检索结果-内蒙古大学图书馆

Identifying cancer patients who received palliative care using the SPICT-LIS in medical records: a rule-based algorithm and text-mining technique

引用

BMC PALLIATIVE CARE 2024年第1期23卷 1-10页

作者： Limsomwong, Pawita Ingviya, Thammasin Fumaneeshoat, Orapan Prince Songkla Univ Dept Family & Prevent Med Hat Yai 90110 Thailand Prince Songkla Univ Fac Med Div Digital Innovat & Data Analyt Hat Yai Campus Hat Yai 90110 Thailand Prince Songkla Univ Fac Med Dept Clin Res & Med Data Sci Hat Yai 90110 Thailand

Background Due to limited numbers of palliative care specialists and/or resources, accessing palliative care remains limited in many low and middle-income countries. Data science methods, such as rule-based algorithms and text mining, have potential to improve palliative care by facilitating analysis of electronic healthcare records. This study aimed to develop and evaluate a rule-based algorithm for identifying cancer patients who may benefit from palliative care based on the Thai version of the Supportive and Palliative Care Indicators for a Low-Income Setting (SPICT-LIS) *** The medical records of 14,363 cancer patients aged 18 years and older, diagnosed between 2016 and 2020 at Songklanagarind Hospital, were analyzed. Two rule-based algorithms, strict and relaxed, were designed to identify key SPICT-LIS indicators in the electronic medical records using tokenization and sentiment analysis. The inter-rater reliability between these two algorithms and palliative care physicians was assessed using percentage agreement and Cohen's kappa coefficient. Additionally, factors associated with patients might be given palliative care as they will benefit from it were *** The strict rule-based algorithm demonstrated a high degree of accuracy, with 95% agreement and Cohen's kappa coefficient of 0.83. In contrast, the relaxed rule-based algorithm demonstrated a lower agreement (71% agreement and Cohen's kappa of 0.16). Advanced-stage cancer with symptoms such as pain, dyspnea, edema, delirium, xerostomia, and anorexia were identified as significant predictors of potentially benefiting from palliative *** The integration of rule-based algorithms with electronic medical records offers a promising method for enhancing the timely and accurate identification of patients with cancer might benefit from palliative care.

关键词： Palliative care cancer patients rule-based algorithm SPICT-LIS criteria Text-mining techniques

来源：评论

学校读者我要写书评

暂无评论

Graduate Tracer Monitoring Platform with Decision Support Feature and Mapping Recommendations Analysis Using rule-based algorithm 15

Graduate Tracer Monitoring Platform with Decision Support Fe...

引用

IEEE 15th Control and System Graduate Research Colloquium (ICSGRC)

作者： Gonzales, Joseph G. Lagman, Ace C. De Angel, Roman M. Raguro, Ma Corazon F. Bulacan, Raquel C. Adriano Canlas, Joel D. FEU Inst Technol Informat Technol Dept Manila Philippines FEU Inst Technol Coll Comp Studies Manila Philippines State Univ Malolos Bulacan Philippines Don Honorio Ventura State Univ Pampanga Philippines

ISBN: (纸本)9798350386561;9798350386554

This study enabled the researcher to create a graduate tracer monitoring platform. It aimed to provide a centralized channel to monitor institutions' graduates in terms of their job employment, to assess academic programs using modified instruments so necessary interventions may be provided, and to provide a matching algorithm that can be used both by industry partners and respective alumni. This study employed a Decision Support System and mapping recommendation analysis using a rule-based algorithm to evaluate the results of alumni program evaluation on five areas or dimensions, namely curriculum, faculty, facility, laboratory, and student services. It sets the threshold to determine if the results of the areas mentioned above are beyond the passing rate and implements the interventions for each area. The content management system was also used in this study to change the contents of the Alumni Program Evaluation, the interventions, the threshold, and many more. based on the results, no intervention must be implemented in all areas/dimensions since the mean and the composite mean were more than the 4.0 threshold that was set in the proposed system. The overall rating of the respondents using the technology acceptance model numerical rating is 4.42 with an interpretation of "Agree." As observed all criteria are rated either agree or strongly agree which indicates a high standard has been set in the development of the system. This means that the system is ready for deployment.

关键词： Graduate Tracer Study Decision Support System Mapping Recommendation Analysis rule-based algorithm Employability Content Management System

来源：评论

学校读者我要写书评

暂无评论

Fault detection and diagnostic method of diesel engine by combining rule-based algorithm and BNs/BPNNs

引用

JOURNAL OF MANUFACTURING SYSTEMS 2020年 57卷 148-157页

作者： Cai, Baoping Sun, Xiutao Wang, Jiaxing Yang, Chao Wang, Zhengda Kong, Xiangdi Liu, Zengkai Liu, Yonghong China Univ Petr Natl Engn Lab Offshore Geophys & Explorat Equipme Qingdao 266580 Shandong Peoples R China China Univ Petr Coll Mech & Elect Engn Qingdao 266580 Shandong Peoples R China CRRC Qingdao Sifang Rolling Sock Res Inst CO LTD Qingdao 266033 Shandong Peoples R China

The stable operation of diesel engine is critical to the normal production of the industry, and the prevention, monitoring, and identification of faults are of great significance. At present, the fault research on diesel engines still has some defects, such as only few types of faults diagnosis are identified, the accuracy of fault diagnosis is still low, and fault identification is located at a fixed speed. A novel fault detection and diagnostic method of diesel engine by combining rule-based algorithm and Bayesian networks (BNs) or Back Propagation neural networks (BPNNs) is proposed. The signals are processed by wavelet threshold denoising and ensemble empirical mode decomposition. The signal-sensitive feature values are extracted from the decomposed intrinsic mode function. Seven faults are roughly identified using rule-based algorithm and finely identified using BNs or BPNNs. Results show the proposed fault diagnosis method has a good diagnostic performance for a wide range of rotation speeds when the training data for BNs and BPNNs are from fixed speeds. In addition, the influences of the layers of decomposed signals, sensor noise and external excitation interference on the fault diagnostic performance are also researched.

关键词： Bayesian networks BP neural networks diesel engine fault diagnosis rule-based algorithm

来源：评论

学校读者我要写书评

暂无评论

rule-based automation algorithm for generating 2D deliverables from BIM

引用

JOURNAL OF BUILDING ENGINEERING 2024年 97卷

作者： Kim, Yije Chin, Sangyoon Choo, Seungyeon Sungkyunkwan Univ Dept Convergence Engn Future City Suwon 16419 South Korea Sungkyunkwan Univ Sch Civil Architectural Engn & Landscape Architect Suwon 16419 South Korea Kyungpook Natl Univ Sch Architecture Daegu 41566 South Korea

Efficient generation of two-dimensional (2D) deliverables from building information models (BIM) entails remarkable challenges, impacting project productivity. To address this issue, BIMDrawGEN, a rule-based algorithm, was developed in this study to streamline the creation of essential 2D deliverables during the design development phase. This approach involves an analysis of the BIM design process, resulting in the derivation of 76 automation rule sets for generating logically defined 2D deliverables from BIM data. A prototype add-in interfacing with BIM authoring tools was developed to validate the model, demonstrating significant reductions in work nodes and time by 94.54 % and 93.26 %, respectively, for BIM-based drawing creation. Significant reduction in working hours, from nearly a week to under half a day, using BIMDrawGEN enhances both industrial and academic outcomes. This efficiency enables designers to focus more on design rather than documentation. This study identifies and addresses inefficient processes in BIM, demonstrating that targeted automation could significantly improve design quality and productivity.

关键词： Building information modeling (BIM) Design development stage BIM design BIM-based drawing 2D deliverable 2D extract Automation rule-based algorithm

来源：评论

学校读者我要写书评

暂无评论

Aiding Rhinoplasty Surgeons with 3D Imaging and a rule-based Adjustment algorithm

Aiding Rhinoplasty Surgeons with 3D Imaging and a Rule-Based...

引用

IEEEE Southeast Conference (SoutheastCon)

作者： AlRashidi, Yara Toloza, Sarai Denys, Hailey Gattuso, Jacob Nunez, Emily Akbas, Mustafa Ilhan Embry Riddle Aeronaut Univ Dept Elect Engn & Comp Sci Daytona Beach FL 32114 USA

ISBN: (纸本)9781665403795

Rhinoplasty surgery is considered one of the most complex cosmetic surgeries because of its uncertainty. Therefore, plastic surgeons need to use modern-day technology to aid them in conducting such a procedure. The recent advances in 3-D imaging and software-aided tools present invaluable opportunities for rhinoplasty. In this paper, we will explain how the combination of using an algorithm and 3D imaging tool is helpful in the preoperative stage of a rhinoplasty procedure. We present a rule-based adjustment algorithm that utilizes 3D facial models to assist rhinoplasty surgeons. Our system uses an existing web application that gives us the database of people that act as viable patients. This data helps show the algorithm's general usage paired with the 3D modeling tool. The system assists surgeons by giving them the difference in measurements needed to change the patient's nose and aid the patients in visualizing what they will look like after those said measurements. The system outputs numeric values that will assist the surgeon in the rhinoplasty procedure, and it will also output the 3D model of the patient's face where the points of the new nose exist on the model. We ran the algorithm for all patients in the database and calculated the differences;the 3D modeling software makes it simple to visualize the reliable, quantified suggestions of the system.

关键词： Rhinoplasty 3D imaging rule-based algorithm Plastic Surgery

来源：评论

学校读者我要写书评

暂无评论

Ensemble learning of rule-based evolutionary algorithm using multi-layer perceptron for supporting decisions in stock trading problems

引用

APPLIED SOFT COMPUTING 2015年 36卷 357-367页

作者： Mabu, Shingo Obayashi, Masanao KuremotoGraduate, Takashi Yamaguchi Univ Grad Sch Sci & Engn Ube Yamaguchi 7558611 Japan

Classification is a major research field in pattern recognition and many methods have been proposed to enhance the generalization ability of classification. Ensemble learning is one of the methods which enhance the classification ability by creating several classifiers and making decisions by combining their classification results. On the other hand, when we consider stock trading problems, trends of the markets are very important to decide to buy and sell stocks. In this case, the combinations of trading rules that can adapt to various kinds of trends are effective to judge the good timing of buying and selling. Therefore, in this paper, to enhance the performance of the stock trading system, ensemble learning mechanism of rule-based evolutionary algorithm using multi-layer perceptron (MLP) is proposed, where several rule pools for stock trading are created by rule-based evolutionary algorithm, and effective rule pools are adaptively selected by MLP and the selected rule pools cooperatively make decisions of stock trading. In the simulations, it is clarified that the proposed method shows higher profits or lower losses than the method without ensemble learning and buy&hold. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Ensemble learning Evolutionary computation rule-based algorithm Multi-layer perceptron Trend judgment Stock trading

来源：评论

学校读者我要写书评

暂无评论

Energy management of microgrids: from a mixed- integer linear programming problem to a rule-based real-time algorithm 47

Energy management of microgrids: from a mixed- integer linea...

引用

47th Annual Conference of the IEEE-Industrial-Electronics-Society (IECON)

作者： Roy, Anthony Auger, Francois Olivier, Jean-Christophe Auvity, Bruno Schaeffer, Emmanuel Bourguet, Salvy Univ Nantes IREENA St Nazaire France Univ Nantes LTEN Nantes France

ISBN: (纸本)9781665435543

To ensure the economic viability and the reliability of microgrid operation, an adapted energy management system (EMS) has to be designed. Most of the studies have discussed optimization-based approaches, for example with a mixed-integer linear programming (MILP) problem, to get the best operating profiles for each microgrid device allowing economic, technical or environmental objectives to be met. However, this kind of EMS requires a forecasting ability of the power generation and of the demand, and the management of the uncertainties. In some microgrids, especially in industrial areas, the power generation and the load demand cannot be accurately forecasted. In such cases, only a rule-based algorithm can be considered for the real-time energy management. In this paper, a rule-based algorithm is proposed for the management of a seaport multi-energy microgrid, using electricity and hydrogen as energy vectors. The rules are designed on the basis of the results obtained with MILP problem solving with the aim being to maximize income and use the energy generated by the local energy sources as well as possible by taking dynamic pricing into account. Moreover, specific strategies are designed for the management of the electrolyzer and hydrogen tank to avoid premature ageing. The results show that the proposed real-time algorithm and rules enable the economic and energetic criteria to reach values close to those obtained with MILP problem solving, with an increase of the payback period less than 2%.

关键词： Microgrid energy management rule-based algorithm storage management

来源：评论

学校读者我要写书评

暂无评论

Development of a Smart Application for Indoor Navigation (INMaps)

引用

WIRELESS PERSONAL COMMUNICATIONS 2024年第1期138卷 127-148页

作者： Mahadevaswamy, U. B. Chiranth, N. L. JSS Sci & Technol Univ Sri Jayachamarajendra Coll Engn Dept Elect & Commun Mysuru Karnataka India

Indoor navigation framework plays a significant role in day today life. In the outdoor application, GPS signals identifies the exact location or points of the user, but it is not true in indoor scenarios. To overcome this issue there are various techniques have been devised to predict the position and identify the location of the user in the indoor application. These include attaching sensors to the shoes or suites or ceiling of the building and using WIFI signals to predict the position and navigate user to the destination. But not all the time this is possible as the sensors may get damaged and signal interferences may lead to large accumulated errors in the results. This paper proposes a novel technique to predict the position and navigate the user making use of the sensors present in the smartphone. Use of smartphone eliminates the need for external sensors to be attached to the shoes or suits, as it has inbuilt magnetometer, accelerometer, and gyroscope. The data generated by these sensors are used to estimate the pitch and roll values and also the heading information. The step count and the time at which the user performs each step are calculated using peak detection algorithm. A rule-based algorithm is proposed to estimate the step length and the smart phone beacon signals are used to provide the heading information. A voice based guiding facility is also built in to alert the user in case he selects the wrong path. With all these features, the proposed system certainly helps the user to navigate correctly from source location to the intended destination. The experiments are carried out in different scenarios under various realistic conditions and the results displays that, the proposed method achieves a high position accuracy with significant reduction in the error (less than 2.5%) and performs well compared to the conventional estimation methods. The performance is assessed in terms of displacement and root mean square error and compared with the position-e

关键词： Low-pass filter Pead-detection algorithm Heading estimation Smartphone rule-based algorithm I-Beacons

来源：评论

学校读者我要写书评

暂无评论

Interpretable rule Mining for Real-Time ECG Anomaly Detection in IoT Edge Sensors

引用

IEEE INTERNET OF THINGS JOURNAL 2023年第15期10卷 13095-13108页

作者： Sivapalan, Gawsalyan Nundy, Koushik Kumar James, Alex Cardiff, Barry John, Deepu Meta Real Lab Redmond WA 98052 USA Think Biosolut Ltd Dublin D08 YPP9 Ireland Digital Univ Kerala Thiruvananthapuram 695581 India Univ Coll Dublin Sch Elect & Elect Engn Dublin 4 Ireland

Electrocardiogram (ECG) analysis is widely used in the diagnosis of cardiovascular diseases. This article proposes an explainable rule-mining strategy for prioritizing abnormal class detection in ECG data. The proposed method utilizes a biased-trained artificial neural network (ANN) with input features derived from an ECG beat sequence and formulates a set of rules at each node of an on-demand tree-like search algorithm. The rule base at each node is derived from a linear combination of the most impactful features identified using gradient analysis in an ANN. The final derived model is an explainable rule-based system that detects abnormal heartbeats based on statistical and morphological features from ECG. The model achieves the target sensitivity, and accuracy with a low run time complexity through a comprehensive offline rule-mining process and is trained using the MIT-BIH Arrhythmia Database. The system achieves an accuracy of 93% with only nine nodes and a test sensitivity of 90% and 80%, respectively, for VEB and SVEB beat types, when tested on previously unseen ECG data from the INCART database. The model performance and complexity can be easily adjusted based on the real-time resource constraints of a wearable sensor. The model was deployed on an ARM Cortex M4-based embedded device and is shown to achieve a > 50% reduction in sensor power consumption when only abnormal beats are wirelessly transmitted. That is, RF transmission is gated using the model output and transmission is disabled when the subject's ECG is normal. The proposed technique is highly suited for healthcare applications because of its explainability, lower complexity, and real-time flexibility when deployed in the Internet of Things (IoT)-enabled wearable edge sensors.

关键词： Anomaly detection artificial neural network (ANN) electrocardiogram (ECG) explainability heart rate variability (HRV) Internet of Things (IoT) edge sensors rule-based algorithm

来源：评论

学校读者我要写书评

暂无评论

An Individual-Oriented algorithm for Stress Detection in Wearable Sensor Measurements

引用

IEEE SENSORS JOURNAL 2023年第19期23卷 22845-22856页

作者： Moser, Martin Karl Resch, Bernd Ehrhart, Maximilian Univ Salzburg Dept Geoinformat A-5020 Salzburg Austria Harvard Univ Ctr Geog Anal Cambridge MA 02138 USA

Accurately measuring a person's level of stress can have a wide variety of impacts, not only on human health, but also on the perceived feeling of safety when going after daily habits, such as walking, cycling, or driving from one place to another. While there is a vast amount of research done on stress and the related physiological responses of the human body, there is no go-to method when it comes to measuring acute stress in a live setting. This work proposes an advancement of the rule-based stress detection algorithm proposed by Kyriakou et al., to identify moments of stress (MOS) more reliably, through an adaptation, and individualization of the rules proposed in the original paper. The proposed algorithm leverages electrodermal activity (EDA) and skin temperature (ST), both recorded by the Empatica E4 wristband, for the assessment of an individual's stress when exposed to an audible stimulus. The algorithm achieves an average recall of 81.31%, with a precision of 46.23%, and an accuracy of 92.74%, measured on 16 test subjects. The tradeoff between precision and recall can be controlled by adjusting the MOS threshold that needs to be reached for an MOS to be detected.

关键词： Electrodermal activity (EDA) individual-specific physiological responses rule-based algorithm skin temperature (ST) stress detection

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：