Detection Problem Research Articles

Deep learning application in prediction of cancer molecular alterations based on pathological images: a bibliographic analysis via CiteSpace

BackgroundThe advancements in artificial intelligence (AI) technology for image recognition were propelling molecular pathology research into a new era.ObjectiveTo summarize the hot spots and research trends in the field of molecular pathology image recognition.MethodsRelevant articles from January 1st, 2010, to August 25th, 2023, were retrieved from the Web of Science Core Collection. Subsequently, CiteSpace was employed for bibliometric and visual analysis, generating diverse network diagrams illustrating keywords, highly cited references, hot topics, and research trends.ResultsA total of 110 relevant articles were extracted from a pool of 10,205 articles. The overall publication count exhibited a rising trend each year. The leading contributors in terms of institutions, countries, and authors were Maastricht University (11 articles), the United States (38 articles), and Kather Jacob Nicholas (9 articles), respectively. Half of the top ten research institutions, based on publication volume, were affiliated with Germany. The most frequently cited article was authored by Nicolas Coudray et al. accumulating 703 citations. The keyword "Deep learning" had the highest frequency in 2019. Notably, the highlighted keywords from 2022 to 2023 included “microsatellite instability”, and there were 21 articles focusing on utilizing algorithms to recognize microsatellite instability (MSI) in colorectal cancer (CRC) pathological images.ConclusionThe use of DL is expected to provide a new strategy to effectively solve the current problem of time-consuming and expensive molecular pathology detection. Therefore, further research is needed to address issues, such as data quality and standardization, model interpretability, and resource and infrastructure requirements.Graphical abstract

On the influence of artificially distorted images in firearm detection performance using deep learning

Detecting people carrying firearms in outdoor or indoor scenes usually identifies (or avoids) potentially dangerous situations. Nevertheless, the automatic detection of these weapons can be greatly affected by the scene conditions. Commonly, in real scenes these firearms can be seen from different perspectives. They also may have different real and apparent sizes. Moreover, the images containing these targets are usually cluttered, and firearms can appear as partially occluded. It is also common that the images can be affected by several types of distortions such as impulse noise, image darkening or blurring. All these perceived variabilities could significantly degrade the accuracy of firearm detection. Current deep detection networks offer good classification accuracy, with high efficiency and under constrained computational resources. However, the influence of practical conditions in which the objects are to be detected has not sufficiently been analyzed. Our article describes an experimental study on how a set of selected image distortions quantitatively degrade the detection performance on test images when the detection networks have only been trained with images that do not present the alterations. The analyzed test image distortions include impulse noise, blurring (or defocus), image darkening, image shrinking and occlusions. In order to quantify the impact of each individual distortion on the firearm detection problem, we have used a standard YOLOv5 network. Our experimental results have shown that the increased addition of impulse salt-and-pepper noise is by far the distortion that affects the most the performance of the detection network.

Finding and counting small tournaments in large tournaments

We present new algorithms for counting and detecting small tournaments in a given tournament. In particular, we prove that every tournament on four vertices (there are four) can be detected in O(n2) time and counted in O(nω) time where ω<2.372 is the matrix multiplication exponent. We further prove that any tournament on five vertices (there are 12) can be counted in O(nω+1) time. As for lower-bounds, we prove that for almost all k-vertex tournaments, the complexity of the detection problem is not easier than the complexity of the corresponding well-studied counting problem for undirected cliques of order k−O(log⁡k).

Sliding window SA-CNN-based CFAR detector for extended target in shipborne HFSWR

ABSTRACT In shipborne high-frequency surface wave radar (HFSWR), the change of platform speed or heading will cause variations in the extension of the Doppler spectrum for vessel targets located in different directions, subsequently resulting in alterations to the signal-to-noise ratio (SNR). These alterations in vessel target echo present challenges for manual parameter adjustments in traditional constant false alarm rate (CFAR) methods for shipborne HFSWR, thereby hindering the maintenance of stable target detection capabilities. In this paper, a self-attention-convolutional neural network (SA-CNN)-based CFAR detector is proposed, which transforms the detection problem into signal structure classification. First, the extension characteristics of vessel target echoes resulting from changes in speed or heading of the shipborne platform are quantitatively analysed, thereby guiding the selection of an optimal sliding window and constructing input vectors for the neural network. Subsequently, the SA-CNN is designed to efficiently extract the structural features of the signal and accurately predict the probability of target presence. Finally, the Monte Carlo method is used to control the false alarm rate effectively. Simulation and real dataset verification demonstrate that the proposed method exhibits superior detection performance compared to traditional methods in shipborne HFSWR, especially for detecting extended targets.

Data Mining Approach for Evil Twin Attack Identification in Wi-Fi Networks

Recent cyber security solutions for wireless networks during internet open access have become critically important for personal data security. The newest WPA3 network security protocol has been used to maximize this protection; however, attackers can use an Evil Twin attack to replace a legitimate access point. The article is devoted to solving the problem of intrusion detection at the OSI model’s physical layers. To solve this, a hardware–software complex has been developed to collect information about the signal strength from Wi-Fi access points using wireless sensor networks. The collected data were supplemented with a generative algorithm considering all possible combinations of signal strength. The k-nearest neighbor model was trained on the obtained data to distinguish the signal strength of legitimate from illegitimate access points. To verify the authenticity of the data, an Evil Twin attack was physically simulated, and a machine learning model analyzed the data from the sensors. As a result, the Evil Twin attack was successfully identified based on the signal strength in the radio spectrum. The proposed model can be used in open access points as well as in large corporate and home Wi-Fi networks to detect intrusions aimed at substituting devices in the radio spectrum where IEEE 802.11 networking equipment operates.

An Efficient Detection Mechanism of Network Intrusions in IoT Environments Using Autoencoder and Data Partitioning

In recent years, with the development of the Internet of Things and distributed computing, the “server-edge device” architecture has been widely deployed. This study focuses on leveraging autoencoder technology to address the binary classification problem in network intrusion detection, aiming to develop a lightweight model suitable for edge devices. Traditional intrusion detection models face two main challenges when directly ported to edge devices: inadequate computational resources to support large-scale models and the need to improve the accuracy of simpler models. To tackle these issues, this research utilizes the Extreme Learning Machine for its efficient training speed and compact model size to implement autoencoders. Two improvements over the latest related work are proposed: First, to improve data purity and ultimately enhance detection performance, the data are partitioned into multiple regions based on the prediction results of these autoencoders. Second, autoencoder characteristics are leveraged to further investigate the data within each region. We used the public dataset NSL-KDD to test the behavior of the proposed mechanism. The experimental results show that when dealing with multi-class attacks, the model’s performance was significantly improved, and the accuracy and F1-Score were improved by 3.5% and 2.9%, respectively, maintaining its lightweight nature.

Partial recovery and weak consistency in the non-uniform hypergraph stochastic block model

Abstract We consider the community detection problem in sparse random hypergraphs under the non-uniform hypergraph stochastic block model (HSBM), a general model of random networks with community structure and higher-order interactions. When the random hypergraph has bounded expected degrees, we provide a spectral algorithm that outputs a partition with at least a $\gamma$ fraction of the vertices classified correctly, where $\gamma \in (0.5,1)$ depends on the signal-to-noise ratio (SNR) of the model. When the SNR grows slowly as the number of vertices goes to infinity, our algorithm achieves weak consistency, which improves the previous results in Ghoshdastidar and Dukkipati ((2017) Ann. Stat.45(1) 289–315.) for non-uniform HSBMs. Our spectral algorithm consists of three major steps: (1) Hyperedge selection: select hyperedges of certain sizes to provide the maximal signal-to-noise ratio for the induced sub-hypergraph; (2) Spectral partition: construct a regularised adjacency matrix and obtain an approximate partition based on singular vectors; (3) Correction and merging: incorporate the hyperedge information from adjacency tensors to upgrade the error rate guarantee. The theoretical analysis of our algorithm relies on the concentration and regularisation of the adjacency matrix for sparse non-uniform random hypergraphs, which can be of independent interest.

Seal Pipeline: Enhancing Dynamic Object Detection and Tracking for Autonomous Unmanned Surface Vehicles in Maritime Environments

This study addresses the dynamic object detection problem for Unmanned Surface Vehicles (USVs) in marine environments, which is complicated by boat tilting and camera illumination sensitivity. A novel pipeline named “Seal” is proposed to enhance detection accuracy and reliability. The approach begins with an innovative preprocessing stage that integrates data from the Inertial Measurement Unit (IMU) with LiDAR sensors to correct tilt-induced distortions in LiDAR point cloud data and reduce ripple effects around objects. The adjusted data are grouped using clustering algorithms and bounding boxes for precise object localization. Additionally, a specialized Kalman filter tailored for maritime environments mitigates object discontinuities between successive frames and addresses data sparsity caused by boat tilting. The methodology was evaluated using the VRX simulator, with experiments conducted on the Volga River using real USVs. The preprocessing effectiveness was assessed using the Root Mean Square Error (RMSE) and tracking accuracy was evaluated through detection rate metrics. The results demonstrate a 25% to 30% improvement in detection accuracy and show that the pipeline can aid industry even with sparse object representation across different frames. This study highlights the potential of integrating sensor fusion with specialized tracking for accurate dynamic object detection in maritime settings, establishing a new benchmark for USV navigation systems’ accuracy and reliability.

Experimental and Theoretical Comparison and Analysis of Surface-Enhanced Raman Scattering Substrates with Different Morphologies

The following research paper concerns the analysis and characterisation of commercially available surface-enhanced Raman scattering (SERS) substrates. SERS has long been a potentially very powerful method with a great deal of interest around it; however, there are still many obstacles which do not allow SERS to be easily applied to real-world detection and analysis problems. As such, research around the various types of substrates is ongoing, in the hope of streamlining and improving the Raman enhancement mechanism. Scanning electron microscope images were obtained for each of the three substrates, and their features and scales were described. Enhanced Raman spectra for Rhodamine B were obtained for a range of concentrations using each of the three substrates, and, in addition, surface enhancement maps are presented. Enhancement factors were calculated for the 1358 cm−1 peak of Rhodamine B. Complementing the experimental work, theoretical FEM modelling in COMSOL Multiphysics was performed, with the resulting calculations yielding an enhancement prediction adequately accurate to the real substrates.

An advanced symbol detection approach for MIMO-FBMC/OQAM scheme based on migrating birds optimization algorithm

Application of multiple-input multiple-output (MIMO) technology to the filter bank multicarrier/offset quadrate amplitude modulation (FBMC/OQAM) system provides great improvements on its robustness to channel fading effects. Nevertheless, the unique qualities of MIMO-FBMC/OQAM scheme do not make any sense without solving the symbol detection problem on its receiver part. To this end, an efficient symbol detecting strategy having the capability of recovering the transmitted symbol sequences with the highest accuracy is needed for the related system. Maximum likelihood (ML) detector is known with its excellent symbol detection performance in the literature. However, due to the usage of exhaustive search procedure, the computational complexity of the ML detector reaches extremely high levels with the increase of antenna size and modulation order. On the other hand, in the case that the exhaustive search procedure is substituted with the symbol optimization process, it becomes possible to achieve a large amount of complexity reduction in the conventional ML scheme without compromising too much on its symbol detection performance. In order to carry out an efficient symbol optimization in discrete space, we propose migrating birds optimization (MBO) algorithm based on cyclic bit flipping procedure in this paper. By virtue of employing the proposed MBO algorithm reinforced by the cyclic bit flipping mechanism for optimizing the symbol sequences, the computational complexity of the conventional ML is reduced to quite low levels. The percentages of complexity reduction achieved by the proposed scheme over the classical ML for 4 × 4, 6 × 6 and 8 × 8 MIMO configurations are equal to 29.688%, 87.188% and 98.299%, respectively. In addition to these huge complexity gains, an efficient symbol detection performance quite near to that of conventional ML is obtained thanks to the usage of aforementioned MBO-based symbol optimization procedure.

MRI-based microplastic tracking in vivo and targeted toxicity analysis

Microplastics (MPs) as an emerging pollutant have raised significant concerns in environmental health. However, elucidating the distribution of MPs in living organisms remains challenging due to their trace residue and tough detection problems. In this study, a novel magnetic resonance imaging (MRI)-based tracking method was employed to monitor functionalized MPs biodistribution in vivo. Our results identified that the liver is the primary accumulation site of polystyrene microplastics (PS-MPs) in biological systems through continuous in vivo monitoring spanning 21 days. Biochemical tests were performed to assess the toxicological effects of functionalized MPs on the liver tissue, revealing hepatocyte death, inflammatory cell infiltration, and alterations in alkaline phosphatase levels. Notably, positively charged MPs exhibited more severe effects. A combined metabolomics-proteomics analysis further revealed that PS-MPs interfered with hepatic metabolic pathways, particularly bile secretion and ABC transporters. Overall, this study effectively assessed the distribution of functionalized MPs in vivo utilizing MRI technology, validated toxicity in targeted organ, and conducted an in-depth study on underlying biotoxicity mechanism. These findings offer crucial scientific insights into the potential impact of MPs in the actual environment on human health.

Long afterglow nanoprobes labeled image enhancement using deep learning in rapid and sensitive lateral flow immunoassay

Point-of-care testing (POCT) is currently the predominant method of in vitro diagnostics, with lateral flow immunoassay(LFIA) being commonly utilized in POCT. The performance of the probe in LFIA will directly affect the results of the detection. Therefore, the selection of probes is particularly important. However, the current commercially produced probes generally suffer from short luminescence lifetime, high detection cost, and poor anti-interference capability. Meanwhile, the traditional detection system has difficulties in detecting weakly positive samples. These ultimately lead to the problem of poor detection sensitivity. In order to address the above issues, we have synthesized an ultralong organic phosphorescence nanoprobe (UOPN). The UOPNs exhibit a long afterglow phosphorescence signal of around 300 ms after being excited, which can be used to eliminate endogenous interference. Meanwhile, focusing on the problem of poor detection of weakly positive samples in conventional detection systems, and the weak inherent signal of UOPNs, resulting in a low signal-to-noise ratio, we have developed a detection system that combines image processing and neural network-driven analysis for long afterglow image analysis. Through the analysis of the long afterglow images of serum amyloid A (SAA) in human blood, a detection limit of 0.01 μg/mL and a linear range of 0.1–251 μg/mL were achieved. The whole analysis was completed within 5 minutes. After pre-processing with the denoising algorithm, the system demonstrated an impressive classification accuracy of 99.24 %, validating the reliability of the detection system. This approach has further enhanced the sensitivity of immunoassay, contributing to the advancement of point-of-care testing.

WHITE COLLAR CRIME AS ORGANIZED INSTITUTIONAL CRIME

The object of treatment in this paper is the problem of detection and treatment of corruption. There is no single definition for corruption and in this case it is limited to the corruption practices of white-collar crime, being a link to institutional organized crime, with confirmation of the suspicion of crime in the Prosecutor's Office - especially that of serious crimes which is the main pillar of the state in this right to enforce the law and fight the phenomenon, as well as the state courts. Its meaning is broad and cannot be defined only by accepting or giving a bribe to an official or buying it, as is often practiced. Corruption is often carried out by a highly organized group of people, which gives us elements of institutional organized crime. Since corruption, especially political corruption, is carried out by highly qualified and professional persons, this greatly complicates the operation of the law, detection, investigation, prosecution and judgment of authoritative persons, decision-makers, due to the great powers to hide the traces of corruption and especially the crime of money laundering, being a serious consequence and with great material and moral damage for the citizens of a state. Due to the problems leading to the discovery and proof of this crime and due to the way it is committed, the secret nature, corruption is part of the crimes where the rate of proof is extremely low or even definitely impossible. The work is mainly elaborated on the problems encountered not only by the agencies, the bodies that have a mandate to prevent and fight this negative phenomenon in our society, but also the media and especially the citizens who are involved in harm from authoritative persons and state institutions. A major problem where the citizen there is no address for orientation and when the organized Institutional group usurps the State Institutions and in some form is created as a Mafia group.

Spoofing countermeasure for fake speech detection using brute force features

Due to the progress in deep learning technology, techniques that generate spoofed speech have significantly emerged. Such synthetic speech can be exploited for harmful purposes, like impersonation or disseminating false information. Researchers in the area investigate the useful features for spoof detection. This paper extensively investigates three problems in spoof detection in speech, namely, the imbalanced sample per class, which may negatively affect the performance of any detection models, the effect of the feature early and late fusion, and the analysis of unseen attacks on the model. Regarding the imbalanced issue, we have proposed two approaches (a Synthetic Minority Over Sampling Technique (SMOTE)-based and a Bootstrap-based model). We have used the OpenSMILE toolkit, to extract different feature sets, their results and early and late fusion of them have been investigated. The experiments are evaluated using the ASVspoof 2019 datasets which encompass synthetic, voice-conversion, and replayed speech samples. Additionally, Support Vector Machine (SVM) and Deep Neural Network (DNN) have been adopted in the classification. The outcomes from various test scenarios indicated that neither the imbalanced nature of the dataset nor a specific feature or their fusions outperformed the brute force version of the model as the best Equal Error Rate (EER) achieved by the Imbalance model is 6.67 % and 1.80 % for both Logical Access (LA) and Physical Access (PA) respectively.

Modeling disagreement in automatic data labeling for semi-supervised learning in Clinical Natural Language Processing.

Computational models providing accurate estimates of their uncertainty are crucial for risk management associated with decision-making in healthcare contexts. This is especially true since many state-of-the-art systems are trained using the data which have been labeled automatically (self-supervised mode) and tend to overfit. In this study, we investigate the quality of uncertainty estimates from a range of current state-of-the-art predictive models applied to the problem of observation detection in radiology reports. This problem remains understudied for Natural Language Processing in the healthcare domain. We demonstrate that Gaussian Processes (GPs) provide superior performance in quantifying the risks of three uncertainty labels based on the negative log predictive probability (NLPP) evaluation metric and mean maximum predicted confidence levels (MMPCL), whilst retaining strong predictive performance. Our conclusions highlight the utility of probabilistic models applied to "noisy" labels and that similar methods could provide utility for Natural Language Processing (NLP) based automated labeling tasks.

Provenance-based APT campaigns detection via masked graph representation learning

Advanced Persistent Threats (APTs) are well-planned, persistent, and highly stealthy cyberattacks designed to steal confidential information or disrupt specific target systems. Recent studies have used system audit logs to construct provenance graphs that describe system interactions to detect potentially malicious activities. Although they are effective, they still suffer from problems such as the need for a priori knowledge, lack of attack data, and high computational overhead that limit their application. In this paper, we propose a self-supervised learning-based APT detection model, APT-MGL, which learns the embedded representations of nodes through a graph mask self-encoder and transforms the detection problem into an outlier detection problem for malicious nodes. APT-MGL characterizes the behavior of nodes based on node type, action, and interaction frequency, and fuses the features through a multi-head self-attention mechanism. Then the node embedding is obtained by combining graph features and structural information using masked graph representation learning. Finally, the unsupervised outlier detection method is used to analyze the computed embeddings and obtain the final detection results. The experimental results show that APT-MGL outperforms existing monitoring models and achieves a small overhead.

Detection Problems in the Spiked Random Matrix Models

Detection Problems in the Spiked Random Matrix Models

SPCF-YOLO: Dense Small Target Detection Algorithm for Autonomous Driving

Abstract In the automatic driving scene, the pedestrian and vehicle targets are dense and block each other, and the problem of target false detection and missing detection is easy to occur. In this paper, a dense small target detection algorithm SPCF-YOLO is proposed. A new SPCSA module has been designed to strengthen the capture of edge features in occluded small targets. MPDIoU replaces the original CIOU loss function to address cases where the predicted and real frames have the same aspect ratio, but the aspect ratio difference of anchor frame is large. Experimental results show that in KITTI 2D data set, compared with the original YOLOv7 algorithm, mAP@0.5 is 93.5%, an increase of 0.5%. mAP@0.5:0.95 is 66.9%, an increase of 2%; micro-target mAP@0.5:0.95 is 50.3%, an increase of 2.6%; and the computational load and parameter number remain basically unchanged, which proves the effectiveness of the design algorithm.

Extended Representation Learning Based Neural Network Model for Outlier Detection

Outlier detection problems have drawn much attention in recent times for their variety of applications. An outlier is a data point that is different from the rest of the data and can be detected based on some measure. In recent years, Artificial Neural Networks (ANN) have been used extensively for finding outliers more efficiently. This method is highly competitive with other methods currently in use such as similarity searches, density-based approaches, clustering, distance-based approaches, linear methods, etc. In this paper, we have proposed an extended representation learning based neural network. This model follows a symmetric structure like an autoencoder where the dimensions of the data are initially increased from their original dimensions and then reduced. Root mean square error is used to compute the outlier score. Reconstructed error is calculated and analyzed to detect the possible outliers. The experimental findings are documented by applying it to two distinct datasets. The performance of the proposed model is compared to several state-of-art approaches such as Rand Net, Hawkins, LOF, HiCS, and Spectral. Numerical results show that the proposed method outperforms all of these methods in terms of 5 validation scores, Accuracy (AC), Precision (P), Recall, F1 Score, AUC score.

Faint Space Target Information Extraction Based on Small Aperture Telescope in Complex Background

AbstractThere are many problems in space debris monitoring with ground‐based telescopes, such as too many stars in the same field of view, uneven background and optical distortion in the optical system. We propose a two‐stage weak debris detection algorithm. In the first stage, wavelet transform is used to extract different components of three frames of images, and the median of corresponding components of the images is taken respectively to eliminate the influence of stars. In the second stage, an improved version of the faint space target extraction based on principal component analysis. The algorithm uses a smooth‐detection idea to extract target information. Based on a 150 mm aperture telescope, we improved the existing method of faint space debris extraction based on principal component analysis by introducing the smooth‐detection idea, and transformed the target detection problem into the separation problem of sparse matrix and low‐rank matrix. We applied a certain preprocessing consisting of wavelet‐based star removal and median pre‐filtering to keep as little noise and other contaminants as possible. After experimental measurements by observers, the algorithm demonstrated advanced detection capabilities on multiple indicators.