Robust Detection Research Articles

Genomic background sequences systematically outperform synthetic ones in de novo motif discovery for ChIP-seq data.

Efficient de novo motif discovery from the results of wide-genome mapping of transcription factor binding sites (ChIP-seq) is dependent on the choice of background nucleotide sequences. The foreground sequences (ChIP-seq peaks) represent not only specific motifs of target transcription factors, but also the motifs overrepresented throughout the genome, such as simple sequence repeats. We performed a massive comparison of the 'synthetic' and 'genomic' approaches to generate background sequences for de novo motif discovery. The 'synthetic' approach shuffled nucleotides in peaks, while in the 'genomic' approach selected sequences from the reference genome randomly or only from gene promoters according to the fraction of A/T nucleotides in each sequence. We compiled the benchmark collections of ChIP-seq datasets for mouse, human and Arabidopsis, and performed de novo motif discovery. We showed that the genomic approach has both more robust detection of the known motifs of target transcription factors and more stringent exclusion of the simple sequence repeats as possible non-specific motifs. The advantage of the genomic approach over the synthetic approach was greater in plants compared to mammals. We developed the AntiNoise web service (https://denovosea.icgbio.ru/antinoise/) that implements a genomic approach to extract genomic background sequences for twelve eukaryotic genomes.

DriverDetector: An R package providing multiple statistical methods for cancer driver genes detection and tools for downstream analysis

Identifying driver genes in cancer is a difficult task because of the heterogeneity of cancer as well as the complex interactions among genes. As sequencing data become more readily available, there is a growing need for detecting cancer driver genes based on statistical and mathematical modeling methods. Currently, plenty of driver gene identification algorithms have been published, but they fail to achieve consistent results. In order to obtain gene sets with high confidence, we present DriverDetector, an R package providing a convenient workflow for cancer driver genes detection and downstream analysis. We develop the background mutation rate calculating module based on the distance between genes in covariate space and binomial test, followed by the driver gene selection module which integrates 11 methods, including two already recognized approaches, a de novo method, and five variants of Fisher's method which are applied to driver gene identification for the first time. Through verification on 12 TCGA datasets, each method is able to identify a set of confirmed driver genes while the number of resulting genes vary significantly across different methods. For robust driver genes detection, a voting strategy based on 10 of the statistical methods is further applied. Results show that the collective prediction based on the voting strategy demonstrates superiority in achieving the consistency of prediction while ensuring a reasonable number of predicted genes and confirmed drivers. By comparing the results of each cancer dataset, we also find that sample size has a huge impact on the number of predicted genes. For downstream analysis, DriverDetector automatically generates plenty of plots and tables to elaborate the results. We propose DriverDetector as a user-friendly tool promoting early diagnosis of cancer and the development of targeted drugs.

A Rapid PCR-Based Diagnostic Method for Skin Infection with Mycobacterium marinum.

The increasing incidence of chronic skin infections caused by Mycobacterium marinum, coupled with the time-consuming and low detection rates nature of traditional culture and histological-based diagnostic methods, underscores the need for an expedited approach. The study aims to develop a rapid and efficient method for detecting M. marinum with PCR technology. We designed four pairs of primers based on DNA sequences from GeneBank and prior studies, we utilized both PCR and Real-time PCR to identify M. marinum. Specificity and sensitivity assessments were conducted in vitro by DNAs extracted from M. marinum and other bacterial or fungal cultures. Further validation was performed through the implementation of a mouse skin infection model to optimize and confirm the efficacy of the detection method in both fresh and paraffin-embedded skin tissues. The same PCR testing system was further confirmed with paraffin-embedded skin tissues samples from patients as well. The results of the study indicate promising outcomes for the four-pair primers system. It demonstrated 100% sensitivity in detecting M. marinum from purified cultures, including typical strains and nine clinical isolates, while achieving a specificity of 100%. This specificity was evidenced by the absence of PCR products from 12 bacterial species, 12 fungi species, and six other non-tuberculous mycobacterium (NTM) species. In the animal model, the PCR assay exhibited high detection efficacy for both infected fresh tissues and paraffin-embedded tissues, with a slight superiority observed in fresh tissues. However, the PCR assay exhibited high detection efficacy for clinical paraffin-embedded tissues. These findings collectively underscore the robust detection capabilities of our four-pair primers in both in vitro and in vivo settings. A sensitive and highly specific rapid detection system has been successfully developed that can be used to detect M. marinum in both infected fresh tissues and paraffin-embedded tissues.

Acquiring a Machine Learning Data Set for Structural Health Monitoring of Hydrogen Pressure Vessels at Operating Conditions using Guided Ultrasonic Waves

Hydrogen is an energy source of increasing importance. As hydrogen is very reactive to air and needs to be stored under high pressure, it is crucial to provide safe transportation and storage. Therefore, structural health monitoring, based on guided ultrasonic waves and machine learning methods, is used for Composite Overwrapped Pressure Vessels (COPVs) containing hydrogen. To acquire data that allows robust detection of COPV defects, there are two main process parameters to consider. These are the pressurization of the vessel and the temperature conditions at the vessel. This paper will focus on the derivation of a design of experiment (DoE) from the needs of various validation scenarios (e.g. concerning pressure, temperature or excitation frequency). Practical limitations must be considered as well. We designed experiments with multiple reversible damages at different positions. A network of 25 transducers, structured as five rings with five sensors in one line, is installed on a vessel. Guided ultrasonic waves are used via the pitch-catch procedure, which means that the transducers act pairwise as transmitter and receiver in order to measure all transmitterreceiver combinations. This leads to 600 signal paths, recorded by a Verasonics Vantage 64 LF data acquisition system. Finally, the influences of temperature and pressure within the acquired data set are going to be visualized.

Intrusion Detection System to Secure a Network using ACNN Model and Machine Learning

As cyber threats continue to evolve in sophistication and diversity, the need for robust Intrusion Detection Systems (IDS) becomes paramount to safeguarding network integrity. This research explores the application of an innovative approach by integrating an Attention-based Convolutional Neural Network (ACNN) model with machine learning techniques to enhance the accuracy and efficiency of intrusion detection. The proposed system leverages the ACNN's ability to capture contextual dependencies in network traffic data, enabling the extraction of intricate patterns indicative of potential intrusions. The ACNN's attention mechanism focuses on relevant features within the data, improving the model's discriminative power and adaptability to dynamic cyber threats. To achieve optimal performance, the ACNN is complemented with a machine learning framework that includes feature engineering, dimensionality reduction, and classification algorithms. This integrated approach allows the system to adapt and learn from evolving attack vectors, providing a proactive defense mechanism against both known and unknown threats. The research evaluates the proposed ACNN-based IDS using benchmark datasets and real-world network traffic scenarios. Comparative analysis against traditional IDS models showcases the superiority of the ACNN in terms of detection accuracy, false positive rates, and computational efficiency. Furthermore, the system's adaptability to emerging threats is demonstrated through continuous learning and retraining mechanisms. Results indicate that the ACNN-based IDS not only exhibits superior performance but also demonstrates resilience against evasion techniques employed by malicious actors. The research findings contribute to the advancement of network security by presenting a cuttingedge solution that combines deep learning and machine learning for effective and adaptive intrusion detection.

Decoding Emotions: Machine Learning Approach to Speech Emotion Recognition

Speech Emotion Recognition (SER) stands at the forefront of human-computer interaction, offering profound implications for fields such as healthcare, education, and entertainment. This project report delves into the application of Machine Learning (ML) techniques for SER, aiming to discern the emotional content from speech signals. The report begins with an overview of the significance of SER in various domains, emphasizing the need for accurate and robust emotion detection systems. Following this,a detailed exploration of the methodologies employed in SER is presented, encompassing feature extraction techniques, classification algorithms, and model evaluation metrics. In the implementation phase, diverse ML algorithms such as Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) are employed to classify emotional states from speech data. Feature sets including prosodic features, spectral features, and deep learning-based representations are extracted from the speech signals to capture nuanced emotional cues.

IOT NETWORK INTRUSION DETECTION SYSTEM USING MACHINE LEARNING TECHNIQUES

The proliferation of Internet of Things (IoT) devices has transformed various industries by providing smart and automated solutions. However, the extensive connectivity and diverse nature of IoT devices have also introduced significant security challenges, particularly in terms of network intrusion. This paper explores the development and implementation of an Intrusion Detection System (IDS) for IoT networks using Machine learning techniques. The proposed IDS aims to detect and mitigate various cyber threats by analyzing network traffic and identifying anomalous patterns indicative of intrusions. This research contributes to the field of IoT security by providing a robust and scalable intrusion detection solution that leverages the power of machine learning.

A Comprehensive Review on an Advanced Machine Learning Approach for Enhancing Phishing Website Detection

Abstract: Phishing attacks continue to pose a significant threat to online security, exploiting user trust to steal sensitive information. This paper presents a comprehensive review of advanced machine learning techniques for enhancing phishing website detection. We analyze recent developments in feature engineering, focusing on content-based, URL-based, and networkbased attributes. Various machine learning algorithms, including supervised and unsupervised learning, are examined, highlighting their strengths and limitations in this domain. Furthermore, we investigate the potential of ensemble methods and deep learning models to improve detection accuracy. Additionally, we address challenges such as concept drift and adversarial attacks, discussing potential mitigation strategies. Finally, we outline future research directions, emphasizing the need for adaptable and real-time detection systems to counter evolving phishing tactics. This review serves as a valuable resource for researchers and practitioners seeking to develop more robust and effective phishing website detection solutions.

Performance evaluation and clinical application of the UA-5600 automatic dry chemistry urine analyzer in renal diseases.

Urine testing as a routine screening programme, abnormal test results can be suggestive to clinicians but can sometimes be overlooked, and the establishment of a diagnostic model can better assist clinicians in identifying potential problems. BLD (blood), LEU (leukocyte), PRO (protein) and GLU (glucose) are the four most important parameters in urine testing, and the accuracy of their results is a key concern for clinicians, so it is essential to verify the accuracy of their results. In this study, we evaluated the analytical and clinical performance of Mindray's automatic urine dry chemistry analyzer, the UA-5600 (Hereinafter referred to as the (UA-5600), and the test strips configured with the instrument, and developed a machine-learning (ML) model for kidney disease screening from the results of 11 parameters output from the UA-5600 with the aim of detecting abnormal urine test results. Urine samples from outpatients and inpatients at The First Affiliated Hospital of Sun Yat-sen University were collected from August to September 2022 to evaluate the performance of the Mindray UA-5600 dry chemistry analyzer and test strips. The evaluation of the UA-5600 and its test strips focused on the agreement of the urine BLD and LEU readings with the RBC (red blood cell) and WBC (white blood cell) counts obtained by the Mindray EH-2090 urine formed element analyzer. We also compared the PRO and GLU readings with the results of the Mindray BS-2800M biochemistry analyzer. Urine samples from outpatients and inpatients were retrospectively analysed and grouped according to LIS diagnosis. Additionally, eight ML models for kidney disease screening were developed using 11 parameters measured by the UA-5600. And the model was validated by the validation set. The UA-5600 had an 89.55% concordance rate for BLD and a 91.04% concordance rate for LEU compared to the EH-2090 analyzer. When benchmarked against the BS-2800M, the concordance rates for PRO and GLU were 94.14% and 95.20%, respectively. A total of 1,691 samples were used for the construction of the ML models, of which 346 patients (135 males and 211 females, age range: 18 to 98 years) diagnosed with renal disease, and 1,345 patients (397 males and 948 females, age range: 18 to 92 years) with non-renal disease diagnosed with other conditions. Notably, the Naïve Bayes (NB) model, which was built from the UA-5600 parameters, demonstrated superior predictive capabilities for renal disease, with an area under the receiver operating characteristic curve of 0.9470, a sensitivity of 0.7767, and a specificity of 0.9457. The Mindray UA-5600 demonstrates robust detection abilities for both BLD and LEU, and its results for PRO and GLU align closely with those obtained from the chemistry analyzer. The NB model has a good screening ability and shows promise as an effective screening tool.

Multi-Height and Heterogeneous Sensor Fusion Discriminant with LSTM for Weak Fire Signal Detection in Large Spaces with High Ceilings

Fire is a significant cause of fatalities and property loss. In tall spaces, early smoke dispersion is hindered by thermal barriers, and initial flames with limited smoke production may be obscured by ground-level structures. Consequently, smoke, temperature, and other fire sensor signals are weakened, leading to delays in fire detection by sensor networks. This paper proposes a multi-height and heterogeneous fusion discriminant model with a multilayered LSTM structure for the robust detection of weak fire signals in such challenging situations. The model employs three LSTM structures with cross inputs in the first layer and an input-weighted LSTM structure in the second layer to capture the temporal and cross-correlation features of smoke concentration, temperature, and plume velocity sensor data. The third LSTM layer further aggregates these features to extract the spatial correlation patterns among different heights. The experimental results demonstrate that the proposed algorithm can effectively expedite alarm response during sparse smoke conditions and mitigate false alarms caused by weak signals.

Unveiling Anomalies in Surveillance Videos

Abstract: The implementation of Convolutional Neural Network (CNN) algorithm for the detection of anomalies like fire and potholes in images or videos. Leveraging deep learning technique, the model aims to accurately identify fire, potholes, etc. within various contexts. The CNN architecture is trained on a dataset comprising diverse images to enhance its ability to generalize. This proposed project not only addresses safety concerns by promoting helmet usage and proper maintenance of roads but also contributes to the broader field of computer vision and object detection. This implementation involves training the CNN on annotated datasets, fine-tuning the model for optimal performance, and integrating it into a practical application for efficient anomaly identification. With a focus on real-time detection, the system utilizes image processing techniques and a trained CNN model to analyze visual data from cameras or video feeds. The system's versatility allows integration into surveillance systems, industrial sites, or any environment where fire detection is crucial for safety. By automating the detection process, the project contributes to minimizing human error and ensuring consistent monitoring. The proposed solution holds the potential to significantly impact safety protocols, particularly in industries where protective headgear is paramount. Potholes pose a significant threat to both drivers and pedestrians, leading to accidents and infrastructure damage. The proposed solution leverages CNN's ability to effectively process visual data, making it well-suited for image recognition tasks. Our approach involves training the CNN on a diverse dataset of road images to enable it to accurately identify potholes. The model will learn distinctive features and patterns associated with potholes, allowing for robust detection under various environmental conditions. Real-time implementation on embedded systems or cameras along roadways will enable instantaneous identification and alerting.

Adaptive Robust Subspace Detection Based on GLRT, Rao, Wald, Gradient, and Durbin Tests

Adaptive Robust Subspace Detection Based on GLRT, Rao, Wald, Gradient, and Durbin Tests

Dual-mode SERS-ECL biosensor for robust detection of circulating miRNAs based on in-situ synthesized probes

A novel dual-mode biosensor integrating surface-enhanced Raman spectroscopy (SERS) and electrochemiluminescence (ECL) was developed for the reliable detection of acute myocardial infarction (AMI) related circulating miRNAs. The DNA walker nucleic acid amplification technique was employed for signal amplification and facilitated in-situ synthesis of ECL luminescent clusters and SERS probes. The alkynyl-modified silver nanocluster (AgNC) template strand and the azido-modified DNA probe on the electrode were connected through linker release facilitated by the continuous rolling and cutting action of the DNA walker on the spherical substrate. Under Cu+ catalysis, the alkynyl and azide groups at the junction undergo conversion into triazole molecules, which can serve as SERS probes. Subsequently, AgNCs were synthesized using a template method, with SERS signals emitted due to plasma resonance effects of triazole molecules situated between Au nanoparticles and AgNCs. The developed dual-mode analysis platform efficiently minimizes the potential for signal leakage, significantly corrects systematic errors, improves detection accuracy and sensitivity, and facilitates dependable identification of circulating miRNA. The detection of miRNA-133a exhibited a linear relationship within the concentration range of 100 aM to 1 nM, with detection limits of 32 aM and 0.17 fM in ECL and SERS modes, respectively. The SERS-ECL dual-mode detection platform may provide forward-looking ideas for the field of biosensing and clinical analysis.

Ransomware Early Detection using Machine Learning Approach and Pre-Encryption Boundary Identification

The escalating ransomware threat has catalysed the formation of a sophisticated network of cybercriminal enterprises. Addressing this issue, our research provides a detailed exploration of the ransomware menace and an evaluation of contemporary detection methodologies. A successful ransomware attack leverages many factors: robust encryption methods that defy decryption, the anonymity of cyber currencies, and the widespread availability of ransomware kits that enable even inexperienced actors to launch attacks. Such dynamics have cultivated a niche for cybercriminal specialists in the digital underworld. In response to these challenges, our study proposes a detection framework based on machine learning, a domain where regression algorithms have gained popularity without yielding a definitive protective model. We employ API call analysis as the foundation to assess various machine learning classifiers' efficiency in identifying ransomware. The evaluation demonstrates that the Naive Bayes classifier underperforms due to suboptimal accuracy, making it unsuitable for this application. Conversely, Logistic Regression, with an AUC of 0.951, minimal training time, and substantial efficacy gains, emerges as a strong contender. The Decision Tree and Random Forest classifiers exhibit comparable proficiency; however, the Decision Tree's interpretability and Random Forest's computational swiftness present unique advantages. Superior still, SVM and Gradient Boosted Trees command the highest AUC and gains, albeit at the cost of increased training duration. Our findings affirm the pivotal role of API call analysis in ransomware detection and the potency of machine learning approaches in learning from extensive datasets to identify novel malware strains. Given the continual evolution of malware, detection methodologies must adapt correspondingly. This study's comparative analysis elucidates the trade-offs between accuracy, computational speed, and training time, guiding the selection of the optimal machine learning algorithm for robust ransomware detection.

Hunt-inspired Transformer for visual object tracking

This paper presents a hunt-inspired Transformer for visual object tracking, dubbed as HuntFormer. The HuntFormer focuses on robust target detection and identification, simulating natural hunting processes. Specifically, the HuntFormer comprises two essential module designs including a predictor for detection and a verifier for identification. The predictor emulates the detection stage by designing a motion trajectory guided particle filter, which identifies potential target locations by predicting the motion state within a particle filtering framework. The predictor utilizes spatio-temporal correlation scores between dynamic target templates and the search region to guide the learning process to generate a set of reliable particles. This enables the base tracker to narrow its search range to focus on the target, and swiftly re-detect the target in case of model drift. Once the target is re-detected, the verifier assesses the detection result as a reliable tracked item. The verifier initially maintains a dynamic memory that stores reliable target templates and their corresponding locations in the motion trajectory. It then models the uncertainty of appearance information within this memory probabilistically. The output uncertainty score determines whether the memory gets updated or not. Ultimately, the predictor and the verifier collaborate, ensuring a robust tracking outcome. Extensive evaluations on six challenging benchmark datasets demonstrate HuntFormer’s favorable performance against various state-of-the-art trackers. Notably, in the VOT-LT2022 tracking challenge, the HuntFormer won the third place with an F-score of 0.598, closely competing for the second place with an F-score of 0.600.

HEN: a novel hybrid explainable neural network based framework for robust network intrusion detection

HEN: a novel hybrid explainable neural network based framework for robust network intrusion detection

AI Integrity Solutions for Deepfake Identification and Prevention

The increasing complexity of deepfake technology has sparked significant worries over individual privacy, the spread of false information, and deficiencies in cybersecurity. Deepfakes have the ability to effectively modify audio and visual content, resulting in a growing challenge to differentiate between real and fake content. To address this critical challenge, the study is conducting a survey to reveal a broad range of perspectives on the familiarity, encounters, and concerns related to deepfake technology. In addition, the study evaluates the effectiveness of current strategies in addressing the spread of deepfake material and proposes future approaches for improving the integrity of AI. The survey was delivered digitally, and responses were examined to provide an in- depth analysis of the latest techniques and difficulties in the context of deepfake detection. The outcomes demonstrate a range of perspectives on understanding deepfakes with an explicit agreement on the importance of risk presented by harmful deepfake applications. Although the participants showed an understanding of the available interventions, they also identified considerable challenges and the need for improved awareness, robust detection tools, and ethical standards in AI development to address the challenges posed by deepfakes with the present detection method. Implementing AI ethical guidelines to avoid deepfakes has a significant and beneficial effect on several industries by providing protection against their harmful effects. By fostering AI ethical guidelines, these policies are able to foster societal trust, mitigate risk, and cultivate a more robust digital environment.

Robust brain tumor detection and classification via multi-technique image analysis

Accurate detection and classification of brain tumors play a critical role in neurological diagnosis and treatment.Proposed work developed a sophisticated technique to precisely identify and classify brain neoplasms in medical imaging. Our approach integrates various techniques, including Otsu’s thresholding, anisotropic diffusion, modified 3-category Fuzzy C-Means (FCM) for segmentation after skull stripping and wavelet transformation for post-processing for segmentation, and Convolution neural networks for classification. This approach not only recognizes that discriminating healthy brain tissue from tumor-affected areas is challenging, yet it also focuses on finding abnormalities inside brain tumors and early detection of tiny tumor structures. Initial preprocessing stages improve the visibility of images and the identification of various regions while accurately classifying tumor locations into core, edema, and enhancing regions by segmentation as well. Ultimately, these segmented zones are refined using wavelet transforms, which remove noise and improve feature extraction. Our CNN architecture uses learned abstractions to distinguish between healthy and malignant regions, ensuring robust classification. It is particularly good at identifying tiny tumors and detecting anomalies inside tumor regions, which provides substantial advances in accurate tumor detection. Comprehensive hypothetical evaluations validate its efficacy, which could improve clinical diagnostics and perhaps influence brain tumor research and treatment approaches.

A revolutionary approach to use convolutional spiking neural networks for robust intrusion detection

A revolutionary approach to use convolutional spiking neural networks for robust intrusion detection

Rapid detection of pathogenic E. coli based on CRISPR Cas system.

Access to safe and nutritious food is critical for maintaining life and supporting good health. Eating food that is contaminated with pathogens leads to serious diseases ranging from diarrhea to cancer. Many foodborne infections can cause long-term impairment or even death. Hence, early detection of foodborne pathogens such as pathogenic Escherichia coli strains is essential for public safety. Conventional methods for detecting these bacteria are based on culturing on selective media and following standard biochemical identification. Despite their accuracy, these methods are time-consuming. PCR-based detection of pathogens relies on sophisticated equipment and specialized technicians which are difficult to find in areas with limited resources. Whereas CRISPR technology is more specific and sensitive for identifying pathogenic bacteria because it employs programmable CRISPR-Cas systems that target particular DNA sequences, minimizing non-specific binding and cross-reactivity. In this project, a robust detection method based on CRISPR-Cas12a sensing was developed, which is rapid, sensitive and specific for detection of pathogenic E. coli isolates that were collected from the fecal samples from adult goats from 17 farms in Tennessee. Detection reaction contained amplified PCR products for the pathogenic regions, reporter probe, Cas12a enzyme, and crRNA specific to three pathogenic genes-stx1, stx2, and hlyA. The CRISPR reaction with the pathogenic bacteria emitted fluorescence when excited under UV light. To evaluate the detection sensitivity and specificity of this assay, its results were compared with PCR based detection assay. Both methods resulted in similar results for the same samples. This technique is very precise, highly sensitive, quick, cost effective, and easy to use, and can easily overcome the limitations of the present detection methods. This project can result in a versatile detection method that is easily adaptable for rapid response in the detection and surveillance of diseases that pose large-scale biosecurity threats to human health, and plant and animal production.