a semi-objectively defined threshold helped distinguish target comparisons with acceptably low inconsistency from those with material inconsistency when statistical tests for inconsistency were inconclusive.

MG+: Towards Efficient Context Inconsistency Detection by Minimized Link Generation

ABSTRACTSelf‐adaptive applications are becoming increasingly attractive, with the ability to smartly understand their runtime environments (or contexts) and deliver adaptive services, for example, location‐aware navigation or resource‐sensitive suggestions. However, due to inherent noises in the process of sensing and interpreting environmental information, there is a growing demand for guarding the consistency of collected contexts to avoid application misbehaviour and, at the same time, minimize extra costs. Existing work attempted to achieve this by speeding up the kernel constraint checking module inside the consistency guarding process. Most of these efforts were spent on reusing previous checking results or parallelizing the checking process, but they all leave one central step of constraint checking, that is, link generation, untouched. In this step, the checking engine provides reasons to explain the violation of constraints under check. It occupies a substantial part of the total time cost. Focusing on this key link generation step, we proposed MG, which deploys a rigourous analysis to automatically identify and avoid redundancy in the link generation without harming any correctness of the checking results. MG has been proven sound (always guaranteeing correctness) and complete (entirely removing redundancy). Moreover, based on our observation that MG's redundancy elimination also assists another core step of constraint checking to reduce unnecessary computation further, we additionally enhance MG with an escape‐condition optimization to escape unnecessary evaluation of truth values to further improve the efficiency of constraint checking in an aspect other than link generation. We call it MG+ for distinguishing. Our experiments with synthesized and real‐world consistency constraints reported that, compared with existing work, MG eliminates all link redundancy (83% to 0%), and based on it, MG+ further reduces significant truth value calculations (e.g., 49.74% reduction when combined with ECC and Con‐C). Generally, MG brought 14–500 speed‐ups in link generation, and MG+ further made 1.2–1.9 speed‐ups in truth value evaluation. Altogether, MG reduced the total constraint checking time up to 45.4%, and MG+ reduced it up to 61.0%.

Detection of semantic inconsistencies of motor actions: From language to praxis

Semantics of actions includes three types of knowledge: a) of the function of objects and tools, b) of the actions independently of the tools, and c) of the organization of simple actions in sequences. These types of knowledge might be structured as thematic roles into the semantics of actions. To test these hypothesis, 125 illustrations, divided into five conditions: i) Congruent (C), ii) Agent Inconsistent (AI), iii) Instrument Inconsistent (II), iv) Patient Inconsistent (PI), and v) Location Inconsistent (LI), were presented to 23 volunteers (50 % women), aged 20–25, who were asked to respond whether the image was congruent or incongruent. Electrical brain activity was recorded through 20 channels to obtain the event-related potentials (ERP) associated. Lower reaction times for II and PI than C, and a greater number of incorrect trials for C were found. A N300/N400 effect appeared for AI and LI conditions with respect to C. Finally, II and LI conditions present a deflected P600 in reference to C. These findings suggest semantic of actions is sensitive to thematic role manipulations and constitute evidence in favor of a semantic processing shared between visually observed praxis and words.

Analysis of the efficiency of a Solar Photovoltaic Power Plant linked to the electrical grid

The growing need for energy in emerging nations gives rise to apprehensions over energy security, so underscoring the criticality of harnessing the potential of renewable resources. Empirical evidence has demonstrated that photovoltaic systems integrated into the network are the optimal options for large-scale renewable energy. The analysis of the performance of these network-connected centrals can enhance the design, operation, and maintenance of new systems. The commissioning of a 12 MW photovoltaic solar power plant in Sidi Bel Abbès, located in the Dhaya region, has established it as one of the largest solar power plants in Algeria. The site yields a mean solar radiation of 5.21 kilowatt-hours per square metre per day and an average yearly temperature of 18.9 degrees Celsius. The present work provides an analysis of the yearly performance and conceptual aspects of the photovoltaic central unit. We compare the performance outcomes of the power plant with the simulated values generated by the SolarGis PvPlanner program. Analysis of real-world performance in relation to simulations allows for the detection of inconsistencies and the enhancement of future initiatives. SolarGis PvPlanner is an essential modelling program for accurately forecasting performance and effectively strategising solar projects, therefore guaranteeing sustainable and dependable energy for the future.

SemID: Blind Image Inpainting with Semantic Inconsistency Detection

SemID: Blind Image Inpainting with Semantic Inconsistency Detection

Knowledge-based expert system to drive an informationally interoperable manufacturing system: An experimental application in the Aerospace Industry

The industrial revolutions have challenged organisations to rethink their product design and manufacturing processes, making them faster and more connected to market demands and changes. Digital technologies have emerged with solutions to virtual represent physical objects, processes, systems, or assets to simulate and analyse the impact of manufacturing changes before actual implementation. However, the challenge is to deal with thousands of heterogeneous information sets which must be shared simultaneously by different groups within and across institutional boundaries. Each manufacturing industry has its format and model to represent the product in the development, manufacturing process, material features, etc. In this context, this paper explores a knowledge-based expert system to support the information exchange and inconsistency detection across the manufacturing process, specifically in an experimental application in the Aerospace Industry. The proposed framework was based on knowledge formalisation and semantic rules through ontologies, semantic reconciliation strategies and connectivity interfaces to manage information and knowledge and identify inconsistencies across the manufacturing system. It was mainly evaluated across the product and manufacturing design of sheet metal forming aluminium thin wall parts for the aerospace industry. Results demonstrate the capability of the approach to enhance data accuracy, coherence, and efficiency throughout the manufacturing of complex products. However, the solution presents challenges such as interdisciplinary collaboration in product design, specific information requirements for manufacturing planning, and the impact of production planning on manufacturing capacities.

A comparison of two models for detecting inconsistency in network meta-analysis.

The application of network meta-analysis is becoming increasingly widespread, and for a successful implementation, it requires that the direct comparison result and the indirect comparison result should be consistent. Because of this, a proper detection of inconsistency is often a key issue in network meta-analysis as whether the results can be reliably used as a clinical guidance. Among the existing methods for detecting inconsistency, two commonly used models are the design-by-treatment interaction model and the side-splitting models. While the original side-splitting model was initially estimated using a Bayesian approach, in this context, we employ the frequentist approach. In this paper, we review these two types of models comprehensively as well as explore their relationship by treating the data structure of network meta-analysis as missing data and parameterizing the potential complete data for each model. Through both analytical and numerical studies, we verify that the side-splitting models are specific instances of the design-by-treatment interaction model, incorporating additional assumptions or under certain data structure. Moreover, the design-by-treatment interaction model exhibits robust performance across different data structures on inconsistency detection compared to the side-splitting models. Finally, as a practical guidance for inconsistency detection, we recommend utilizing the design-by-treatment interaction model when there is a lack of information about the potential location of inconsistency. By contrast, the side-splitting models can serve as a supplementary method especially when the number of studies in each design is small, enabling a comprehensive assessment of inconsistency from both global and local perspectives.

Integration of background knowledge for automatic detection of inconsistencies in gene ontology annotation.

Biological background knowledge plays an important role in the manual quality assurance (QA) of biological database records. One such QA task is the detection of inconsistencies in literature-based Gene Ontology Annotation (GOA). This manual verification ensures the accuracy of the GO annotations based on a comprehensive review of the literature used as evidence, Gene Ontology (GO) terms, and annotated genes in GOA records. While automatic approaches for the detection of semantic inconsistencies in GOA have been developed, they operate within predetermined contexts, lacking the ability to leverage broader evidence, especially relevant domain-specific background knowledge. This paper investigates various types of background knowledge that could improve the detection of prevalent inconsistencies in GOA. In addition, the paper proposes several approaches to integrate background knowledge into the automatic GOA inconsistency detection process. We have extended a previously developed GOA inconsistency dataset with several kinds of GOA-related background knowledge, including GeneRIF statements, biological concepts mentioned within evidence texts, GO hierarchy and existing GO annotations of the specific gene. We have proposed several effective approaches to integrate background knowledge as part of the automatic GOA inconsistency detection process. The proposed approaches can improve automatic detection of self-consistency and several of the most prevalent types of inconsistencies. https://github.com/jiyuc/de-inconsistency.

Readers’ Behavior during a Monitoring Task in English as a Foreign Language: Connecting Outcomes and Mental Processing

Metacognitive skills are important for text comprehension, especially at university where most learning processes are unsupervised, and students rely on self-control and regulation when reading for comprehension. In today’s universities, English as L2 has become the vehicle language for teaching and learning. However, some studies have concluded that university students who read English as L2 have inadequate metacognitive monitoring skills. Higher level processing skills, such as comprehension monitoring, are difficult to study and then improve. The main goal of the present study was to analyze the mental processing of readers when they monitored expository texts in English as L2 considering their English proficiency. Mental processing was related to readers’ behavior when performing a reading task by using a set of variables guided by a psychological mechanism proposed for inconsistency detection. A total of 169 university students participated. The task was modeled on the error detection paradigm, which involved assessing the comprehensibility of scientific texts in English and reporting comprehension difficulties encountered. A special software was used to collect detailed data online about the readers’ text processing and written reports. The results confirmed the set of processing variables and the theory-based predictions.

Understanding the Energy Landscape of Intrinsically Disordered Protein Ensembles.

A substantial portion of various organisms' proteomes comprises intrinsically disordered proteins (IDPs) that lack a defined three-dimensional structure. These IDPs exhibit a diverse array of conformations, displaying remarkable spatiotemporal heterogeneity and exceptional conformational flexibility. Characterizing the structure or structural ensemble of IDPs presents significant conceptual and methodological challenges owing to the absence of a well-defined native structure. While databases such as the Protein Ensemble Database (PED) provide IDP ensembles obtained through a combination of experimental data and molecular modeling, the absence of reaction coordinates poses challenges in comprehensively understanding pertinent aspects of the system. In this study, we leverage the energy landscape visualization method (JCTC, 6482, 2019) to scrutinize four IDP ensembles sourced from PED. ELViM, a methodology that circumvents the need for a priori reaction coordinates, aids in analyzing the ensembles. The specific IDP ensembles investigated are as follows: two fragments of nucleoporin (NUL: 884-993 and NUS: 1313-1390), yeast sic 1 N-terminal (1-90), and the N-terminal SH3 domain of Drk (1-59). Utilizing ELViM enables the comprehensive validation of ensembles, facilitating the detection of potential inconsistencies in the sampling process. Additionally, it allows for identifying and characterizing the most prevalent conformations within an ensemble. Moreover, ELViM facilitates the comparative analysis of ensembles obtained under diverse conditions, thereby providing a powerful tool for investigating the functional mechanisms of IDPs.

Forgered Image Perception System using CNN Algorithms

The progression and diversification of methodologies in digital image forensics and manipulation detection are evident in existing work, presenting innovative techniques tailored to specific aspects of forgery detection. These methodologies encompass various challenges such as copy-move forgery, manipulation detection, demosaicing artifacts, image splicing, edge detection, and compression analysis. Together, these studies exemplify ongoing efforts to enhance the accuracy, efficiency, and reliability of forgery detection methods within the constantly evolving landscape of digital image manipulation. The proposed image forgery detection system represents a pioneering advancement, surpassing the limitations of conventional methodologies. It integrates a comprehensive array of detection techniques, including copy-move analysis, color filter array scrutiny, noise variance inconsistency detection, and double JPEG artifact identification. These techniques are bolstered by Convolutional Neural Networks (CNNs). This innovative fusion not only addresses the limitations inherent in existing systems but also signifies a significant leap forward in functionality and efficacy. By synergistically leveraging the strengths of each detection method within a CNN framework, our approach promises heightened accuracy, robustness, and adaptability in discerning even the most sophisticated forms of image tampering. Keywords— Image Tampering, Double JPEG Compression, Demosaicing Artifacts, Recursive Edge Detection, Copy-Move Forgery Detection.

A novel deep learning model for detection of inconsistency in e-commerce websites

On most e-commerce websites, there are two crucial factors that customers rely on to assess product quality and dependability: customer reviews provided online and related ratings. Reviews offer feedback to customers about the product’s merits, reasons for negative reviews, and feelings of satisfaction or dissatisfaction with the provided service. As for ratings, they express customer opinions about the product’s quality as numerical values from one to five (one or two for the worst opinion, three for the neutral opinion, and four or five for the best opinion). Usually, the customer reviews may be inconsistent with their relevant ratings; the customer may write the worst review despite providing a four- or five-star rating or write the best review with only a one- or two-star rating. Due to this inconsistency, customers may need help to identify relevant information. Therefore, it is required to develop a model that can classify reviews as either positive or negative, depending on the polarity of thoughts, to demonstrate if there is an inconsistency between customer reviews and their actual ratings by comparing them with the ratings resulting from the model. This paper proposes an efficient deep learning (DL) model for classifying customer reviews and assessing whether there is inconsistency. The recommended model’s performance and stability are examined on a large dataset of product reviews from Amazon e-commerce. The experimental findings showed that the proposed model dominates and significantly outperforms its peers regarding prediction accuracy and other performance measures.

Code Comment Inconsistency Detection Based on Confidence Learning

Code Comment Inconsistency Detection Based on Confidence Learning

A novel approach for detecting deep fake videos using graph neural network

Deep fake technology has emerged as a double-edged sword in the digital world. While it holds potential for legitimate uses, it can also be exploited to manipulate video content, causing severe social and security concerns. The research gap lies in the fact that traditional deep fake detection methods, such as visual quality analysis or inconsistency detection, need help to keep up with the rapidly advancing technology used to create deep fakes. That means there's a need for more sophisticated detection techniques. This paper introduces an enhanced approach for detecting deep fake videos using graph neural network (GNN). The proposed method splits the detection process into two phases: a mini-batch graph convolution network stream four-block CNN stream comprising Convolution, Batch Normalization, and Activation function. The final step is a flattening operation, which is essential for connecting the convolutional layers to the dense layer. The fusion of these two phases is performed using three different fusion networks: FuNet-A (additive fusion), FuNet-M (element-wise multiplicative fusion), and FuNet-C (concatenation fusion). The paper further evaluates the proposed model on different datasets, where it achieved an impressive training and validation accuracy of 99.3% after 30 epochs.

Interactive medical and safety monitoring in clinical trials with clinDataReview: a validated and open-source reporting tool.

Continuous medical and safety monitoring of subject data during a clinical trial is a critical part of evaluating the safety of trial participants and as such is governed by protocol procedures and regulatory guidelines to meet the trial's intended objectives. We present an open-source validated graphical tool (clinDataReview R package) which provides access to the trial data with drill-down to individual patient profiles. The tool incorporates functionalities that facilitate detection of error and data inconsistencies requiring follow-up. It supports regular medical monitoring and oversight as well as safety monitoring committees with interactive tables and listings alongside graphical visualizations of the primary safety data in reports. An implementation example is given where the tool is used to deliver validated outputs following FDA/EMA guidelines. As such, this tool enables a more efficient, interactive, and reproducible review of safety data collected during an ongoing clinical trial.

In Situ Inversion of Lithium-Ion Battery Pack Unbalanced Current for Inconsistency Detection Using Magnetic Field Imaging

In Situ Inversion of Lithium-Ion Battery Pack Unbalanced Current for Inconsistency Detection Using Magnetic Field Imaging

Understanding the impact of requirements evolution and reaction on evolution of software: a survey and comparison

In software systems, the continuous changing of requirements, known as requirements evolution, is considered one of the significant issues. Requirements' evolution denotes the postـdeployment changes in the requirements. This article reviews the most related requirements evolution approaches. Different approaches have been presented in modelling requirements evolution, managing requirements evolution, and relevant analysis techniques, like inconsistency detection and change impact analysis. The relevant approaches of requirements evolution can be generally classified into the impact of evolution and reaction on evolution. The article also has given a comparison among those approaches. The approaches that have been surveyed in this article exhibited many limitations. These limitations need to be addressed and coped with for the approaches to be more effective in managing the evolution of software requirements. One of the solutions to these limitations is to develop an approach that addresses the reasoning behind software requirements evolution.

A framework for software vendor selection by applying Inconsistency and Conflict Removal (ICR) method

In a software ecosystem, companies’ stakeholders make various decisions and perform various tasks to ensure the strategic and architectural goals of the company. Analyzing vendor capabilities and making decisions to select software vendors requires expert professionals. To analyze vendors’ capabilities and accessing them according to the company’s strategic and architectural goals is presently an ad-hoc and manual process. Presently, there is no systematic process for ‘vendor analysis and selection’ specifically for the software industry. Therefore, this study introduces a novel framework which elaborates all the tasks required for vendor proposal evaluation. It also includes the automatic detection of inconsistencies and conflicts prevalent during this process. A new method called ‘Inconsistency and Conflict Removal (ICR)’ is proposed as part of this framework. ICR automates the process of spotting inconsistencies and conflicts by taking scores of vendor capabilities as input reported by different decision-makers. Further, to illustrate this framework, ‘a case of Hospital’ has been considered. This study provides valuable knowledge that would facilitate organizations in software vendor selection. It will lead to substantial savings in terms of economics, such as actual costs, time, and improved administrative processes.

Comparative Different Interventions to Improve Exercise Adherence in Patients in the Postoperative Breast Cancer Phase of Care: A Network Meta-analysis.

Global Cancer Statistics 2020 reported that breast cancer had exceeded lung cancer as the most frequently diagnosed cancer. Surgery is the primary treatment modality for breast cancer, but postoperative upper limb dysfunction often occurs; functional exercise can alleviate this and restore upper limb function. However, exercise compliance is low in postoperative breast cancer patients; thus, many studies have been conducted in recent years to improve patient compliance with exercise. The aim of this study was to compare the effectiveness of different interventions to improve exercise adherence in postoperative breast cancer patients. We searched PubMed, Cochrane Library, Web of Science, EMBASE, Wan Fang, CNKI, VIP, and CBM databases for eligible studies. Exercise adherence rate and quality-of-life difference were assessed as outcomes. Sensitivity analysis and inconsistency detection were performed to evaluate whether the exclusion of high-risk studies affected the validity. Risk of bias was assessed using the risk-of-bias table in RevMan 5.4. Surface under the cumulative ranking was used to estimate the rankings among different interventions. Twenty-five randomized controlled trials involving 9 interventions were included, and the network meta-analysis results showed that patients in the pedometer + counseling group had the best exercise adherence. Pedometer + counseling care measures are recommended to improve exercise adherence in postoperative breast cancer patients. Oncology nurses can improve patients' exercise compliance through counseling and by giving them pedometers to wear.