Low False Positive Rate Research Articles

MULTI-BLOCK: A novel ML-based intrusion detection framework for SDN-enabled IoT networks using new pyramidal structure

The ever-expanding Internet of Things (IoT) landscape faces significant security challenges due to limitations in traffic monitoring, device heterogeneity, and weak security practices, leaving networks vulnerable to multi-target and coordinated attacks like large-scale botnets and Distributed Denial-of-Service (DDoS). Existing intrusion detection systems can be computationally expensive and resource-intensive. This can be problematic for resource-constrained IoT devices with limited processing power, memory, and battery life. This paper proposes MULTI-BLOCK, a novel, multi-module framework that leverages machine learning, stateful P4 processing, and a Software-Defined Networking (SDN)-based multi-controller architecture. MULTI-BLOCK tackles critical management tasks within IoT networks, including synchronized communication, traffic monitoring, intrusion detection, and attack mitigation. This comprehensive framework comprises four modules. The first, the proposed pyramidal conceptually decentralized multi-controller structure (PCDMCS), introduces Decentralized Control Interfaces (DCIs) for real-time threat identification through a Decentralized Warning Conduit (DWC). The second module provides comprehensive network monitoring using P4-enabled 24-state tables. The third module leverages 30 new P4-extracted/calculated features and the Enhanced Weighted Ensemble Algorithm (EWEA) for enhanced anomaly detection. The final module presents a novel mitigation approach with 22 steps distributed across multiple controllers for scalability. Extensive evaluation using established IoT datasets (X-IIoTID, TON_IoT, and Edge-IIoTset) and diverse test scenarios (including single-victim and multi-victim attacks) demonstrates MULTI-BLOCK's exceptional performance, achieving high accuracy (99.75 %), precision (99.32 %), F1-score (99.53 %), recall (99.67 %), specificity (99.60 %), low false positive rates (FPR) (0.40 %), and low Average Detection Time (ADT) (2.11 ms). By offering a robust and adaptable solution against evolving threats, MULTI-BLOCK represents a significant advancement in IoT network security.

Revolutionizing Cybersecurity with Machine Learning: A Comprehensive Review and Future Directions

In the realm of computing, data science has revolutionized cybersecurity operations and technologies. The key to creating automated and intelligent security systems lies in extracting patterns or insights from cybersecurity data and building data-driven models. Data science, encompassing various scientific approaches, machine learning techniques, processes, and systems, studies real-world occurrences through data analysis. Machine learning techniques, known for their flexibility, scalability, and adaptability to new and unknown challenges, have been applied across many scientific fields. Cybersecurity is rapidly expanding due to significant advancements in social networks, cloud and web technologies, online banking, mobile environments, smart grids, and more. Various machine learning techniques have effectively addressed a wide range of computer security issues. This article reviews several machine learning applications in cybersecurity, including phishing detection, network intrusion detection, keystroke dynamics authentication, cryptography, human interaction proofs, spam detection in social networks, smart meter energy consumption profiling, and security concerns associated with machine learning techniques themselves. The methodology involves collecting a large dataset of phishing and legitimate instances, extracting relevant features such as email headers, content, and URLs, and training a machine learning model using supervised learning algorithms. These models can effectively identify phishing emails and websites with high accuracy and low false positive rates. To enhance phishing detection, it is recommended to continuously update the training dataset to include new phishing techniques and employ ensemble methods that combine multiple machine learning models for improved performance

Longitudinal method comparison: modeling polygenic risk for post-traumatic stress disorder over time in individuals of African and European ancestry.

Cross-sectional data allow the investigation of how genetics influence health at a single time point, but to understand how the genome impacts phenotype development, one must use repeated measures data. Ignoring the dependency inherent in repeated measures can exacerbate false positives and requires the utilization of methods other than general or generalized linear models. Many methods can accommodate longitudinal data, including the commonly used linear mixed model and generalized estimating equation, as well as the less popular fixed-effects model, cluster-robust standard error adjustment, and aggregate regression. We simulated longitudinal data and applied these five methods alongside naïve linear regression, which ignored the dependency and served as a baseline, to compare their power, false positive rate, estimation accuracy, and precision. The results showed that the naïve linear regression and fixed-effects models incurred high false positive rates when analyzing a predictor that is fixed over time, making them unviable for studying time-invariant genetic effects. The linear mixed models maintained low false positive rates and unbiased estimation. The generalized estimating equation was similar to the former in terms of power and estimation, but it had increased false positives when the sample size was low, as did cluster-robust standard error adjustment. Aggregate regression produced biased estimates when predictor effects varied over time. To show how the method choice affects downstream results, we performed longitudinal analyses in an adolescent cohort of African and European ancestry. We examined how developing post-traumatic stress symptoms were predicted by polygenic risk, traumatic events, exposure to sexual abuse, and income using four approaches-linear mixed models, generalized estimating equations, cluster-robust standard error adjustment, and aggregate regression. While the directions of effect were generally consistent, coefficient magnitudes and statistical significance differed across methods. Our in-depth comparison of longitudinal methods showed that linear mixed models and generalized estimating equations were applicable in most scenarios requiring longitudinal modeling, but no approach produced identical results even if fit to the same data. Since result discrepancies can result from methodological choices, it is crucial that researchers determine their model a priori, refrain from testing multiple approaches to obtain favorable results, and utilize as similar as possible methods when seeking to replicate results.

Clinical implementation of first trimester screening for congenital heart defects.

To examine the feasibility and performance of implementing a standardized fetal cardiac scan at the time of a routine first-trimester ultrasound scan. A retrospective, single-center study in an unselected population between March 2021 and July 2022. A standardized cardiac scan protocol consisting of a four-chamber and 3-vessel trachea view with color Doppler was implemented as part of the routine first-trimester scan. Sonographers were asked to categorize the fetal heart anatomy. Data were stratified into two groups based on the possibility of evaluating the fetal heart. The influence of maternal and fetal characteristics and the detection of major congenital heart disease were investigated. A total of 5083 fetuses were included. The fetal heart evaluation was completed in 84.9%. The proportion of successful scans increased throughout the study period from 76% in the first month to 92% in the last month. High maternal body mass index and early gestational age at scan significantly decreased the feasibility. The first-trimester detection of major congenital heart defects was 7/16, of which four cases were identified by the cardiac scan protocol with no false-positive cases. First-trimester evaluation of the fetal heart by a standardized scan protocol is feasible to implement in daily practice. It can contribute to the earlier detection of congenital heart defects at a very low false positive rate.

Automated detection and tracking of photovoltaic modules from 3D remote sensing data

This study addresses the growing demand for increased performance and reliability of photovoltaic (PV) installations by developing innovative monitoring technologies. The strategy consists of flying an unmanned aerial vehicle (UAV) equipped with a dual camera (RGB and thermal) over the PV plant of interest, followed by the generation of photogrammetric 3D models derived from the overlapped aerial images. The resulting datasets involve orthoimages and point clouds by processing RGB and thermal imagery. The key contribution of this study is twofold: (1) the thermal image mapping on dense and high-resolution point clouds that represent the status and geometry of PV solar modules, and (2) the automatic identification of individual solar panels in 3D space and their thermal characterization along their oriented surface. Then, the vector layer of each PV panel is projected onto the 3D thermal point cloud to extract the thermal values associated with each panel. To evaluate the capability of the proposed method, it was replicated in different scenarios, considering rural and urban environments with different light conditions and PV structures. The results demonstrate the robustness of our method, which achieves a remarkably high detection rate, around 99.12% of true positives, and a low false positive rate, close to 0.88%. Consequently, this method means an advance over previous work by proposing a comprehensive and automated solution for individual and highly detailed monitoring of each solar panel from 3D remotely sensed data. This study opens up new frontier research related to real-time monitoring of photovoltaic modules, an inspection of solar photovoltaic cells, the simulation of solar resources and forecasting, the development of digital twins, solar radiation modelling, and analysis of modular floating solar farms under wave motion.

Real-Time Navigation Roads: Lightweight and Efficient Convolutional Neural Network (LE-CNN) for Arabic Traffic Sign Recognition in Intelligent Transportation Systems (ITS)

Smart cities are now embracing the new frontier of urban living, with advanced technology being used to enhance the quality of life for residents. Many of these cities have developed transportation systems that improve efficiency and sustainability, as well as quality. Integrating cutting-edge transportation technology and data-driven solutions improves safety, reduces environmental impact, optimizes traffic flow during peak hours, and reduces congestion. Intelligent transportation systems consist of many systems, one of which is traffic sign detection. This type of system utilizes many advanced techniques and technologies, such as machine learning and computer vision techniques. A variety of traffic signs, such as yield signs, stop signs, speed limits, and pedestrian crossings, are among those that the traffic sign detection system is trained to recognize and interpret. Ensuring accurate and robust traffic sign recognition is paramount for the safe deployment of self-driving cars in diverse and challenging environments like the Arab world. However, existing methods often face many challenges, such as variability in the appearance of signs, real-time processing, occlusions that can block signs, low-quality images, and others. This paper introduces an advanced Lightweight and Efficient Convolutional Neural Network (LE-CNN) architecture specifically designed for accurate and real-time Arabic traffic sign classification. The proposed LE-CNN architecture leverages the efficacy of depth-wise separable convolutions and channel pruning to achieve significant performance improvements in both speed and accuracy compared to existing models. An extensive evaluation of the LE-CNN on the Arabic traffic sign dataset that was carried out demonstrates an impressive accuracy of 96.5% while maintaining superior performance with a remarkably low inference time of 1.65 s, crucial for real-time applications in self-driving cars. It achieves high accuracy with low false positive and false negative rates, demonstrating its potential for real-world applications like autonomous driving and advanced driver-assistance systems.

Enhancing kidney disease prediction with optimized forest and ECG signals data

To improve the early detection of Chronic Kidney Disease (CKD) utilizing electrocardiogram (ECG) data, this study explores the use of the Optimized Forest (Opt-Forest) model. Exploiting the possible relationship between kidney function and ECG data, we investigate Opt-Forest's performance in comparison to popular machine learning (ML) models. We evaluate Opt-Forest and find that it outperforms other options in CKD prediction based on many measures such as classification accuracy (CA), false positive rate (FPR), and true positive rate (TPR). In comparison to previous models, Opt-Forest has superior sensitivity and specificity, with a TPR of 0.787 and a low FPR of 0.174. With an accuracy of 78.68 %, a KS of 0.641, and a low RMSE of 0.174, Opt-Forest also demonstrates robustness in CKD prediction. This study demonstrates the potential of Opt-Forest to improve patient outcomes and medical diagnostics, as well as the usefulness of ECG data in enhancing early CKD diagnosis. Prospective research avenues to advance precision medicine in nephrology involve investigating deep learning methodologies and incorporating patient-specific data.

Non-invasive cell-free DNA prenatal screening for trisomy 21 as part of primary screening strategy in twin pregnancy.

The performance of non-invasive prenatal screening using cell-free DNA testing of maternal blood in twin pregnancy is underevaluated, while serum marker-based strategies yield poor results. This study aimed to assess the performance of non-invasive prenatal screening for trisomy 21 in twin pregnancy as a first-tier test. Secondary objectives were to assess its failure rate and factors associated with failure. This retrospective cohort study included twin pregnancies in which non-invasive prenatal screening using cell-free DNA was performed as the primary screening strategy between May 2017 and October 2019. We used the NIPT VeriSeq® test for in-vitro diagnosis and set a fetal fraction cut-off of 4% for monochorionic pregnancies and 8% for dichorionic ones. Clinical data and pregnancy outcome were collected from physicians or midwives via a questionnaire or were retrieved directly on-site. We calculated the performance of non-invasive cell-free DNA screening for trisomy 21, analyzed its failure rate and assessed potentially associated factors. Among 1885 twin pregnancies with follow-up, there were six (0.32%) confirmed cases of trisomy 21. The sensitivity of non-invasive prenatal screening for trisomy 21 was 100% (95% CI, 54.1-100%) and the false-positive rate was 0.23% (95% CI, 0.06-0.59%). The primary failure rate was 4.6%, with 4.0% being due to insufficient fetal fraction. A successful result was obtained for 65.4% of women who underwent a new blood draw, reducing the overall failure rate to 2.8%. Maternal body mass index, gestational age at screening as well as chorionicity were significantly associated with the risk of failure. This study provides further evidence of the high performance, at an extremely low false-positive rate, of non-invasive prenatal screening in twins as part of a primary screening strategy for trisomy 21. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Advancing face detection efficiency: Utilizing classification networks for lowering false positive incidences

The advancement of convolutional neural networks (CNNs) has markedly progressed in the field of face detection, significantly enhancing accuracy and recall metrics. Precision and recall remain pivotal for evaluating CNN-based detection models; however, there is a prevalent inclination to focus on improving true positive rates at the expense of addressing false positives. A critical issue contributing to this discrepancy is the lack of pseudo-face images within training and evaluation datasets. This deficiency impairs the regression capabilities of detection models, leading to numerous erroneous detections and inadequate localization. To address this gap, we introduce the WIDERFACE dataset, enriched with a considerable number of pseudo-face images created by amalgamating human and animal facial features. This dataset aims to bolster the detection of false positives during training phases. Furthermore, we propose a new face detection architecture that incorporates a classification model into the conventional face detection model to diminish the false positive rate and augment detection precision. Our comparative analysis on the WIDERFACE and other renowned datasets reveals that our architecture secures a lower false positive rate while preserving the true positive rate in comparison to existing top-tier face detection models.

Reinventing Web Security: An Enhanced Cycle-Consistent Generative Adversarial Network Approach to Intrusion Detection

Web3.0, as the link between the physical and digital domains, faces increasing security threats due to its inherent complexity and openness. Traditional intrusion detection systems (IDSs) encounter formidable challenges in grappling with the multidimensional and nonlinear traffic data characteristic of the Web3.0 environment. Such challenges include insufficient samples of attack data, inadequate feature extraction, and resultant inaccuracies in model classification. Moreover, the scarcity of certain traffic data available for analysis by IDSs impedes the system’s capacity to document instances of malicious behavior. In response to these exigencies, this paper presents a novel approach to Web3.0 intrusion detection, predicated on the utilization of cycle-consistent generative adversarial networks (CycleGANs). Leveraging the data transformation capabilities of its generator, this method facilitates bidirectional conversion between normal Web3.0 behavioral data and potentially intrusive behavioral data. This transformative process not only augments the diversity and volume of recorded intrusive behaviors but also clandestinely simulates various attack scenarios. Furthermore, through fostering mutual competition and learning between the discriminator and generator, the approach enhances the ability to discern the defining characteristics of potential intrusive behaviors, thereby bolstering the accuracy of intrusion detection. To substantiate the efficacy of the CycleGAN-based intrusion detection method, simulation experiments were conducted utilizing public datasets, including KDD CUP 1999 (KDD), CIC-DDOS2019, CIC-IDS2018, and SR-BH 2020. The experimental findings evince the method’s remarkable accuracies across the four datasets, attaining rates of 99.81%, 97.79%, 89.25%, and 95.15%, respectively, while concurrently maintaining low false-positive rates. This research contributes novel insights and methodologies toward the advancement of Web3.0 intrusion detection through the application of CycleGAN technology, which is poised to play a pivotal role in fortifying the security landscape of Web3.0.

Deepfake Face Detection Using Machine Learning with LSTM

Deep fake videos, which employ artificial intelligence to manipulate and generate highly convincing fake content, have emerged as a significant threat to society, potentially undermining trust in visual media. Detecting these deceptive videos is outmost importance to combat the spread of misinformation and protect the integrity of digital media. In this study, we propose a novel approach for deep fake face video detection utilizing Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN). Our approach capitalizes on the temporal patterns and context within video sequences, harnessing the unique strengths of LSTM in capturing sequential information. We demonstrate the effectiveness of our methodology by training the LSTM network on a diverse dataset comprising both real and deep fake videos. The network’s ability to learn temporal dependencies and identify inconsistencies in facial expressions, eye movements, and other subtle cues allows it to distinguish between genuine and manipulated content. To further enhance the accuracy and robustness of our deep fake face detection system, we integrate pre-processing techniques for frame- level analysis, such as optical flow computation and facial landmarks extraction. Additionally, we employ a comprehensive ensemble of LSTM models and other machine learning algorithms to improve the overall detection performance. In our experiments, we evaluate the LSTM-based deep fake detection system on a large-scale dataset of both known and unseen deep fake videos, achieving high detection accuracy and low false positive rates. We also compare our approach with existing methods, demonstrating its superiority in terms of robustness and generalization. The results of this study signify the potential of LSTM-based models for mitigating the adverse effects of deep fake content on society. As deep fake technology continues to evolve, our approach showcases a promising step towards combating the dissemination of deceptive multimedia, promoting media integrity, and upholding trust in visual information. Keywords: LSTM Networks, Recurrent Neural Network, Optical flow computation, Facial landmarks extraction, False positive rates.

Phishing Email Detection using Machine Learning

The increasing sophistication of phishing attacks poses a significant threat to cybersecurity, demanding advanced and adaptive detection mechanisms. This project focuses on the development and implementation of a phishing detection system leveraging machine learning algorithms. The objective is to enhance the security measures for users by employing a robust and intelligent system capable of identifying and thwarting phishing attempts. The project involves the collection and curation of diverse datasets containing examples of phishing and legitimate communication. Supervised learning techniques will be employed to train the machine learning model, utilizing features such as email content, sender information, and website attributes. The model's training will be continuously refined to adapt to emerging phishing tactics and enhance its accuracy. Additionally, unsupervised learning methods will be explored to detect novel phishing patterns and anomalies that may not be present in the training dataset. Clustering algorithms will assist in grouping similar instances, aiding the identification of previously unseen phishing techniques. The implementation will be evaluated through extensive testing using real-world datasets, measuring the system's effectiveness in detecting phishing attempts with a low false-positive rate. The project aims to contribute to the field of cybersecurity by providing a proactive and adaptive solution to counter the evolving nature of phishing threats. The successful implementation of this phishing detection system will enhance user confidence in online interactions and contribute to the overall resilience of digital ecosystems. Key Words: Phishing attacks, Cybersecurity, Detection mechanisms, Machine learning algorithms, Supervised learning, Unsupervised learning, Email content analysis, Sender information, Website attributes, Training dataset, Real-world datasets, False-positive rate, Proactive cybersecurity, Adaptive solutions, Digital ecosystems.

Fatigue Driving Detection Based on Driver Facial Temporal Sequences

Addressing the issues of low real-time performance and high false positive rates in driver fatigue detection methods based on deep learning, this paper proposes a temporal sequence Transformer-based fatigue detection method grounded in the localization of facial landmarks in drivers. Initially, the facial positions are obtained using the single-stage face detection algorithm RetinaFace. Subsequently, a lightweight GM module is designed as the principal feature extraction module for constructing a multi-scale fusion facial landmark detection network, and facial fatigue feature parameters based on temporal sequences are calculated according to the facial landmarks. Finally, a fatigue driving classification method based on temporal sequences Transformers is developed for classifying the sequences of fatigue feature parameters. Experimental results demonstrate that the inference time required for facial detection and landmark detection is merely 16.8 milliseconds, with the per-frame inference time for facial landmark detection being only 2.5 milliseconds, thus fulfilling the real-time requirements of fatigue driving detection during the feature extraction phase. A temporal sequence of fatigue feature parameters built on the NTHU-DDD dataset and the trained temporal sequence Transformer model resulted in an accuracy rate of 91.4% for the proposed method.

Computer-aided urban energy systems cyber attach detection and mitigation: Intelligence hybrid machine learning technique for security enhancement of smart cities

This paper introduces a sophisticated computer-aided system for enhancing the security of smart cities through urban cyber attack detection and mitigation. The proposed system employs a comprehensive mathematical framework that models the dynamics of cyber attacks, detection, and mitigation, capturing the intricate relationships within a smart city environment. Leveraging a hybrid approach combining Transfer Learning and Meta-Learning, the system adapts to evolving threats and tasks, showcasing superior performance in comparison to standalone methods. Simulation results demonstrate the system’s robustness, with low False Positive and False Negative Rates, high System Security, and effective Mitigation Strategies. This research contributes a state-of-the-art solution for securing smart cities, leveraging intelligent hybrid machine learning techniques.

Development of a Real-time Force-based Algorithm for Infusion Failure Detection.

Continuous subcutaneous insulin infusion (CSII) is a common treatment option for people with diabetes (PWD), but insulin infusion failures pose a significant challenge, leading to hyperglycemia, diabetes burnout, and increased hospitalizations. Current CSII pumps' occlusion alarm systems are limited in detecting infusion failures; therefore, a more effective detection method is needed. We conducted five preclinical animal studies to collect data on infusion failures, utilizing both insulin and non-insulin boluses. Data were captured using in-line pressure and flow rate sensors, with additional force data from CSII pumps' onboard sensors in one study. A novel classifier model was developed using this dataset, aimed at detecting different types of infusion failures through direct utilization of force sensor data. Performance was compared against various occlusion alarm thresholds from commercially available CSII pumps. The testing dataset included 251 boluses. The Bagging classifier model showed the highest performance metrics among the models tested, exhibiting high accuracy (96%), sensitivity (94%), and specificity (98%), with lower false-positive and false-negative rate compared with traditional occlusion alarm pressure thresholds. Our study developed a novel non-threshold classifier that outperforms current occlusion alarm systems in CSII pumps in detecting infusion failures. This advancement has the potential to reduce the risk of hyperglycemia and hospitalizations due to undetected infusion failures, offering a more reliable and effective CSII therapy for PWD. Further studies involving human participants are recommended to validate these findings and assess the classifier's performance in a real-world setting.

Probabilistic Prediction of Gastrointestinal Ischemia after Cardiothoracic Surgery.

Gastrointestinal ischemia (GIisch) is challenging to diagnose in patients after cardiothoracic surgery. Computed tomography angiography (CTA) carries substantial false-negative and false-positive rates. The aim of the study was to evaluate if a combination of readily available variables improves the diagnosis of GIisch after cardiothoracic surgery. This retrospective study included patients receiving intensive care after cardiothoracic surgery. GIisch was confirmed by surgical and/or endoscopic findings. A GIisch prediction score was developed using the Spiegelhalter-Knill-Jones system in a training cohort then tested in a validation cohort (patients without obvious signs of GIisch on CTA). The training cohort comprised 125 consecutive patients with suspected GIisch in 2008 to 2019, including 85 with confirmed GIisch. CTA, performed in 92 patients, had a high false-negative rate of 17/60 (28%) and a lower false-positive rate of 7/32 (22%). The score included cardiopulmonary bypass, negatively associated with GIisch, and six variables positively associated with GIisch: intraoperative mean arterial pressure < 50 mm Hg, aspartate aminotransferase > 15 N, lactate increase in 24 hour > 20%, and 3 CTA findings, namely, bowel dilation, bowel wall thickening, and mesenteric vasoconstriction. The area under the receiver operating characteristic was 0.82 (95% confidence interval [CI], 0.51-0.93) in the training cohort and 0.82 (95% CI, 0.68-0.96) in the validation cohort (n = 34 patients). Reliability of the predicted probabilities was greatest for probabilities ≤ 30% or ≥ 70%. In patients receiving intensive care after cardiothoracic surgery, GIisch cannot be ruled out based solely on CTA findings. A scoring system combining CTA findings with other variables may improve the diagnosis of GIisch in this population.

Effect of genotyping errors on linkage map construction based on repeated chip analysis of two recombinant inbred line populations in wheat (Triticum aestivum L.)

Linkage maps are essential for genetic mapping of phenotypic traits, gene map-based cloning, and marker-assisted selection in breeding applications. Construction of a high-quality saturated map requires high-quality genotypic data on a large number of molecular markers. Errors in genotyping cannot be completely avoided, no matter what platform is used. When genotyping error reaches a threshold level, it will seriously affect the accuracy of the constructed map and the reliability of consequent genetic studies. In this study, repeated genotyping of two recombinant inbred line (RIL) populations derived from crosses Yangxiaomai × Zhongyou 9507 and Jingshuang 16 × Bainong 64 was used to investigate the effect of genotyping errors on linkage map construction. Inconsistent data points between the two replications were regarded as genotyping errors, which were classified into three types. Genotyping errors were treated as missing values, and therefore the non-erroneous data set was generated. Firstly, linkage maps were constructed using the two replicates as well as the non-erroneous data set. Secondly, error correction methods implemented in software packages QTL IciMapping (EC) and Genotype-Corrector (GC) were applied to the two replicates. Linkage maps were therefore constructed based on the corrected genotypes and then compared with those from the non-erroneous data set. Simulation study was performed by considering different levels of genotyping errors to investigate the impact of errors and the accuracy of error correction methods. Results indicated that map length and marker order differed among the two replicates and the non-erroneous data sets in both RIL populations. For both actual and simulated populations, map length was expanded as the increase in error rate, and the correlation coefficient between linkage and physical maps became lower. Map quality can be improved by repeated genotyping and error correction algorithm. When it is impossible to genotype the whole mapping population repeatedly, 30% would be recommended in repeated genotyping. The EC method had a much lower false positive rate than did the GC method under different error rates. This study systematically expounded the impact of genotyping errors on linkage analysis, providing potential guidelines for improving the accuracy of linkage maps in the presence of genotyping errors.

Feature Importance Analysis and Machine Learning for Alzheimer’s Disease Early Detection: Feature Fusion of the Hippocampus, Entorhinal Cortex, and Standardized Uptake Value Ratio

Introduction: Alzheimer’s disease (AD) is a progressive neurological disorder characterized by mild memory loss and ranks as a leading cause of mortality in the USA, accounting for approximately 120,000 deaths per year. It is also the primary form of dementia. Early detection is critical for timely intervention as the neurodegenerative process often starts 15–20 years before cognitive symptoms manifest. This study focuses on determining feature importance in AD classification using fused texture features from 3D magnetic resonance imaging hippocampal and entorhinal cortex and standardized uptake value ratio (SUVR) derived from positron emission tomography (PET) images. Methods: To achieve this objective, we employed four distinct classifiers (Linear Support Vector Classification, Linear Discriminant Analysis, Logistic Regression, and Logistic Regression Classifier with Stochastic Gradient Descent Learning). These classifiers were used to derive both average and top-ranked importance scores for each feature based on their outputs. Our framework is designed to distinguish between two classes, AD-negative (or mild cognitive impairment stable [MCIs]) and AD-positive (or MCI conversion [MCIc]), using a probabilistic neural network classifier and the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Results: The findings from the feature importance highlight the crucial role of the GLCM texture features extracted from the hippocampus and entorhinal cortex, demonstrating their superior performance compared to the volume and SUVR. GLCM texture AD classification achieved approximately 90% sensitivity in identifying MCIc cases while maintaining low false positives (below 30%) when fused with other features. Moreover, the receiver operating characteristic curves validate the GLCMs’ superior performance in distinguishing between MCIs and MCIc. Additionally, fusing different types of features improved classification performance compared to relying solely on any single feature category. Conclusion: Our study emphasizes the pivotal role of GLCM texture features in early Alzheimer’s detection.

Traffic Rules Violation Detection using Dashcam Footage

Traffic Rules Violation Detection using Dashcam Video Footage offers a novel strategy for improving traffic management and road safety through automated violation identification and reporting. The project's goal is to create a video processing system that can use dashcam data to identify and classify frequent traffic infractions. The system can recognize traffic infractions including speeding, lane changes without signaling, helmet recognition, and instances of triple riding on two-wheelers with high accuracy thanks to its integration of YOLO, OpenCV and RESNET50 classifier. The project also includes functionality for user account management and the implementation of a secure user authentication system. Users can examine and validate complete violation reports generated by the system prior to submission. The outcomes show a low false positive rate, rapid real-time processing, and good detection accuracy. Law enforcement organizations have shown. This initiative is an example of how important technical innovation is to solving societal issues and advancing public safety. Key Words: YOLO (You Only Look Once), OpenCV, ResNet50 (Residual Neural Network), Dashcam Video Footage.

Towards Enhanced Security: An improved approach to Phishing Email Detection

Email phishing assaults remain a widespread catastrophe to individuals and businesses, using human weaknesses to obtain unauthorised access to sensitive information. This research study presents an upgraded email phishing detection system that uses machine learning approaches. To construct a robust and adaptable model, the system includes a complete feature set such as email content analysis, sender reputation, and behavioural patterns. The one that has been proposed uses a new combination of supervised and unsupervised machine learning algorithms to analyse email properties and user behaviour, allowing for the detection of subtle phishing signs. The term of body content analysis, URL analysis, and QR code information are among the features retrieved and analysed utilising advanced natural language processing and pattern recognition algorithms. Novelty lies in the integration of supervised and unsupervised machine learning algorithms to identify subtle phishing indicators, along with advanced natural language processing and pattern recognition algorithms for analyzing email properties. A benchmark dataset is used for the proposed system's validation, and a comparison with other phishing detection techniques shows improved, lower false-positive rates. The results indicate the system's ability to effectively discern phishing emails while minimizing the impact on legitimate communication. The system demonstrates a notable improvement by including a diverse range of features and state-of-the-art machine learning algorithms, which makes it a valuable asset to the cybersecurity toolkit for safeguarding email correspondence.