Harnessing hyperspectral imaging and deep learning for advanced e-waste classification using three spectral bands

Abstract. Hyperspectral images (HSIs) contain hundreds of spectral bands, providing high-resolution spectral information pertaining to the Earth’s surface. Additionally, abundant spatial contextual information can also be obtained simultaneously from a HSI. To characterize the properties of ground objects, classification is the most widely-used technology in the field of remote sensing, where each pixel in a HSI is assigned to a pre-defined class. Over the past decade, deep learning has attracted increasing attention in the machine-learning and computer-vision domains, due to its favourable performances for various types of tasks, and it has been successfully introduced to the remote-sensing community. Instead of utilizing the shallow features within in a given image, which is the approach that is generally adopted in other conventional classification methods, deep-learning algorithms can extract hierarchical features from raw HSI data. Within the deep-learning framework, recurrent neural networks (RNNs), which are able to encode sequential features, have exhibited promising capabilities and have achieved encouraging performances, especially for the natural-language processing and speech-recognition communities. As multi-temporal remote-sensing images can be readily obtained from increasing numbers of satellite and unmanned aircraft systems, and since analysis of such multi-temporal data comprises a critical issue within numerous research subfields, including land-cover and land-change analyses, and land-resource management, RNNs have been applied in recent studies in order to extract temporal sequential features from multi-temporal remote-sensing images for the purpose of image classification. Apart from using multi-temporal image datasets, RNNs can also be utilized on a single image, where the spectral feature/band of each individual pixel can be taken as a sequential feature for the input layer of RNNs. However, the application of such sequential feature extraction that relies on a single image still needs to be further investigated since applying RNNs to spectral bands will directly introduce more parameters that need to be optimized, consequently increasing the total training time.In this study, we propose a novel RNN-based HSI classification framework. In this framework, unlabelled pixels obtained from a single image are considered when constructing sequential features. Two spatial similarity measurements, referred to as pixel-matching and block-matching, respectively, are employed to extract pixels that are “similar” to the target pixel. Then, the sequential feature of the target pixel is constructed by exploiting several of the most “similar” pixels and ordering them based on their similarities to the target pixel. The aforementioned two schemes are advantageous, as unlabelled pixels within the given HSI are taken into consideration for similarity measurement and sequential feature construction for the RNN model. Moreover, the block-matching scheme also takes advantage of spatial contextual information, which has been widely utilized in spatial-spectral-based HSI classification methods. To evaluate the proposed methods, two benchmark HSIs are used, including a HSI collected over Pavia University, Italy by the airborne Reflective Optics System Imaging Spectrometer (ROSIS) sensor, and an image acquired over the Salinas Valley, California, USA via the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor. Spatio-temporally coincident ground-reference data accompanies each of these respective HSIs. In addition, the proposed methods are compared with three state-of-the-art algorithms, including support vector machine (SVM), the 1-dimensional convolutional neural network (1DCNN), and the 1-dimensional RNN (1DRNN).Experimental results indicate that our proposed methods achieve markedly better classification performance compared with the baseline algorithms on both datasets. For example, for the Pavia University image, the block-matching based RNN achieves the highest overall classification accuracy, with 94.32% accuracy, which is 9.87% higher than the next most accurate algorithm of the aforementioned three baseline methods, which in this case is the 1DCNN, with 84.45% overall accuracy. More specifically, the block-matching method performs better than the pixel-matching method in terms of both quantitative and qualitative assessments. Based on visual assessment/interpretation of the classification maps, it is apparent that “salt-and-pepper” noise is markedly alleviated; with block-matching, smoother classified images are generated compared with pixel-matching-based methods and the three baseline algorithms. Such results demonstrate the effectiveness of utilizing spatial contextual information in the similarity measurement.

Despite numerous studies of selection on position and number of spectral vision bands, explanations to the function of narrow spectral bands are lacking. We investigate dragonflies (Odonata), which have the narrowest spectral bands reported, in order to investigate what features these narrow spectral bands may be used to perceive. We address whether it is likely that narrow red bands can be used to identify conspecifics by the optical signature from wing interference patterns (WIPs). We investigate the optical signatures of Odonata wings using hyperspectral imaging, laser profiling, ellipsometry, polarimetric modulation spectroscopy, and laser radar experiments. Based on results, we estimate the prospects for Odonata perception of WIPs to identify conspecifics in the spectral, spatial, intensity, polarization, angular, and temporal domains. We find six lines of evidence consistent with an ability to perceive WIPs. First, the wing membrane thickness of the studied Odonata is 2.3 μm, coinciding with the maximal thickness perceivable by the reported bandwidth. Second, flat wings imply that WIPs persist from whole wings, which can be seen at a distance. Third, WIPs constitute a major brightness in the visual environment only second after the solar disk. Fourth, WIPs exhibit high degree of polarization and polarization vision coincides with frontal narrow red bands in Odonata. Fifth, the angular light incidence on the Odonata composite eye provides all prerequisites for direct assessment of the refractive index which is associated with age. Sixth, WIPs from conspecifics in flight make a significant contribution even to the fundamental wingbeat frequency within the flicker fusion bandwidth of Odonata vision. We conclude that it is likely that WIPs can be perceived by the narrow red bands found in some Odonata species and propose future behavioral and electrophysiological tests of this hypothesis.

CT-Based Radiomics and Deep Learning for Preoperative Thyroid Nodule Classification: A Systematic Review, Meta-analysis, and Radiologist Comparison.

Automated peanut defect detection using hyperspectral imaging and deep learning: A real-time approach for smart agriculture

With numerous and contiguous spectral bands acquired from visible light (400?1,000 nm) to (near) infrared (1,000?1,700 nm and over), hyperspectral imaging (HSI) can potentially identify different objects by detecting minor changes in temperature, moisture, and chemical content. As a result, HSI has been widely applied in a number of application areas, including remote sensing [1]. HSI data contains two-dimensional (2-D) spatial and one-dimensional spectral information, and naturally forms a three-dimensional (3-D) hypercube with a high spectral resolution in nanometers that enables robust discrimination of ground features. However, new challenges arise in dealing with extremely large data sets. For a hypercube with relatively small spatial dimension of 600 ? 400 pixels at 16 bits-per-band-per-pixel, the data volume becomes 120 MB for 250 spectral bands. In some cases, this large data volume can be linearly increased when multiple hypercubes are acquired across time to monitor system dynamics in consecutive time instants. When the ratio between the feature dimension (spectral bands) and the number of data samples (in vector-based pixels) is vastly different, high-dimensional data suffers from the well-known curse of dimensionality. For feature extraction and dimensionality reduction, principal components analysis (PCA) is widely used in HSI [2], where the number of extracted components is significantly reduced compared to the original feature dimension, i.e., the number of spectral bands. For effective analysis of large-scale data in HSI, conventional PCA faces three main challenges:

Hyperspectral image (HSI) classification is a classical task in remote sensing image analysis. With the development of deep learning, schemes based on deep learning have gradually become the mainstream of HSI classification. However, existing HSI classification schemes either lack the exploration of category-specific information in the spectral bands and the intrinsic value of information contained in features at different scales, or are unable to extract multiscale spatial information and global spectral properties simultaneously. To solve these problems, in this article, we propose a novel HSI classification framework named CL-MGNet, which can fully exploit the category-specific properties in spectral bands and obtain features with multiscale spatial information and global spectral properties. Specifically, we first propose a spectral weight learning (SWL) module with a category consistency loss to achieve the enhancement of information in important bands and the mining of category-specific properties. Then, a multiscale backbone is proposed to extract the spatial information at different scales and the cross-channel attention via multiscale convolution and a grouping attention module. Finally, we employ an attention multilayer perceptron (attention-MLP) block to exploit the global spectral properties of HSI, which is helpful for the final fully connected layer to obtain the classification result. The experimental results on five representative hyperspectral remote sensing datasets demonstrate the superiority of our method.

Cognitive learning strategies are focused on the improvement of the learner’s ability to analyze information in a deeper manner and efficiently handle new situations by transferring and applying the knowledge. These techniques result in enhanced and better- retained learning. In order to cater to the needs of different students having different levels of cognitive learning, it’s very important to assess their learning ability. In this paper, a method based on deep learning is presented to classify the learners based on their past performance. This technique takes the students’ past semester marks, their total failures in subjects/passing heads, and their current semester attendance. The proposed method classifies the learners into three categories, namely slow, fast, and average learners. A deep learning classifier with multilayer perceptron–based nodes is built for the classification. The proposed method is fully automatic and robust. The final accuracy of 90% is achieved in the classification of the learners in their cognitive learning level.

Malignant glioma resection is often the first line of treatment in neuro-oncology. During glioma surgery, the discrimination of tumor's edges can be challenging at the infiltration zone, even by using surgical adjuncts such as fluorescence guidance (e.g., with 5-aminolevulinic acid). Challenging cases in which there is no visible fluorescence include lower-grade gliomas, tumor cells infiltrating beyond the margin as visualized on pre- and/or intraoperative MRI, and even some high-grade tumors. One field of research aiming to address this problem involves inspecting in detail the light emission spectra from different tissues (e.g., tumor vs. normal brain vs. brain parenchyma infiltrated by tumor cells). Hyperspectral imaging measures the emission spectrum at every image pixel level, thus combining spatial and spectral information. Assuming that different tissue types have different "spectral footprints," eventually related to higher or lower abundances of fluorescent dyes or auto-fluorescing molecules, the tissue can then be segmented according to type, providing surgeons a detailed spatial map of what they see. However, processing from raw hyperspectral data cubes to maps or overlays of tissue labels and potentially further molecular information is complex. This chapter will explore some of the classical methods for the various steps of this process and examine how they can be improved with machine learning approaches. While preliminary work on machine learning in hyperspectral imaging has had relatively limited success in brain tumor surgery, more recent research combines this with fluorescence to obtain promising results. In particular, this chapter describes a pipeline that isolates biopsies in ex vivo hyperspectral fluorescence images for efficient labeling, extracts all the relevant emission spectra, preprocesses them to correct for various optical properties, and determines the abundance of fluorophores in each pixel, which correspond directly with the presence of cancerous tissue. Each step contains a combination of classical and deep learning-based methods. Furthermore, the fluorophore abundances are then used in four machine learning models to classify tumor type, WHO grade, margin tissue type, and isocitrate dehydrogenase (IDH) mutation status in brain tumors. The classifiers achieved average test accuracies of 87%, 96.1%, 86%, and 93%, respectively, thus greatly outperforming prior work both with and without fluorescence. This field is new, but these early results show great promise for the feasibility of data-driven hyperspectral imaging for intraoperative classification of brain tumors during fluorescence-guided surgery.

Medical imaging is an indispensable tool in clinical diagnosis and therapeutic decision-making, encompassing a wide range of modalities such as radiography, ultrasound, CT, and MRI. With the rapid advancement of deep learning technologies, significant progress has been made in medical image analysis. However, existing deep learning methods are often limited by dataset size, which can lead to overfitting, while traditional approaches relying on hand-crafted features lack specificity and fail to fully capture complex pathological information. To address these challenges, we propose RadioGuide-DCN, an innovative radiomics-guided decorrelated classification network. Our method integrates radiomics features as prior information into deep neural networks and employs a feature decorrelation loss mechanism combined with an anti-attention feature fusion module to effectively reduce feature redundancy and enhance the model's capacity to capture both local details and global patterns. Specifically, we utilize a Kolmogorov-Arnold Network (KAN) classifier with learnable activation functions to further boost performance across various medical imaging datasets. Experimental results demonstrate that RadioGuide-DCN achieves an accuracy of 93.63% in BUSI image classification and consistently outperforms conventional radiomics and deep learning methods in multiple medical imaging classification tasks, significantly improving classification accuracy and AUC scores. Our study offers a novel paradigm for integrating deep learning with traditional imaging approaches and holds broad clinical application potential, particularly in tumor detection, image classification, and disease diagnosis.

Spectral data provide material-specific information across a broad electromagnetic wavelength range by acquiring numerous spectral bands. However, acquiring such a significant volume of data introduces challenges such as data redundancy, long acquisition times, and substantial storage capacity. To address these challenges, band selection is introduced as a strategy that focuses on only using the most significant bands to preserve spectral information for a specific task. State-of-the-art methods focus on searching for the most significant bands from previously acquired data, regardless of the optical system and the classification model. Nevertheless, some deep-learning methods, such as end-to-end frameworks, allow the design of optical systems and the learning of the classification network parameters. In this paper, we model the optical band selection as a trainable layer that is coupled with a classification network, where the parameters are learned in an end-to-end framework. To guarantee a physically implementable system, we proposed two regularization terms in the training step to promote binarization and also the number of the selected bands, as we need to provide the conditions to design the physical element where the light passes through. The proposed method provides better performance than state-of-the-art band selection methods for three different spectral datasets under the same conditions.

Hyperspectral images with hundreds of spectral bands have been proven to yield high performance in material classification. However, despite intensive advancement in hardware, the spatial resolution is still somewhat low, as compared to that of color and multispectral (MS) imagers. In this paper, we aim at presenting some ideas that may further enhance the performance of some remote sensing applications such as border monitoring and Mars exploration using hyperspectral images. One popular approach to enhancing the spatial resolution of hyperspectral images is pansharpening. We present a brief review of recent image resolution enhancement algorithms, including single super-resolution and multi-image fusion algorithms, for hyperspectral images. Advantages and limitations of the enhancement algorithms are highlighted. Some limitations in the pansharpening process include the availability of high resolution (HR) panchromatic (pan) and/or MS images, the registration of images from multiple sources, the availability of point spread function (PSF), and reliable and consistent image quality assessment. We suggest some proactive ideas to alleviate the above issues in practice. In the event where hyperspectral images are not available, we suggest the use of band synthesis techniques to generate HR hyperspectral images from low resolution (LR) MS images. Several recent interesting applications in border monitoring and Mars exploration using hyperspectral images are presented. Finally, some future directions in this research area are highlighted.

Classifying hyperspectral images (HSI) is inherently challenging due to their high-dimensional nature, which involves numerous spectral bands and a scarcity of labelled training samples. Deep learning techniques, particularly deep neural networks, have shown significant promise for feature extraction and effective classification of HSI. Nonetheless, the presence of redundant information across spectral bands and interference pixels within spatial patches impedes discriminative feature extraction. To address these issues, a novel approach, the Levy Artificial Bee Colony Optimized Kernel Vision Transformer-based Cascaded Neural Network (LABCO-KVCNN) is proposed to enhance and classify hyperspectral images. This methodology employs various preprocessing techniques including Gaussian filtering, interpolation, and normalization, and leverages dimensionality reduction through Kernel Principal Component Analysis (KPCA). Feature extraction is performed using the ICViT model while the LF-ABC algorithm is used for optimized band selection. Further improve classification accuracy and efficiency an optimal subset of spectral bands selected the Artificial Bee Colony (ABC) optimization algorithm. The final step is the classification of hyperspectral images with the Cascaded Convolutional neural Network (CCNN) model. Moreover, five Benchmark datasets are used for evaluation. The test outcomes show that the developed model performs better than other approaches and attained 98.6% accuracy and 96.16% average accuracy.

Introduction/Background*The most important prognostic factor for the survival of advanced-stage ovarian cancer is the completeness of cytoreductive surgery (CRS). Therefore, an intraoperative technique to detect microscopic tumours would be of...

Hyperspectral image (HSI) data have large numbers of bands that probably not all bands are equally informative and predictive for an effective HSI classification. Effective algorithms are highly desired in many real-world HSI applications, especially in cases requiring rapid learning with limited computing power. To address the abovementioned case, we present in this article a novel plug-and-play compact band weighting (CBW) module based on the attention-driven mechanism that evaluates different spectral bands according to their contributions to a given classification task. Compared to existing band weighting (BW) modules with tens of thousands of network parameters by deep learning, the proposed CBW is a lightweight module with only 20 parameters. Both model complexity and time cost are significantly reduced. The CBW module implements BW by making full use of the correlation among the adjacent spectral bands and spectral statistic information and, thereby, leads to the effect of recalibrated HSI. The experimental study has been conducted on three widely used HSI data sets, and results show the superiority of the proposed algorithm over current state-of-the-art methods of BW. The source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/JarvenYi/CBW</uri> .

Powered by advanced deep-learning technology, multi-spectral image super-resolution methods based on convolutional neural networks have recently achieved great progress. However, the single hyperspectral image super-resolution remains a challenging problem due to the high-dimensional and complex spectral characteristics of hyperspectral data, which make it difficult for general 2D convolutional neural networks to simultaneously capture spatial and spectral prior information. To deal with this issue, we propose a novel Feedback Refined Local-Global Network (FRLGN) for the super-resolution of hyperspectral image. To be specific, we develop a new Feedback Structure and a Local-Global Spectral block to alleviate the difficulty in spatial and spectral feature extraction. The Feedback Structure can transfer the high-level information to guide the generation process of low-level features, which is achieved by a recurrent structure with finite unfoldings. Furthermore, in order to effectively use the high-level information passed back, a Local-Global Spectral block is constructed to handle the feedback connections. The Local-Global Spectral block utilizes the feedback high-level information to correct the low-level feature from local spectral bands and generates powerful high-level representations among global spectral bands. By incorporating the Feedback Structure and Local-Global Spectral block, the FRLGN can fully exploit spatial-spectral correlations among spectral bands and gradually reconstruct high-resolution hyperspectral images. Experimental results indicate that FRLGN presents advantages on three public hyperspectral datasets.