检索结果-内蒙古大学图书馆

Logistic Regression Algorithm for Patient’s Length of Stay Prediction in Emergency department 1

6th International Conference on Smart computing and Informatics, SCI 2024

作者： Sulaie, Saleh Al Laxmi Lydia, E. Vijaya Kumar, K. Rao, Kommu Gangadhara Department of Mechanical and Industrial Engineering College of Engineering and Computing in Al-Qunfudah Umm Al-Qura University Makkah Saudi Arabia Department of Computer Science and Engineering GMR Institute of Technology Rajam India Department of Computer Science Engineering GITAM School of Technology Gitam University Visakhapatnam India Department of IT Chaitanya Bharathi Institute of Technology Hyderabad India

ISBN: (数字)9789819619818

ISBN: (纸本)9789819619801

Hospital systems are currently dealing with a large patient influx brought on by a number of circumstances, including seasonal flows or epidemic-related health problems. Hospital facilities, especially emergency departments (EDs), have to admit people for medical care regardless of the severity of the care requirements. However, the large patient volume frequently results in longer length of stay (LOS) for patients and causes issues with congestion in emergency departments. Hospital administrators must forecast the patient’s length of stay (LOS), as this is a crucial metric for evaluating ED congestion and the utilization of medical resources (allocation, planning, and utilization rates). Thus, to enhance ED management, precise LOS prediction is required. In this study, a logistic regression algorithm (LRA) model-based method for forecasting patient length of stay (LOS) in the ED is proposed. Without making any presumptions about the distribution of the data, it flexibly learns pertinent information from linear and nonlinear processes and greatly improves prediction accuracy. In order to facilitate decision-making and avoid crowding, we also categorized the anticipated patients’ length of stay (LOS) based on the amount of time they spent in the pediatric emergency department (PED). The PED provided real data that was used in the trials. We compared the LRA results with those from other models. The results show that LRA performs better than the other models and attest to the models’ suitability for forecasting patient length of stay. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Review and Explore the Transformative Impact of Artificial Intelligence (AI) in Smart Healthcare Systems

Review and Explore the Transformative Impact of Artificial I...

引用

2024 International Conference on Advances in computing research on science engineering and Technology, ACROSET 2024

作者： Nagar, Sneha Patidar, Mukesh Sheikh, Rashid Singh, Sudhanshu Kashiv, Ashutosh Jain, Ankit Namdeo, Shravan Kumar Paranjpe, Pranav Mandloi, Devendra Singh Indore Institute of Science and Technology Department of Electronics and Communication Engineering Indore India Parul Institute of Engineering and Technology Parul University Department of Computer Science & Engineering Vadodara India Acropolis Institute of Technology and Research Department of Computer Science & Engineering Indore India Indian Institute of Technology Indore Department of Electronics and Communication Engineering Indore India

ISBN: (纸本)9798350388800

Because of its high level of complexity and data collection capabilities, the healthcare industry employs artificial intelligence (AI) more than other sectors. Artificial intelligence is becoming an increasingly important part of our daily routines. AI's features include extremely low error rates, constant accessibility, quick analysis, and real-time data dissemination. This paper examines the crucial role of artificial intelligence in intelligent healthcare systems, with a particular emphasis on enhancing healthcare delivery. Artificial intelligence in healthcare is rapidly evolving, with the potential to significantly enhance patient care, diagnosis, treatment, and cost distribution. It also presents issues of transparency, honesty, and availability. This study will look into the benefits, drawbacks, and other aspects of artificial intelligence in intelligent healthcare systems. © 2024 IEEE.

关键词： Artificial Intelligence (AI) Ethical Considerations Explainable AI (XAI) Healthcare Resource Allocation Healthcare Systems Smart Treatment Planning

来源：评论

学校读者我要写书评

暂无评论

Approximation Schemes for Geometric Knapsack for Packing Spheres and Fat Objects 51

Approximation Schemes for Geometric Knapsack for Packing Sph...

引用

51st International Colloquium on Automata, Languages, and Programming, ICALP 2024

作者： Acharya, Pritam Bhore, Sujoy Gupta, Aaryan Khan, Arindam Mondal, Bratin Wiese, Andreas Department of Mathematics Indian Institute of Science Education and Research Pune India Department of Computer Science and Engineering Indian Institute of Technology Bombay India Department of Computer Science and Automation Indian Institute of Science Bengaluru India Department of Mathematics Technical University of Munich Germany

ISBN: (纸本)9783959773225

We study the geometric knapsack problem in which we are given a set of d-dimensional objects (each with associated profits) and the goal is to find the maximum profit subset that can be packed non-overlappingly into a given d-dimensional (unit hypercube) knapsack. Even if d = 2 and all input objects are disks, this problem is known to be NP-hard [Demaine, Fekete, Lang, 2010]. In this paper, we give polynomial time (1 + Ε)-approximation algorithms for the following types of input objects in any constant dimension d: disks and hyperspheres, a class of fat convex polygons that generalizes regular k-gons for k ≥ 5 (formally, polygons with a constant number of edges, whose lengths are in a bounded range, and in which each angle is strictly larger than π/2), arbitrary fat convex objects that are sufficiently small compared to the knapsack. We remark that in our PTAS for disks and hyperspheres, we output the computed set of objects, but for a OΕ(1) of them we determine their coordinates only up to an exponentially small error. However, it is not clear whether there always exists a (1 + Ε)-approximate solution that uses only rational coordinates for the disks’ centers. We leave this as an open problem which is related to well-studied geometric questions in the realm of circle packing. © Pritam Acharya, Sujoy Bhore, Aaryan Gupta, Arindam Khan, Bratin Mondal, and Andreas Wiese.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Custom Transformer-Based Approach for Enhanced Bengali Automatic Speech Recognition 1

Custom Transformer-Based Approach for Enhanced Bengali Autom...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Deepa, R. Jayalakshmi, V. Thilakavathy, P. Manikandan, G. Surendran, R. SRM Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Ramapuram Chennai India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Anna University St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376517

Automated speech recognition (ASR) systems struggle with Bengali, which is the fifth most spoken language. Bengali has a varied morphology, many dialects, and limited high-quality annotated voice data. Traditional voice recognition techniques work well however struggle with Bengali phonetics and syntax. This method eliminates the need for large amounts of tagged data and the difficulties of differentiating sounds in different languages, both issues are addressed by this procedure. The research in this paper offers an Intellectual Bengali Speech Recognition System using Deep Learning Techniques (IBSRS-DLT). The model in this system uses transformer architecture and attention processes to manage Bengali speech pattern long-range dependencies. The IBSRS-DLT outperforms standard models in recognition accuracy using a pre-trained transformer model modified for phonetic and lexical correctness and fine-tuned on Bengali datasets. After training on a vast Bengali speech corpus, real-world datasets and rigorous simulations confirm the system. IBSRS-DLT can be used for automatic transcription, voice-controlled devices, and Bengali virtual assistants, such applications are efficient and accessible. The simulation showed a considerable boost in recognition speed and a decrease in keyword mistakes compared to current methods. This paper shows that deep learning can solve linguistic issues in ASR systems, enabling scalable regional language detection. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A fast high throughput plant phenotyping system using YOLO and Chan-Vese segmentation

引用

Soft computing 2024年第20期28卷 12323-12336页

作者： Jain, S. Ramesh, Dharavath Damodar Reddy, E. Rathod, Santosha Ondrasek, Gabrijel Jharkhand Dhanbad826004 India Department of Computer Science and Engineering National Institute of Technology Goa Farmagudi403401 India ICAR—Indian Institute of Rice Research Telangana Hyderabad500030 India Faculty of Agriculture University of Zagreb Zagreb10000 Croatia Department of Computer Science University of Economics and Human Sciences Warsaw Poland

Understanding plant traits is essential for decoding the behavior of various genomes and their reactions to environmental factors, paving the way for efficient and sustainable agricultural practices. Image-based plant phenotyping has become increasingly popular in modern agricultural research, effectively analyzing large-scale plant data. This study introduces a new high-throughput plant phenotyping system designed to examine plant growth patterns using segmentation analysis. This system consists of two main components: (i) A plant detector module that identifies individual plants within a high-throughput imaging setup, utilizing the Tiny-YOLOv4 (You Only Look Once) architecture. (ii) A segmentation module that accurately outlines the identified plants using the Chan-Vese segmentation algorithm. We tested our approach using top-view RGB tray images of the ‘Arabidopsis Thaliana’ plant species. The plant detector module achieved an impressive localization accuracy of 96.4% and an average Intersection over Union (IoU) of 77.42%. Additionally, the segmentation module demonstrated strong performance with dice and Jaccard scores of 0.95 and 0.91, respectively. These results highlight the system’s capability to define plant boundaries accurately. Our findings affirm the effectiveness of our high-throughput plant phenotyping system and underscore the importance of employing advanced computer vision techniques for precise plant trait analysis. These technological advancements promise to boost agricultural productivity, advance genetic research, and promote environmental sustainability in plant biology and agriculture. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Enhanced Intrusion Detection with Advanced Deep Features and Ensemble Classifier Techniques

引用

SN computer science 2025年第4期6卷 1-17页

作者： Toralkar, Pawan Mainalli, Kavita Allagi, Shridhar Debnath, Sanjoy Kumar Bagchi, Susama Leong, Wai Yie Khan, Muhammad Numan Ali Department of Artificial Intelligence Madanapalle Institute of Technology and Science Andhra Pradesh Madanapalle India Department of Computer Science and Engineering KLEIT: KLE Institute of Technology Karnataka Hubballi India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India INTI International University and Colleges Negeri Sembilan Nilai Malaysia College of Computing and Applied Sciences University of Technology and Applied Sciences Shinas Oman

Intrusion detection is crucial for modern cyber-security, aiming to detect and mitigate unauthorized access and malicious activities within networks. Traditional systems often rely on linear models, which may fail to capture complex patterns in advanced threats. This study proposes a heuristic approach to select the best deep features through an ensemble framework consisting of Random Forest (RF) and Support Vector Machine (SVM) classifiers using soft voting. The novelty of this work is the deep feature extraction through Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Autoencoder for intrusion detection. These extracted features were fed separately for classification. In order to balance the explainability and accuracy, the ensemble classifier consisting of RF and SVM, uses feature importance ranking (RF) and unambiguous decision bounds (SVM) to provide partial interpretability. Evaluating the NSL-KDD and CICDDoS2019 datasets, our ensemble model with CNN features achieves near-perfect accuracy of 99.99% and 99.91% respectively. RNN and Autoencoder models also show high performance, each reaching 99.3% accuracy on the CICDDoS2019 dataset with Soft Voting classifiers. This work highlights the importance of the ensemble method with better feature selection in intrusion detection. The proposed system outperformed the standard methods by providing a robust, scalable solution for organizational security. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolution neural network (CNN) Intrusion detection Random forest (RF) Recurrent neural network (RNN) Voting classification (Voting)

来源：评论

学校读者我要写书评

暂无评论

An Improved Sparrow Search Algorithm for Node Localization in WSN

引用

computers, Materials & Continua 2022年第4期71卷 2037-2051页

作者： RThenmozhi Abdul Wahid Nasir Vijaya Krishna Sonthi TAvudaiappan Seifedine Kadry Kuntha Pin Yunyoung Nam Department of Computer Science and Engineering College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur603203India Department of Electronics Communication and Engineering CMR Institute of TechnologyBengaluru560037India Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaram522502Andhra PradeshIndia Department of Computer Science and Engineering K.Ramakrishnan College of engineeringTiruchirappalli621112India Department of Applied Data Science Noroff University CollegeKristiansandNorway Department of ICT Convergence Soonchunhyang UniversityKorea Department of Computer Science and Engineering Soonchunhyang UniversityKorea

Wireless sensor networks(WSN)comprise a set of numerous cheap sensors placed in the target region.A primary function of the WSN is to avail the location details of the event occurrences or the node.A major challenge in WSN is node localization which plays an important role in data gathering *** GPS is expensive and inaccurate in indoor regions,effective node localization techniques are *** major intention of localization is for determining the place of node in short period with minimum *** achieve this,bio-inspired algorithms are used and node localization is assumed as an optimization problem in a multidimensional *** paper introduces a new Sparrow Search Algorithm with Doppler Effect(SSA-DE)for Node Localization in Wireless *** SSA is generally stimulated by the group wisdom,foraging,and anti-predation behaviors of ***,the Doppler Effect is incorporated into the SSA to further improve the node localization *** addition,the SSA-DE model defines the position of node in an iterative manner using Euclidian distance as the fitness *** presented SSA-DE model is implanted in MATLAB *** extensive set of experimentation is carried out and the results are examined under a varying number of anchor nodes and ranging *** attained experimental outcome ensured the superior efficiency of the SSA-DE technique over the existing techniques.

关键词： Localization wireless networks

来源：评论

学校读者我要写书评

暂无评论

Cultivating Cluster Enactment in Wireless Sensor Networks Through Hybrid Metaheuristics Intended for Energy Optimization

引用

SN computer science 2025年第3期6卷 1-12页

作者： Kushwaha, Ajay Goswami, Anjali Sharada, K. Sharma, Manmohan Berar, Gagandeep Edara, Deepak Chowdary Department of Computer Science and Engineering Rungta College of Engineering and Technology R1 CG Bhilai India Department of Mathematics and Statistics College of Science and Theoretical Studies Saudi Electronic University Riyadh 13323 Saudi Arabia Department of Computer Science and Engineering GITAM (Deemed to be University) AP Visakhapatnam India Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Department of Computer Science and Engineering Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Department of CSE Vignan’s Foundation for Science Technology and Research Vadlamudi AP Guntur India

Though traditional search methods shine when faced with local goals and a plethora of decision factors, they could struggle when faced with engineering design limitations. On the other hand, metaheuristic approaches promise to find global optima in real-world optimization problems, even in nonlinear and multimodal settings. In order to improve cluster head selection in Wireless Sensor Networks (WSNs), this research presents a new metaheuristic method that combines the principles of Cuckoo Search method (CSA) and Selection by Optimization (SBO). When choosing a Chief Cluster Head (CCH), the CSA algorithm takes hop count into account, whereas SBO finds the best cluster heads by considering communication range. By comparing the suggested approach to both stand-alone SBO and CSA methods, we can see how well it performs in terms of throughput, latency, energy usage, delivery ratio, and packet overhead. The combined SBO-CSA method improves cluster performance, simplifies cluster head selection in WSNs, and increases network efficiency overall, according to the results. To prove its efficacy in enhancing network performance, the suggested solution outperforms standalone SBO and CSA approaches across a range of performance parameters, such as throughput, latency, energy consumption, and packet overhead. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： CCH CH CSA Metaheuristic methods SBO

来源：评论

学校读者我要写书评

暂无评论

Security model to identify block withholding attack in blockchain

Security model to identify block withholding attack in block...

引用

International Conference on Artificial Intelligence, Blockchain, computing and Security, ICABCS 2023

作者： Keshta, Ismail Reegu, Faheem Ahmad Ahmad, Adeel Saxena, Archana Chandan, Radha Raman Mahalakshmi, V. Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia College of Computer Science and Information Technology Jazan University Jazan Saudi Arabia Department of Computer Applications Invertis University UP Bareilly India Department of Computer Science and Engineering Shambhunath Institute of Engineering and Technology College Jhalwa Prayagraj India Department of Computer Science College of Computer Science and Information Technology Jazan University Jazan Saudi Arabia

ISBN: (纸本)9781032669663

Block interception attack, also known as block withholding attack, is an attack method in the blockchain. The attacker penetrates the target mining pool for passive mining to destroy the target mining pool. This paper briefly introduces the mining mechanism and the working principle of block interception attack, summarizes several models of block interception attack, studies the attack methods and benefits of the existing block interception attack models, and analyses their attack effects. A block interception attack model is constructed to increase the rate of return while increasing the rate of return. The completed model is verified through simulated mining experiments. The typical and made models are compared and analyzed based on the rate of return. Finally, the applicable environments of different attack models are given based on the experimental results. © 2024 The Author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Generalized hybrid LiFi-WiFi UniPHY learning framework towards intelligent UAV-based indoor networks

引用

International Journal of Intelligent Networks 2024年第1期5卷 255-266页

作者： Ahmad, Rizwana Anwar, Dil Nashin Bany Salameh, Haythem Elgala, Hany Ayyash, Moussa Almajali, Sufyan El-Khazali, Reyad Electronic and Electrical Engineering Department University of Cambridge United Kingdom Electrical and Computer Engineering Department University at Albany-State University of New York United States Artificial Intelligence Research Center Al Ain University Al Ain United Arab Emirates Telecommunications Engineering Department Yarmouk University Irbid Jordan Department of Computing Information and Technology Chicago State University ChicagoIL United States Department of Computer Science Princess Sumaya University for Technology Amman Jordan Electrical Engineering and Computer Science Department Khalifa University Abu Dhabi United Arab Emirates

Advancements in unmanned aerial vehicle (UAV) technology, along with indoor hybrid LiFi-WiFi networks (HLWN), promise the development of cost-effective, energy-efficient, adaptable, reliable, rapid, and on-demand HLWN-capable indoor flying networks (IFNs). To achieve this, a unified physical layer (UniPHY) capable of simultaneous control communication, data transfer, and sensing is crucial. However, traditional block-based decoders, designed independently for LiFi and WiFi, perform poorly in complex and hybrid LiFi-WiFi-enabled UniPHY systems. In this study, we propose an end-to-end learning framework based on convolutional neural networks (CNNs) for UniPHY, which can be trained to serve hybrid LiFi-WiFi transmissions to improve error performance and simplify UAV hardware. In this work, the performance of the proposed framework is assessed and compared with that of the conventional independent block-based communication system. Furthermore, a comprehensive summary of optimal hyper-parameters for efficient training of our learning framework has been provided. It is shown that, with optimal hyper-parameters, the proposed CNN-based framework outperforms the conventional block-based approach by providing a signal-to-noise ratio gain of approximately 7 dB for the LiFi channel and 23 dB for the WiFi channel. In addition, we evaluate the complexity and training convergence for loss and accuracy. © 2024 The Authors

关键词： Data transfer

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

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

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：