检索结果-内蒙古大学图书馆

Unitig-centered pan-genome machine learning approach for predicting antibiotic resistance and discovering novel resistance genes in bacterial strains

引用

Computational and Structural Biotechnology Journal 2024年 23卷 1864-1876页

作者： Do, Duyen Thi Yang, Ming-Ren Vo, Tran Nam Son Le, Nguyen Quoc Khanh Wu, Yu-Wei Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei Taiwan Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Business Administration College of Management Lunghwa University of Science and Technology Taoyuan City Taiwan Professional Master Program in Artificial Intelligence in Medicine College of Medicine Taipei Medical University Taipei Taiwan Clinical Big Data Research Center Taipei Medical University Hospital Taipei Taiwan TMU Research Center for Digestive Medicine Taipei Medical University Taipei Taiwan

In current genomic research, the widely used methods for predicting antimicrobial resistance (AMR) often rely on prior knowledge of known AMR genes or reference genomes. However, these methods have limitations, potentially resulting in imprecise predictions owing to incomplete coverage of AMR mechanisms and genetic variations. To overcome these limitations, we propose a pan-genome-based machine learning approach to advance our understanding of AMR gene repertoires and uncover possible feature sets for precise AMR classification. By building compacted de Brujin graphs (cDBGs) from thousands of genomes and collecting the presence/absence patterns of unique sequences (unitigs) for Pseudomonas aeruginosa, we determined that using machine learning models on unitig-centered pan-genomes showed significant promise for accurately predicting the antibiotic resistance or susceptibility of microbial strains. Applying a feature-selection-based machine learning algorithm led to satisfactory predictive performance for the training dataset (with an area under the receiver operating characteristic curve (AUC) of > 0.929) and an independent validation dataset (AUC, approximately 0.77). Furthermore, the selected unitigs revealed previously unidentified resistance genes, allowing for the expansion of the resistance gene repertoire to those that have not previously been described in the literature on antibiotic resistance. These results demonstrate that our proposed unitig-based pan-genome feature set was effective in constructing machine learning predictors that could accurately identify AMR pathogens. Gene sets extracted using this approach may offer valuable insights into expanding known AMR genes and forming new hypotheses to uncover the underlying mechanisms of bacterial AMR. © 2024 The Authors

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-SVM Approach for Malaria in Blood Cell Detection

A Hybrid CNN-SVM Approach for Malaria in Blood Cell Detectio...

引用

Software Engineering and Information Technology (ICoSEIT), International Conference on

作者： Andrea Stevens Karnyoto Mahmud Isnan Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

There is still a severe malaria problem worldwide, particularly in regions with limited access to diagnostic tools. It is crucial to develop a system for detecting malaria in blood cells. This paper presents a hybrid Convolutional Neural Network (CNN), and as a classifier, we use a Support Vector Machine (SVM) framework for the automated detection of malaria parasites in blood cell images. The proposed system leverages the strengths of CNNs in feature extraction and representation learning from images, combined with the discriminative power of SVMs for classification. Initially, CNN extracts intricate features from blood cell images, capturing essential patterns indicative of malaria infection. Subsequently, the extracted features are used to train an SVM classifier, enabling accurate discrimination between parasitized and uninfected blood cells. Experimental dataset evaluations were obtained from the Lister Hill National Center for Biomedical Communications website of the National Library of Medicine. The proposed model achieves a better f1-score, outperforming individual CNN or SVM models, around 0.015 compared to individual CNN models and 0.27 compared to individual SVM models. This hybrid CNN-SVM methodology offers a promising solution for accurately and efficiently detecting malaria parasites in blood cell images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mitigating Berkson's Paradox with Neural Propensity Score Matching in E-Commerce Deals

Mitigating Berkson's Paradox with Neural Propensity Score Ma...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Nicholas Dominic Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Within observational data science workloads, Berkson's paradox can lead to false causal inferences. One of the prominent quasi-experimental methods to mitigate this selection bias is Propensity Score Matching (PSM). An approach called Neural PSM (NPSM) was developed to overcome the drawbacks of conventional regression-based PSM, including its limited flexibility to model high-dimensional data and non-linear relationships that could cause imperfect covariate balance. In this study, a three-layer depth of Deep Neural Networks was designed to estimate propensity scores and finally balance both control and treatment groups of the Groupon dataset. An unsupervised k-Nearest Neighbor algorithm then helped the model to efficiently detect and cluster similar matching points. From the five salient features presented, NPSM successfully achieved lower differences in Cohen's d effect size, i.e., 0.313 for coupon duration, 0.017 for promotion length, 0.425 for quantity sold, -0.199 for limited supply, and 0.395 for Facebook likes. While these results mostly outperformed Linear Regression (LR) and Random Forest (RF) models, further evaluation is needed to verify the true effectiveness of NPSM in mitigating Berkson's paradox in broader e-commerce contexts.

关键词： Radio frequency Social networking (online) High dimensional data Linear regression Nearest neighbor methods data science Electronic commerce Intelligent systems Cybernetics Context modeling

来源：评论

学校读者我要写书评

暂无评论

Systematic Literature Review on Metaheuristic Algorithms in SNP Analysis for Diseases

Systematic Literature Review on Metaheuristic Algorithms in ...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Jason Sebastian Sulistyawan Kuncahyo Setyo Nugroho Bens Pardamean Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Single-nucleotide polymorphism (SNP) analysis has become a pivotal strategy for drug discovery within bioinformatics, especially for incurable diseases like cancer. With the increasing number of researchers starting to embrace metaheuristic methods, a review was done by gathering papers from the Google Scholar database from 2018 to 2023, which resulted in 20 papers after title, abstract, and content filtering. The findings show that the Genetic Algorithm and the Harmony Search Algorithm have become popular approaches in SNP analysis, particularly in studies on breast cancer, age-related macular degeneration, and colorectal cancer. However, the review shows that while researchers have proven most methods effective in finding disease-related SNPs, a more measurable study in SNP analysis is needed, due to the lack of elaboration on measurement metrics in the found studies.

关键词： Macular degeneration Filtering databases Metaheuristics Time measurement Internet Drug discovery Intelligent systems Genetic algorithms Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Analysis of Rates Derived from Count data Using Generalized Fused Lasso Poisson Model 15th

Spatio-Temporal Analysis of Rates Derived from Count Data ...

引用

15th International KES Conference on Intelligent Decision Technologies, KESIDT 2023

作者： Yamamura, Mariko Ohishi, Mineaki Yanagihara, Hirokazu Department of Statistics Radiation Effects Research Foundation Hiroshima732-0815 Japan Center for Data-driven Science and Artificial Intelligence Tohoku University Sendai980-8576 Japan Mathematics Program Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Higashi-Hiroshima739-8526 Japan

ISBN: (纸本)9789819929689

We propose a method to statistically analyze rates obtained from count data in spatio-temporal terms, allowing for regional and temporal comparisons. Generalized fused Lasso Poisson model is used to estimate the spatio-temporal effects of the rates;the coordinate descent algorithm is used for estimation. The results of an analysis using data on crime rates in Japan’s Osaka Prefecture from 1995 to 2008 confirm the validity of the approach. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Adaptive fused lasso Coordinate descent algorithm Spatio-temporal proportion data

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph-Enhanced Semantic Cache for Low-Latency and Cost-Effective Inference in Large Language Models

Knowledge Graph-Enhanced Semantic Cache for Low-Latency and ...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Nicholas Dominic Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

In organizational knowledge management, Large Language Model (LLM) caches act as a semantic repository gathered from previous LLM responses. Due to intensive calls from multiple users, LLM may suffer from high inference latency. While there are many prior available approaches to solve this problem, most of them are inherently complex. This paper introduced a Knowledge Graph-enhanced Semantic Cache mechanism as an alternative, lightweight technique to boost retrieval for similar prompts. The latest state-of-the-art open-source LLM, named Google's Gemma-2B-it, was used to generate sample prompts and responses as a draft, while a knowledge graph (KG) was built from Wikipedia sentences. To create embeddings of prompts and KG, all-MiniLM-L6-v2 from SentenceTransformer was used. This new cache system resulted in up to 28% improvement over a standard model. In particular, reinforcement with KG cache embeddings yielded more than 85% semantic cache accuracy. To map the next trajectory of this pilot study, an overview of the extended framework for LLM knowledge management was also presented in this paper. The framework includes the new KG- enhanced cache system equipped with scalable security and fallback mechanisms that can promote green technology through substantial improvements in latency, throughput, and overall LLM costs.

关键词： Large language models Semantics Throughput Knowledge management Internet Trajectory Security Online services Low latency communication Standards

来源：评论

学校读者我要写书评

暂无评论

Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment

Compressing VAE-Based Out-of-Distribution Detectors for Embe...

引用

IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)

作者： Aditya Bansal Michael Yuhas Arvind Easwaran College of Computing and Data Science Nanyang Technological University Singapore Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore

ISBN: (数字)9798350387957

ISBN: (纸本)9798350387964

Out-of-distribution (OOD) detectors can act as safety monitors in embedded cyber-physical systems by identifying samples outside a machine learning model’s training distribution to prevent potentially unsafe actions. However, OOD detectors are often implemented using deep neural networks, which makes it difficult to meet real-time deadlines on embedded systems with memory and power constraints. We consider the class of variational autoencoder (VAE) based OOD detectors where OOD detection is performed in latent space, and apply quantization, pruning, and knowledge distillation. These techniques have been explored for other deep models, but no work has considered their combined effect on latent space OOD detection. While these techniques increase the VAE’s test loss, this does not correspond to a proportional decrease in OOD detection performance and we leverage this to develop lean OOD detectors capable of real-time inference on embedded CPUs and GPUs. We propose a design methodology that combines all three compression techniques and yields a significant decrease in memory and execution time while maintaining AUROC for a given OOD detector. We demonstrate this methodology with two existing OOD detectors on a Jetson Nano and reduce GPU and CPU inference time by 20% and 28% respectively while keeping AUROC within 5% of the baseline.

关键词： Training Quantization (signal) Embedded systems Memory management Graphics processing units Detectors Machine learning Real-time systems Safety Monitoring

来源：评论

学校读者我要写书评

暂无评论

Implementation of Computer Vision of Jakarta Weather Image Categorization Using ResNet 8

Implementation of Computer Vision of Jakarta Weather Image C...

引用

8th International Conference on Computer science and Computational Intelligence, ICCSCI 2023

作者： Purwandari, Kartika Sigalingging, Join W.C. Hidayat, Alam Ahmad Cenggoro, Tjeng Wawan Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Database Center Division of BMKG Meteorological Climatological and Geophysical Agency Jakarta10720 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

At the moment, weather data is crucial for supporting neighborhood activities. The economy and trade are both centered in Jakarta, which is also Indonesia's capital. Therefore, it is crucial to have access to weather information so that these activities don't get disrupted, which would then hinder commercial and trade activity. Social media has been a very popular tool for spreading information recently. Particularly on Instagram, where users favor taking images and sharing the information they encounter. @jktinfo is the Instagram account that posts information about the situation in Jakarta and the area, including the current weather. The @jktinfo account is utilized in this project to gather data. Utilizing a variety of techniques, the collected photographs of sunny, cloudy, and wet situations were. © 2023 The Authors. Published by Elsevier B.V.

关键词： computer vision data augmentation deep transfer learning residual network weather image categorization

来源：评论

学校读者我要写书评

暂无评论

Real-Time Detection of Cattle Behavior Using YOLOv9 with AutoAugment and Mixup data Augmentation Techniques

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第12期73卷 2326-2332页

作者： Lee, Su-Bin Park, Jae-Beom Cho, Hyun-Chong Dept. of Electronics Engineering Dept. of Data Science Kangwon National University Korea Republic of Dept. of Data Science Kangwon National University Korea Republic of Dept. of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

As the number of livestock farms in Korea decreases, the scale of individual farms has grown, necessitating advanced methods for efficient livestock management. Recent studies have increasingly applied computer vision and deep learning to monitor livestock behavior, health, and disease, aiming to enhance productivity and animal welfare. This study introduces a real-time cattle behavior detection system utilizing YOLOv9, a state-of-the-art object detection algorithm known for its high accuracy and efficiency. The YOLOv9-s model, optimized for real-time detection with minimal computational overhead, was employed. To further enhance detection accuracy, we incorporated AutoAugment, a data augmentation technique that automatically selects the optimal augmentation policies, and mixup, a method that improves model generalization by creating new training samples through linear interpolation of existing ones. The application of AutoAugment improved the mean Average Precision (mAP) from 0.926 to 0.941, while the addition of mixup raised the mAP to 0.947, representing a 2.1% performance increase. These results confirm the system's capability for accurate and efficient real-time detection of cattle behavior. Copyright © The Korean Institute of Electrical Engineers.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

An Object Driven Fuzzy Decision Model for Sugarcane Yield Prediction in Indonesia’s Sugar Industry

An Object Driven Fuzzy Decision Model for Sugarcane Yield Pr...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Ditdit Nugeraha Utama Muhammad Asrol Suharjito Christian Harito Napthaleni Muhammad Syafrudin Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia Industrial Engineering Department BINUS Graduate Program Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia Department of Artificial Intelligence and Data Science Sejong University Seoul South Korea

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

A sugarcane yield of one plantation area depends on several independent variables. Practically it is challenging to predict accurately by using conventional methods. This study aims to develop a decision model based on a combination of fuzzy logic and object-oriented methods to predict sugarcane yield. The research is conducted in four main stages, employing object-oriented methods for model design and fuzzy logic for model construction. Object and activity diagrams are used for the object-oriented model design. The fuzzy membership functions employed are a combination of trapezoidal and triangular shapes. The resulting decision model can simulate 2,225 data from plantation areas in Indonesia. Based on the 10 examples of plantation area data in Indonesia, plantation number one obtained the largest sugarcane yield, which was 4.79%, with a similarity value of 0.90 (when compared to manual calculations as its ground truth). This similarity value is a higher value when compared to the average similarity value, which is 0.89.

关键词： Fuzzy logic Seminars Shape Object oriented modeling Plantations Manuals Predictive models Sugar industry Intelligent systems Information technology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：