Development of materials for fluorescence imaging with a wide optical range is important for clinical applications. In this work, a solution synthesis method was used for making Ag–Ho, Ag–Sm, Ag–Zn, Ag–Cu Ag–Cs, Ag–Zr, Ag–Er, Ag–Y and Ag–Co metal organic compound nanoparticles. XRD, XPS and TEM were carried out for sample characterization. They showed broad fluorescence from the UV to NIR region. In particular, they presented near-infrared (NIR) fluorescence (800–1100 nm) when excitation light of 785 nm was used. Furthermore, a white-to-green or blue-to-white transition was observed when excitation light varied from 290 nm to 370 nm. Proof-of-concept experiments were performed via UV light (359–371 nm), blue light (450–490 nm), green light (540–552 nm) and NIR light (center wavelength = 785 nm) excitation with pig-kidney tissue samples. They showed potential for biomedical fluorescence imaging in the UV-Vis-NIR range.

The development of nanomaterials with special optical window is critical for clinical applications and the optoelectronic industry. In this work, eight kinds of samarium-based metal organic compound nanoparticles (Sm–Fe, Sm–Ga, Sm–Mn, Sm–Na, Sm–Nb, Sm–W, Sm–Cu, and Sm–Al) were synthesized through a solution method. They show polychromatic-photoluminescence spectra extended from the UV to near-infrared (NIR) region when excited by 280 nm, 380 nm, 480 nm, 580 nm, and 785 nm light. They emit direct white light with respect to UV excitation. Tunable white-to-green fluorescence can be achieved by variation of excitation light around 300–400 nm. When they are excited by a 785 nm light source, they show intense fluorescence around 800–1100 nm, which is promising for NIR bio-imaging. Their application in multicolor ultra-wide-range bio-tissue fluorescence imaging is demonstrated by UV (359–371 nm), blue (450–490 nm), green (540–552 nm), and NIR light (central wavelength = 785 nm) excitation with pig kidney tissue samples.

Neuromorphic hardware systems have been gaining ever-increasing focus in many embedded applications as they use a brain-inspired, energy-efficient spiking neural network (SNN) model that closely mimics the human cortex mechanism by communicating and processing sensory information via spatiotemporally sparse spikes. In this paper, we fully leverage the characteristics of spiking convolution neural network (SCNN), and propose a scalable, cost-efficient, and high-speed VLSI architecture to accelerate deep SCNN inference for real-time low-cost embedded scenarios. We leverage the snapshot of binary spike maps at each time-step, to decompose the SCNN operations into a series of regular and simple time-step CNN-like processing to reduce hardware resource consumption. Moreover, our hardware architecture achieves high throughput by employing a pixel stream processing mechanism and fine-grained data pipelines. Our Zynq-7045 FPGA prototype reached a high processing speed of 1250 frames/s and high recognition accuracies on the MNIST and Fashion-MNIST image datasets, demonstrating the plausibility of our SCNN hardware architecture for many embedded applications.

Infrared sensors capture thermal radiation emitted by objects. They can operate in all weather conditions and are thus employed in fields such as military surveillance, autonomous driving, and medical diagnostics. However, infrared imagery poses challenges such as low contrast and indistinct textures due to the long wavelength of infrared radiation and susceptibility to interference. In addition, complex enhancement algorithms make real-time processing challenging. To address these problems and improve visual quality, in this paper, we propose a multi-scale FPGA-based method for real-time enhancement of infrared images by using rolling guidance filter (RGF) and contrast-limited adaptive histogram equalization (CLAHE). Specifically, the original image is first decomposed into various scales of detail layers and a base layer using RGF. Secondly, we fuse detail layers of diverse scales, then enhance the detail information by using gain coefficients and employ CLAHE to improve the contrast of the base layer. Thirdly, we fuse the detail layers and base layer to obtain the image with global details of the input image. Finally, the proposed algorithm is implemented on an FPGA using advanced high-level synthesis tools. Comprehensive testing of our proposed method on the AXU15EG board demonstrates its effectiveness in significantly improving image contrast and enhancing detail information. At the same time, real-time enhancement at a speed of 147 FPS is achieved for infrared images with a resolution of 640 × 480.

Distracted driving is currently a global issue causing fatal traffic crashes and injuries. Although deep learning has achieved significant success in various fields, it still faces the trade-off between computation cost and overall accuracy in the field of distracted driving behavior recognition. This paper addresses this problem and proposes a novel lightweight attention-based (LWANet) network for image classification tasks. To reduce the computation cost and trainable parameters, we replace standard convolution layers with depthwise separable convolutions and optimize the classic VGG16 architecture by 98.16% trainable parameters reduction. Inspired by the attention mechanism in cognitive science, a lightweight inverted residual attention module (IRAM) is proposed to simulate human attention, extract more specific features, and improve the overall accuracy. LWANet achieved an accuracy of 99.37% on Statefarm’s dataset and 98.45% on American University in Cairo’s dataset. With only 1.22 M trainable parameters and a model file size of 4.68 MB, the quantitative experimental results demonstrate that the proposed LWANet obtains state-of-the-art overall performance in deep learning-based distracted driving behavior recognition.

The construction of smart courts promotes the in-deep integration of internet, big data, cloud computing and artificial intelligence with judicial trial work, which can both improve trials and ensure judicial justice with more efficiency. High-quality structured legal facts, obtained by extracting information from unstructured legal texts, are the foundation for the construction of smart courts. Based on the strong normative characteristics of Chinese legal text content and structure composition and the strong text feature learning ability of deep learning, this paper proposes an ontology-based and deep learning-driven method for extracting legal facts from Chinese legal texts. The proposed method utilizes rules and patterns generated in the process of knowledge modeling to extract simple entities, and then extracts complex entities hidden in legal text details with deep learning methods. Finally, the extracted entities are mapped into structured legal facts with clear logical relationships by the Chinese Legal Text Ontology. In the information extraction test of judicial datasets composed of Chinese legal texts on theft, the proposed method effectively extracts up to 38 categories of legal facts from legal texts and the number of categories extracted increases significantly. Among them, the rule-based extractor obtains an F1-score of 99.70%, and the deep learning-driven extractor obtains an F1-score of 91.43%. Compared with existing methods, the proposed method has great advantages in extracting the completeness and accuracy of legal facts.