检索结果-内蒙古大学图书馆

A classification of biochemical compounds based on their primitive structures and graph kernels

学校读者我要写书评

暂无评论

A classification of biochemical compounds based on their pri...

International Joint Conference on Computer Science and Software Engineering (JCSSE)

作者： Peemapat Wongsriphisant Chidchanok Lursinsap Apichat Suratanee Kitiporn Plaimas Advanced Virtual and Intelligent Computing (AVIC) Center Faculty of Science Chulalongkorn University Bangkok 10800 Thailand Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok 10330 Thailand

ISBN: (数字)9781728161679

ISBN: (纸本)9781728161686

The data encoded in the form of a graph are widely used in many fields of study. In cheminformatics, the data of biochemical compounds can be encoded as a graph where its vertices are atoms, and its edges are chemical bonds between pairs of atoms. By this representation, we can identify the molecular functions of a labeled biochemical compound with the graph classification methods which most of them depend on graph kernel. In this study, we proposed an algorithm to extract primitive substructures of the compounds and encode them in a new form of graph for feeding them a support vector machine with a graph kernel. The algorithm was tested with four data sets and yield the average accuracy of 0.847. Furthermore, the performance of the algorithm was also better than that of the solely graph kernels without primitive substructure extraction. All in all, the extraction of the primitive substructures can be a great tool in extracting compound structure features in biochemical compound classification.

关键词： Kernel Compounds Atomic measurements Histograms Chemicals Transforms Social networking (online)

Non-Adversarial Learning: Vector-Quantized Common Latent Space for Multi-Sequence MRI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Han, Luyi Tan, Tao Zhang, Tianyu Wang, Xin Gao, Yuan Lu, Chunyao Liang, Xinglong Dou, Haoran Huang, Yunzhi Mann, Ritse Department of Radiology and Nuclear Medicine Radboud University Medical Centre Geert Grooteplein 10 Nijmegen6525 GA Netherlands Department of Radiology The Netherlands Cancer Institute Plesmanlaan 121 Amsterdam1066 CX Netherlands Faculty of Applied Sciences Macao Polytechnic University Macao Special 999078 China GROW School for Oncology and Developmental Biology Maastricht University Medical Centre P. Debyelaan 25 Maastricht6202 AZ Netherlands Center for Computational Imaging and Simulation Technologies in Biomedicine School of Computing The University of Leeds LeedsLS2 9JT United Kingdom School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China

Adversarial learning helps generative models translate MRI from source to target sequence when lacking paired samples. However, implementing MRI synthesis with adversarial learning in clinical settings is challenging due to training instability and mode collapse. To address this issue, we leverage intermediate sequences to estimate the common latent space among multi-sequence MRI, enabling the reconstruction of distinct sequences from the common latent space. We propose a generative model that compresses discrete representations of each sequence to estimate the Gaussian distribution of vector-quantized common (VQC) latent space between multiple sequences. Moreover, we improve the latent space consistency with contrastive learning and increase model stability by domain augmentation. Experiments using BraTS2021 dataset show that our non-adversarial model outperforms other GAN-based methods, and VQC latent space aids our model to achieve (1) anti-interference ability, which can eliminate the effects of noise, bias fields, and artifacts, and (2) solid semantic representation ability, with the potential of one-shot segmentation. Our code is publicly available 7 Copyright © 2024, The Authors. All rights reserved.

关键词： Vector spaces

RECOMED: A Comprehensive Pharmaceutical Recommendation System

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zomorodi, Mariam Ghodsollahee, Ismail Martin, Jennifer H. Talley, Nicholas J. Salari, Vahid Plawiak, Pawel Rahimi, Kazem Acharya, U. Rajendra Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Krakow Poland Department of Computer Engineering Ferdowsi University of Mashhad Iran The University of Newcastle CallaghanNSW Australia Institute for Quantum Science and Technology Department of Physics and Astronomy University of Calgary Alberta Canada Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Deep Medicine Nuffield Department of Women’s and Reproductive Health University of Oxford Oxford United Kingdom School of Mathematics Physics and Computing University of Southern Queensland ToowoombaQLD Australia

OBJECTIVES: To build datasets containing useful information from drug databases and recommend a list of drugs to physicians and patients with high accuracy by considering features of a spectrum of people, diseases, and chemicals. METHODS: A comprehensive pharmaceutical recommendation system was designed based on the features of a spectrum of people, diseases, and medicines extracted from two major drug databases, a dataset of patients and drug information. Then the recommendation was given, and the response was analysed using patient and caregiver ratings and the knowledge obtained from drug specifications and interactions. Sentiment analysis was employed by natural language processing approaches in pre-processing, along with neural network-based methods and recommender system algorithms for modelling the system. Patient conditions and medicine features were used for making two models based on matrix factorisation. Then we used drug interaction criteria to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs by using data from 2304 patients as a training set, and then we used data from 660 patients as our validation set. We used knowledge from critical drug information and combined the model’s outcome into a knowledge-based system with the rules obtained from constraints on taking medicine. RESULTS: The results show that our recommendation system can recommend an acceptable combination of medicines according to the existing real-life prescriptions available. Compared with conventional matrix factorisation, our proposed model improves the accuracy, sensitivity, and hit rate by 26%, 34%, and 40%, respectively. In addition, it improves the accuracy, sensitivity, and hit rate by an average of 31%, 29%, and 28% compared to other machine learning methods. We have open-sourced our implementation in Python. CONCLUSION: Compared to conventional machine learning approaches, we obtained average accuracy, sens

关键词： Recommender systems

On asymptotic fairness in voting with greedy sampling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gutierrez, Abraham Müller, Sebastian Šebek, Stjepan Institute of Discrete Mathematics Graz University of Technology Graz Austria Aix Marseille Université CNRS Centrale Marseille I2M - UMR 7373 Marseille13453 France IOTA Foundation Berlin10405 Germany Department of Applied Mathematics Faculty of Electrical Engineering and Computing University of Zagreb Croatia

The basic idea of voting protocols is that nodes query a sample of other nodes and adjust their own opinion throughout several rounds based on the proportion of the sampled opinions. In the classic model, it is assumed that all nodes have the same weight. We study voting protocols for heterogeneous weights with respect to fairness. A voting protocol is fair if the influence on the eventual outcome of a given participant is linear in its weight. Previous work used sampling with replacement to construct a fair voting scheme. However, it was shown that using greedy sampling, i.e., sampling with replacement until a given number of distinct elements is chosen, turns out to be more robust and performant. In this paper, we study fairness of voting protocols with greedy sampling and propose a voting scheme that is asymptotically fair for a broad class of weight distributions. We complement our theoretical findings with numerical results and present several open questions and conjectures. Copyright © 2021, The Authors. All rights reserved.

关键词： Heterogeneous networks

Investigating the Capability of Agile Processes to Support Medical Devices Regulations: The Case of XP, Scrum, and FDD with EU MDR Regulations 15th

学校读者我要写书评

暂无评论

Investigating the Capability of Agile Processes to Support M...

15th International Conference on Intelligent computing, ICIC 2019

作者： Alsaadi, Mohmood Lisitsa, Alexei Khalaf, Mohammed Qasaimeh, Malik Applied Computing Research Group Al-Maarif University College Anbar Iraq Department of Computer Science University of Liverpool Liverpool United Kingdom King Hussein Faculty of Computing Sciences Princess Sumaya University for Technology Amman Jordan

ISBN: (纸本)9783030267650

Nowadays, medical devices rely on software whether completely such as mobile medical applications or as embedded software into medical chips such as tele surgery systems. Medical device software usually developed by using traditional development methods such as V-model and Waterfall model as these methods are straightforward and has the ability to comply with regulatory requirements such as documentation that ensures traceability. However, these methods could take a long time, could be costly, and these are inappropriate in case of requirements changing. In contrast, agile processes have several benefits such as producing a product of a high-quality with low cost and in short period with the capability to embrace change during development. Therefore, companies that develop medical device software can benefit from adopting agile practices. While the adoption rate of agile practices in software development in different industries is increasing, healthcare industries still have a low rate of agile adoption. This due to the gaps between agile practices and the stringent requirements of healthcare regulations such as documentation, traceability, and formality. The main question of this research is how capable are Agile processes can be in dealing with MDR requirements? This paper will investigate the capability of agile processes to support European Medical Device Regulation (MDR) requirements by extracting the MDR requirements that are related to software development life cycle. Then investigating the robustness of agile processes, to support MDR regulations. These objectives will be conducting by comparing and analysing the most popular agile processes (XP, Scrum, and FDD) to identify the gaps between MDR requirements and agile processes. The analysis revealed that XP is inappropriate for MDR requirements since it lacks the fixed up-front planning and also have insufficient documentations for treatability, Scrum has a model status report can be used for traceability bu

关键词： Life cycle

Analytical simulations for rate type nanomaterial stretching flow with dual convection

学校读者我要写书评

暂无评论

Partial Differential Equations in applied Mathematics 2025年 13卷

作者： Ahmad, Manzoor Khan, Sami Ullah Quratulain, Syeda Adnan Waqas, M. Garalleh, Hakim AL Zamri, Nurnadiah Abduvalieva, Dilsora Gupta, Manish Department of Mathematics University of Azad Jammu & Kashmir Muzaffarabad 13100 Pakistan Department of Mathematics Namal University Mianwali 42250 Pakistan Department of Mathematics Mohi-ud-Din Islamic University Nerian Sharif 12080 AJ&K Pakistan NUTECH School of Applied Sciences and Humanities National University of Technology Islamabad 44000 Pakistan Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Besut Campus Terengganu Besut 22200 Malaysia Department of Mathematical Science College of Engineering University of Business and Technology Jeddah 21361 Saudi Arabia Department of Mathematics and Information Technologies Tashkent State Pedagogical University Bunyodkor avenue 27 Tashkent 100070 Uzbekistan Division of Research and Development Lovely Professional University Phagwara India

Owing to high thermal performances and stable properties, multiple applications of nanomaterials have been studied in different industrial and engineering processes. Ongoing continuous research in nanofluid suggested different applications of nanomaterials in catalysis, aerospace engineering, oil industry, various optical devices, medical imaging etc. The objective for exploring current investigation is to disclose the thermal impact of Oldroyd-B nanofluid comprising the buoyancy driven flow. The heat and mass transfer analysis is predicted with insight of Brownian motion and thermophoresis phenomenon. The flow is subject to bidirectional surface maintaining the uniform velocity. The zero-mass constraints are utilized for analyzing the flow phenomenon. The analytical treatment is suggested regarding the computations of developed system. Fundamental of thermal transport phenomenon are suggested with physical aspects. It is observed that velocity profile enhances with applications of buoyancy forces. The temperature profile reduces due to velocity ratio parameter. Current results present applications in cooling processes, thermal management devices, heating control, extrusion processes, chemical systems etc. © 2025

关键词： Analytical solution Buoyancy forces Mixed convection Oldroyd-B nanofluid Zero-mass constraints

Privacy preserving passive DNS

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Papadopoulos, Pavlos Pitropakis, Nikolaos Buchanan, William J. Lo, Owen Katsikas, Sokratis School of Computing Edinburgh Napier University Edinburgh United Kingdom Department of Information Security and Communication Technology Norwegian University of Science and Technology Norway Faculty of Pure and Applied Sciences Open University of Cyprus Cyprus

The Domain Name System (DNS) was created to resolve the IP addresses of the web servers to easily remembered names. When it was initially created, security was not a major concern;nowadays, this lack of inherent security and trust has exposed the global DNS infrastructure to malicious actors. The passive DNS data collection process creates a database containing various DNS data elements, some of which are personal and need to be protected to preserve the privacy of the end users. To this end, we propose the use of distributed ledger technology. We use Hyperledger Fabric to create a permissioned blockchain, which only authorized entities can access. The proposed solution supports queries for storing and retrieving data from the blockchain ledger, allowing the use of the passive DNS database for further analysis, e.g. for the identification of malicious domain names. Additionally, it effectively protects the DNS personal data from unauthorized entities, including the administrators that can act as potential malicious insiders, and allows only the data owners to perform queries over these data. We evaluated our proposed solution by creating a proof-of-concept experimental setup that passively collects DNS data from a network and then uses the distributed ledger technology to store the data in an immutable ledger, thus providing a full historical overview of all the records. Copyright © 2020, The Authors. All rights reserved.

关键词： Data acquisition

Exploring the molecular subclasses and stage-specific genes of oral cancer: A bioinformatics analysis

学校读者我要写书评

暂无评论

Cancer Treatment and Research Communications 2021年 27卷 100320-100320页

作者： Shafana, Abdul Raheem Fathima Uwanthika, Gatamanna Arachchige Isuri Kartheeswaran, Thangathurai Department of Information and Communication Technology Faculty of Technology South Eastern University of Sri Lanka Oluvil Sri Lanka Department of Computer Science Faculty of Computing General Sir John Kotelawala Defence University Ratmalana Sri Lanka Department of Physical Science Vavuniya Campus of the University of Jaffna Vavuniya Sri Lanka Department of Computer Science and Informatics Faculty of Applied Sciences Uva Wellassa University of Sri Lanka Badulla Sri Lanka

The rate of people getting affected by Oral cancer in Sri Lanka is growing rapidly since the root cause of such cancer, betel quid chewing is tightly coupled with the tradition of the country. The five-year survival rate of the disease is also pretty low as it is typically detected at advanced stages. This urges a comprehensive study on the marker genes of oral cancer for the successful therapeutic revisions that would potentially identify cancer in its early stages. Further, the identification of molecular subclasses can assist in individualizing the treatment for this type of fatal disease. This study uses the bioinformatics analysis on the gene expression dataset of 56 oral cancer patients from Sri Lanka and the United Kingdom to identify the differentially expressed genes where these genes are later clustered and classified into molecular subclasses. Molecular subclasses are found by clustering the genes that stratify together and the stages were identified with the use of gene co-expression networks. Five molecular subclasses of oral cancer were identified and the genes associated with each tumour stage. Out of the genes that are clustered and classified, TAGLN2, CCND2 and CCL8 were well-known tumour suppressor genes and GPX3, GRN and ITGB4 genes are involved in several carcinomas. Putative marker genes of Oral Squamous Cell Carcinoma were identified which could facilitate the medical practitioner in the early detection of oral cancer and also in the improvement of treatment methods. © 2021

关键词： Betel quid chewing Gene co-expression network Microarray molecular subclasses Oral Squamous Cell Carcinoma

Scalability of network visualisation from a cognitive load perspective

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yoghourdjian, Vahan Yang, Yalong Dwyer, Tim Lawrence, Lee Wybrow, Michael Marriott, Kim The Department of Human-Centred Computing Faculty of Information Technology Monash University Melbourne Australia The Faculty of Business and Economics Monash University Melbourne Australia The School of Engineering and Applied Sciences Harvard University MA United States

Node-link diagrams are widely used to visualise networks. However, even the best network layout algorithms ultimately result in 'hairball' visualisations when the graph reaches a certain degree of complexity, requiring simplification through aggregation or interaction (such as filtering) to remain usable. Until now, there has been little data to indicate at what level of complexity node-link diagrams become ineffective or how visual complexity affects cognitive load. To this end, we conducted a controlled study to understand workload limits for a task that requires a detailed understanding of the network topology-finding the shortest path between two nodes. We tested performance on graphs with 25 to 175 nodes with varying density. We collected performance measures (accuracy and response time), subjective feedback, and physiological measures (EEG, pupil dilation, and heart rate variability). To the best of our knowledge this is the first network visualisation study to include physiological measures. Our results show that people have significant difficulty finding the shortest path in high density node-link diagrams with more than 50 nodes and even low density graphs with more than 100 nodes. From our collected EEG data we observe functional differences in brain activity between hard and easy tasks. We found that cognitive load increased up to certain level of difficulty after which it decreased, likely because participants had given up. We also explored the effects of global network layout features such as size or number of crossings, and features of the shortest path such as length or straightness on task difficulty. We found that global features generally had a greater impact than those of the shortest path. Copyright © 2020, The Authors. All rights reserved.

关键词： Data visualization