Generalized M-sparse algorithms for constructing fault tolerant RBF networks.

In the construction process of radial basis function (RBF) networks, two common crucial issues arise: the selection of RBF centers and the effective utilization of the given source without encountering the overfitting problem. Another important issue is the fault tolerant capability. That is, when noise or faults exist in a trained network, it is crucial that the network's performance does not undergo significant deterioration or decrease. However, without employing a fault tolerant procedure, a trained RBF network may exhibit significantly poor performance. Unfortunately, most existing algorithms are unable to simultaneously address all of the aforementioned issues. This paper proposes fault tolerant training algorithms that can simultaneously select RBF nodes and train RBF output weights. Additionally, our algorithms can directly control the number of RBF nodes in an explicit manner, eliminating the need for a time-consuming procedure to tune the regularization parameter and achieve the target RBF network size. Based on simulation results, our algorithms demonstrate improved test set performance when more RBF nodes are used, effectively utilizing the given source without encountering the overfitting problem. This paper first defines a fault tolerant objective function, which includes a term to suppress the effects of weight faults and weight noise. This term also prevents the issue of overfitting, resulting in better test set performance when more RBF nodes are utilized. With the defined objective function, the training process is designed to solve a generalized M-sparse problem by incorporating an ℓ0-norm constraint. The ℓ0-norm constraint allows us to directly and explicitly control the number of RBF nodes. To address the generalized M-sparse problem, we introduce the noise-resistant iterative hard thresholding (NR-IHT) algorithm. The convergence properties of the NR-IHT algorithm are subsequently discussed theoretically. To further enhance performance, we incorporate the momentum concept into the NR-IHT algorithm, referring to the modified version as "NR-IHT-Mom". Simulation results show that both the NR-IHT algorithm and the NR-IHT-Mom algorithm outperform several state-of-the-art comparison algorithms.

DCDLN: A densely connected convolutional dynamic learning network for malaria disease diagnosis.

Malaria is a significant health concern worldwide, particularly in Africa where its prevalence is still alarmingly high. Using artificial intelligence algorithms to diagnose cells with malaria provides great convenience for clinicians. In this paper, a densely connected convolutional dynamic learning network (DCDLN) is proposed for the diagnosis of malaria disease. Specifically, after data processing and partitioning of the dataset, the densely connected block is trained as a feature extractor. To classify the features extracted by the feature extractor, a classifier based on a dynamic learning network is proposed in this paper. Based on experimental results, the proposed DCDLN method demonstrates a diagnostic accuracy rate of 97.23%, surpassing the diagnostic performance than existing advanced methods on an open malaria cell dataset. This accurate diagnostic effect provides convincing evidence for clinicians to make a correct diagnosis. In addition, to validate the superiority and generalization capability of the DCDLN algorithm, we also applied the algorithm to the skin cancer and garbage classification datasets. DCDLN achieved good results on these datasets as well, demonstrating that the DCDLN algorithm possesses superiority and strong generalization performance.

Appearance-preserved Portrait-to-anime Translation via Proxy-guided Domain Adaptation.

Converting a human portrait to anime style is a desirable but challenging problem. Existing methods fail to resolve this problem due to the large inherent gap between two domains that cannot be overcome by a simple direct mapping. For this reason, these methods struggle to preserve the appearance features in the original photo. In this paper, we discover an intermediate domain, the coser portrait (portraits of humans costuming as anime characters), that helps bridge this gap. It alleviates the learning ambiguity and loosens the mapping difficulty in a progressive manner. Specifically, we start from learning the mapping between coser and anime portraits, and present a proxy-guided domain adaptation learning scheme with three progressive adaptation stages to shift the initial model to the human portrait domain. In this way, our model can generate visually pleasant anime portraits with well-preserved appearances given the human portrait. Our model adopts a disentangled design by breaking down the translation problem into two specific subtasks of face deformation and portrait stylization. This further elevates the generation quality. Extensive experimental results show that our model can achieve visually compelling translation with better appearance preservation and perform favorably against the existing methods both qualitatively and quantitatively. Our code and datasets are available at https://github.com/NeverGiveU/PDA-Translation.

Overexpression of ELF3 facilitates cell growth and metastasis through PI3K/Akt and ERK signaling pathways in non-small cell lung cancer.

ELF3 is one of the member of transcription factors from E-twenty-six family, its role varies in different types of cancer. However, the role and specific mechanisms of ELF3 in the development of non-small cell lung cancer (NSCLC) still remains largely unknown. In our study, ELF3 was observed to be upregulated in NSCLC tissues compared to the corresponding normal lung tissue at mRNA and protein levels, and its expression level was correlated with the overall survival of patients with NSCLC. Silencing of the ELF3 gene in NSCLC cells inhibited the proliferation and metastasis significantly in vitro and in vivo. Conversely, overexpression of ELF3 in NSCLC cells promoted cancer growth and metastasis in vitro. Mechanistically, ELF3 activated PI3K/AKT and ERK signaling pathways and its downstream effectors, thus regulating the cell cycle and epithelial-mesenchymal transition (EMT). Furthermore, the promotive effects of ELF3 on cellular proliferation and metastasis could be rescued by Ly294002 (inhibitor of PI3K) and U0126 (inhibitor of MEK1/2). The results show that ELF3 promotes cell growth and metastasis by regulating PI3K/Akt and ERK pathways in NSCLC and that it may be a promising new target for the treatment of NSCLC patients.

Elevated Expression of Zinc Finger Protein 703 Promotes Cell Proliferation and Metastasis through PI3K/AKT/GSK-3ß Signalling in Oral Squamous Cell Carcinoma.

BACKGROUND/AIMS: Zinc finger protein 703 (ZNF703), initially identified as a novel oncogene in human breast cancer, is a member of the NET/NlZ family of zinc finger transcription factors. It is recognized that the overexpression of ZNF703 is associated with various types of human cancers, but the role and molecular mechanism of ZNF703 in oral squamous cell carcinoma (OSCC) are unknown. METHODS: ZNF703 expression levels were examined in OSCC tissues and non-cancerous tissues by qRT-PCR and immunohistochemistry (IHC). The molecular mechanisms of ZNF703 and its effects on cell growth and metastasis were explored in vitro and in vivo using the CCK8 assay, colony formation assay, cell cycle analysis, migration and invasion assays, wound-healing assay, western blotting and xenograft experiments in nude mice. RESULTS: In this study, ZNF703 was found to be upregulated in OSCC tissues compared to that in normal tissues at both mRNA and protein levels, and its expression level was closely correlated with the overall survival of patients with OSCC. Silencing of the ZNF703 gene in OSCC cells significantly inhibited cell growth and metastasis in vitro and in vivo. Conversely, the overexpression of ZNF703 in OSCC cells promoted cancer growth and metastasis in vitro. Mechanistically, ZNF703 activated the PI3K/AKT/GSK-3ß signalling pathway and its downstream effectors, thus regulating the cell cycle and epithelial-mesenchymal transition (EMT). Furthermore, the promotive effects of ZNF703 on cellular proliferation and metastasis could be rescued by LY294002 (a PI3K-specific inhibitor) and MK2206 (an Akt-specific inhibitor). CONCLUSION: The results show that ZNF703 promotes cell growth and metastasis through PI3K/Akt/GSK-3ß signalling in OSCC and that it may be a promising target in the treatment of patients with OSCC.