Glaucoma, a leading cause of irreversible blindness worldwide, can be effectively managed if detected early. Glaucoma is directly associated with aging as it commonly occurs in people over the age of 40 and in elderly...
详细信息
Glaucoma, a leading cause of irreversible blindness worldwide, can be effectively managed if detected early. Glaucoma is directly associated with aging as it commonly occurs in people over the age of 40 and in elderly people. Glaucoma detection in retinal fundus images typically involves utilizing image processing and machine learning techniques. By leveraging advancements in computer vision, a robust and automated system is developed to assist ophthalmologists in screening and diagnosing glaucoma from retinal fundus images. Furthermore, fundus images can vary significantly in quality due to factors like illumination variations, focus, and artifacts. Ensuring consistent image quality across different datasets and acquisition devices is essential for reliable detection. Addressing these challenges requires interdisciplinary collaboration between ophthalmologists to develop robust and reliable solutions for the detection of glaucoma. Hence a novel mask autoencoder-based crossover binary sand cat (MA-CBSC) algorithm is proposed to detect glaucoma. In this algorithm, the mask autoencoder recognizes the features indicating the presence of glaucoma in the input images and the crossover binary sand cat algorithm is used to fine tune the overall performance of the algorithm by selecting the most appropriate features escaped due to overfitting issues. Preprocessing steps such as image enhancement, filtering, and data cleaning are applied to the extracted ROI for the purpose of increasing the image quality and enhancing the visibility of features relevant to glaucoma detection. ROI extraction attributes namely optic disc, cup-to-disc ratio, bean-pot cupping, and vertical enlargement are derived from the ROI along with some other relevant features. In this work, the crossover-based binary sand cat optimization algorithm is utilized for hyperparameter tuning to enhance the efficiency of the MA-CBSC method. Extensive experimental assessments are conducted, comparing the effectiv
Diffractive deep neural network (D2NN), known for its high speed and strong parallelism, is applied across various fields, including pattern recognition, image processing, and image transmission. However, existing net...
详细信息
Diffractive deep neural network (D2NN), known for its high speed and strong parallelism, is applied across various fields, including pattern recognition, image processing, and image transmission. However, existing network architectures primarily focus on data representation within the original domain, with limited exploration of the latent space, thereby restricting the information mining capabilities and multifunctional integration of D2NNs. Here, an all-optical autoencoder (OAE) framework is proposed that linearly encodes the input wavefield into a prior shape distribution in the diffractive latent space (DLS) and decodes the encoded pattern back to the original wavefield. By leveraging the bidirectional multiplexing property of D2NN, the OAE modelsfunction as encoders in one direction and as decoders in the opposite direction. The models are applied to three areas: image denoising, noise-resistant reconfigurable image classification, and image generation. Proof-of-concept experiments are conducted to validate numerical simulations. The OAE framework exploits the potential of latent representations, enabling single set of diffractive processors to simultaneously achieve image reconstruction, representation, and generation. This work not only offers fresh insights into the design of optical generative models but also paves the way for developing multifunctional, highly integrated, and general optical intelligent systems.
Identifying and evaluating favorable areas is crucial for shale oil exploration and development, well-location deployment, and fracturing design. Traditional machine learning methods struggle to accurately extract the...
详细信息
Identifying and evaluating favorable areas is crucial for shale oil exploration and development, well-location deployment, and fracturing design. Traditional machine learning methods struggle to accurately extract the characteristics of favorable shale oil areas with limited labeled data, affecting accuracy and generalization. This study proposes an intelligent method for identifying favorable shale oil areas under semi-supervised learning (SSAEplus) to identify and evaluate favorable shale oil areas of the Qingshankou Formation in the Songliao Basin. The experimental results show that this method can effectively overcome the favorable area identification models' reliance on labeled data and can adaptively extract the characteristics of favorable shale oil areas without supervision. The accuracy of model identification is as high as 98.82%. Compared with other methods, the SSAE-plus yields higher accuracy and efficiency, while being more stable and generalizable. The SSAE-plus achieved over 95% accuracy in identifying favorable shale oil areas across six datasets. It has broad application prospects in identifying and evaluating favorable areas, and provides valuable theoretical insights for shale oil development and exploration well layout.
Generative Artificial Intelligence (AI) techniques have become integral part in advancing next generation wireless communication systems by enabling sophisticated data modeling and feature extraction for enhanced netw...
详细信息
Generative Artificial Intelligence (AI) techniques have become integral part in advancing next generation wireless communication systems by enabling sophisticated data modeling and feature extraction for enhanced network performance. In the realm of open radio access networks (O-RAN), characterized by their gregated architecture and heterogeneous components from multiple vendors, the deployment of generative models offers significant advantages for network management such as traffic analysis, traffic forecasting anomaly detection. However, the complex and dynamic nature of O-RAN introduces challenges that necessitate not only accurate detection mechanisms but also reduced complexity, scalability, and most importantly interpretability to facilitate effective network management. In this study, we introduce the XAInomaly framework, an explainable and interpretable Semi-supervised (SS) Deep Contractive autoencoder (DeepCAE) design for anomaly detection in O-RAN. Our approach leverages the generative modeling capabilities SS-DeepCAE model to learn compressed, robust representations of normal network behavior, which captures essential features, enabling the identification of deviations indicative of anomalies. To address the black nature of deep learning models, we propose reactive Explainable AI (XAI) technique called fastshap-C, is providing transparency into the model's decision-making process and highlighting the features contributing to anomaly detection.
One of the most serious security threats faced by the Internet today is multi-stage attacks. In response to this challenge, anomaly detection-based methods have been widely used to identify different stages of such at...
详细信息
One of the most serious security threats faced by the Internet today is multi-stage attacks. In response to this challenge, anomaly detection-based methods have been widely used to identify different stages of such attacks. However, current anomaly detection approaches for detecting attack stages face several challenges: (1) Traditional methods often adopt a global perspective, lacking detailed consideration of the traffic characteristics at each stage, which may reduce the accuracy in detecting specific stages. (2) Many detection methods rely on deep learning models with complex internal structures, making their decision-making process opaque and difficult for users to interpret. This also complicates model optimization and improvement. To address these challenges, this paper proposes an attack stage detection method based on a vector reconstruction error autoencoder. By analyzing each stage independently, the proposed method enhances detection precision. It also integrates the permutation feature importance technique to quantify and interpret the model's reliance on different features, guiding feature selection and model optimization. Experiments conducted using the CIC-IDS2017 and CSE-CIC-IDS2018 datasets demonstrate that the proposed method achieves higher accuracy, precision, recall, and F1 score compared to other methods, confirming its feasibility and effectiveness in detecting multi-stage attacks.
This paper introduces a novel methodology for evaluating human driving behavior influenced by shoe type and its impact on collision risk. While human factors, such as footwear, are recognized to affect driving safety,...
详细信息
This paper introduces a novel methodology for evaluating human driving behavior influenced by shoe type and its impact on collision risk. While human factors, such as footwear, are recognized to affect driving safety, studies quantitively assessing the effects of shoe types on safety has been limited. To address this, we utilize an autoencoder and human-centered risk assessment algorithms to investigate human driving behavior and collision risk. Experiments were conducted in various real-world driving scenarios, involving two distinct types of shoes. The autoencoder extracts features from the driving data and enables us to analyze the effects of shoe type on driving behavior. Additionally, collision risk analysis is used to verify the validity and impact of the feature extraction results on safe driving. This study contributes to enhancing our understanding of how footwear influences driver behavior and safety. Furthermore, this methodology establishes a groundwork for future research on applying quantitative evaluations to other human factors that influence driving behavior.
High-dimensional hyperspectral imagery presents significant challenges for accurate unmixing due to spectral variability, limited spatial resolution, and noise. Traditional unmixing approaches often rely on spatial mu...
详细信息
High-dimensional hyperspectral imagery presents significant challenges for accurate unmixing due to spectral variability, limited spatial resolution, and noise. Traditional unmixing approaches often rely on spatial multi-scale processing, leading to redundant computations and suboptimal feature representations. In response to these challenges, we propose a novel Channel Multi-Scale Dual-Stream autoencoder (CMSDAE) that innovatively integrates channel-level multi-scale feature extraction with dedicated spectral information guidance. By leveraging Channel-level Multi-Scale Perception Blocks and a Hybrid Attention-Aware Feature Block, CMSDAE efficiently captures diverse and robust spectral-spatial features while significantly reducing computational redundancy. Extensive experiments on both synthetic and real-world datasets demonstrate that CMSDAE not only improves unmixing accuracy and robustness against noise but also offers enhanced computational efficiency compared to state-of-the-art methods. This work provides new insights into spectral-spatial modeling for hyperspectral unmixing, promising more reliable and scalable analysis in challenging remote sensing applications.
The growth of interconnected devices has led to an enormous volume of temporal data that requires specialized compression models for efficient storage. Besides this, most applications need to classify these data effic...
详细信息
The growth of interconnected devices has led to an enormous volume of temporal data that requires specialized compression models for efficient storage. Besides this, most applications need to classify these data efficiently, and having to reconstruct the original data from the compressed representation to then classify them is not optimal. For this reason, we propose a Recurrent autoencoder for Time-series Compression and Classification, termed RAT-CC, that allows to perform any classification task on the compressed representation without needing to reconstruct the original time-series data. RAT-CC leverages a Long Short-Term Memory (LSTM) recurrent autoencoder with a dual-loss function: the standard reconstruction loss to minimize reconstruction error;and an embedding loss to preserve relative distances in the compressed embedding space. This combined loss ensures that the learned embeddings remain meaningful for classification tasks while preserving the necessary information for reconstruction. We assess the compression and classification performance of RAT-CC on four datasets taken from different domains. RAT-CC is implemented in Keras and freely available at (https://***/ChJ4m3s/RAT-CC).
Electrocardiograms (ECG) are vital for diagnosing various cardiac conditions but are often corrupted by noise from multiple sources, which can hinder accurate interpretation. Denoising ECG signals is particularly chal...
详细信息
Electrocardiograms (ECG) are vital for diagnosing various cardiac conditions but are often corrupted by noise from multiple sources, which can hinder accurate interpretation. Denoising ECG signals is particularly challenging because noise usually overlaps with the frequency range of the signal of interest. We proposed a convolutional autoencoder with sequential and channel attention (CAE-SCA) to address this issue. Sequential attention (SA) is based on long short-term memory (LSTM), which captures causal-temporal relationships. Meanwhile, channel attention (CA) is used to emphasize important features within channels. SA is applied to the skip connection of each encoder block, and CA is applied after each decoder block. We validated the CAE-SCA using the MIT-BIH and SHDB-AF databases as clean ECG signals, with the MIT-BIH Noise Stress Test Database as the noise source. Experimental results give an average SNR value of 16.187 dB, RMSE of 0.059, and PRD value of 18.529 in the MIT-BIH database. While in the SHDB-AF dataset, the model obtained 15.308 dB of SNR, 0.049 of RMSE, and 19.220 of PRD. These results demonstrate our CAE-SCA outperforms all the state-of-the-art methods across all tested metrics. For efficiency, CAE-SCA achieved competitive results in the metrics of floating-point operations (FLOPs), inference time, and total parameters. This allowed CAE-SCA to be implemented in edge devices as we tested using our custom ECG acquisition circuit. A significance test further confirms a statistically significant improvement in SNR values achieved by the CAE-SCA compared to baseline models, suggesting the CAE-SCA's potential for advancing ECG processing in healthcare applications.
Objective. Non-stationarity in electroencephalogram (EEG) signals poses significant challenges for the performance and implementation of brain-computer interfaces (BCIs). Approach. In this study, we propose a novel me...
详细信息
Objective. Non-stationarity in electroencephalogram (EEG) signals poses significant challenges for the performance and implementation of brain-computer interfaces (BCIs). Approach. In this study, we propose a novel method for cross-session BCI tasks that employs a supervised autoencoder to reduce session-specific information while preserving task-related signals. Our approach compresses high-dimensional EEG inputs and reconstructs them, thereby mitigating non-stationary variability in the data. In addition to unsupervised minimization of the reconstruction error, the objective function of the network includes two supervised terms to ensure that the latent representations exclude session identity information and are optimized for subsequent classification. Main results. Evaluation across three different motor imagery datasets demonstrates that our approach effectively addresses domain adaptation challenges, outperforming both na & iuml;ve cross-session and within-session methods. Significance. Our method eliminates the need for data from new sessions, making it fully unsupervised concerning new session data and reducing the necessity for recalibration with each session. Furthermore, the reduction of session-specific information in the reconstructed signals indicates that our approach effectively denoises non-stationary signals, thereby enhancing the accuracy of BCI models. Future applications could extend this model to a broader range of BCI tasks and explore the residual signals to investigate sources of non-stationary brain components and other cognitive processes.
暂无评论