A5048314269- DNA and Biological Computing
- Advanced biosensing and bioanalysis techniques
- Advanced Memory and Neural Computing
- Advanced Steganography and Watermarking Techniques
- Tactile and Sensory Interactions
- Computer Graphics and Visualization Techniques
- Machine Learning in Bioinformatics
- 3D Shape Modeling and Analysis
- Cancer-related gene regulation
- Genomics and Phylogenetic Studies
- Computational Drug Discovery Methods
- Quantum-Dot Cellular Automata
- Chaos-based Image/Signal Encryption
- Cellular Automata and Applications
- Modular Robots and Swarm Intelligence
- Aviation Industry Analysis and Trends
- COVID-19 diagnosis using AI
- Air Traffic Management and Optimization
- Medical Image Segmentation Techniques
- Peptidase Inhibition and Analysis
- Vehicle Routing Optimization Methods
- Advanced Numerical Analysis Techniques
- Cancer Mechanisms and Therapy
- Mechanisms of cancer metastasis
- Spatial Cognition and Navigation
University of Canterbury
2016-2025
Swinburne University of Technology Sarawak Campus
2015-2019
Lanzhou University
2019
Lanzhou University Second Hospital
2019
Central South University
2013-2017
Hunan Cancer Hospital
2013-2017
Universiti Sains Malaysia
2009-2017
Technical University of Munich
2010-2016
Klinikum rechts der Isar
2016
University of Technology Malaysia
2015
Spiking neural P systems (SN systems) are bio-inspired neural-like computing models, which obtained by abstracting the way of biological neurons' spiking and communication means spikes in central nervous systems. SN performed well describing modeling behaviors that occur simultaneously, yet weak at complex with limits using a single spike. In this paper, drawing on idea from colored petri nets, proposed, where finite set colors is introduced to mark such each spike associated unique color....
Spiking neural P systems (SN systems) are a class of distributed and parallel neural-like computing models, inspired from the way neurons communicate by means spikes. In this paper, new variant systems, called SN with learning functions, is introduced. Such can dynamically strengthen weaken connections among during computation. A specific simple Hebbian function constructed to recognize English letters. The experimental results show that achieve average accuracy rate 98.76% in test case...
Deoxyribonucleic acid (DNA) has become an ideal medium for long-term storage and retrieval due to its extremely high density stability. But access efficiency is existing bottleneck in DNA storage, especially the lack of high-quality random address sequences. Therefore, this paper, we report a series approaches based on k-weakly mutually uncorrelated (k-WMU) codes design sequence improve storage. To problem sequences that are poorly scalable at base level, propose 0-m-ruling coding scheme...
Abstract Background Tissue fibrosis is an integral component of chronic inflammatory (liver and pancreas) diseases pancreatic cancer. Activated pancreatic- (PSC) hepatic- (HSC) stellate cells play a key role in fibrogenesis. To identify organ- disease-specific cell transcriptional fingerprints, we employed genome-wide analysis primary human PSC HSC isolated from patients with inflammation or Methods Stellate were ductal adenocarcinoma (n = 5), pancreatitis 6), liver cirrhosis 5) metastasis...
AbstractBackground: Pim-1 is a proto-oncogene involved in cell survival, differentiation and proliferation several hematologic epithelial malignancies. Clinical, absence of expression correlates with poor prognosis prostate cancer. In the present study, analyzed pancreatic cancer correlated to clinicopathological parameters.Methods: mRNA protein was evaluated quantitative real-time RT-PCR, immunofluorescence immunocytochemistry analyses. Ex vivo analysis using semi-quantitative...
Spiking neural P systems, otherwise known as named SN are bio-inspired parallel and distributed neural-like computing models. Due to the spiking behavior, systems fall into category of networks, considered be an auspicious candidate 3G networks. It has been reported that with colored spikes computationally capable, perform well in describing behaviors complex systems. Nonetheless, some practical issue is open investigate, such workflow traffic flow modeling. In this paper, a pattern modeling...
Abstract Neural-like computing models are versatile mechanisms in the field of artificial intelligence. Spiking neural P systems (SN for short) one recently developed spiking network inspired by way neurons communicate. The communications among essentially achieved spikes, i. e. short electrical pulses. In terms motivation, SN fall into third generation models. this study, a novel variant systems, namely with self-organization, is introduced and computational power system investigated...
Recent years have seen tremendous success in the design of novel drug molecules through deep generative models. Nevertheless, existing methods only generate drug-like molecules, which require additional structural optimization to be developed into actual drugs. In this study, a learning method for generating target-specific ligands was proposed. This is useful when dataset limited. Deep can extract and learn features (representations) data-driven way with little or no human participation....
Abstract DNA molecules as storage media are characterized by high encoding density and low energy consumption, making a highly promising method. However, has shortcomings, especially when storing multimedia data, wherein image reconstruction fails address errors occur, resulting in complete data loss. Therefore, we propose parity local mean iteration (PELMI) scheme to achieve robust of images. The proposed satisfies the common biochemical constraints sequences undesired motif content. It...
The incidence of cholelithiasis is more than 10% in the natural population. It a common and frequently occurring disease worldwide. lesions are predominantly sand-like difficult to distinguish medical images. Although ultrasound often first-line technique for diagnosing cholelithiasis, CT plays an important role complications related gallstones. To best our knowledge, no effective method has been proposed segmenting images address this difficulty, we have novel deep learning segmentation...
Prediction on drug-target interaction has always been a crucial link for drug discovery and repositioning, which have witnessed tremendous progress in recent years. Despite many efforts made, the existing representation learning or feature generation approaches of both drugs proteins remain complicated as well high dimension. In addition, it is difficult current methods to extract local important residues from sequence information while remaining focused global structure. At same time,...
Lung cancer has complex biological characteristics and a high degree of malignancy. It always been the number one "killer" in cancer, threatening human life health. The diagnosis early treatment lung still require improvement further development. With morbidity mortality, there is an urgent need for accurate method. However, existing computer-aided detection system complicated process low accuracy. To solve this problem, paper proposed two-stage method based on dynamic region-based...
The small size of labelled samples is one the challenging problems in identifying early lung nodules from CT images using deep learning methods. Recent literature on topic shows that convolutional generative adversarial network (DCGAN) has been used medical data synthesis and gained some success, but does not demonstrate satisfactory results synthesizing images. It primarily suffers problem model convergence prone to mode collapse. In this paper, we propose a (GAN) with prior knowledge...
The epithelial-mesenchymal transition (EMT) process is believed to play a crucial role in nasopharyngeal carcinoma (NPC) progression, squamous cell of the head and neck with tendency metastasize early. At present, much attention has been given inducer EMT involved NPC while antagonists have less intensively characterized. In this study, unbiased analysis EMT-associated gene expression patterns was performed using data mining global profiles derived from samples, leading successful...
Ovarian cancer is one of the most common malignant tumours female reproductive organs in world. The pelvic CT scan a examination method used for screening ovarian cancer, which shows advantages safety, efficiency, and providing high-resolution images. Recently, deep learning applications medical imaging attract more attention research field tumour diagnostics. However, due to limited number relevant datasets reliable models, it remains challenging problem detect on In this work, we first...
Unsupervised image segmentation is an essential topic in the field of computer vision, which broke limitation training data and expanded application scenarios. Off-the-shelf clustering methods simply rely on semantic concepts incomplete boundary cues, resulting incorrect object boundaries. Therefore, this paper proposes unsupervised framework combining differentiable double (DDC) edge-aware superpixel (EA), outperform prior work accuracy art. First, a multi-layer feature extraction network...
Chemo-resistance is a major obstacle to the treatment of esophageal squamous cell carcinoma (ESCC). Interferon alpha-inducible protein 27 (IFI27) has been reported be associated with ESCC progression. This study designed explore role and mechanism IFI27 in cisplatin (DDP) resistance ESCC. Ubiquitin-specific peptidase 18 (USP18) levels were detected by real-time quantitative polymerase chain reaction (RT-qPCR). IFI27, multidrug resistance-associated 1 (MRP1), USP18, Homeobox A5 (HOXA5)...
Hepatocellular carcinoma (HCC) is the most common primary tumor of liver and sixth lethal cancer worldwide. Recent evidences demonstrated that oxidored nitro domain containing protein 1 (NOR1), a putative suppressor gene, overexpressed in human HCC tissues. However, role NOR1 development remains unclear. Here, we described level elevated associated with poorer clinical outcome. ecotopic overexpression cell line HepG2 cells had no effect on proliferation, migration, clonality....