Majority Voting Method Research Articles

Deep learning-driven multi-omics sequential diagnosis with Hybrid-OmniSeq: Unraveling breast cancer complexity

Breast cancer results from an uncontrolled growth of breast tissue. Many methods of diagnosis are using multi-omics data to better understand the complexity of breast cancer. The new strategy laid out in this work, called “Hybrid-OmniSeq,” is a deep learning-based multi-omics data analysis technology that uses molecular subtypes of breast cancer gene to increase the precision and effectiveness of breast cancer diagnosis. For preprocessing, the BC-VM procedure is utilized, and for molecular subtype analysis, the BC-MSA procedure is utilized. The implementation of Deep Neural Network (DNN) technology in conjunction with Sequential Forward Floating Selection (SFFS) and Truncated Singular Value Decomposition (TSVD) entropy enable adaptive learning from multi-omics gene data. Five machine learning classifiers are used for classification purpose. Hybrid-OmniSeq uses a variety of machine learning classifiers in a thorough analytical process to achieve remarkable diagnostic accuracy. Deep Learning-based multi-omics sequential approach was evaluated using METABRIC RNA-seq data sets of intrinsic subtypes of breast cancer. According to test results, Logistic Regression (LR) had ER (Estrogen Receptor) status values of 94.51%, ER status values of 96.33%, and HER2 (Human Epidermal growth factor Receptor) status values of 92.3%; Random Forest (RF) had ER status values of 93.77%, ER status values of 95.23%, and HER2 status values of 93.4%. LR and RF increase the cancer detection accuracy for all subtypes when compared to alternative machine learning classifiers or the majority voting method, providing a comprehensive understanding of the underlying causes of breast cancer.

Comparison of Classification Results of SVM, KNN, Decision Tree, and Ensemble Methods in Diabetes Diagnosis

This study aims to determine which algorithms and test techniques are the most optimal in detecting diabetes mellitus and obtaining the best results based on the value of accuracy, precision, and recall. In this study, approaches were used in early diagnosis of diabetes using KNN, SVM, Decision Tree, and Ensemble Majority Voting methods in Percentage Split and K-Fold Cross Validation methods. Diabetes is a disease characterized by high blood sugar (glucose) levels and can cause a variety of disease complications and damage to the body's organs if not treated immediately. Early diagnosis of diabetes is becoming crucial so that people can take immediate action to the hospital for immediate treatment. The data used is Healthcare-Diabetes from Kaggle. The results of this study have found that the K-Fold Cross Validation method is better because it can provide an average improvement in Ensemble accuracy of 13.42% compared to the Percentage Split method which only gives an average increase in Ensamble accuracy of 9.15%. The best algorithm for classifying diabetes disease is the Ensemble Majority Voting algorithm using the K-Fold Cross Validation method with a 98.81% accuracy rate. These excellent research results may contribute to detecting early symptoms of diabetes before it become too severe.

Water Wheel Plant Dingo Optimizer enabled Deep Convolutional Neural Network for disease detection using hyperspectral leaf image

ProblemIn many countries, agriculture is themain sourceofpeople’s livelihoodandsatisfiestheir nutritional needs.Earlydetection ofplantdiseases throughagriculturalremote monitoringis important to prevent the disease’s spread. The traditional methods require sampling and can damage the plant, but hyperspectral imaging is non-destructive. AimThe major aim of this research is to devise a Water Wheel Plant Dingo Optimizer_Deep Convolutional Neural Network (WWPDO_Deep CNN) for disease detection using a hyperspectral leaf image. MethodsInitially, the input leaf image is given into the leaf segmentation phase, which is done using the proposed Water Wheel Plant Dingo Optimizer (WWPDO), which is the amalgamation of the Water Wheel Plant Algorithm (WWPA) and Dingo Optimizer (DOX). The selected bands’ outputs are subjected to leaf segmentation and which is carried out by employing Bayesian Fuzzy Clustering (BFC). Thereafter, leaf segmented outputs are fussed using the majority voting method. Fused output and individual leaf segmentation output are given into the feature extraction process to extract features, such as local binary patterns and Weber local descriptors. Finally, leaf disease detection is performed using a deep Convolutional Neural Network (Deep CNN) for normal and abnormal cases. The hyperparameters of the Deep CNN are fine-tuned based on the proposed WWPADO. ResultsThe proposed WWPDO_Deep CNN achieved an excellent performance with an accuracy of 91.35 %, a True Positive Rate (TPR) of 93.13 % and a True Negative Rate (TNR) of 90.76 %. ConclusionThe WWPDO_Deep CNN is applicable for early diagnosis under the new classification system and provides a new direction for early diagnosis based on hyperspectral images. Also, the devised model provides an accurate diagnosis of plant diseases. Early and accurate detection allows targeted treatment, reduces the need for widespread pesticide application and promotes more sustainable farming practices.

Automatic Age and Gender Recognition Using Ensemble Learning

The use of speech-based recognition technologies in human–computer interactions is increasing daily. Age and gender recognition, one of these technologies, is a popular research topic used directly or indirectly in many applications. In this research, a new age and gender recognition approach based on the ensemble of different machine learning algorithms is proposed. In the study, five different classifiers, namely KNN, SVM, LR, RF, and E-TREE, are used as base-level classifiers and the majority voting and stacking methods are used to create the ensemble models. First, using MFCC features, five base-level classifiers are created and the performance of each model is evaluated. Then, starting from the one with the highest performance, these classifiers are combined and ensemble models are created. In the study, eight different ensemble models are created and the performances of each are examined separately. The experiments conducted with the Turkish subsection of the Mozilla Common Voice dataset show that the ensemble models increase the recognition accuracy, and the highest accuracy of 97.41% is achieved with the ensemble model created by stacking five classifiers (SVM, E-TREE, RF, KNN, and LR). According to this result, the proposed ensemble model achieves superior accuracy compared to similar studies in recognizing age and gender from speech signals.

A recommendation attack detection approach integrating CNN with Bagging

Due to their open architecture, collaborative filtering recommender systems are susceptible to recommendation attacks, in which attackers inject fake rating data into the system to affect the accuracy of recommendation results. To detect these attacks, numerous detection methods have been designed and proven effective. However, in recent years, deep learning-based recommendation attack models such as GSA-GAN have shown higher concealment, posing new challenges to existing detection methods. Motivated by the need for improved detection, in this paper we propose a new approach called CNN-BAG, which integrates convolutional neural network (CNN) and Bagging (BAG) techniques. CNN-BAG can enhance the detection performance by simultaneously leveraging the deep learning capabilities of CNN and the ensemble learning strengths of Bagging. Firstly, we construct a deep neural network based on CNN as the base learner to automatically extract and learn features of recommendation attacks. Secondly, we use the Bagging algorithm to perform bootstrap sampling on the training data to generate multiple diverse training subsets. The above constructed base learners are then trained on these generated training subsets to produce multiple base classifiers for classifying recommendation attacks. Finally, we combine the base classifiers’ outputs using a majority voting method to obtain the final detection results. To assess the performance of CNN-BAG in detecting recommendation attacks, we compared it against several well-established detection methods on the Movielens-10M and Amazon datasets. Our experiments revealed that CNN-BAG is adept at identifying various attack types, including the deep learning-based recommendation attack models.

Emergence of Diverse Epidermal Patterns via the Integration of the Turing Pattern Model with the Majority Voting Model

Animal skin patterns are increasingly explained using the Turing pattern model proposed by Alan Turing. The Turing model, a self-organizing model, can produce spotted or striped patterns. However, several animal patterns exist that do not correspond to these patterns. For example, the body patterns of the ornamental carp Nishiki goi produced in Japan vary randomly among individuals. Therefore, predicting the pattern of offspring is difficult based on the parent fish. Such a randomly formed pattern could be explained using a majority voting model. This model is a type of cellular automaton model that counts the surrounding states and transitions to high-number states. Nevertheless, the utility of these two models in explaining fish patterns remains unclear. Interestingly, the patterns generated by these two models can be detected among very closely related species. It is difficult to think that completely different epidermal formation mechanisms are used among species of the same family. Therefore, there may be a basic model that can produce both patterns. Herein, the Turing pattern and majority voting method are represented using cellular automata, and the possibility of integrating these two methods is examined. This integrated model is equivalent to both models when the parameters are adjusted. Although this integrated model is extremely simple, it can produce more varied patterns than either one of the individual models. However, further research is warranted to determine whether this model is consistent with the mechanisms involved in the formation of animal fish patterns from a biological perspective.

A fault diagnosis framework based on heterogeneous ensemble learning for air conditioning chiller with unbalanced samples

Big data-based air conditioning fault diagnosis research has developed rapidly in recent years, but in actual engineering, the fault sample size of air conditioning systems is much smaller than the normal sample size, and the resulting sample imbalance problem makes conventional data-driven diagnostic methods based on low accuracy and poor stability. In order to solve the problem of unbalanced fault diagnosis of air-conditioning chillers, this paper proposes an integrated learning-based diagnostic model, which achieves diagnosis by combining multiple base models and by majority voting. The method uses four classification models, namely, random forest model, decision tree model, k nearest neighbor model, and isomorphic integration model, as base classifiers, and synthesizes the four base classifiers into a heterogeneous integration algorithmic model (IMV) through integrated learning, and performs diagnostic detection of seven types of typical faults of chiller units using the majority voting method of integrated learning. The effectiveness of the proposed algorithm is verified on the RP-1043 dataset, and the experimental results show that the accuracy of the heterogeneous integrated algorithm model (IMV) can reach 96.87%, which is a significant improvement compared with the accuracy of the other four base classifier models (81.04%–96.25%). Therefore, the integrated learning model has some application prospects in fault diagnosis when targeting unbalanced datasets.

EEG-based schizophrenia detection using fusion of effective connectivity maps and convolutional neural networks with transfer learning.

Schizophrenia (SZ) is a serious mental disorder that can mainly be distinguished by symptoms including delusions and hallucinations. This mental disorder makes difficult conditions for the person and her/his relatives. Electroencephalogram (EEG) signal is a sophisticated neuroimaging technique that helps neurologists to diagnose this mental disorder. Estimating and evaluating brain effective connectivity between electrode pairs is an appropriate way of diagnosing brain states in neuroscience studies. In this study, we construct a novel image from multi-channels of EEG based on the fusion of three effective connectivity, partial directed coherence (PDC), and direct directed transfer function (dDTF) and transfer entropy (TE) at three consecutive time windows. Then, this image was used as input of five well-known convolutional neural networks (CNNs) through transfer learning (TL) to learn patterns related to SZ patients to diagnose this disorder from normal participants from two public databases. Also, the majority voting method was used to improve these results based on ensemble results of the five CNNs, i.e., ResNet-50, Inception-v3, DenseNet-201, EfficientNetB0, and NasNet-Mobile. The highest average accuracy, specificity and sensitivity to diagnose SZ patients from healthy participants were obtained using EfficientNetB0 through the Leave-One-Subject-out (LOSO) Cross-Validation criterion equal to 96.67%, 96.23%, 96.82%, 95.15%, 94.42% and 96.28% for the first and second databases, respectively. Also, as we suggested, the ensemble approach of EfficientNetB0, ResNet-50 and NasNet-Mobile increased the accuracy by approximately 3%. Our results show the effectiveness of providing fused images from multichannel EEG signals to the ensemble of CNNs through TL to diagnose SZ than state-of-the-art studies.

A Comprehensive Approach to Safeguard Credit Card Transactions and Fraud Prevention

The escalating prevalence of financial fraud within the financial sector poses profound challenges. Detecting credit card fraud in online transactions necessitates data mining due to inherent complexities. Addressing two key issues—evolving patterns in legitimate and fraudulent behaviors and highly skewed datasets of credit card frauds—renders the task challenging. This paper scrutinizes the performance of naive Bayes, KNN, and logistic regression on significantly imbalanced credit card fraud data comprising 284,807 transactions from European cardholders. The dataset's skewness is addressed through a hybrid under-sampling and oversampling approach. The three techniques are applied to both unprocessed and preprocessed data. Fraud detection, defined as a set of activities thwarting illicit acquisition of assets or funds through deceptive means, varies across industries and methods. Credit card fraud, particularly susceptible due to its ease and prevalence in e-commerce and online platforms, prompted the adoption of diverse machine learning strategies to combat rising fraud rates. This paper employs machine learning algorithms for credit card fraud detection, utilizing a publicly available credit card dataset for model evaluation. While acknowledging that achieving 100% accuracy in fraud detection is elusive, the paper emphasizes the real-world applicability of its findings through the analysis of credit card data from a financial institution. In addition to assessing model efficacy, the study introduces noise into the data samples to evaluate algorithm robustness. Experimental outcomes underscore the effectiveness of the majority voting method, achieving commendable accuracy rates in detecting credit card fraud cases. The study sheds light on the pressing issue of credit card fraud, emphasizing the importance of deploying robust machine learning approaches for timely and accurate detection in real-world scenarios.

Artificial Intelligence in the Diagnosis of Colorectal Cancer: A Literature Review.

The aim of this review is to explore the role of artificial intelligence in the diagnosis of colorectal cancer, how it impacts CRC morbidity and mortality, and why its role in clinical medicine is limited. A targeted, non-systematic review of the published literature relating to colorectal cancer diagnosis was performed with PubMed databases that were scouted to help provide a more defined understanding of the recent advances regarding artificial intelligence and their impact on colorectal-related morbidity and mortality. Articles were included if deemed relevant and including information associated with the keywords. The advancements in artificial intelligence have been significant in facilitating an earlier diagnosis of CRC. In this review, we focused on evaluating genomic biomarkers, the integration of instruments with artificial intelligence, MR and hyperspectral imaging, and the architecture of neural networks. We found that these neural networks seem practical and yield positive results in initial testing. Furthermore, we explored the use of deep-learning-based majority voting methods, such as bag of words and PAHLI, in improving diagnostic accuracy in colorectal cancer detection. Alongside this, the autonomous and expansive learning ability of artificial intelligence, coupled with its ability to extract increasingly complex features from images or videos without human reliance, highlight its impact in the diagnostic sector. Despite this, as most of the research involves a small sample of patients, a diversification of patient data is needed to enhance cohort stratification for a more sensitive and specific neural model. We also examined the successful application of artificial intelligence in predicting microsatellite instability, showcasing its potential in stratifying patients for targeted therapies. Since its commencement in colorectal cancer, artificial intelligence has revealed a multitude of functionalities and augmentations in the diagnostic sector of CRC. Given its early implementation, its clinical application remains a fair way away, but with steady research dedicated to improving neural architecture and expanding its applicational range, there is hope that these advanced neural software could directly impact the early diagnosis of CRC. The true promise of artificial intelligence, extending beyond the medical sector, lies in its potential to significantly influence the future landscape of CRC's morbidity and mortality.

Lightweight Multilevel Feature-Fusion Network for Built-Up Area Mapping from Gaofen-2 Satellite Images

The timely, accurate acquisition of geographic spatial information such as the location, scope, and distribution of built-up areas is of great importance for urban planning, management, and decision-making. Due to the diversity of target features and the complexity of spatial layouts, the large-scale mapping of urban built-up areas using high-resolution (HR) satellite imagery still faces considerable challenges. To address this issue, this study adopted a block-based processing strategy and constructed a lightweight multilevel feature-fusion (FF) convolutional neural network for the feature representation and discrimination of built-up areas in HR images. The proposed network consists of three feature extraction modules composed of lightweight convolutions to extract features at different levels, which are further fused sequentially through two attention-based FF modules. Furthermore, to improve the problem of incorrect discrimination and severe jagged boundaries caused by block-based processing, a majority voting method based on a grid offset is adopted to achieve a refined extraction of built-up areas. The effectiveness of this method is evaluated using Gaofen-2 satellite image data covering Shenzhen, China. Compared with several state-of-the-art algorithms for detecting built-up areas, the proposed method achieves a higher detection accuracy and preserves better shape integrity and boundary smoothness in the extracted results.

Detecting Fake Social Media Profiles Using the Majority Voting Approach

INTRODUCTION: The rise of social media platforms has brought about a concerning surge in the creation of fraudulent user profiles, with intentions ranging from spreading false information and perpetrating fraud to engaging in cyberbullying. The detection of these deceptive profiles has emerged as a critical imperative to safeguard the trustworthiness and security of online communities.OBJECTIVES: This paper focused on the detection and identification of fake social media profiles.METHODS: This paper introduces an innovative approach for discerning and categorizing counterfeit social media profiles by leveraging the majority voting approach. The proposed methodology integrates a range of machine learning algorithms, including Decision Trees, XGBoost, Random Forest, Extra Trees, Logistic Regression, AdaBoost and K-Nearest Neighbors each tailored to capture distinct facets of user behavior and profile attributes. This amalgamation of diverse methods results in an ensemble of classifiers, which are subsequently subjected to a majority voting mechanism to render a conclusive judgment regarding the legitimacy of a given social media profile.RESULTS: We conducted thorough experiments using a dataset containing both legitimate and fake social media profiles to determine the efficiency of our methodology. Our findings substantiate that the Majority Voting Technique surpasses individual classifiers, attaining an accuracy rate of 99.12%, a precision rate of 99.12%, a recall rate of 99.12%, and an F1-score of 99.12%.CONCLUSION: The results show that the majority vote method is reliable for detecting and recognising fake social media profiles.

Bio-Inspired Algorithm Based Undersampling Approach and Ensemble Learning for Twitter Spam Detection

Currently, social media networks such as Facebook and Twitter have evolved into valuable platforms for global communication. However, due to their extensive user bases, Twitter is often misused by illegitimate users engaging in illicit activities. While there are numerous research papers available that delve into combating illegitimate users on Twitter, a common shortcoming in most of these works is the failure to address the issue of class imbalance, which significantly impacts the effectiveness of spam detection. Few other research works that have addressed class imbalance have not yet applied bio-inspired algorithms to balance the dataset. Therefore, we introduce PSOB-U, a particle swarm optimization-based undersampling technique designed to balance the Twitter dataset. In PSOB-U, various classifiers and metrics are employed to select majority samples and rank them. Furthermore, an ensemble learning approach is implemented to combine the base classifiers in three stages. During the training phase of the base classifiers, undersampling techniques and a cost-sensitive random forest (CS-RF) are utilized to address the imbalanced data at both the data and algorithmic levels. In the first stage, imbalanced datasets are balanced using random undersampling, particle swarm optimization-based undersampling, and random oversampling. In the second stage, a classifier is constructed for each of the balanced datasets obtained through these sampling techniques. In the third stage, a majority voting method is introduced to aggregate the predicted outputs from the three classifiers. The evaluation results demonstrate that our proposed method significantly enhances the detection of illegitimate users in the imbalanced Twitter dataset. Additionally, we compare our proposed work with existing models, and the predicted results highlight the superiority of our spam detection model over state-of-the-art spam detection models that address the class imbalance problem. The combination of particle swarm optimization-based undersampling and the ensemble learning approach using majority voting results in more accurate spam detection.

Conditional Most-Correlated Distribution-Based Load-Balancing Scheme for Hybrid LiFi/WiGig Network.

A hybrid network has recently been proposed as a framework for a high-speed wireless communication network. Basically, it integrates light fidelity (LiFi) with radio frequency wireless gigabit alliance (WiGig) networks that operate, simultaneously, in a completely different frequency band. To assign the best access point (AP) and provide enough resources for each user, an effective load-balancing (LB) strategy is needed. However, the traditional LB strategies involve sophisticated iterative computing procedures whenever the user distribution changes. Hence, the first contribution of this work is to offer a more adaptable, two-step, conditional, and most-correlated distribution (CMCD) algorithm. Thus, the low-complexity most-correlated distribution (MCD) LB scheme is applied, and the average data rates for all users are then calculated. If the results achieve the predefined performance threshold (PDT), the decisions will be confirmed; otherwise, the proposed scheme automatically switches to the more accurate, but more complex, consecutive assign WiGig first separate optimization algorithms (CAWFS) algorithm. The suggested algorithm provides a clear performance-complexity trade-off, which could be simply controlled by choosing the suitable performance tolerance factor. The second contribution of this paper is the correlation-weighted majority voting (CWMV) method, which attempts to benefit from as many prior decision votes as possible, instead of relying just on one vote. In the CWMV technique, the weight of each vote is calculated based on the correlation between the history distribution vectors and the new user distribution vector. A significant increase in the system performance is evident from the simulation results.

Crop mapping through a hybrid machine learning and deep learning method

A major function of satellite imagery is crop identification and separation, which is of key importance in acreage estimation, yield estimation, and agricultural management. This study aimed to examine the capability of the object-based method and machine learning and deep learning algorithms in combining optical and radar images to generate crop-type maps. For this purpose, Sentinel-1 and Sentinel-2 satellite images were used for the 2019 crop year in the northwest of Ardabil, Iran. Image segmentation was performed through the multiscale method and various spectral, textural, and radar backscattering characteristics. The main features were identified using Random Forest feature selection and fed to support vector machine, random forest, and convolutional neural network algorithms. The results of these algorithms were combined via the majority voting method. The results showed that the convolutional neural network algorithm performed better than other methods with an overall accuracy of 88.03% and a kappa coefficient of 85.99%. Meanwhile, the support vector machine method showed poor performance compared to the other two methods. According to the findings, combining the results of these algorithms through the majority voting method yielded the best crop identification result with an overall accuracy of 90.34% and a Kappa coefficient of 88.72%.

Developing reliable classification of dual IDO1/TDO inhibitors using data fusion and majority voting

Indoleamine 2,3-dioxygenase 1 (IDO1) and tryptophan 2,3-dioxygenase (TDO) are promising dual-targeting inhibitors in cancer and neurodegenerative diseases treatment. Data fusion of receptor-based and ligand-based information of dual IDO1/TDO inhibitors were employed for active/inactive classification performance. A reliable decision making procedure was used here to identify active/inactive dual IDO1/TDO inhibitors using majority voting method and pools of individual classifications instead of individual models. All classification models were validated using prediction set, cross-validation and y-scrambling tests. The classification outcomes indicate that the sensitivity, specificity, precision, accuracy, G-mean and F1 score values increases up to ∼90% using data fusion and majority voting method. Compare to individual classification models with a single prediction point, the majority voting method has more reliable results due to the integration of the pool of individual classification models. This classification strategy may lead to more reliable identification of active/inactive dual-targeting inhibitors in cancer immunotherapy. Communicated by Ramaswamy H. Sarma

Neonatal Hypoxic-Ischemic Encephalopathy Grading from Multi-Channel EEG Time-Series Data Using a Fully Convolutional Neural Network

A deep learning classifier is proposed for grading hypoxic-ischemic encephalopathy (HIE) in neonates. Rather than using handcrafted features, this architecture can be fed with raw EEG. Fully convolutional layers were adopted both in the feature extraction and classification blocks, which makes this architecture simpler, and deeper, but with fewer parameters. Here, two large (335 h and 338 h, respectively) multi-center neonatal continuous EEG datasets were used for training and testing. The model was trained based on weak labels and channel independence. A majority vote method was used for the post-processing of the classifier results (across time and channels) to increase the robustness of the prediction. A dimension reduction tool, UMAP, was used to visualize the model classification effect. The proposed system achieved an accuracy of 86.09% (95% confidence interval: 82.41–89.78%), an MCC of 0.7691, and an AUC of 86.23% on the large unseen test set. Two convolutional neural network architectures which utilized time-frequency distribution features were selected as the baseline as they had been developed or tested on the same datasets. A relative improvement of 23.65% in test accuracy was obtained as compared with the best baseline. In addition, if only one channel was available, the test accuracy was only reduced by 2.63–5.91% compared with making decisions based on the eight channels.

Clinical Usability-Oriented Automatic Contour Quality Evaluation for Deep Learning Auto-Segmentation

Various auto-segmentations, including deep learning auto-segmentation (DLAS), are being increasingly adopted in radiotherapy. A common method to evaluate quality of auto-segmented contours uses thresholds of various quantitative metrics (e.g., dice similarity coefficient (DSC), mean distance to agreement (MDA), etc.) that are often averaged over all contour slices. This method fails to detect contour errors on individual slices, thus, does not reflect the current clinical practice (slice-by-slice evaluation) and the clinical usability (e.g., expected contour editing time). In addition, the use of multi-metrics is generally not easy to interpret. This work aims to develop a novel contour quality classification (CQC) model to evaluate auto-segmented contours based on their clinical applicability. The CQC method was designed to classify a contour on a slice into acceptable, minor edit or major edit category, based on the expected editing effort/time. Organ-specific supervised ensemble tree classification models were trained to relate the slice-based quality category with the combination of seven commonly used calculatable quantitative metrics (i.e., DSC, MDA, Hausdorff 95% distance, surface DSC, added path length (APL), slice area and relative APL). The proposed method was demonstrated by training CQC models using DLAS contours of five abdominal organs (i.e., pancreas, duodenum, stomach, and small and large bowels) from 50 MRI sets and evaluating on 20 MRI and 9 CT testing sets. These test datasets were labelled by six individual observers and the consensus labels were generated through majority vote method. The model performance was evaluated using accuracy (acc), and risk rate (RR, the percentage of unacceptable slices mislabeled as acceptable) and compared with inter-observer variation and baseline threshold-based method. Compared to the majority vote labels, the obtained CQC models achieved a mean accuracy of 95.8% ([94.5%-99.1%]) and 94.3% ([90.6%-96.9%]), and the mean RR of 0.8% ([0.3%-1.3%]) and 0.7% ([0%-1.1%]) for the MRI and CT testing sets, respectively. The CQC performance was comparable to the inter-observer variation and significantly higher than those from the threshold-based method with single or multiple metrics. The execution time on a typical abdominal dataset (e.g., 70 slices) took less than 3 seconds. Table 1 CQC models performance for different organs CONCLUSION: The proposed CQC model can classify the quality of a contour slice with high accuracy. This slice-based single-output evaluation method better reflects the current clinical practice and may be used to evaluate/compare performance of DLAS on any image modality, facilitating its clinical implementation and quality assurance.

Crowdsourcing Subjective Annotations Using Pairwise Comparisons Reduces Bias and Error Compared to the Majority-vote Method

How to better reduce measurement variability and bias introduced by subjectivity in crowdsourced labelling remains an open question. We introduce a theoretical framework for understanding how random error and measurement bias enter into crowdsourced annotations of subjective constructs. We then propose a pipeline that combines pairwise comparison labelling with Elo scoring, and demonstrate that it outperforms the ubiquitous majority-voting method in reducing both types of measurement error. To assess the performance of the labelling approaches, we constructed an agent-based model of crowdsourced labelling that lets us introduce different types of subjectivity into the tasks. We find that under most conditions with task subjectivity, the comparison approach produced higher f1 scores. Further, the comparison approach is less susceptible to inflating bias, which majority voting tends to do. To facilitate applications, we show with simulated and real-world data that the number of required random comparisons for the same classification accuracy scales log-linearly O(N log N) with the number of labelled items. We also implemented the Elo system as an open-source Python package.

Identification of Solid and Liquid Materials Using Acoustic Signals and Frequency-Graph Features.

Material identification is playing an increasingly important role in various sectors such as industry, petrochemical, mining, and in our daily lives. In recent years, material identification has been utilized for security checks, waste sorting, etc. However, current methods for identifying materials require direct contact with the target and specialized equipment that can be costly, bulky, and not easily portable. Past proposals for addressing this limitation relied on non-contact material identification methods, such as Wi-Fi-based and radar-based material identification methods, which can identify materials with high accuracy without physical contact; however, they are not easily integrated into portable devices. This paper introduces a novel non-contact material identification based on acoustic signals. Different from previous work, our design leverages the built-in microphone and speaker of smartphones as the transceiver to identify target materials. The fundamental idea of our design is that acoustic signals, when propagated through different materials, reach the receiver via multiple paths, producing distinct multipath profiles. These profiles can serve as fingerprints for material identification. We captured and extracted them using acoustic signals, calculated channel impulse response (CIR) measurements, and then extracted image features from the time-frequency domain feature graphs, including histogram of oriented gradient (HOG) and gray-level co-occurrence matrix (GLCM) image features. Furthermore, we adopted the error-correcting output code (ECOC) learning method combined with the majority voting method to identify target materials. We built a prototype for this paper using three mobile phones based on the Android platform. The results from three different solid and liquid materials in varied multipath environments reveal that our design can achieve average identification accuracies of 90% and 97%.