False Positive Reduction Research Articles

TPAAD: Two‐phase authentication system for denial of service attack detection and mitigation using machine learning in software‐defined network

AbstractSoftware‐defined networking (SDN) has received considerable attention and adoption owing to its inherent advantages, such as enhanced scalability, increased adaptability, and the ability to exercise centralized control. However, the control plane of the system is vulnerable to denial‐of‐service (DoS) attacks, which are a primary focus for attackers. These attacks have the potential to result in substantial delays and packet loss. In this study, we present a novel system called Two‐Phase Authentication for Attack Detection that aims to enhance the security of SDN by mitigating DoS attacks. The methodology utilized in our study involves the implementation of packet filtration and machine learning classification techniques, which are subsequently followed by the targeted restriction of malevolent network traffic. Instead of completely deactivating the host, the emphasis lies on preventing harmful communication. Support vector machine and K‐nearest neighbours algorithms were utilized for efficient detection on the CICDoS 2017 dataset. The deployed model was utilized within an environment designed for the identification of threats in SDN. Based on the observations of the banned queue, our system allows a host to reconnect when it is no longer contributing to malicious traffic. The experiments were run on a VMware Ubuntu, and an SDN environment was created using Mininet and the RYU controller. The results of the tests demonstrated enhanced performance in various aspects, including the reduction of false positives, the minimization of central processing unit utilization and control channel bandwidth consumption, the improvement of packet delivery ratio, and the decrease in the number of flow requests submitted to the controller. These results confirm that our Two‐Phase Authentication for Attack Detection architecture identifies and mitigates SDN DoS attacks with low overhead.

Lowered cutoffs to reduce false positives on the Word Memory Test

ABSTRACT Objective To adjust the decision criterion for the Word Memory Test (WMT, Green, 2003) to minimize the frequency of false positives. Method Archival data were combined into a database (n = 3,210) to examine the best cut score for the WMT. We compared results based on the original scoring rules and those based on adjusted scoring rules using a criterion based on 16 performance validity tests (PVTs) exclusive of the WMT. Cutoffs based on peer-reviewed publications and test manuals were used. The resulting PVT composite was considered the best estimate of validity status. We focused on a specificity of .90 with a false-positive rate of less than .10 across multiple samples. Results Each examinee was administered the WMT, as well as on average 5.5 (SD = 2.5) other PVTs. Based on the original scoring rules of the WMT, 31.8% of examinees failed. Using a single failure on the criterion PVT (C-PVT), the base rate of failure was 45.9%. When requiring two or more failures on the C-PVT, the failure rate dropped to 22.8%. Applying a contingency analysis (i.e., X2) to the two failures model on the C-PVT measure and using the original rules for the WMT resulted in only 65.3% agreement. However, using our adjusted rules for the WMT, which consisted of relying on only the IR and DR WMT subtest scores with a cutoff of 77.5%, agreement between the adjusted and the C-PVT criterion equaled 80.8%, for an improvement of 12.1% identified. The adjustmeny resulted in a 49.2% reduction in false positives while preserving a sensitivity of 53.6%. The specificity for the new rules was 88.8%, for a false positive rate of 11.2%. Conclusions Results supported lowering of the cut score for correct responding from 82.5% to 77.5% correct. We also recommend discontinuing the use of the Consistency subtest score in the determination of WMT failure.

BeatProfiler: Multimodal In Vitro Analysis of Cardiac Function Enables Machine Learning Classification of Diseases and Drugs.

Goal: Contractile response and calcium handling are central to understanding cardiac function and physiology, yet existing methods of analysis to quantify these metrics are often time-consuming, prone to mistakes, or require specialized equipment/license. We developed BeatProfiler, a suite of cardiac analysis tools designed to quantify contractile function, calcium handling, and force generation for multiple in vitro cardiac models and apply downstream machine learning methods for deep phenotyping and classification. Methods: We first validate BeatProfiler's accuracy, robustness, and speed by benchmarking against existing tools with a fixed dataset. We further confirm its ability to robustly characterize disease and dose-dependent drug response. We then demonstrate that the data acquired by our automatic acquisition pipeline can be further harnessed for machine learning (ML) analysis to phenotype a disease model of restrictive cardiomyopathy and profile cardioactive drug functional response. To accurately classify between these biological signals, we apply feature-based ML and deep learning models (temporal convolutional-bidirectional long short-term memory model or TCN-BiLSTM). Results: Benchmarking against existing tools revealed that BeatProfiler detected and analyzed contraction and calcium signals better than existing tools through improved sensitivity in low signal data, reduction in false positives, and analysis speed increase by 7 to 50-fold. Of signals accurately detected by published methods (PMs), BeatProfiler's extracted features showed high correlations to PMs, confirming that it is reliable and consistent with PMs. The features extracted by BeatProfiler classified restrictive cardiomyopathy cardiomyocytes from isogenic healthy controls with 98% accuracy and identified relax90 as a top distinguishing feature in congruence with previous findings. We also show that our TCN-BiLSTM model was able to classify drug-free control and 4 cardiac drugs with different mechanisms of action at 96% accuracy. We further apply Grad-CAM on our convolution-based models to identify signature regions of perturbations by these drugs in calcium signals. Conclusions: We anticipate that the capabilities of BeatProfiler will help advance in vitro studies in cardiac biology through rapid phenotyping, revealing mechanisms underlying cardiac health and disease, and enabling objective classification of cardiac disease and responses to drugs.

Movement Tracking and False Positive Reduction Method for Microwave Colonoscopy Systems

Movement Tracking and False Positive Reduction Method for Microwave Colonoscopy Systems

3D ARCNN: An Asymmetric Residual CNN for False Positive Reduction in Pulmonary Nodule.

Lung cancer is with the highest morbidity and mortality, and detecting cancerous lesions early is essential for reducing mortality rates. Deep learning-based lung nodule detection techniques have shown better scalability than traditional methods. However, pulmonary nodule test results often include a number of false positive outcomes. In this paper, we present a novel asymmetric residual network called 3D ARCNN that leverages 3D features and spatial information of lung nodules to improve classification performance. The proposed framework uses an internally cascaded multi-level residual model for fine-grained learning of lung nodule features and multi-layer asymmetric convolution to address the problem of large neural network parameters and poor reproducibility. We evaluate the proposed framework on the LUNA16 dataset and achieve a high detection sensitivity of 91.6%, 92.7%, 93.2%, and 95.8% for 1, 2, 4, and 8 false positives per scan, respectively, with an average CPM index of 0.912. Quantitative and qualitative evaluations demonstrate the superior performance of our framework compared to existing methods. 3D ARCNN framework can effectively reduce the possibility of false positive lung nodules in the clinical.

Application of Ion Mobility Spectrometry and the Derived Collision Cross Section in the Analysis of Environmental Organic Micropollutants.

Ion mobility spectrometry (IMS) is a rapid gas-phase separation technique, which can distinguish ions on the basis of their size, shape, and charge. The IMS-derived collision cross section (CCS) can serve as additional identification evidence for the screening of environmental organic micropollutants (OMPs). In this work, we summarize the published experimental CCS values of environmental OMPs, introduce the current CCS prediction tools, summarize the use of IMS and CCS in the analysis of environmental OMPs, and finally discussed the benefits of IMS and CCS in environmental analysis. An up-to-date CCS compendium for environmental contaminants was produced by combining CCS databases and data sets of particular types of environmental OMPs, including pesticides, drugs, mycotoxins, steroids, plastic additives, per- and polyfluoroalkyl substances (PFAS), polycyclic aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs), and polybrominated diphenyl ethers (PBDEs), as well as their well-known transformation products. A total of 9407 experimental CCS values from 4170 OMPs were retrieved from 23 publications, which contain both drift tube CCS in nitrogen (DTCCSN2) and traveling wave CCS in nitrogen (TWCCSN2). A selection of publicly accessible and in-house CCS prediction tools were also investigated; the chemical space covered by the training set and the quality of CCS measurements seem to be vital factors affecting the CCS prediction accuracy. Then, the applications of IMS and the derived CCS in the screening of various OMPs were summarized, and the benefits of IMS and CCS, including increased peak capacity, the elimination of interfering ions, the separation of isomers, and the reduction of false positives and false negatives, were discussed in detail. With the improvement of the resolving power of IMS and enhancements of experimental CCS databases, the practicability of IMS in the analysis of environmental OMPs will continue to improve.

Ex‐vivo microbleed detection in community‐based older adults using confidence‐aware learning

AbstractBackgroundCerebral microbleed (CMB) detection on MRI scans of autopsied brains of community‐based older adults is crucial for MR‐pathology studies of cerebral small vessel disease (SVD). However, training an ex‐vivo CMB detection model is difficult due to the low prevalence of CMBs in the brains of community‐based older adults, and the fact that CMB mimics greatly outnumber CMBs on ex‐vivo MRI. We demonstrate that confidence‐aware deep learning, a technique for enforcing correct ranking of examples during neural network training, significantly improves ex‐vivo CMB detection performance and enhances the interpretability of model predictions.MethodCMBs from 286 participants from two longitudinal cohort studies of aging were included in this work. T2*‐weighted gradient echo scans of autopsied brains with a voxel size of 1×1×1 mm were used. Confidence‐aware learning was used to regularize deep learning model predictions such that they reflect the degree of confidence the detection model has in a prediction. Model confidence was estimated during training by correctness, the number of correct prediction events across epochs divided by the total number of epochs. The objective loss function was modified to include a correctness ranking loss (CRL) term that encourages correspondence between correctness and predicted probabilities. Models are trained with and without the CRL loss term to evaluate the impact of confidence‐aware learning on model performance. An end‐to‐end CMB detection framework that combines data synthesis, candidate selection, false positive reduction, and full scan evaluation was used as the backbone for this work.ResultCMB detection models trained using correctness ranking loss achieved a significantly higher ensemble average precision (0.2915) compared with models trained without correctness ranking loss (0.2379). The CRL trained model achieved a 25% higher sensitivity at 0.5 false positives per subject and 12% higher sensitivity at 3 false positives per subject when compared to models trained without CRL.ConclusionThis work demonstrates that training with confidence‐aware learning can improve the performance and interpretability of ex‐vivo CMB detection algorithms in community‐based cohorts. The use of a confidence‐aware CMB detection algorithm for assisted CMB annotation in ex‐vivo MRI will aid in future MR‐pathology studies into the relationships between CMBs and neuropathology.

Deep learning-assisted IoMT framework for cerebral microbleed detection

The Internet of Things (IoT), big data, and artificial intelligence (AI) are all key technologies that influence the formation and implementation of digital medical services. Building Internet of Medical Things (IoMT) systems that combine advanced sensors with AI-powered insights is critical for intelligent medical systems. This paper presents an IoMT framework for brain magnetic resonance imaging (MRI) analysis to lessen the unavoidable diagnosis and therapy faults that occur in human clinical settings for the accurate detection of cerebral microbleeds (CMBs). The problems in accurate CMB detection include that CMBs are tiny dots 5–10 mm in diameter; they are similar to healthy tissues and are exceedingly difficult to identify, necessitating specialist guidance in remote and underdeveloped medical centers. Secondly, in the existing studies, computer-aided diagnostic (CAD) systems are designed for accurate CMB detection, however, their proposed approaches consist of two stages. Potential candidate CMBs from the complete MRI image are selected in the first stage and then passed to the phase of false-positive reduction. These pre-and post-processing steps make it difficult to build a completely automated CAD system for CMB that can produce results without human intervention. Hence, as a key goal of this work, an end-to-end enhanced UNet-based model for effective CMB detection and segmentation for IoMT devices is proposed. The proposed system requires no pre-processing or post-processing steps for CMB segmentation, and no existing research localizes each CMB pixel from the complete MRI image input. The findings indicate that the suggested method outperforms in detecting CMBs in the presence of contrast variations and similarities with other normal tissues and yields a good dice score of 0.70, an accuracy of 99 %, as well as a false-positive rate of 0.002 %.© 2017 Elsevier Inc. All rights reserved.

Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB Imagery

Mapping and monitoring tree seedlings is essential for reforestation and restoration efforts. However, achieving this on a large scale, especially during the initial stages of growth, when seedlings are small and lack distinct morphological features, can be challenging. An accurate, reliable, and efficient method that detects seedlings using unmanned aerial vehicles (UAVs) could significantly reduce survey costs. In this study, we used an unsupervised approach to map young conifer seedlings utilising spatial, spectral, and structural information from UAV digital aerial photogrammetric (UAV-DAP) point clouds. We tested our method across eight trial stands of radiata pine with a wide height range (0.4–6 m) that comprised a total of ca. 100 ha and spanned diverse site conditions. Using this method, seedling detection was excellent, with an overall precision, sensitivity, and F1 score of 95.2%, 98.0%, and 96.6%, respectively. Our findings demonstrated the importance of combining spatial, spectral, and structural metrics for seedling detection. While spectral and structural metrics efficiently filtered out non-vegetation objects and weeds, they struggled to differentiate planted seedlings from regenerating ones due to their similar characteristics, resulting in a large number of false positives. The inclusion of a row segment detection algorithm overcame this limitation and successfully identified most regenerating seedlings, leading to a significant reduction in false positives and an improvement in overall detection accuracy. Our method generated vector files containing seedling positions and key structural characteristics (seedling height, crown dimensions), offering valuable outputs for precision management. This automated pipeline requires fewer resources and user inputs compared to manual annotations or supervised techniques, making it a rapid, cost-effective, and scalable solution which is applicable without extensive training data. While serving as primarily a standalone tool for assessing forestry projects, the proposed method can also complement supervised seedling detection methods like machine learning, i.e., by supplementing training datasets.

Automatic suppression of false positive alerts in anti-money laundering systems using machine learning

Criminal activities generate an estimated $2 trillion in laundered money per year, highlighting the need for financial institutions to detect and report suspicious activity to protect their reputation. However, rule-based models commonly used for this purpose generate a high number of false positives, draining compliance team time, and increasing investigation costs. However, the application of machine learning in conjunction with rule-based models presents noteworthy implications, encompassing the potential reduction in false positives and the concomitant risk of machine learning inadvertently suppressing true positive alerts. This paper proposes a framework called automatic suppression based on XGBoost for anti-money laundering (ASXAML) to enhance detection by reducing false positives. ASXAML leverages recursive feature elimination with cross-validation for optimal feature selection. Subsequently, Optuna is employed to fine-tune hyperparameters for the XGBoost model. Results indicate that ASXAML achieves an optimal balance between reducing false positives and avoiding missed money laundering events, with an 86% F-beta score and only 11% money laundering customers were incorrectly closed out of 1926 in the test data.

Seeking an optimal approach for Computer-aided Diagnosis of Pulmonary Embolism

Pulmonary Embolism (PE) represents a thrombus (“blood clot”), usually originating from a lower extremity vein, that travels to the blood vessels in the lung, causing vascular obstruction and in some patients death. This disorder is commonly diagnosed using Computed Tomography Pulmonary Angiography (CTPA). Deep learning holds great promise for the Computer-aided Diagnosis (CAD) of PE. However, numerous deep learning methods, such as Convolutional Neural Networks (CNN) and Transformer-based models, exist for a given task, causing great confusion regarding the development of CAD systems for PE. To address this confusion, we present a comprehensive analysis of competing deep learning methods applicable to PE diagnosis based on four datasets. First, we use the RSNA PE dataset, which includes (weak) slice-level and exam-level labels, for PE classification and diagnosis, respectively. At the slice level, we compare CNNs with the Vision Transformer (ViT) and the Swin Transformer. We also investigate the impact of self-supervised versus (fully) supervised ImageNet pre-training, and transfer learning over training models from scratch. Additionally, at the exam level, we compare sequence model learning with our proposed transformer-based architecture, Embedding-based ViT (E-ViT). For the second and third datasets, we utilize the CAD-PE Challenge Dataset and Ferdowsi University of Mashad’s PE Dataset, where we convert (strong) clot-level masks into slice-level annotations to evaluate the optimal CNN model for slice-level PE classification. Finally, we use our in-house PE-CAD dataset, which contains (strong) clot-level masks. Here, we investigate the impact of our vessel-oriented image representations and self-supervised pre-training on PE false positive reduction at the clot level across image dimensions (2D, 2.5D, and 3D). Our experiments show that (1) transfer learning boosts performance despite differences between photographic images and CTPA scans; (2) self-supervised pre-training can surpass (fully) supervised pre-training; (3) transformer-based models demonstrate comparable performance but slower convergence compared with CNNs for slice-level PE classification; (4) model trained on the RSNA PE dataset demonstrates promising performance when tested on unseen datasets for slice-level PE classification; (5) our E-ViT framework excels in handling variable numbers of slices and outperforms sequence model learning for exam-level diagnosis; and (6) vessel-oriented image representation and self-supervised pre-training both enhance performance for PE false positive reduction across image dimensions. Our optimal approach surpasses state-of-the-art results on the RSNA PE dataset, enhancing AUC by 0.62% (slice-level) and 2.22% (exam-level). On our in-house PE-CAD dataset, 3D vessel-oriented images improve performance from 80.07% to 91.35%, a remarkable 11% gain. Codes are available at GitHub.com/JLiangLab/CAD_PE.

Behavioural Analysis of Deaf and Mute People Using Gesture Detection

Deaf and mute people have unique communication and social challenges that make it hard to express their thoughts, needs, and ideas. Understanding people's behavior is more important to protect them and help them integrate into society. This study discusses the critical need for behavioral analysis on deaf and mute people and introduces the Automatic Behavioral Analysis Employing Gesture Detection Framework (ABA-GDF). Gesture detection technology has gained popularity recently. This emphasis may be due to its ability to overcome communication hurdles and illuminate nonverbal communication. Current methods have various challenges, including limited accuracy and adaptability. The ABA-GDF architecture comprises three phases: dataset collection, modeling, and deployment. The data collection technique includes hand signals used by deaf and quiet people. The material is then processed to partition and normalize the hand area for consistent analysis. During Modelling, feature descriptor attributes are developed to extract relevant motion information. A classifier learns and predicts using the feature vectors, enabling the framework to recognize and interpret motions and actions. Large-scale simulations of ABA-GDF showed promising results. The ABA-GDF framework achieved 92% gesture recognition accuracy on the dataset. The system's robustness is demonstrated by its capacity to understand non-verbal messages. The research showed a 15% reduction in false positives compared to earlier methods, demonstrating its real-world usefulness.

B-148 Analytical Validation and Performance Characteristics of A Targeted Metagenomics Next-generation Sequencing Respiratory Pathogen ID/AMR Panel

Abstract Background The COVID-19 global pandemic underscored the importance of access to diagnostic testing, broad community surveillance, and genomic analysis of pathogen variants. The dearth of testing in the initial days and months of the pandemic highlighted the need to improve public health infrastructure. The subsequent onset of viral evolution, producing new and functionally different CoV2 strains, increased the importance for the availability and scalability of pathogen genome sequencing and data sharing pipelines through national surveillance programs. As SARS-CoV-2 moves from a pandemic to endemic state, the scientific and medical community must not forget the lessons learned and continue to reinforce the value of ongoing monitoring of circulating pathogens. Methods Aegis Sciences performed an analytical validation of the Respiratory Pathogen ID/AMR Target Enrichment Panel (RPIP, Illumina RUO), a next-generation sequencing assay that uses target capture-based enrichment for detection, quantification, and characterization of 282 viral, bacterial, and fungal respiratory pathogens and over 2000 antimicrobial resistance (AMR) genes. A total of 1598 validation samples were sequenced via the NextSeq 550 Dx (Illumina) and demultiplexed and assembled FASTQ files were analyzed with Explify RPIP Analysis application in BaseSpace Sequencing Hub (Illumina). Samples tested were contrived specimens using 60 different pathogen isolates various concentrations and clinical comparative samples, and the study included the evaluation of concentration vs genome coverage, inclusivity, exclusivity, and orthogonal analyses. Results RPIP is a highly sensitive, robust sequencing assay that can detect organisms at very low concentrations. Evaluation of copy number vs genome coverage revealed that 53 out of 60 organisms were detected at 1 copy/µL (PPV = 86.67%), and 60 out of 60 were detected at 10 copies/µL (PPV = 98.33%) and 50 copies/µL (PPV = 96.67%). The average coverage across the genome improved with increasing concentration and was 59.97% at 1 copy/µL, 72.45% at 10 copies/µL, and >90% at 50 copies/µL. Inclusivity and exclusivity studies revealed an increase in false positives at low concentrations (1 copy/µL = 35.11%) and a reduction of false positives at higher concentrations (10 copies/µL = 20.3%) of isolates, and higher copy numbers of isolates allow for the true positives to be distinguished from contaminants and off-target organisms with very low coverage and quantification results. Orthogonal studies with upper respiratory clinical specimens tested previously by validated PCR methods revealed the following performance characteristics for respiratory pathogens, including SARS-CoV-2, influenza, parainfluenza, and rhinovirus: PPV = 81.11%, NPV = 99.66%, Sensitivity = 98.46%, and Specificity = 93.89%. Conclusions Completion of these studies demonstrated that next-generation sequencing is a cost effective, high-throughput option for broad pathogen tracking and surveillance. Laboratories, like Aegis, must continue to leverage collaborative relationships with public and private sector entities to expand resources, foster innovation, and broaden capabilities to quickly respond to biological threats.

A low complexity binary-weighted energy disaggregation framework for residential electricity consumption

The discipline of Non-Intrusive Load Monitoring (NILM) has witnessed a surge in the application of machine learning and pattern recognition approaches, enabling researchers to investigate NILM problems. This paper introduces a novel energy disaggregation system that employs a binary-weight matrix to separate the power consumption into distinct signal patterns. The framework includes filtering techniques, followed by event detection and energy disaggregation. To address the challenges of event detection, a regional threshold-based algorithm is developed, eliminating the need for predefined thresholds. A comprehensive complexity analysis of the developed algorithms reveals a reduced computational complexity, making the framework suitable for real-time deployment. For performance assessment, the Reference Energy Disaggregation dataset (REDD) and Energy Monitoring via Building Electricity Disaggregation dataset (EMBED) are utilized. A frequency of 1 Hz is maintained to ensure accurate evaluation. The proposed event detection algorithm achieves a precision of 92.5% and an f1-score of 73.6% on EMBED data, improving average precision by 23.5% and a substantial reduction in false positives compared to an existing method. The energy disaggregation algorithm separates the power consumption of four devices in 15.6 s and the entire framework (filtering, event detection, and energy disaggregation) takes 15.9 s for execution, all achieved using a semi-supervised training-less approach.

Multiscale entropy analysis of single lead ECG and ECG derived respiration for AI based prediction of sleep apnea events

Sleep apnea (SA) is a prevalent sleep disorder that affects a significant portion of the adult population. The proposed method involves coarse graining a signal at different scales, using the popular multiscale entropy algorithms to detect apnea and normal events from single lead Electrocardiography (ECG), Instantaneous Heart Rate and ECG derived respiration. The idea of nonlinear dynamical systems analysis for feature extraction along with machine learning approach, the authors present here a moderately accurate sleep apnea detection model with an accuracy ranging from 70% to 100% based on two different probabilistic thresholds of 50 % and 70% with reduction in false positive rate from 28% to 14 % for applications in development of AI based IoT connected smart wearable devices. The two thresholding modes offer a choice to do a trade-off between high training accuracy with high false positive rate and low accuracy with low false positive rate. The performance metrics of each model have been reported and choice is made for best suitable model with prospectives of implementation for diagnostic purposes. The effectiveness of the proposed method in accurate detection of sleep apnea requires further validation of the models with out of distribution dataset.

Signatures of Extreme Longevity: A Perspective from Bivalve Molecular Evolution.

Among Metazoa, bivalves have the highest lifespan disparity, ranging from 1 to 500+ years, making them an exceptional testing ground to understand mechanisms underlying aging and the evolution of extended longevity. Nevertheless, comparative molecular evolution has been an overlooked approach in this instance. Here, we leveraged transcriptomic resources spanning 30 bivalve species to unravel the signatures of convergent molecular evolution in four long-lived species: Margaritifera margaritifera, Elliptio complanata, Lampsilis siliquoidea, and Arctica islandica (the latter represents the longest-lived noncolonial metazoan known so far). We applied a comprehensive approach-which included inference of convergent dN/dS, convergent positive selection, and convergent amino acid substitution-with a strong focus on the reduction of false positives. Genes with convergent evolution in long-lived bivalves show more physical and functional interactions to each other than expected, suggesting that they are biologically connected; this interaction network is enriched in genes for which a role in longevity has been experimentally supported in other species. This suggests that genes in the network are involved in extended longevity in bivalves and, consequently, that the mechanisms underlying extended longevity are-at least partially-shared across Metazoa. Although we believe that an integration of different genes and pathways is required for the extended longevity phenotype, we highlight the potential central roles of genes involved in cell proliferation control, translational machinery, and response to hypoxia, in lifespan extension.

A Hybrid Cluster Variational Autoencoder Model for Monitoring the Multimode Blast Furnace System

Efficient monitoring of the blast furnace system is crucial for maintaining high production efficiency and ensuring product quality. This article introduces a hybrid cluster variational autoencoder model for monitoring the blast furnace ironmaking process which exhibits multimode behaviors. In contrast to traditional approaches, this method utilizes neural networks to learn data features and effectively handles the diverse feature types observed in different production modes. Through the utilization of a clustering process within the hidden layer of the variational autoencoder, the proposed technique facilitates efficient fault detection in the context of multimodal blast furnace data. Based on the variational autoencoder model, this study further establishes a unified monitoring index and defines a method for computing the control limits. The application of the model to real blast furnace data reveals its proficiency in accurately identifying faults across diverse modes; compared with the probabilistic principal component analysis based on the local nearest neighbor standardization method and the recursive probabilistic principal component analysis, the model shows a reduction in false positives by up to 10.3% and a substantial reduction of 19.2% in the missed detection rate. This method achieves a remarkable false detection rate of only 0.2% and 0 instances of missed detection.

Early and repeated screening detects children with persistent attention-deficit/hyperactivity disorder

Preschool screening of attention-deficit/hyperactivity disorder (ADHD) has been found too inaccurate to be clinically useful. This may be due to the known instability of ADHD symptoms from preschool onwards, and the use of a single screening only. We hypothesized that by identifying a group of children with persistent ADHD from preschool to school age and repeating the screening, the clinical usefulness of screening would increase. This study is part of the prospective longitudinal, population-based Norwegian Mother, Father and Child Cohort Study, with a diagnostic parent interview at 3.5 years and follow-up with parent questionnaires at ages 5 and 8 years (n = 707). We identified a group classified with ADHD at all three time points (persistent ADHD). We then used the Child Behavior Checklist ADHD DSM-oriented scale at ages 3.5 and 5 years to investigate the accuracies of single- and two-stage screening at different thresholds to identify children with persistent ADHD. About 30% of the children were classified with ADHD at least once across time (at ages 3.5, 5, and/or 8 years), but only 4% (n = 30) had persistent ADHD. At all thresholds, the two-stage screening identified children with persistent ADHD more accurately than single screening, mainly due to a substantial reduction in false positives. Only a small group of children were classified with persistent ADHD from preschool to school age, underlining that future screening studies should distinguish this group from those with fluctuating symptoms when estimating screening accuracies. We recommend a two-stage screening process to reduce false positives.

Reduction of False Positives for Runtime Errors in C/C++ Software: A Comparative Study

In software development, early defect detection using static analysis can be performed without executing the source code. However, defects are detected on a non-execution basis, thus resulting in a higher ratio of false positives. Recently, studies have been conducted to effectively perform static analyses using machine learning (ML) and deep learning (DL) technologies. This study examines the techniques for detecting runtime errors used in existing static analysis tools and the causes and rates of false positives. It analyzes the latest static analysis technologies that apply machine learning/deep learning to decrease false positives and compares them with existing technologies in terms of effectiveness and performance. In addition, machine-learning/deep-learning-based defect detection techniques were implemented in experimental environments and real-world software to determine their effectiveness in real-world software.

Novel algorithms improve arrhythmia detection accuracy in insertable cardiac monitors.

Insertable cardiac monitors (ICMs) are commonly used to diagnose cardiac arrhythmias. False detections in the latest ICM systems remain an issue, primarily due to inaccurate R-wave sensing. New discrimination algorithms were developed and tested to reduce false detections of atrial fibrillation (AF), pause, and tachycardia episodes in ICMs. Stored electrograms (EGMs) of AF, pause, and tachycardia episodes detected by Abbott Confirm Rx™ ICMs were extracted from the Merlin.net™ Patient Care Network, and manually adjudicated to establish independent training and testing datasets. New discrimination algorithms were developed to reject false episodes due to inaccurate R-wave sensing, P-wave identification, and R-R interval patterns. The performance of these new algorithms was quantified by false positive reduction (FPR) and true positive maintenance (TPM), relative to the existing algorithms. The new AF detection algorithm was trained on 5911 EGMs from 744 devices, resulting in 66.9% FPR and 97.8% TPM. In the testing data set of 1354 EGMs from 119 devices, this algorithm achieved 45.8% FPR and 97.0% TPM. The new pause algorithm was trained on 7178 EGMs from 1490 devices, resulting in 70.9% FPR and 98.7% TPM. In the testing data set of 1442 EGMs from 340 devices, this algorithm achieved 74.4% FPR and 99.3% TPM. The new tachycardia algorithm was trained on 520 EGMs from 204 devices, resulting in 57.0% FPR and 96.6% TPM. In the testing data set of 459 EGMs from 237 devices, this algorithm achieved 57.9% FPR and 96.5% TPM. The new algorithms substantially reduced false AF, pause, and tachycardia episodes while maintaining the majority of true arrhythmia episodes detected by the Abbott ICM algorithms that exist today. Implementing these algorithms in the next-generation ICM systems may lead to improved detection accuracy, in-clinic efficiency, and device battery longevity.