273 research outputs found
Advanced modelling and analytics for effective change and anomaly detection in hyperspectral images.
Get PDFThe main objective of this research is to design and implement novel models and analytics techniques for hyperspectral change detection and anomaly detection. With the widespread applications of hyperspectral imagery (HSI) in fields such as remote sensing, environmental monitoring and agriculture, the need for accurate and efficient change detection and anomaly detection has become increasingly critical. However, existing methods often face huge challenges related to the complexity of processing high-dimensional HSI data, especially the severe sensitivity to noise that causes low detection accuracy, and high computational costs. To address these issues, this thesis first provides a comprehensive literature review of the current state of research in hyperspectral change detection and anomaly detection, systematically organising the representative algorithms and analysing their trends and advancements in the past, especially in the recent three years. Building on this foundation, the thesis proposes a novel accumulated band-wise binary distancing (ABBD) model for unsupervised parameter-free HCD, which requires no parameter setting and can maintain high detection accuracy across different scenarios, thereby simplifying the operational complexity in practical applications. Additionally, this study introduces a novel 2D self-attention module, leading to the development of two lightweight deep learning networks focused on extracting local spatial-spectral features for more accurate change detection. The first network, namely CBANet, integrates a cross-band feature extraction module with the 2D self-attention, achieving higher detection accuracy and fewer hyperparameters compared to other advanced deep learning-based methods. The second lightweighted network, SSA-LHCD, combines the singular spectrum analysis (SSA) as a preprocessing step with a 2D self-attention module, further improving the detection accuracy while reducing the number of the hyperparameters of the model. Experimental results demonstrate that these two proposed techniques outperform a few state-of-the-art methods on several commonly used hyperspectral change detection datasets, highlighting their superiority in practical applications. Moreover, this thesis introduces a novel deep learning-based model called GASSM, marking the first exploration of combining the state-space-model (SSM) based Mamba model with the global attention for hyperspectral change detection. GASSM effectively overcomes the limitations of traditional convolutional neural networks in terms of the limited receptive field and the high computational complexity associated with transformer-based methods, offering new directions for future research. Additionally, this study proposes a background reconstruction-based hyperspectral anomaly detection method, which has been shown to exhibit robustness and high detection accuracy across six different scenario datasets. Overall, this study significantly advances the field of hyperspectral change detection and anomaly detection by proposing and validating several novel models and analytics methods, laying a solid foundation for further research and applications in this area
SSA-LHCD: a singular spectrum analysis-driven lightweight network with 2-D self-attention for hyperspectral change detection.
Get PDFAs an emerging research hotspot in contemporary remote sensing, hyperspectral change detection (HCD) has attracted increasing attention in remote sensing Earth observation, covering land mapping changes and anomaly detection. This is primarily attributable to the unique capacity of hyperspectral imagery (HSI) to amalgamate both the spectral and spatial information in the scene, facilitating a more exhaustive analysis and change detection on the Earth's surface, proving to be successful across diverse domains, such as disaster monitoring and geological surveys. Although numerous HCD algorithms have been developed, most of them face three major challenges: (i) susceptibility to inherent data noise, (ii) inconsistent accuracy of detection, especially when dealing with multi-scale changes, and (iii) extensive hyperparameters and high computational costs. As such, we propose a singular spectrum analysis-driven-lightweight network for HCD, where three crucial components are incorporated to tackle these challenges. Firstly, singular spectrum analysis (SSA) is applied to alleviate the effect of noise. Next, a 2-D self-attention-based spatial–spectral feature-extraction module is employed to effectively handle multi-scale changes. Finally, a residual block-based module is designed to effectively extract the spectral features for efficiency. Comprehensive experiments on three publicly available datasets have fully validated the superiority of the proposed SSA-LHCD model over eight state-of-the-art HCD approaches, including four deep learning models
Siamese Residual Neural Network for Musical Shape Evaluation in Piano Performance Assessment
Full text linkUnderstanding and identifying musical shape plays an important role in music
education and performance assessment. To simplify the otherwise time- and
cost-intensive musical shape evaluation, in this paper we explore how
artificial intelligence (AI) driven models can be applied. Considering musical
shape evaluation as a classification problem, a light-weight Siamese residual
neural network (S-ResNN) is proposed to automatically identify musical shapes.
To assess the proposed approach in the context of piano musical shape
evaluation, we have generated a new dataset, containing 4116 music pieces
derived by 147 piano preparatory exercises and performed in 28 categories of
musical shapes. The experimental results show that the S-ResNN significantly
outperforms a number of benchmark methods in terms of the precision, recall and
F1 score.Comment: X.Li, S.Weiss, Y.Yan, Y.Li, J.Ren, J.Soraghan, M.Gong,"Siamese
residual neural network for musical shape evaluation in piano performance
assessment" in Proc. of the 31st European Signal Processing Conference,
Helsinki, Finlan
Siamese residual neural network for musical shape evaluation in piano performance assessment.
Get PDFUnderstanding and identifying musical shape plays an important role in music education and performance assessment. To simplify the otherwise time- and cost-intensive musical shape evaluation, in this paper we explore how artificial intelligence (AI) driven models can be applied. Considering musical shape evaluation as a classification problem, a light-weight Siamese residual neural network (S-ResNN) is proposed to automatically identify musical shapes. To assess the proposed approach in the context of piano musical shape evaluation, we have generated a new dataset, namely MSED-4k, containing 4116 music pieces derived by 147 piano preparatory exercises and performed in 28 categories of musical shapes. The experimental results show that the S-ResNN significantly outperforms a number of benchmark methods in terms of the precision, recall and F1 score
Non-Destructive Peat Analysis using Hyperspectral Imaging and Machine Learning
Full text linkPeat, a crucial component in whisky production, imparts distinctive and
irreplaceable flavours to the final product. However, the extraction of peat
disrupts ancient ecosystems and releases significant amounts of carbon,
contributing to climate change. This paper aims to address this issue by
conducting a feasibility study on enhancing peat use efficiency in whisky
manufacturing through non-destructive analysis using hyperspectral imaging.
Results show that shot-wave infrared (SWIR) data is more effective for
analyzing peat samples and predicting total phenol levels, with accuracies up
to 99.81%.Comment: 4 pages,4 figure
PIMSYN: Synthesizing Processing-in-memory CNN Accelerators
Full text linkProcessing-in-memory architectures have been regarded as a promising solution
for CNN acceleration. Existing PIM accelerator designs rely heavily on the
experience of experts and require significant manual design overhead. Manual
design cannot effectively optimize and explore architecture implementations. In
this work, we develop an automatic framework PIMSYN for synthesizing PIM-based
CNN accelerators, which greatly facilitates architecture design and helps
generate energyefficient accelerators. PIMSYN can automatically transform CNN
applications into execution workflows and hardware construction of PIM
accelerators. To systematically optimize the architecture, we embed an
architectural exploration flow into the synthesis framework, providing a more
comprehensive design space. Experiments demonstrate that PIMSYN improves the
power efficiency by several times compared with existing works. PIMSYN can be
obtained from https://github.com/lixixi-jook/PIMSYN-NN
Unsupervised Change Detection in Hyperspectral Images using Principal Components Space Data Clustering
Get PDFChange detection of hyperspectral images is a very important subject in the field of remote sensing application. Due to the large number of bands and the high correlation between adjacent bands in the hyperspectral image cube, information redundancy is a big problem, which increases the computational complexity and brings negative factor to detection performance. To address this problem, the principal component analysis (PCA) has been widely used for dimension reduction. It has the capability of projecting the original multi-dimensional hyperspectral data into new eigenvector space which allows it to extract light but representative information. The difference image of the PCA components is obtained by subtracting the two dimensionality-reduced images, on which the change detection is considered as a binary classification problem. The first several principal components of each pixel are taken as a feature vector for data classification using k-means clustering with k=2, where the two classes are changed pixels and unchanged pixels, respectively. The centroids of two clusters are determined by iteratively finding the minimum Euclidean distance between pixel's eigenvectors. Experiments on two publicly available datasets have been carried out and evaluated by overall accuracy. The results have validated the efficacy and efficiency of the proposed approach.</p
ChipGPT: How far are we from natural language hardware design
Full text linkAs large language models (LLMs) like ChatGPT exhibited unprecedented machine
intelligence, it also shows great performance in assisting hardware engineers
to realize higher-efficiency logic design via natural language interaction. To
estimate the potential of the hardware design process assisted by LLMs, this
work attempts to demonstrate an automated design environment that explores LLMs
to generate hardware logic designs from natural language specifications. To
realize a more accessible and efficient chip development flow, we present a
scalable four-stage zero-code logic design framework based on LLMs without
retraining or finetuning. At first, the demo, ChipGPT, begins by generating
prompts for the LLM, which then produces initial Verilog programs. Second, an
output manager corrects and optimizes these programs before collecting them
into the final design space. Eventually, ChipGPT will search through this space
to select the optimal design under the target metrics. The evaluation sheds
some light on whether LLMs can generate correct and complete hardware logic
designs described by natural language for some specifications. It is shown that
ChipGPT improves programmability, and controllability, and shows broader design
optimization space compared to prior work and native LLMs alone
CBANet: an end-to-end cross band 2-D attention network for hyperspectral change detection in remote sensing.
Get PDFAs a fundamental task in remote sensing observation of the earth, change detection using hyperspectral images (HSI) features high accuracy due to the combination of the rich spectral and spatial information, especially for identifying land-cover variations in bi-temporal HSIs. Relying on the image difference, existing HSI change detection methods fail to preserve the spectral characteristics and suffer from high data dimensionality, making them extremely challenging to deal with changing areas of various sizes. To tackle these challenges, we propose a cross-band 2-D self-attention Network (CBANet) for end-to-end HSI change detection. By embedding a cross-band feature extraction module into a 2-D spatial-spectral self-attention module, CBANet is highly capable of extracting the spectral difference of matching pixels by considering the correlation between adjacent pixels. The CBANet has shown three key advantages: 1) less parameters and high efficiency; 2) high efficacy of extracting representative spectral information from bi-temporal images; and 3) high stability and accuracy for identifying both sparse sporadic changing pixels and large changing areas whilst preserving the edges. Comprehensive experiments on three publicly available datasets have fully validated the efficacy and efficiency of the proposed methodology
- …
