检索结果-内蒙古大学图书馆

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

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)9798331519643

ISBN: (纸本)9798331519650

Many smoking-related diseases are difficult to treat and often fatal. Rather than treating diseased smokers, preventing the diseased is more achievable, though, many of them deny to being smokers, leading to another problem. Thus, this study aims to detect important aspects that can detect that the person is a smoker or not through their bio-signals through using SHAP, along with a comprehensive analysis of the used methods, gradient-boosting algorithms XGBoost, LightGBM, and CatBoost, known for their efficiency in handling complex datasets and non-linear relationships. The study then found that triglyceride, Gtp, hemoglobins significantly affect the body's responses to smoking, based on the CatBoosts’ results, having an AUC score of up to 0.8612 and an accuracy score of up to 0.7776 with the selected features.

关键词： Seminars Measurement Accuracy Predictive models Feature extraction Boosting Physiology Classification algorithms Reliability Diseases

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

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

Pitfall of genome-wide association studies: Sources of inconsistency in genotypes and their effects

引用

Journal of Biomedical Science and Engineering 2012年第10期5卷 557-573页

作者： Huixiao Hong Lei Xu Zhenqiang Su Jie Liu Weigong Ge Jie Shen Hong Fang Roger Perkins Leming Shi Weida Tong Bioinformatics Graduate Program University of Arkansas at Little Rock/University of Arkansas for Medical Sciences Little Rock AR 72079 USA Division of Bioinformatics and Biostatistics National Center for Toxicological Research US Food and Drug Administration Jefferson AR 72079 USA ICF International at National Center for Toxicological Research US Food and Drug Administration Jefferson AR 72079 USA School of Materials Science and Engineering Chang’an University Xi’an China

Personalized medicine will improve heath outcomes and patient satisfaction. However, implementing personalized medicine based on individuals’ biological information is far from simple, requiring genetic biomarkers that are mainly developed and used by the pharmaceutical companies for selecting those patients who benefit more, or have less risk of adverse drug reactions, from a particular drug. Genome-wide Association Studies (GWAS) aim to identify genetic variants across the human genome that might be utilized as genetic biomarkers for diagnosis and prognosis. During the last several years, high-density genotyping SNP arrays have facilitated GWAS that successfully identified common genetic variants associated with a variety of phenotypes. However, each of the identified genetic variants only explains a very small fraction of the underlying genetic contribution to the studied phenotypic trait. The replication studies demonstrated that only a small portion of associated loci in the initial GWAS can be replicated, even within the same populations. Given the complexity of GWAS, multiple sources of Type I (false positive) and Type II (false negative) errors exist. The inconsistency in genotypes that caused either by the genotypeing experiment or by genotype calling process is a major source of the false GWAS findings. Accurate and reproducible genotypes are paramount as inconsistency in genotypes can lead to an inflation of false associations. This article will review the sources of inconsistency in genotypes and discuss its effect in GWAS findings.

关键词： Genotype Association Reproducibility Inconsistency Batch Effect Genotyping Platform

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of CNN Approaches in Classifying Brain Tumor

A Systematic Literature Review of CNN Approaches in Classify...

引用

International Conference of Computer and Informatics Engineering (IC2IE)

作者： Aedentrisa Yasmanda Paulindino Bens Pardamean Gregorius Natanael Elwirehardja 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

The ability of Convolutional Neural Networks (CNNs) to accurately discriminate between normal and tumorous brain tissues has been promising. The review focuses on the different CNN models, pre-processing methods, data augmentation, and Transfer Learning (TL) strategies used in this research. This Systematic Literature Review (SLR) collected the data from Google Scholar. The results of this study indicate that open-source datasets from Kaggle and Brain MRI Images for Brain Tumor Detection are the most used datasets. However, limited data and imbalanced class problems remain common challenges across various datasets. To overcome those challenges, using a larger dataset, oversampling, Generative Adversarial Network (GAN), federated learning, and Self-Supervised Learning (SSL) to handle the imbalance are the potential solution. Additionally, popular CNN architectures for brain tumor classification extensively use pre-trained models such as VGG16, VGG19, DenseNet121, DenseNet201, GoogleNet, ResNet-50, and Inception-v3. TL strategies are preferred, allowing CNNs to leverage knowledge from large datasets, improving generalization even with limited labeled data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Diversity Inventory Monitoring System of Riparian Vegetation 4

A Diversity Inventory Monitoring System of Riparian Vegetati...

引用

4th International Conference on Cybernetics and Intelligent System, ICORIS 2022

作者： Putra, Dian Pratama Nugraha, Nanda Satya Suparyanto, Teddy Hidayat, Alam Ahmad Sudigyo, Digdo Pardamean, Bens STIPER Agricultural Institute Faculty of Agricultural Technology Yogyakarta55282 Indonesia STIPER Agricultural Institute Yogyakarta Faculty of Agricultural Technology Faculty of Forestry Yogyakarta55282 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665453950

To strengthen conservation efforts for preserving biodiversity in a conservation area, forest inventory is important to understand the natural succession process in the area and to establish a monitoring strategy. Further, tree inventory aims to monitor the output yielded in the area. More specifically, the tree inventory in the watershed area plays a key role to achieve Sustainable Development Goals (SDG), especially in riparian zones which are also vital parts of green zones in forests. However, the traditional inventory approach is time-consuming and laborious therefore the development of an expert system to assist in inventory monitoring is required. In this study, we develop a monitoring system via a mobile application to collect, analyze and visualize tree inventory data. The application includes algorithms required to compute tree biodiversity, distribution, and richness for the given input of the data of all tree species in a conservation area. For the model validation stage, we compare the traditional inventory approach with our proposed application-based approach to compute diversity inventory in two riparian locations: Klaten Conservation Park and Wonosobo Conservation Park. After the three-day data collection in the areas, we obtain that the accuracy of reading data of our proposed system can achieve more than 90% in comparison with the manual approach. This demonstrates that the system can assist forestry workers to perform more efficient tree inventories in different locations. © 2022 IEEE.

关键词： Biodiversity

来源：评论

学校读者我要写书评

暂无评论

Mobile Application Implementation as Agriculture 4.0 Strategy for Sugarcane Yield Prediction 9

Mobile Application Implementation as Agriculture 4.0 Strateg...

引用

9th International HCI and UX Conference in Indonesia, CHIuXiD 2023

作者： Mawandha, Hangger Gahara Rahutomo, Reza Suparyanto, Teddy Pardamean, Bens Institut Pertanian Stiper Faculty of Agricultural Technology Yogyakarta55282 Indonesia Bina Nusantara University School of Information Systems Information Systems Department Jakarta 11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta 11480 Indonesia Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta 11480 Indonesia

ISBN: (纸本)9798350304084

Information engineering strategies play a significant and transformative role in shaping the landscape of digital agriculture. It drives innovation and efficiency in modern farming practices, with a specific focus on enhancing the value of agricultural commodities, such as sugarcane. The application of mobile technology plays a crucial part in achieving increased sugarcane productivity. Mobile applications, equipped with advanced developer features, offer rapid and user-friendly access to vital information. Traditional methods of estimating sugarcane production relied on manual data recording on paper, followed by data transfer to computer systems, typically managed by sugar factory junior plant officers. This conventional approach presents several inherent weaknesses, including time and effort intensiveness during data recording and entry. Additionally, the potential for errors in calculation and data input is a concern. The storage capacity for paper-based documents is finite, and farmers are often unable to autonomously assess their production potential. The objective of this research is to confront these obstacles by creating a sugarcane production application for Android. This application functions as an information engineering approach focused on forecasting sugarcane yields for plantation owners and their assistants. The development procedure adhered to the systematic waterfall method, following the principles of the Software Development Life Cycle (SDLC) model. Data collection was carried out through observations, while interviews with junior plant officers provided valuable insights into sugarcane estimation techniques. Analysis involved the synthesis of observational and interview data to inform the design of the application's interface and algorithmic system. The resulting application significantly simplifies the process of estimating production potential for farmers, enabling them to access sugarcane productivity data during harvest. Consequently, sugar

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Implementation of expert systems in potassium deficiency in cocoa plants using forward chaining method

引用

Procedia Computer Science 2023年 216卷 136-143页

作者： Muhammad Titan Hafizal Dian Pratama Putra Herry Wirianata Nanda Satya Nugraha Teddy Suparyanto Alam Ahmad Hidayat Bens Pardamean Faculty of Forestry STIPER Institute of Agriculture Yogyakarta 55282 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta 11480 Indonesia

As one of the largest exporters in the world, cocoa (Theobroma cacao L.) production in Indonesia provides an important contribution to the plantation sector that can, directly and indirectly, attribute to the national economic development. However, recent data shows a decline in cocoa productivity in Indonesia. This is arguably caused by various factors, including poor agricultural management and practices in cocoa plantations, that may lead to lower fertility in the soil and an increased risk of diseases and pests. Potassium deficiency is a major contributing factor to the low soil fertility that affects cocoa yields. Therefore, in this work, we implement an application with an expert system utilizing the forward chaining method to detect potassium deficiency in cocoa plants and then give a fertilization-based recommendation based on the plants’ condition. The system employs a set of rules to identify symptoms related to the deficiency on the sample photo of a cocoa leaf according to the channels of red, green, and blue of the image. The sample images of cocoa leaves are submitted to the application with an easy-to-use interface that can show the scanning result and proceed to display the suggested quantity of fertilizers to prevent potassium deficiency. Implementing the system can contribute constructive impacts to improve current practices in the overall cropping system of cocoa plants.

关键词： agriculture cocoa expert system forward chaining recommendation system

来源：评论

学校读者我要写书评

暂无评论

Confidentiality. Integrity, and Availability (CIA) Approach for Private Dataset Management System Design 9

Confidentiality. Integrity, and Availability (CIA) Approach ...

引用

9th International Conference on Information Technology and Digital Applications, ICITDA 2024

作者： Isnan, Mahmud Elwirehardja, Gregorius Natanael Ariansyah, Dedy Rahutomo, Reza Pardamean, Bens School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Binus Graduate Program Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331510732

Dataset management systems are essential for assisting research and development (R&D) organizations in applying data governance protocols, especially in managing the utilization of datasets. In R&D, datasets are vital sources for producing analysis, machine learning prediction, and supporting decision-making. As such, it is important to deploy dataset management systems with considerations regarding the aspects of Confidentiality, Integrity, and Availability (CIA) which is a design principle that emphasized information protection and collaboration facilitation among dataset users. The study proposed an analysis and a design for a dataset management system that takes CIA aspects into account. In the future, the proposed design will be utilized as a benchmark for building a dataset management system. In this study, the Waterfall method was adopted. A use case diagram, an ERD (Entity Relationship Diagram), and an activity diagram were constructed in the design stage. In the project implementation stage, the Laravel framework including Laravel Jetstream was considered to be used. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

A novel label-free electrochemical immunosensor for the detection of heat shock protein 70 of lung adenocarcinoma cell line following paclitaxel treatment using l-cysteine-functionalized Au@MnO2/MoO3 nanocomposites

引用

RSC Advances 2023年第43期13卷 29847-29861页

作者： Chen, Yi-An Shie, Ming-You Ho, Chia-Che Ye, Sheng-Wen Chen, I.-Wen Peter Shih, Yu-Yin Shen, Yu-Fang Chen, Yi-Wen x-Dimension Center for Medical Research and Translation China Medical University Hospital Taichung City404332 Taiwan The Master Program for Biomedical Engineering China Medical University Taichung City406040 Taiwan Department of Biomedical Engineering China Medical University Taichung City40447 Taiwan Department of Bioinformatics and Medical Engineering Asia University Taichung City41354 Taiwan Department of Chemistry National Cheng Kung University Tainan70101 Taiwan Graduate Institute of Biomedical Sciences China Medical University Taichung City40447 Taiwan

The future trend in achieving precision medicine involves the development of non-invasive cancer biomarker sensors that offer high accuracy, low cost, and time-saving benefits for risk clarification, early detection, disease detection, and therapeutic monitoring. A facile approach for the synthesis of MoO3 nanosheets was developed by thermally oxidizing MoS2 nanosheets in air followed by thermal annealing. Subsequently, Au@MnO2 nanocomposites were prepared using a combined hydrothermal process and in situ chemical synthesis. In this study, we present a novel immunosensor design strategy involving the immobilization of antiHSP70 antibodies on Au@MnO2/MoO3 nanocomposites modified on a screen-printed electrode (SPE) using EDC/NHS chemistry. This study establishes HSP70 as a potential biomarker for monitoring therapeutic response during anticancer therapy. Impedance measurements of HSP70 on the Au@MnO2/MoO3/SPE immunosensor using EIS showed an increase in impedance with an increase in HSP70 concentration. The electrochemical immunosensor demonstrated a good linear response in the range of 0.001 to 1000 ng mL−1 with a detection limit of 0.17 pg mL−1 under optimal conditions. Moreover, the immunosensor was effective in detecting HSP70 at low concentrations in a lung adenocarcinoma cell line following Paclitaxel treatment, indicating its potential for early detection of the HSP70 biomarker in organ-on-a-chip and clinical applications. © 2023 The Royal Society of Chemistry.

关键词： Nanosheets

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：