Majority Voting Research Articles

The Research of Multi-Node Collaborative Compound Jamming Recognition Algorithm Based on Model-Agnostic Meta-Learning and Time-Frequency Analysis

Deep learning has presented its spectacular potential in the jamming recognition field. Yet, sufficient samples required by normal deep learning analysis methods are not always available, especially in the 6G communication field. This situation appears to be more challenging in the communication field. In this article, Model-Agnostic Meta-Learning (MAML) is imported into the jamming recognition field in order to accomplish compound jamming recognition in the circumstances of few-shot learning. Further, the existing research on jamming recognition techniques is mostly based on single-node recognition. This technique cannot make full and efficient use of the jamming information collected. Therefore, this article adds a multi-node collaborative technique into the compound jamming recognition algorithm that is based on MAML and time-frequency analysis. Based on the fact that each cognitive node can recognize independently, the recognition results are be sent to the fusion center. The fusion center completes the fusion of the recognition results according to the majority rule. The experiments demonstrate that, with the fusion of the multi-node collaborative technique, the precision of compound jamming recognition in the condition of few-shot learning has been effectively improved.

Tumor Subtype Classification Tool for HPV-associated Head and Neck Cancers.

Molecular subtypes of HPV-associated Head and Neck Squamous Cell Carcinoma (HNSCC), named IMU (immune strong) and KRT (highly keratinized), are well-recognized and have been shown to have distinct mechanisms of carcinogenesis, clinical outcomes, and potentially differing optimal treatment strategies. Currently, no standardized method exists to subtype a new HPV+ HNSCC tumor. Our paper introduces a machine learning-based classifier and webtool to reliably subtype HPV+ HNSCC tumors using the IMU/KRT paradigm and highlights the importance of subtype in HPV+ HNSCC. To develop a robust, accurate machine learning-based classification tool that standardizes the process of subtyping HPV+ HNSCC, and to investigate the clinical, demographic, and molecular features associated with subtype in a meta-analysis of four patient cohorts. We conducted RNA-seq on 67 HNSCC FFPE blocks from University of Michigan hospital. Combining this with three publicly available datasets, we utilized a total of 229 HPV+ HNSCC RNA-seq samples. All participants were HPV+ according to RNA expression. An ensemble machine learning approach with five algorithms and three different input training gene sets were developed, with final subtype determined by majority vote. Several additional steps were taken to ensure rigor and reproducibility throughout. The classifier was trained and tested using 84 subtype-labeled HPV+ RNA-seq samples from two cohorts: University of Michigan (UM; n=18) and TCGA-HNC (n=66). The classifier robustness was validated with two independent cohorts: 83 samples from the HPV Virome Consortium and 62 additional samples from UM. We revealed 24 of 39 tested clinicodemographic and molecular variables significantly associated with subtype. The classifier achieved 100% accuracy in the test set. Validation on two additional cohorts demonstrated successful separation by known features of the subtypes. Investigating the relationship between subtype and 39 molecular and clinicodemographic variables revealed IMU is associated with epithelial-mesenchymal transition (p=2.25×10-4), various immune cell types, and lower radiation resistance (p=0.0050), while KRT is more highly keratinized (p=2.53×10-8), and more likely female than IMU (p=0.0082). This study provides a reliable classifier for subtyping HPV+ HNSCC tumors as either IMU or KRT based on bulk RNA-seq data, and additionally, improves our understanding of the HPV+ HNSCC subtypes.

Machine Learning-Based Identification of Diagnostic Biomarkers for Korean Male Sarcopenia Through Integrative DNA Methylation and Methylation Risk Score: From the Korean Genomic Epidemiology Study (KoGES).

Sarcopenia, characterized by a progressive decline in muscle mass, strength, and function, is primarily attributable to aging. DNA methylation, influenced by both genetic predispositions and environmental exposures, plays a significant role in sarcopenia occurrence. This study employed machine learning (ML) methods to identify differentially methylated probes (DMPs) capable of diagnosing sarcopenia in middle-aged individuals. We also investigated the relationship between muscle strength, muscle mass, age, and sarcopenia risk as reflected in methylation profiles. Data from 509 male participants in the urban cohort of the Korean Genome Epidemiology Study_Health Examinee study were categorized into quartile groups based on the sarcopenia criteria for appendicular skeletal muscle index (ASMI) and handgrip strength (HG). To identify diagnostic biomarkers for sarcopenia, we used recursive feature elimination with cross validation (RFECV), to pinpoint DMPs significantly associated with sarcopenia. An ensemble model, leveraging majority voting, was utilized for evaluation. Furthermore, a methylation risk score (MRS) was calculated, and its correlation with muscle strength, function, and age was assessed using likelihood ratio analysis and multinomial logistic regression. Participants were classified into two groups based on quartile thresholds: sarcopenia (n = 37) with ASMI and HG in the lowest quartile, and normal ranges (n = 48) in the highest. In total, 238 DMPs were identified and eight probes were selected using RFECV. These DMPs were used to build an ensemble model with robust diagnostic capabilities for sarcopenia, as evidenced by an area under the receiver operating characteristic curve of 0.94. Based on eight probes, the MRS was calculated and then validated by analyzing age, HG, and ASMI among the control group (n = 424). Age was positively correlated with high MRS (coefficient, 1.2494; odds ratio [OR], 3.4882), whereas ASMI and HG were negatively correlated with high MRS (ASMI coefficient, -0.4275; OR, 0.6521; HG coefficient, -0.3116; OR, 0.7323). Overall, this study identified key epigenetic markers of sarcopenia in Korean males and developed a ML model with high diagnostic accuracy for sarcopenia. The MRS also revealed significant correlations between these markers and age, HG, and ASMI. These findings suggest that both diagnostic models and the MRS can play an important role in managing sarcopenia in middle-aged populations.

Measuring Cybercrime in Calls for Police Service

Conventional police databases contain much information on cybercrime, but extracting it remains a practical challenge. This is because these databases rarely contain labels that could be used to automatically retrieve all cybercrime incidents. In this article, we present a supervised machine learning method for extracting cybercrime incidents in calls for police service datasets. Data from the Korean National Police (2020, 9 months, N = 15 million call logs) is used for the demonstration. We combined methods of keyword query selection, minority oversampling, and majority voting techniques to develop a classifier. Three classification techniques, including Naïve Bayes, linear SVM, and kernel SVM, were tested, and the kernel model was chosen to build the final model (accuracy, 93.4%; F1-score, 92.4). We estimate that cybercrime only represents 4.6% of the cases in the selected dataset (excluding traffic-related incidents), but that it can be prevalent with some crime types. We found, for example, that about three quarters (76%) of all fraud incidents have a cyber dimension. We conclude that the cybercrime classification method proposed in this study can support further research on cybercrime and that it offers considerable advantages over manual or keyword-based approaches.

Gamified Crowdsourcing as a Novel Approach to Lung Ultrasound Data Set Labeling: Prospective Analysis.

Machine learning (ML) models can yield faster and more accurate medical diagnoses; however, developing ML models is limited by a lack of high-quality labeled training data. Crowdsourced labeling is a potential solution but can be constrained by concerns about label quality. This study aims to examine whether a gamified crowdsourcing platform with continuous performance assessment, user feedback, and performance-based incentives could produce expert-quality labels on medical imaging data. In this diagnostic comparison study, 2384 lung ultrasound clips were retrospectively collected from 203 emergency department patients. A total of 6 lung ultrasound experts classified 393 of these clips as having no B-lines, one or more discrete B-lines, or confluent B-lines to create 2 sets of reference standard data sets (195 training clips and 198 test clips). Sets were respectively used to (1) train users on a gamified crowdsourcing platform and (2) compare the concordance of the resulting crowd labels to the concordance of individual experts to reference standards. Crowd opinions were sourced from DiagnosUs (Centaur Labs) iOS app users over 8 days, filtered based on past performance, aggregated using majority rule, and analyzed for label concordance compared with a hold-out test set of expert-labeled clips. The primary outcome was comparing the labeling concordance of collated crowd opinions to trained experts in classifying B-lines on lung ultrasound clips. Our clinical data set included patients with a mean age of 60.0 (SD 19.0) years; 105 (51.7%) patients were female and 114 (56.1%) patients were White. Over the 195 training clips, the expert-consensus label distribution was 114 (58%) no B-lines, 56 (29%) discrete B-lines, and 25 (13%) confluent B-lines. Over the 198 test clips, expert-consensus label distribution was 138 (70%) no B-lines, 36 (18%) discrete B-lines, and 24 (12%) confluent B-lines. In total, 99,238 opinions were collected from 426 unique users. On a test set of 198 clips, the mean labeling concordance of individual experts relative to the reference standard was 85.0% (SE 2.0), compared with 87.9% crowdsourced label concordance (P=.15). When individual experts' opinions were compared with reference standard labels created by majority vote excluding their own opinion, crowd concordance was higher than the mean concordance of individual experts to reference standards (87.4% vs 80.8%, SE 1.6 for expert concordance; P<.001). Clips with discrete B-lines had the most disagreement from both the crowd consensus and individual experts with the expert consensus. Using randomly sampled subsets of crowd opinions, 7 quality-filtered opinions were sufficient to achieve near the maximum crowd concordance. Crowdsourced labels for B-line classification on lung ultrasound clips via a gamified approach achieved expert-level accuracy. This suggests a strategic role for gamified crowdsourcing in efficiently generating labeled image data sets for training ML systems.

DNN-BP: a novel framework for cuffless blood pressure measurement from optimal PPG features using deep learning model.

Continuous blood pressure (BP) provides essential information for monitoring one's health condition. However, BP is currently monitored using uncomfortable cuff-based devices, which does not support continuous BP monitoring. This paper aims to introduce a blood pressure monitoring algorithm based on only photoplethysmography (PPG) signals using the deep neural network (DNN). The PPG signals are obtained from 125 unique subjects with 218 records and filtered using signal processing algorithms to reduce the effects of noise, such as baseline wandering, and motion artifacts. The proposed algorithm is based on pulse wave analysis of PPG signals, extracted various domain features from PPG signals, and mapped them to BP values. Four feature selection methods are applied and yielded four feature subsets. Therefore, an ensemble feature selection technique is proposed to obtain the optimal feature set based on major voting scores from four feature subsets. DNN models, along with the ensemble feature selection technique, outperformed in estimating the systolic blood pressure (SBP) and diastolic blood pressure (DBP) compared to previously reported approaches that rely only on the PPG signal. The coefficient of determination ( ) and mean absolute error (MAE) of the proposed algorithm are 0.962 and 2.480 mmHg, respectively, for SBP and 0.955 and 1.499 mmHg, respectively, for DBP. The proposed approach meets the Advancement of Medical Instrumentation standard for SBP and DBP estimations. Additionally, according to the British Hypertension Society standard, the results attained Grade A for both SBP and DBP estimations. It concludes that BP can be estimated more accurately using the optimal feature set and DNN models. The proposed algorithm has the potential ability to facilitate mobile healthcare devices to monitor continuous BP.

Social clustering reinforces external influence on the majority opinion model

Public opinion is subject to peer interaction via social networks and external pressure from the media, advertising, and other actors. In this paper, we study the interaction between external and peer influence on the stochastic opinion dynamics of a majority vote model. We introduce a model where agents update their opinions based on the combined influence of their local neighbourhood (peers) and an external actor in the transition rates. In the first model, the external influence is only felt by agents non-aligned with the external actor (“push strategy”). In the second model, agents are affected by external influence, independently of their opinions (“nudging strategy”). In both cases, the external influence increases the possible macroscopic outcomes. These outcomes are determined by the chosen influence strategy. We also find that the social network structure affects the opinion dynamics, with social clustering positively reinforcing the external influence whereas degree heterogeneity weakens the external forces. These findings are relevant to businesses and policy making, helping to understand how groups of individuals collectively react to external actors.

PENGARUH POLA ASUH ORANGTUA TERHADAP MORAL ANAK USIA 4-5 TAHUN DI RA.TARUNA MULIA KABUPATEN PROBOLINGGO

This research aims to determine the influence of parenting styles on the morale of children aged 4-5 years in RA. Taruna Mulia, Probolinggo district. This research uses qualitative methods with a descriptive approach. Sources of data obtained through interviews, observation and documentation. The research was conducted at RA.Taruna Mulia, Gunung Tugel village, Probolinggo district in group A, totaling 17 children with a sample of 6 people. The sample was determined using purposive sampling to make this research more focused and easier. There are several types of parenting styles according to experts, especially Dictator, Lenient, and Popularity. Of these three types, scientists need to be aware of which parenting style is more dominant in the application of young people's ethics. After testing the direction, the analysts observed that there were only two types of parenting styles applied by the guardians, namely the Tyrant and Majority rule parenting styles. which is considered to have a great influence on children's morals. With this research, parents realize that proper parenting will form good morals. Keywords: Parenting patterns; morals; children aged 4-5 years

ANALYSIS OF HOW AND WHY STYLISTIC LANGUAGE IMPACTS ADVERTISING WITH A JOURNALISTIC APPROACH

Objective and Background: The Internet of Things (IoT) devices store a great volume of data. Therefore, with the advancements in technology, some new protection guidelines have to be developed to preserve data privacy and collection. The present study aimed to determine a secure protective framework using the BTD structure in a specified zone, and provide the idea of hiding the sensory data of an operator device to preserve data privacy without losing the data integrity. Methodology: Two simple and enhanced methods were used. The BTD framework and estimated ground truth were used in both modes. The enhanced method allows the users to use a random weight (variance) when combining their sensory data with the estimated ground truth provided by the agent. We ran the BTD framework in the CloudSim (network simulation framework). Each simulation is run for 500 virtual minutes with 12 iterations. The target zone is set to 50×50 meters. The test results were collected on real-world data traces from sensory systems. In addition to the BTD structure, the Voting method has been also used, and to do so, majority voting and CRH truth discovery method (Conflict Resolution on Heterogeneous Data) which does not take any measures to break the security of the sensor during the process is used. Findings: The comparative results show a 0.70-0.71 error level between the BTD and other functions, at least. As long as there is at least one reliable source, the BTD will have an error level of 0. Simulations show that BTD has a worst-case error of 0.05 and a weighted variance of +/- 5%. Based on previous frameworks, the BTD is improved by three requirements of a population identified in the IoT: Preservation of privacy for the device user, data integrity for the data collection group, and low-cost computation on the user device.

Multi-Modality Ensemble Distortion for Spatial Steganography With Dynamic Cost Correction

This paper tackles a recent challenge in designing an efficient steganographic distortion model, whose goal is to accurately measure the modification cost of a pixel and help design steganographic schemes with high undetectability. Existing distortion models mostly assume that different modification directions of a pixel have an identical cost value and that pixel modifications are independent. These assumptions, however, may not lead to good steganography design because the modification direction of neighbouring pixels may affect the cost measurement of the current pixel. To address this problem, we propose a new distortion calculation method using dynamic cost correction and multi-modality distortion ensemble. The proposed scheme first employs a given distortion model to generate the original cost map. The cost of each pixel is then dynamically adjusted with majority voting according to the modification directions of its neighbouring pixels. Furthermore, different distortion calculation models are integrated to make the final decision on the distortion of each pixel. Experimental results show that compared to existing additive distortion-based steganographic schemes and deep learning-based steganographic schemes, steganography using our proposed distortion model performs better when tested against state-of-the-art steganalysis methods.

Caring for minorities: The Flexible Decision Rule

AbstractSimple majority rule disregards the interests of the losing minority; their vote does not affect the outcome. When vote outcomes are narrow, close to 50% of voters, the concerns of a significant part of the voters are disregarded. This increases polarization in the population and endangers democracy. This paper proposes a new procedure for political decisions by referendums. The Flexible Decision Rule formally takes into account the percentage of voters accepting or rejecting a proposal. The higher the share y of voters accepting it, the more strongly the proposal is to be put into reality; the lower y is, the less strongly the proposal is to be put into reality. This procedure explicitly considers the concerns of both the supporters and the opponents thus raising the fairness of the vote procedure. In contrast to majority voting, each vote marginalizes the outcome and therefore raises the incentive to participate in the vote increase.

Interobserver Agreement and Performance of Concurrent AI Assistance for Radiographic Evaluation of Knee Osteoarthritis.

Background Due to conflicting findings in the literature, there are concerns about a lack of objectivity in grading knee osteoarthritis (KOA) on radiographs. Purpose To examine how artificial intelligence (AI) assistance affects the performance and interobserver agreement of radiologists and orthopedists of various experience levels when evaluating KOA on radiographs according to the established Kellgren-Lawrence (KL) grading system. Materials and Methods In this retrospective observer performance study, consecutive standing knee radiographs from patients with suspected KOA were collected from three participating European centers between April 2019 and May 2022. Each center recruited four readers across radiology and orthopedic surgery at in-training and board-certified experience levels. KL grading (KL-0 = no KOA, KL-4 = severe KOA) on the frontal view was assessed by readers with and without assistance from a commercial AI tool. The majority vote of three musculoskeletal radiology consultants established the reference standard. The ordinal receiver operating characteristic method was used to estimate grading performance. Light kappa was used to estimate interrater agreement, and bootstrapped t statistics were used to compare groups. Results Seventy-five studies were included from each center, totaling 225 studies (mean patient age, 55 years ± 15 [SD]; 113 female patients). The KL grades were KL-0, 24.0% (n = 54); KL-1, 28.0% (n = 63); KL-2, 21.8% (n = 49); KL-3, 18.7% (n = 42); and KL-4, 7.6% (n = 17). Eleven readers completed their readings. Three of the six junior readers showed higher KL grading performance with versus without AI assistance (area under the receiver operating characteristic curve, 0.81 ± 0.017 [SEM] vs 0.88 ± 0.011 [P < .001]; 0.76 ± 0.018 vs 0.86 ± 0.013 [P < .001]; and 0.89 ± 0.011 vs 0.91 ± 0.009 [P = .008]). Interobserver agreement for KL grading among all readers was higher with versus without AI assistance (κ = 0.77 ± 0.018 [SEM] vs 0.85 ± 0.013; P < .001). Board-certified radiologists achieved almost perfect agreement for KL grading when assisted by AI (κ = 0.90 ± 0.01), which was higher than that achieved by the reference readers independently (κ = 0.84 ± 0.017; P = .01). Conclusion AI assistance increased junior readers' radiographic KOA grading performance and increased interobserver agreement for osteoarthritis grading across all readers and experience levels. Published under a CC BY 4.0 license. Supplemental material is available for this article.

A high‐accuracy and robust diagnostic tool for gearbox faults in wind turbines

AbstractFaulty gears are a common cause of wind turbine failures. For this sake, this work was developed as a reliable diagnostic tool for wind turbines to improve wind power stability accordingly. A convolutional extension neural network (CENN) was proposed to identify vibration and audio signals captured from a gearbox. According to the status of the contained faulty gears, a gearbox was categorised as one of the three types: (i) broken, (ii) rusty and (iii) a combination of (i) and (ii). It was further assigned one of the three severity levels: mild, moderate and severe. Therefore, there were a total of nine combinations for identification. Captured raw vibration and audio signals were applied to a chaotic synchronisation detector by which 3D chaotic error scatter feature images were generated to train and test the CENN. The recognition rate provided by CENN and the majority rule reached 99.6%, and then slightly fell to 97.4% in a noise robustness test, and consequently CENN outperformed counterparts in terms of the recognition rate and the robustness against noise. Accordingly, multiple gearbox faults can be well diagnosed for the first time in the literature. Finally, this paper concludes with a simplified version of the original proposal.

Face Anti-Spoofing Detection with Multi-Modal CNN Enhanced by ResNet

The growing prevalence of face recognition technology in various applications, including mobile devices, access control, and financial transactions, highlights its importance. However, the vulnerability of face recognition systems to attacks has been demonstrated, underscoring the necessity of addressing potential weaknesses that attackers may exploit. The paper delves into face presentation attack detection (PAD) within biometric systems, which is crucial for ensuring the reliability and security of face recognition algorithms. To address this issue, the paper proposes a method for face presentation attack detection using ResNet-50 in conjunction with multi-modal data, incorporating RGB, depth, infrared (IR), and thermal channels. The method explores diverse strategies to combine results from each modality, investigating various fusion techniques such as majority voting, weighted voting, average pooling, and a stacking classifier. The system has been tested on the WMCA dataset. It exhibits strong performance compared to existing methods, notably achieving an impressive ACER ratio of 0.087% with the stacking classifier. This approach proves effective by consolidating multiple modalities without requiring individual scenario-specific models, indicating promise for real-world applications

Information manipulation and majority rule

This paper studies endogenous institution in the presence of information manipulation. We show majority rule discourages information manipulation, reducing Type II errors in collective decision-making. In equilibrium, the optimal majority rule strategically balances the reduction in Type II errors associated with discouraging information manipulation with the potential increase in Type I errors. When it comes to green environmental issues, member countries often adopt a majority rule voting system. This is because these issues typically involve high inherent risks that affect all countries on a global scale, and low heterogeneity among members in terms of the desire to address these challenges.

Sistem Proporsional Terbuka Bukan Akar Politik Uang Dalam Pemilu

The influence of an open proportional representation system with a majority vote does not explain the rise of money politics and political corruption after the election period. Systemically, the influence of the electoral system is aimed more at establishing a stable party system and modeling coalition models to produce a model of political balance in managing relations between the Government and Parliament. Meanwhile, the quality of the implementation of the electoral system is actually determined by the quality of the institutionalization of political parties, including the tendency of the type of party. Money politics is the result of the poor quality of political institutions in a type of party that only focuses on electoral interests.

Class-overlap detection based on heterogeneous clustering ensemble for multi-class imbalance problem

The class imbalance problem is one of the main challenges that hinders classifiers from identifying unknown instances. When class distribution imbalance and class overlap coexist in the same data set, the recognition of minority instances by traditional classifiers will be seriously affected. In the binary classification problem, the relationship between the majority class and the minority class is clear, and the overlap problem between classes can be well solved by removing the majority instances in the class-overlap area. However, for multi-class imbalance problems, the relationships between classes will become complex. Clustering techniques are effective methods for identifying overlapping instances; however, a single clustering method cannot effectively identify clusters of different shapes. Therefore, in this paper, a Heterogeneous Clustering Ensemble learning method for Multiple Class-overlap Detection (HCE-MCD) is proposed for multi-class imbalance problems. This method uses a genetic algorithm to select a combination of heterogeneous clustering techniques with the best fitness function from a pool of clustering algorithms and uses majority voting to fuse the results of the clustering algorithm. Furthermore, instances located near the decision boundary are more likely to be overlapping instances. Therefore, according to the clustering results of the heterogeneous clustering ensemble method, we can identify the overlapping instances existing in the data set, thereby eliminating the class overlap problem in the multi-class dataset. Experimental results on 19 open-access datasets show that our proposed method outperforms or partially outperforms state-of-the-art research protocols.

DSWIN: Automated hunger detection model based on hand-crafted decomposed shifted windows architecture using EEG signals

Hunger is a physiological state that arises from complex interactions of multiple factors, including higher brain center control. We purposed to develop an accurate and efficient machine-learning model for the automated detection of hunger using EEG signals. We prospectively acquired 14-channel EEG (sampling frequency 128 Hz) from 43 and 48 fasted and post-prandial healthy subjects (hungry vs. control groups, respectively) using the EMOTIV EPOC+ mobile brain cap system. To augment the hunger response, fasted subjects were also shown video images of food during EEG recording. The EEG signals were divided into 15-second segments. 877 and 852 participants/subjects were in the hungry and control groups. We created a novel handcrafted architecture—decomposed shifted window (DSWIN)—that combined swin patch division with tunable Q-factor wavelet transform-based signal decomposition for multilevel feature extraction of EEG signals. Textural and statistical features were extracted from the multiple patches and decomposed signals using a novel penta pattern-based extractor and statistical moments, respectively, and then merged. Iterative neighborhood component analysis (INCA) and iterative ReliefF (IRF) were applied. Twenty-eight selected feature vectors were generated, which were then fed to a shallow k-nearest neighbors (kNN) classifier to calculate channel-wise prediction vectors. From the 28 channel-wise prediction vectors, another 26 modes of function-based voted results were calculated using iterative hard majority voting, and the best overall model result was selected using a greedy algorithm. Our model attained 99.54% and 82.71% binary classification accuracies of hungry status vs. control using 10-fold and leave-one-subject-out cross-validations, respectively.

Majority voting of doctors improves appropriateness of AI reliance in pathology

As Artificial Intelligence (AI) making advancements in medical decision-making, there is a growing need to ensure doctors develop appropriate reliance on AI to avoid adverse outcomes. However, existing methods in enabling appropriate AI reliance might encounter challenges while being applied in the medical domain. With this regard, this work employs and provides the validation of an alternative approach – majority voting – to facilitate appropriate reliance on AI in medical decision-making. This is achieved by a multi-institutional user study involving 32 medical professionals with various backgrounds, focusing on the pathology task of visually detecting a pattern, mitoses, in tumor images. Here, the majority voting process was conducted by synthesizing decisions under AI assistance from a group of pathology doctors (pathologists). Two metrics were used to evaluate the appropriateness of AI reliance: Relative AI Reliance (RAIR) and Relative Self-Reliance (RSR). Results showed that even with groups of three pathologists, majority-voted decisions significantly increased both RAIR and RSR – by approximately 9% and 31%, respectively – compared to decisions made by one pathologist collaborating with AI. This increased appropriateness resulted in better precision and recall in the detection of mitoses. While our study is centered on pathology, we believe these insights can be extended to general high-stakes decision-making processes involving similar visual tasks.

Card-based Cryptography with a Standard Deck of Cards, Revisited: Efficient Protocols in the Private Model

Card-based cryptography is a secure computation protocol realized by using physical cards. There are two models on card-based cryptography: public and private models. We adopt private one that allows players to handle cards privately. While much of the existing works for card-based cryptography use two-colored cards, it is also a vital task to construct an efficient protocol with playing cards. In the public model, 2n cards are necessary for any n-bit input protocol since at least two cards are required to express a Boolean value. It holds true for both two-colored and playing-card settings. On the other hand, the private model enables us to construct a protocol with fewer than 2n cards. However, all existing protocols that achieve such properties are only in the two-colored setting. This paper shows that the private model enables us to construct a protocol with fewer than 2n cards using the playing cards. We first show two-bit input protocols with fewer than four cards for logical operations, AND, OR, and XOR. Furthermore, we show a three-input majority voting protocol using only three cards, which is constructed by combining our AND and OR protocols. Notably, our proposed protocols require no randomness. All operations are deterministic and depend only on players’ private inputs.