Search

Your search keyword '"Xu, Zhinan"' showing total 720 results
Start Over Author "Xu, Zhinan"
720 results on '"Xu, Zhinan"'

19. M‐Net: A Skin Cancer Classification With Improved Convolutional Neural Network Based on the Enhanced Gray Wolf Optimization Algorithm.

Author

Xu, Zhinan, Zhang, Xiaoxia, and Liu, Luzhou

Subjects
*CONVOLUTIONAL neural networks, *OPTIMIZATION algorithms, *MACHINE learning, *SIMULATED annealing, *DEEP learning
Abstract

Skin cancer is a common malignant tumor causing tens of thousands of deaths each year, making early detection essential for better treatment outcomes. However, the similar visual characteristics of skin lesions make it challenging to accurately differentiate between lesion types. With advancements in deep learning, researchers have increasingly turned to convolutional neural networks for skin cancer detection and classification. In this article, an improved skin cancer classification model M‐Net is proposed, and the enhanced gray wolf optimization algorithm is combined to improve the classification performance. The gray wolf optimization algorithm guides the wolf pack to prey through a multileader structure and gradually converges through the encirclement and pursuit mechanism, so as to perform a more detailed search in the later stage. To further improve the performance of the gray wolf optimization, this study introduces the simulated annealing algorithm to avoid falling into the local optimal state and expands the search range by improving the search mechanism, thus enhancing the global optimization ability of the algorithm. The M‐Net model significantly improves the accuracy of classification by extracting features of skin lesions and optimizing parameters with the enhanced gray wolf optimization algorithm. The experimental results based on the ISIC 2018 dataset show that compared with the baseline model, the feature extraction network of the model has achieved a significant improvement in accuracy. The classification performance of M‐Net is excellent in multiple indicators, with accuracy, precision, recall, and F1 score reaching 0.891, 0.857, 0.895, and 0.872, respectively. In addition, the modular design of M‐Net enables it to flexibly adjust feature extraction and classification modules to adapt to different classification tasks, showing great scalability and applicability. In general, the model proposed in this article performs well in the classification of skin lesions, has broad clinical application prospects, and provides strong support for promoting the diagnosis of skin diseases. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

22. A time-variant channel prediction and feedback framework for interference alignment

Author

Xu, Zhinan, Hofer, Markus, and Zemen, Thomas

Subjects
Computer Science - Information Theory
Abstract

In interference channels, channel state information (CSI) can be exploited to reduce the interference signal dimensions and thus achieve the optimal capacity scaling, i.e. degrees of freedom, promised by the interference alignment technique. However, imperfect CSI, due to channel estimation error, imperfect CSI feedback and time selectivity of the channel, lead to a performance loss. In this work, we propose a novel limited feedback algorithm for single-input single-output interference alignment in time-variant channels. The feedback algorithm encodes the channel evolution in a small number of subspace coefficients, which allow for reduced-rank channel prediction to compensate for the channel estimation error due to time selectivity of the fading process and feedback delay. An upper bound for the rate loss caused by feedback quantization and channel prediction is derived. Based on this bound, we develop a dimension switching algorithm for the reduced-rank predictor to find the best tradeoff between quantization- and prediction-error. Besides, we characterize the scaling of the required number of feedback bits in order to decouple the rate loss due to channel quantization from the transmit power. Simulation results show that a rate gain over the traditional non-predictive feedback strategy can be secured and a 60% higher rate is achieved at 20 dB signal-to-noise ratio with moderate mobility.

Published
2017

30. On the Degrees of Freedom for Opportunistic Interference Alignment with 1-Bit Feedback: The 3 Cell Case

Author

Xu, Zhinan, Gan, Mingming, and Zemen, Thomas

Subjects
Computer Science - Information Theory
Abstract

Opportunistic interference alignment (OIA) exploits channel randomness and multiuser diversity by user selection. For OIA the transmitter needs channel state information (CSI), which is usually measured on the receiver side and sent to the transmitter side via a feedback channel. Lee and Choi show that $d$ degrees of freedom (DoF) per transmitter are achievable in a 3-cell MIMO interference channel assuming perfect real-valued feedback. However, the feedback of a real-valued variable still requires infinite rate. In this paper, we investigate 1-bit quantization for opportunistic interference alignment (OIA) in 3-cell interference channels. We prove that 1-bit feedback is sufficient to achieve the optimal DoF $d$ in 3-cell MIMO interference channels if the number of users per cell is scaled as ${\rm SNR}^{d^2}$. Importantly, the required number of users for OIA with 1-bit feedback remains the same as with real-valued feedback. For a given system configuration, we provide an optimal choice of the 1-bit quantizer, which captures most of the capacity provided by a system with real-valued feedback. Using our new 1-bit feedback scheme for OIA, we compare OIA with IA and show that OIA has a much lower complexity and provides a better rate in the practical operation region of a cellular communication system.

Published
2015

38. Integrated Analysis of Pollution Characteristic and Ecotoxicological Effect Reveals the Fate of Lithium in Soil-Plant Systems: A Challenge to Global Sustainability

Author

Xu, Zhinan, Peng, Si, Pei, Luyao, Zhou, Kecen, and Wang, Xiangrong

Abstract

Lithium, as an emerging contaminant, lacks sufficient information regarding its environmental and ecotoxicological implications within soil-plant systems. Employing maize, wheat, pea, and water spinach, we conducted a thorough investigation utilizing a multispecies, multiparameter, and multitechnique approach to assess the pollution characteristics and ecotoxicological effects of lithium. The findings suggested that lithium might persist in an amorphous state, altering surface functional groups and chemical bonds, although semiquantitative analysis was unattainable. Notably, lithium demonstrated high mobility, with a mild acid-soluble fraction accounting for 29.66–97.02% of the total, while a minor quantity of exogenous lithium tended to be a residual fraction. Plant analysis revealed that in 10–80 mg Li/kg soils lithium significantly enhanced certain growth parameters of maize and pea, and the calculated LC50 values for aerial part length across the four plant species varied from 173.58 to 315.63 mg Li/kg. Lithium accumulation in the leaves was up to 1127.61–4719.22 mg/kg, with its inorganic form accounting for 18.60–94.59%, and the cytoplasm fraction (38.24–89.70%) predominantly harbored lithium. Furthermore, the model displayed that growth stimulation might be attributed to the influence of lithium on phytohormone levels. Water spinach exhibited superior accumulation capacity and tolerance to lithium stress and was a promising candidate for phytoremediation strategies. Our findings contribute to a more comprehensive understanding of lithium’s environmental behavior within soil-plant systems, particularly within the context of global initiatives toward carbon neutrality.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results