Conventional Detection Research Articles

In vivo dynamic tracking of cerebral chloride regulation using molecularly tailored liquid/liquid interfacial ultramicro iontronics.

Chloride ion, a pivotal cerebral anion involved in neuronal inhibition, is implicated in various neurodegenerative diseases. Conventional direct faradaic detection based on electron transfers at solid electrode/solution interfaces has been proven ineffective due to the electrochemically inactive nature of Cl-. Here, we present an approach involving molecularly tailored liquid/liquid interfacial ultramicro iontronics (L/L-UIs) supported at ultramicropipettes filled with organic gel containing lipophilic bis-thioureas ionophores, which represents the first application of amperometric methodology based on electrochemical facilitated ion transfers reactions at a soft L/L ultramicrointerface to achieve in vivo sensing of electrochemically inactive ions, and dynamically tracking cerebral Cl- in vivo. Furthermore, evidence of dynamic neuronal Cl- regulation via KCC2 modulated through GABAB receptors was provided, further substantiating GABAB receptor-mediated Cl--related neuronal inhibition. The proposed L/L-UIs have notable potential for in situ tracking of other crucial electrochemically inactive ions or ionized biomolecules in vivo, thereby facilitating the study of brain diseases and the diagnosis and treatment of related disorders.

Enhancing performance of end-to-end communication system using Attention Mechanism-based Sparse Autoencoder over Rayleigh fading channel

Deep learning has revolutionized communication systems by introducing innovative approaches to address channel impairments through end-to-end models. Autoencoders, a type of deep learning architecture, are adept at learning compact data representations. However, conventional autoencoders in end-to-end models can suffer from overfitting, which limits their effectiveness in noisy communication environments. To address this issue, we propose a Sparse Autoencoder-based (SAE) model that enforces sparsity and promotes the extraction of robust features. Despite its effectiveness, the SAE model may still lack the ability to focus on the most relevant features of the input data. To overcome this limitation, we further introduce an Attention Mechanism-based Sparse Autoencoder (ASA) model. This model integrates the feature extraction capabilities of a sparse autoencoder with an attention mechanism that selectively highlights informative features of the signal. Through simulations, we demonstrate that both proposed models significantly improve M-PSK and M-QAM communication system performance. When trained at 7 dB, both proposed models exhibit significant performance improvements at higher testing average SNRs. Our results show that the SAE model outperforms the conventional Maximum Likelihood Detection (MLD) model and baseline autoencoder systems but suffers from error floor issues. The SAE model suffers from an error floor at average SNRs beyond 16 dB for BPSK and 14 dB for higher-order modulation schemes. As the value of M increases, the performance gap between the MLD and the proposed SAE model narrows. The ASA model, however, effectively mitigates the error floor observed in the SAE model for all values of M and across all modulation schemes. This research highlights the benefits of integrating an attention mechanism with SAE, resulting in enhanced robustness and reliability in communication systems characterized by improved accuracy and reduced error rates.

Pushing the boundaries of aphid detection: An investigation into mmWaveRadar and machine learning synergy

Agriculture, essential for global sustenance and economic vitality, faces significant threats from pest-induced damages, resulting in substantial crop losses and affecting food supply if not detected on time. Traditional pest control methods, primarily reliant on pesticides. However, blindly applying pesticide may cause environmental issue. Therefore detecting the infested crops at early stage is crucial for application of sustainable pest management solutions. This study innovatively employs the IWR1443BOOST FMCW Millimeter Wave Radar (mmWaveRadar) in conjunction with machine learning algorithms such as SVM, Random Forest, Adaboost, Lightgbm, Catboost, and edRVFL for enhanced pest detection in crops. Our novel framework encompasses the collection and pre-processing of mmWaveRadar data from both healthy and infested crops, followed by comprehensive feature extraction. Decision tree-based methods exhibited a remarkable detection accuracy of 98%. EdRVFL demonstrated a 95% detection accuracy. SVM, post-feature selection, achieved a 90% accuracy. The research reveals the efficacy of the mmWaveRadar as a robust tool, overcoming the environmental and concealment limitations of conventional image-based pest detection methods. The integration of curated features with machine learning algorithms has shown promising empirical results, establishing a connection between the discerned features and the real-world attributes of healthy and infested crops. This study underscores the potential of mmWaveRadar, coupled with specific machine learning algorithms, as a significant stride towards sustainable and effective pest management strategies in agricultural technology.

Automated Fire Sensing and Fire Extinguisher Module

The Hazard of fire and fire explosions poses significant risks to both property and human safety, necessitating immediate action to minimize damage. Conventional fire detection methods that rely on human observation may result in delays, particularly in unattended areas. To address these challenges, a specialized fire detection and extinguishing system is being developed with the capability to autonomously detect and extinguish fires. This system will also promptly notify individuals through messages and phone calls upon fire detection, improving response times and ensuring immediate awareness of fire incidents. Equipped with Arduino microcontrollers, the system integrates advanced sensors for precise detection of heat and smoke, allowing accurate pinpointing of fire locations. The use of Arduino technology provides adaptable functionality in various environments, ranging from residential to commercial settings. Effective communication of fire alerts is essential for promptly notifying firefighters and occupants, facilitating timely intervention and safe evacuations. The objective is to create an efficient system that harnesses modern technology to enhance fire safety measures, ultimately reducing fire related risks and effectively protecting lives.

Selective Auditory Attention Detection Using Combined Transformer and Convolutional Graph Neural Networks

Attention is one of many human cognitive functions that are essential in everyday life. Given our limited processing capacity, attention helps us focus only on what matters. Focusing attention on one speaker in an environment with many speakers is a critical ability of the human auditory system. This paper proposes a new end-to-end method based on the combined transformer and graph convolutional neural network (TraGCNN) that can effectively detect auditory attention from electroencephalograms (EEGs). This approach eliminates the need for manual feature extraction, which is often time-consuming and subjective. Here, the first EEG signals are converted to graphs. We then extract attention information from these graphs using spatial and temporal approaches. Finally, our models are trained with these data. Our model can detect auditory attention in both the spatial and temporal domains. Here, the EEG input is first processed by transformer layers to obtain a sequential representation of EEG based on attention onsets. Then, a family of graph convolutional layers is used to find the most active electrodes using the spatial position of electrodes. Finally, the corresponding EEG features of active electrodes are fed into the graph attention layers to detect auditory attention. The Fuglsang 2020 dataset is used in the experiments to train and test the proposed and baseline systems. The new TraGCNN approach, as compared with state-of-the-art attention classification methods from the literature, yields the highest performance in terms of accuracy (80.12%) as a classification metric. Additionally, the proposed model results in higher performance than our previously graph-based model for different lengths of EEG segments. The new TraGCNN approach is advantageous because attenuation detection is achieved from EEG signals of subjects without requiring speech stimuli, as is the case with conventional auditory attention detection methods. Furthermore, examining the proposed model for different lengths of EEG segments shows that the model is faster than our previous graph-based detection method in terms of computational complexity. The findings of this study have important implications for the understanding and assessment of auditory attention, which is crucial for many applications, such as brain–computer interface (BCI) systems, speech separation, and neuro-steered hearing aid development.

Photon-counting detector CT provides superior subsolid nodule characterization compared to same-day energy-integrating detector CT.

To investigate the image quality and the performance of photon-counting detector (PCD) CT compared to conventional energy-integrating detector (EID) CT in identifying subsolid nodule (SSN) characteristics. Participants with SSNs who underwent same-day EID CT and PCD CT between October 2023 and April 2024 were prospectively included. The 1.0 mm EID CT images and, subsequently, 1.0 mm, 0.4 mm, and 0.2 mm PCD CT images were reviewed to assess image noise and subjective image quality on a 5-point Likert scale. SSN characteristics, including lobulation, spiculation, pleural retraction, air cavities, intra-nodular vessel signs, internal vascular changes, and heterogeneous solid components, were evaluated. Additionally, a step-by-step observation and comparison method was used to determine the presence of any additional characteristics. Forty-eight participants (mean age: 56 ± 11 years; 16 males) with 89 SSNs were included. PCD CT significantly reduced radiation dose when using matched scans (1.79 ± 0.39 vs 2.17 ± 0.57 mSv, p < 0.001). Compared to 1.0 mm EID CT, 1.0 mm PCD CT images exhibited significantly lower objective image noise and higher subjective image quality (all p < 0.001). Compared to EID CT, PCD CT demonstrated enhanced visualization of subtle characteristics, except for lobulation, with a 0.4 mm section thickness offering a favorable balance between ultra-high resolution and perceived image quality for radiologists. PCD CT facilitated radiation dose reduction and outperformed conventional EID CT in terms of image quality and visualization of SSN characteristics. Question PCD CT, featuring ultra-high-resolution mode acquisition and a thinner reconstruction, has not been fully explored for characterizing SSNs. Findings Compared to EID CT, PCD CT was associated with lower objective image noise, higher subjective image quality, and superior SSN characterization. Clinical relevance PCD CT effectively reduced the radiation dose delivered to the patients and enabled more precise SSN characterization.

Spin photo detector by using a CoFeB magnetic tunnel junction

Abstract Ultra-fast photoelectric conversion devices are a crucial element in photonics applications and are the subject of intense research and development. In conventional high-speed photo detectors, photoelectric charge generation in semiconductors is rooted in a mechanism that directly outputs current. Owing to the dilemma of the amount of generated charge and high-speed output, it is being faced with fundamental difficult to achieve a higher response. Spin order, rather than charge generation, also exists as a phenomenon that enables ultrafast photoresponses, and magnetic tunnel junction (MTJ) are well-known high-speed electrical detection elements for magnetic states. In this study, we experimentally confirmed the magnetic switching of photoresponsive MTJ using a practical single CoFeB free layer with a high MR ratio of 80% by irradiation with laser light. Furthermore, we experimentally confirmed the operation of the reversible photo detector, and its rise time reached an ultrafast speed of 20 ps. We named it spin photo detector and it has huge potential applications that require ultrafast photo detection.

Survey of Transformer-Based Malicious Software Detection Systems

In the recent past, the level of cyber threats has changed drastically, leading to the current transformation of the cybersecurity landscape. For example, emerging threats like Zero-day and polymorphic malware cannot be detected by conventional detection methods like heuristic and signature-based methods, which have proven useful in the identification of malware. In view of this shift in the cybersecurity paradigm, this study proposes to discuss the utilization of transformer models to improve malware detection effectiveness and the accuracy and efficiency in detecting malicious software. In this regard, this study adopts the application of transformers in identifying different forms of malicious software: ransomware, spyware, and trojans. Transformers are endowed with the ability to handle sequential data and capture intricate patterns. By employing deep learning techniques and conducting thorough contextual analysis, these models enhance the detection process by identifying subtle indications of compromise, which traditional methods may overlook. This research also explains the challenges and limitations related to the application of transformer-based models in real-world cybersecurity settings, which include computing requirements and large-scale labeled datasets’ requirements. By the end, the article suggests potential future research avenues in order to improve and integrate these models into cybersecurity systems.

Noise resilient and accurate target detection using fractional-order Fourier domain correlation

Quantum enhanced optical target detection provides a unique route to increased noise resilience of classical LiDARs (laser imaging, detection, and ranging) by using time correlation of non-classical photon pairs. Such enhancement is dictated by the detector temporal uncertainty that is typically orders of magnitude larger than the intrinsic correlation time. To circumvent such detector limitation, we explore the possibility of measuring correlation in the fractional-order Fourier domain (FrFD), which can be realized with the non-local dispersion cancellation. Experimentally, we verify this principle using a fiber-coupled waveguide source of photon pairs, showing enhanced noise rejection as compared with conventional time-domain coincidence detection and classical intensity detection. For false alarm rates of 10−9, an 89 dB improved detection rate is measured using receiver operating characteristics when comparing our FrFD protocol with classical intensity detection. Additionally, we discussed the resilience of FrFD correlation against intentionally prepared counterfeit signal photons. The possibility enabled by measuring correlation in the FrFD should also provide potential benefit for various sensing and communication protocols that relies on coincidence detection.

EMPViT: Efficient multi-path vision transformer for security risks detection in power distribution network

To maintain the safe operation of power distribution network (PDN) equipment, it is important to accurately and promptly identify security risks. However, conventional drone-based object detection methods face challenges due to noise and similarity features in risk targets, as well as limited computing resources of unmanned aerial vehicles (UAVs). To address these challenges, an efficient embedding-based multi-path fusion architecture is proposed. This architecture uses a re-parameterized depthwise block to embed local context information at different scales, enhancing the extraction of tiny features while preserving inference speed. Additionally, a coordinated self-attention module is proposed to reduce computational complexity while maintaining the performance of global information. By fusing fine and coarse feature representations without requiring a lot of computation, this module efficiently learns from both local and global features from images. The goal is to create an efficient multi-path vision transformer (EMPViT) architecture that achieves a balance between accuracy and efficiency. The proposed EMPViT has been evaluated on two different drone image dataset, demonstrating better performance compared to other architectures. Specifically, the EMPViT-S improves the detection mAP by 1.2%, and the inference speed is improved to 1.24 times on average on Drone-PDN dataset. It has achieved the same performance improvement on VisDrone-DET2019 dataset, gaining detection performance by 1.3% and 1.2 times acceleration on average.

An intelligent model of pulmonary emphysema detection using adaptive image segmentation and multi-dilated densenet with attention mechanism

Pulmonary emphysema is a significant factor in lung cancer and Chronic Obstructive Pulmonary Disease (COPD). Traditional pulmonary emphysema detection models may have difficulty in accurately detecting and diagnosing the severity of the disease. So, this work developed a novel pulmonary emphysema detection system with the help of deep learning frameworks. Originally, the significant images are accumulated from the benchmark sources, and fed into the Adaptive Trans-DenseUnet (ATDUnet)-based segmentation model. The ATDUnet model is highly effective in accurately segmenting pulmonary emphysema from the gathered images. Moreover, to enhance the segmentation process, the parameters are tuned in the ATDUnet using the Statistical Solution of the Osprey Optimization Algorithm (SSOOA). Subsequently, the segmented image is given to the pulmonary emphysema classification phase, where the Multi-Dilated DenseNet with Attention Mechanism (MDDNet-AM) is employed. By incorporating an attention mechanism, MDDNet-AM can focus on important features within the image for improved accuracy and efficiency in diagnosis. Finally, the developed model offered the pulmonary emphysema classified outcome. Then, the outcome of the developed model is compared against conventional pulmonary emphysema detection methods, and given the accuracy to be 93.10. Therefore, the result proved that the use of developed advanced technology in pulmonary emphysema detection has shown promising results in the field of respiratory health.

Leveraging Swarm Intelligence for Invariant Rule Generation and Anomaly Detection in Industrial Control Systems

Industrial control systems (ICSs), which are fundamental to the operation of critical infrastructure, face increasingly sophisticated security threats due to the integration of information and operational technologies. Conventional anomaly detection techniques often lack the ability to provide clear explanations for their detection, and their inherent complexity can impede practical implementation in the resource-constrained environments typical of ICSs. To address these challenges, this paper proposes a novel approach that leverages swarm intelligence algorithms for the extraction of numerical association rules, specifically designed for anomaly detection in ICS. The proposed approach is designed to effectively identify and precisely localize anomalies by analyzing the states of sensors and actuators. Experimental validation using the Secure Water Treatment (SWaT) dataset demonstrates that the proposed approach can detect over 84% of attack instances, with precise anomaly localization achievable by examining as few as two to six sensor or actuator states. This significantly improves the efficiency and accuracy of anomaly detection. Furthermore, since the method is based on the general control dynamics of ICSs, it demonstrates robust generalization, making it applicable across a wide range of industrial control systems.

Novel SoC-Based FBG Calibration Method for Decoupled Temperature and Strain Analysis within LIB Cells

Abstract Internal temperature monitoring of battery cells can be very useful, as the core temperature can deviate significantly from that of the housing, especially in case of cells with a thick electrode stack. Conventional resistance temperature detectors can accurately measure temperature, but are limited to the outer surface of the cell due to induction effects. They are therefore not suitable for internal in situ measurements. Fiber Bragg grating (FBG) sensors are unaffected by the electric field as they operate by reflecting light. However, a specific difficulty is the distinction of temperature vs. strain effects as the grating is sensitive to both. In this work a calibration routine to separate the influences of temperature and strain in a lithium-ion battery cell is presented and examined for two multi-layer stack pouch cells (10 and 20 Ah). The obtained in situ temperature data reveal a difference of up to 2°C between center and cell housing at elevated discharge rate (4C) and a delay in detection of temperature peaks by the external sensor by 12 s. Strain data correlate with numbers of electrode layers in the stack and yield a stress of up to 27.3 MPa in the center of the 20 Ah cell.

A Review of Applications of Photon-Counting Computed Tomography in Head and Neck Imaging.

Photon-counting CT (PCCT), approved for clinical practice for over two years now, both improves on features of conventional energy-integrating detector (EID) CT and introduces new capabilities such as multienergy acquisition. PCCT is already transforming all domains of radiology, including head and neck imaging, and will become increasingly utilized in the approaching years. In this review, we first concisely explain the key physical principles distinguishing PCCT from EID-CT. We then discuss how the underlying physics leads to the novel features associated with PCCT, focusing on improved artifact reduction, spatial resolution, contrast-to-noise ratio, as well as multienergy acquisition and reduced contrast and radiation doses. Next, we review head and neck PCCT applications and comparison to EID-CT in dental imaging, sinus imaging, temporal bone, tumor imaging, and vascular imaging. Within the temporal bone applications, we explore normal anatomy, pathologic anatomy, and the appearance of protheses and implants. Representative imaging is provided to highlight differences between PCCT and EID-CT. Finally, we highlight areas of ongoing research in PCCT.

Black-Box Adversarial Attacks Against SQL Injection Detection Model

Structured Query Language (SQL) injection attacks represent a substantial threat to the security of web applications, making the development of effective detection techniques crucial. These techniques have evolved from traditional signature-based techniques to more advanced techniques based on machine learning models. Machine learning detection models are often vulnerable to adversarial examples. Adversarial examples are deliberately crafted inputs designed to deceive models into making incorrect predictions by subtly altering the original dataset in ways that are typically imperceptible to humans. To train and test these machine learning models, datasets comprising both malicious and normal data are indispensable. However, the lack of sufficient and balanced datasets presents a significant challenge, particularly for models intended to detect SQL injection attacks. Most network traffic datasets exhibit a substantial class imbalance, with a disproportionate amount of normal traffic compared to malicious traffic, making it difficult to train effective and reliable detection models. This study addressed the shortcomings of current SQL injection detection techniques and proposed a conditional tabular generative adversarial network adversarial attack method. We evaluated the effectiveness of the generated adversarial SQL injection examples using qualitative and quantitative methods, measuring their ability to evade the detection model. A conventional neural network algorithm detection model was built and tested, and the generated adversarial examples successfully bypassed the detection model at a rate of up to 6%. The evidence demonstrated that the conditional tabular generative adversarial network successfully captures the statistical properties of real data and generates synthetic data that accurately represents the real data. This method is also expected to address the problem of insufficient and imbalanced SQL injection datasets, which could aid in training various machine learning models beyond the one used in our study.

Comprehensive image quality comparison of conventional and new flat panel detectors under bedside chest radiography beam conditions.

Recently, a novel wireless flat-panel detector with auto-exposure control has become available. This study aimed to elucidate the potential advantages of the new detector over conventional detectors through a comprehensive analysis of the physical image quality characteristics. Measurements were conducted on two models: new (720C) and conventional (710C) versions; this assessment was performed by assuming the beam quality for bedside chest radiography, utilizing a portable device for X-ray exposure. The detective quantum efficiency (DQE) was computed based on the presampled modulation transfer function (MTF) and normalized noise power spectrum. The validity of the DQE results was verified through the visualization of the analog blurring components and a detailed analysis of the noise components. The spatial frequency at which the presampled MTF value reached 10% was 5.2 cycles/mm for 720C and 3.9 cycles/mm for 710C. The full width at half-maximum of the spatial spreading of analog components was estimated at 0.09mm for 720C and 0.14mm for 710C by the visualization. Regarding the DQE, 720C was superior under low-dose conditions despite no significant differences being observed under high-dose conditions. The new detector demonstrated superior resolution characteristics compared with the conventional detector and an improvement in the DQE under low-dose conditions. However, similar to the conventional detector, a significant dose dependence caused by a structural factor was confirmed for the DQE. These results suggest the existence of an appropriate dose range for maximizing detector performance and provide insights crucial for optimization tasks in the X-ray imaging.

Genetic screening of α-thalassemia fusion gene using routine flow-through hybridization.

The fusion gene is a rare form of α-thalassemia. Patients carrying the fusion gene could be misdiagnosed as normal or -α4.2deletion by the conventional thalassemia detection methods. The aim of this study was to present the detection of fusion genes using routine flow-through hybridization, as well as to analyze hematological and molecular characteristics. Samples were collected at our hospital from January 2019 to January 2024. Common thalassemia mutations in the Chinese population were conducted by flow-through hybridization. Samples showing faint coloration at the -α4.2 mutation site on hybridization membrane were considered suspicious. Samples detected as suspicious for -α4.2deletion were rechecked by conventional Gap-PCR. Those samples suspected of having -α4.2deletions were finally confirmed with specific primers for Gap-PCR and Sanger sequencing. Of the 32,083 samples, 25 samples (0.08%) were detected as suspected of having -α4.2 deletion by flow-through hybridization. However, upon reevaluation wtih conventional Gap-PCR reagents capable of detecting -α4.2 deletion, all were found to be negative for the deletion. Specific primers for Gap-PCR were designed, and fusion gene fragments were amplified. DNA sequencing of the HBA gene showed a 7-base mutation corresponding to the α-thalassemia fusion gene. Among the 25 samples, 22 were heterozygous carriers. Three samples were combined: one with Hb QS, one with β-thalassemia, and one with Hb G-Honolulu.Most hematological indices and capillary electrophoresis results were in the normal reference range. The fusion gene was present in 0.08% of the population in the Guangzhou region of Guangdong province, southern China. Conventional genetic methods tend to misdiagnose the fusion gene but can be effectively screened with flow-through hybridization.

Automatic Watershed Segmentation of Cancerous Lesions in Unsupervised Breast Histology Images

Segmentation of nuclei in histology images is key in analyzing and quantifying morphology changes of nuclei features and tissue structures. Conventional diagnosis, segmenting, and detection methods have relied heavily on the manual-visual inspection of histology images. These methods are only effective on clearly visible cancerous lesions on histology images thus limited in their performance due to the complexity of tissue structures in histology images. Hence, early detection of breast cancer is key for treatment and profits from Computer-Aided-Diagnostic (CAD) systems introduced to efficiently and automatically segment and detect nuclei cells in pathology. This paper proposes, an automatic watershed segmentation method of cancerous lesions in unsupervised human breast histology images. Firstly, this approach pre-processes data through various augmentation methods to increase the size of dataset images, then a stain normalization technique is applied to these augmented images to isolate nuclei features from tissue structures. Secondly, data enhancement techniques namely; erosion, dilation, and distance transform are used to highlight foreground and background pixels while removing unwanted regions from the highlighted nuclei objects on the image. Consequently, the connected components method groups these highlighted pixel components with similar intensity values and, assigns them to their relevant labeled component binary mask. Once all binary masked groups have been determined, a deep-learning recurrent neural network from the Keras architecture uses this information to automatically segment nuclei objects with cancerous lesions and their edges on the image via watershed filling. This segmentation method is evaluated on an unsupervised, augmented human breast cancer histology dataset of 11,151 images. This proposed method produced a significant evaluation result of 98% F1-accuracy score.

Proto-DS: A Self-Supervised Learning-Based Nondestructive Testing Approach for Food Adulteration with Imbalanced Hyperspectral Data.

Conventional food fraud detection using hyperspectral imaging (HSI) relies on the discriminative power of machine learning. However, these approaches often assume a balanced class distribution in an ideal laboratory environment, which is impractical in real-world scenarios with diverse label distributions. This results in suboptimal performance when less frequent classes are overshadowed by the majority class during training. Thus, the critical research challenge emerges of how to develop an effective classifier on a small-scale imbalanced dataset without significant bias from the dominant class. In this paper, we propose a novel nondestructive detection approach, which we call the Dice Loss Improved Self-Supervised Learning-Based Prototypical Network (Proto-DS), designed to address this imbalanced learning challenge. The proposed amalgamation mitigates the label bias on the most frequent class, further improving robustness. We validate our proposed method on three collected hyperspectral food image datasets with varying degrees of data imbalance: Citri Reticulatae Pericarpium (Chenpi), Chinese herbs, and coffee beans. Comparisons with state-of-the-art imbalanced learning techniques, including the Synthetic Minority Oversampling Technique (SMOTE) and class-importance reweighting, reveal our method's superiority. Notably, our experiments demonstrate that Proto-DS consistently outperforms conventional approaches, achieving the best average balanced accuracy of 88.18% across various training sample sizes, whereas the Logistic Model Tree (LMT), Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN) approaches attain only 59.42%, 60.38%, and 66.34%, respectively. Overall, self-supervised learning is key to improving imbalanced learning performance and outperforms related approaches, while both prototypical networks and the Dice loss can further enhance classification performance. Intriguingly, self-supervised learning can provide complementary information to existing imbalanced learning approaches. Combining these approaches may serve as a potential solution for building effective models with limited training data.

Non-invasive ultra-sensitive detection of breast cancer biomarker using cerium nanoparticle functionalized graphene oxide enabled impedimetric aptasensor

Epidermal growth factor receptor (EGFR) is a transmembrane protein and a key biomarker implicated in the pathogenesis of breast cancer. Early and precise detection of EGFR is crucial for effective diagnosis, prognosis, and therapeutic intervention. However, conventional EGFR detection techniques, such as biopsy and immunohistochemistry, are often invasive, time-consuming, and limited in sensitivity, highlighting the demand for non-invasive, highly sensitive detection methods. In this study, we fabricated a cerium oxide (CeO₂) and graphene oxide (GO) nanocomposite-based aptasensor for the non-invasive detection of EGFR using electrochemical impedance spectroscopy (EIS). The CeO₂-GO nanocomposite was synthesized via the sol-gel method and characterized through UV–Vis spectroscopy, FTIR, TEM, and XRD, confirming the crystalline structure of hexagonal CeO₂ nanoparticles on amorphous GO sheets. The nanocomposite was functionalized with aptamers specific to EGFR using covalent coupling reactions. The EIS analysis of the fabricated aptasensor (GCE/CeO₂-GO/EGFR-Apt/BSA) demonstrated a wide linear detection range from 10 fg mL-1 to 100 ng mL-1, with an ultralow detection limit of 1.87 fg mL-1 in PBS, 3.16 fg mL-1 in serum, 5.31 fg mL-1 in sweat, and 6.14 fg mL-1 in saliva samples. These results highlight the aptasensor's high sensitivity, specificity, and potential for real-time, non-invasive EGFR monitoring in clinical samples such as serum, sweat, and saliva. This approach would facilitate early detection of cancer and personalized diagnostics in point-of-care settings.