检索结果-内蒙古大学图书馆

Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Leng, Xinyi Liang, Jason Mauro, Jack Wang, Xu Chapman, James Bertozzi, Andrea L. Lin, Junyuan Chen, Bohan Ye, Chenchen Daniel, Temple Brantingham, P. Jeffrey Carleton College Department of Mathematics and Statistics United States Claremont McKenna College Department of Mathematical Sciences United States University of California Los Angeles Department of Mathematics United States Loyola Marymount University Department of Mathematics Statistics and Data Science United States California Institute of Technology Computing + Mathematical Sciences Division of Engineering and Applied Science United States University of California Los Angeles Department of Computer Science United States University of California Los Angeles Department of Anthropology United States

Narrative data spans all disciplines and provides a coherent model of the world to the reader or viewer. Recent advancement in machine learning and Large Language Models (LLMs) have enable great strides in analyzing natural language. However, Large language models (LLMs) still struggle with complex narrative arcs as well as narratives containing conflicting information. Recent work indicates LLMs augmented with external knowledge bases can improve the accuracy and interpretability of the resulting models. In this work, we analyze the effectiveness of applying knowledge graphs (KGs) in understanding true-crime podcast data from both classical Natural Language Processing (NLP) and LLM approaches. We directly compare KG-augmented LLMs (KGLLMs) with classical methods for KG construction, topic modeling, and sentiment analysis. Additionally, the KGLLM allows us to query the knowledge base in natural language and test its ability to factually answer questions. We examine the robustness of the model to adversarial prompting in order to test the model's ability to deal with conflicting information. Finally, we apply classical methods to understand more subtle aspects of the text such as the use of hearsay and sentiment in narrative construction and propose future directions. Our results indicate that KGLLMs outperform LLMs on a variety of metrics, are more robust to adversarial prompts, and are more capable of summarizing the text into topics. © 2024, CC BY.

关键词： Knowledge graph

Generalization of CNNs on Relational Reasoning with Bar Charts

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cui, Zhenxing Chen, Lu Wang, Yunhai Haehn, Daniel Wang, Yong Pfister, Hanspeter School of Computer Science and Technology Shandong University China State Key Lab of CAD&CG Zhejiang University China School of Information Renmin University of China China College of Science and Mathematics University of Massachusetts Boston United States College of Computing and Data Science Nanyang Technological University Singapore School of Engineering and Applied Sciences Harvard University United States

This paper presents a systematic study of the generalization of convolutional neural networks (CNNs) and humans on relational reasoning tasks with bar charts. We first revisit previous experiments on graphical perception and update the benchmark performance of CNNs. We then test the generalization performance of CNNs on a classic relational reasoning task: estimating bar length ratios in a bar chart, by progressively perturbing the standard visualizations. We further conduct a user study to compare the performance of CNNs and humans. Our results show that CNNs outperform humans only when the training and test data have the same visual encodings. Otherwise, they may perform worse. We also find that CNNs are sensitive to perturbations in various visual encodings, regardless of their relevance to the target bars. Yet, humans are mainly influenced by bar lengths. Our study suggests that robust relational reasoning with visualizations is challenging for CNNs. Improving CNNs’ generalization performance may require training them to better recognize task-related visual properties. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

Minimal Ternary Linear Codes from Vectorial Functions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yanjun Kan, Haibin Liu, Fangfang Peng, Jie Zheng, Lijing Zhuo, Zepeng Institute of Statistics and Applied Mathematics Anhui University of Finance and Economics Anhui Bengbu233030 China School of Computer Sciences Fudan University Shanghai200433 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai Engineering Research Center of Blockchain Shanghai Institute for Advanced Communication and Data Science Shanghai200433 China School of Mathematics and Statistics Huaibei Normal University Anhui Huaibei235000 China Mathematics and Science College Shanghai Normal University Guilin Road #100 Shanghai200234 China The School of Mathematics and Physics University of South China Hunan Hengyang421001 China

The study on minimal linear codes has received great attention due to their significant applications in secret sharing schemes and secure two-party computation. Until now, numerous minimal linear codes have been discovered. However, to the best of our knowledge, no infinite family of minimal ternary linear codes was found from vectorial functions. In this paper, we present a necessary and sufficient condition for a large class of ternary linear codes from vectorial functions such that those codes are minimal. Based on that, we construct several minimal ternary linear codes with three-weight from vectorial regular plateaued functions, and determine their weight distributions. Moreover, we also give a necessary and sufficient condition for a large family of ternary linear codes from vectorial functions such that the codes are minimal and violate the AB condition simultaneously. According to this characterization, we find several minimal ternary linear codes violating the AB condition. Notably, our results show that our method can be applied to solve a problem on minimal linear codes proposed by Li et al. Copyright © 2024, The Authors. All rights reserved.

关键词：

RALB-HC: A resource-aware load balancer for heterogeneous cluster

学校读者我要写书评

暂无评论

RALB-HC: A resource-aware load balancer for heterogeneous cl...

作者： Ahmed, Usman Aleem, Muhammad Noman Khalid, Yasir Arshad Islam, Muhammad Azhar Iqbal, Muhammad Department of Computing Mathematics and Physics Faculty of Engineering and Science Western Norway University of Applied Sciences Bergen Norway Islamabad Pakistan Department of Computer Science Capital University of Science and Technology Islamabad Pakistan SWJTU-Leeds Joint School Southwest Jiaotong University Chengdu China

In the heterogeneous computing environment, programmers map the applications either on CPUs or GPUs. However, this default mapping process does not produce improved results, particularly on the heterogeneous clusters. If one resource of the cluster is more compute capable, then most of the scheduling schemes favor that powerful device. In this scenario, the scheduling schemes overload the powerful resources while making all other compute resources remain under utilized. This load imbalance problem results in higher energy consumption and increased execution time. In this research, a novel Resource-Aware Load Balancer for the Heterogeneous Cluster (RALB-HC) is proposed that distributes workload based on resources computing capabilities and applications computing needs. The RALB-HC uses supervised machine learning approach to classify applications using the static code-features. The RALB-HC framework comprises of two phases: (1) job mapping based on the availability of the resources and (2) the resource-aware load balancing to achieve the higher resource utilization ratio. The experimental results on a large set of real-world and synthetic workloads show that the RALB-HC reduces execution time by 31.61%, increased resource utilization ratio by 67.8% and improved throughout 147.35% as compared to baseline scheduling schemes. © 2019 John Wiley & Sons, Ltd.

关键词： Scheduling

Optimal Reordering Trace Files for Improving Software Testing Suitcase

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第4期67卷 1225-1239页

作者： Yingfu Cai Sultan Noman Qasem Harish Garg Hamïd Parvïn Kim-Hung Pho Zulkefli Mansor School of Measurement and Communication Harbin University of Science&TechnologyHarbinChina Computer Science Department College of Computer and Information SciencesAl Imam Mohammad Ibn Saud Islamic University(IMSIU)RiyadhSaudi Arabia Department of Computer Science Faculty of Applied ScienceTaiz UniversityTaizYemen School of Mathematics Thapar Institute of Engineering and TechnologyDeemed UniversityPatiala147004India Institute of Research and Development Duy Tan UniversityDa Nang550000Vietnam Faculty of Information Technology Duy Tan UniversityDa Nang550000Vietnam Department of Computer Science Nourabad Mamasani BranchIslamic Azad UniversityMamasaniIran Fractional Calculus Optimization and Algebra Research GroupFaculty of Mathematics and StatisticsTon Duc Thang UniversityHo Chi Minh CityVietnam Fakulti Teknologi dan Sains Maklumat Universiti Kebangsan MalaysiaUKM BangiSelangor43600Malaysia

An invariant can be described as an essential relationship between program *** invariants are very useful in software checking and *** tools that are used to detect invariants are invariant *** are two types of invariant detectors:dynamic invariant detectors and static invariant *** software is an available computer program that implements a special case of a dynamic invariant detection *** proposes a dynamic invariant detection algorithm based on several runs of the tested program;then,it gathers the values of its variables,and finally,it detects relationships between the variables based on a simple statistical *** method has some *** of its biggest drawbacks is its overwhelming time *** is observed that the runtime for the Daikon invariant detection tool is dependent on the ordering of traces in the trace file.A mechanism is proposed in order to reduce differences in adjacent trace *** is done by applying some special techniques of mutation/crossover in genetic algorithm(GA).An experiment is run to assess the benefits of this *** findings reveal that the runtime of the proposed dynamic invariant detection algorithm is superior to the main approach with respect to these improvements.

关键词： Dynamic invariant detection software testing genetic algorithm

Comparison Model for Forecasting the Total Population in Bangkok

学校读者我要写书评

暂无评论

Comparison Model for Forecasting the Total Population in Ban...

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Nattanicha Tipwong Anuchit Jitpattanakul Wikanda Phaphan Chalermrat Nontapa Sakorn Mekruksavanich Department of Applied Statistics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Statistics Faculty of Science Chiang Mai University Chiang Mai Thailand Research Group in Statistical Learning and Inference Department of Computer Engineering School of Information and Communication University of Phayao Phayao Thailand

The primary aim of this article is to investigate, contrast, and formulate a time series model to predict Bangkok’s overall population. In this study, we intend to propose a hybrid model that combines the Autoregressive Moving Integrated Average (ARIMA) model and machine learning techniques, utilizing a Multilayer Perceptron (MLP). Our data source comprises monthly data from 2002 to 2022, totaling 252 data points, obtained from the official registration statistics system of the Registration Administration Office, Department of Provincial Administration. This dataset has been divided into two subsets: the first subset covers the years from 2002 to 2021, encompassing 240 data points, which will be used for constructing predictive models. The second subset consists of the data for the year 2022, comprising 12 data points, which will serve as a means to compare the accuracy of various forecasting methods. The evaluation criteria employed for this purpose are the minimum mean absolute error (MAE), the mean square error (MSE) and the mean absolute percentage error (MAPE). Furthermore, we will utilize the Python programming language to facilitate data analysis.

关键词：

COVID-19 Infected Lung Computed Tomography Segmentation and Supervised Classification Approach

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第7期68卷 391-407页

作者： Aqib Ali Wali Khan Mashwani Samreen Naeem Muhammad Irfan Uddin Wiyada Kumam Poom Kumam Hussam Alrabaiah Farrukh Jamal Christophe Chesneau Department of Computer Science Concordia College BahawalpurBahawalpur63100Pakistan Department of Computer Science&IT Glim Institute of Modern StudiesBahawalpur63100Pakistan Institute of Numerical Sciences Kohat University of Science&TechnologyKohat26000Pakistan Institute of Computing Kohat University of Science and TechnologyKohat26000Pakistan Program in Applied Statistics Department of Mathematics and Computer ScienceFaculty of Science and TechnologyRajamangala University of Technology ThanyaburiThanyaburi12110Thailand Departments of Mathematics Faculty of ScienceCenter of Excellence in Theoretical and Computational Science(TaCS-CoE)&KMUTT Fixed Point Research LaboratoryRoom SCL 802 Fixed Point LaboratoryScience Laboratory BuildingKing Mongkut’s University of Technology Thonburi(KMUTT)Bangkok10140Thailand Department of Medical Research China Medical University HospitalTaichung40402Taiwan College of Engineering Al Ain UniversityAl Ain64141United Arab Emirates Department of Mathematics Tafila Technical UniversityTafila66110Jordan Department of Statistics The Islamia University of BahawalpurBahawalpur63100Pakistan 11Department of MathematicsUniversitéde CaenLMNOCaen14032France

The purpose of this research is the segmentation of lungs computed tomography(CT)scan for the diagnosis of COVID-19 by using machine learning *** dataset contains data from patients who are prone to the *** contains three types of lungs CT images(Normal,Pneumonia,and COVID-19)collected from two different sources;the first one is the Radiology Department of Nishtar Hospital Multan and Civil Hospital Bahawalpur,Pakistan,and the second one is a publicly free available medical imaging database known as *** the preprocessing,a novel fuzzy c-mean automated region-growing segmentation approach is deployed to take an automated region of interest(ROIs)and acquire 52 hybrid statistical features for each ***,12 optimized statistical features are selected via the chi-square feature reduction *** the classification,five machine learning classifiers named as deep learning J4,multilayer perceptron,support vector machine,random forest,and naive Bayes are deployed to optimize the hybrid statistical features *** is observed that the deep learning J4 has promising results(sensitivity and specificity:0.987;accuracy:98.67%)among all the deployed *** a complementary study,a statistical work is devoted to the use of a new statistical model to fit the main datasets of COVID-19 collected in Pakistan.

关键词： COVID-19 machine learning fuzzy c-mean deep learning J4

Significance of slip velocity and viscosity variation on squeezed film couple-stress properties between a rough plate and a cylinder

学校读者我要写书评

暂无评论

Partial Differential Equations in applied mathematics 2025年 14卷

作者： K, Arshiya Kousar A, Salma Althobaiti, Saja Abdulrahman BN, Hanumagowda Tawade, Jagadish V Abduvalieva, Dilsora Waqas, M. Saeed, Mohammed Azeez Gupta, Manish Department of Mathematics School of Applied Science REVA University India Department of Chemistry College of Sciences & Humanities Prince Sattam Bin Abdulaziz University Saudi Arabia Department of Mathematics Vishwakarma University Pune 411048 India Department of Mathematics and Information Technologies Tashkent State Pedagogical University Bunyodkor avenue 27 Tashkent 100070 Uzbekistan Department of Computer Science National University of Technology Islamabad 44000 Pakistan Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Department of Environmental Engineering College of Engineering Knowlwdge University Erbil 44001 Iraq Division of Research and Development Lovely Professional University Phagwara India

This study examines the impact of surface roughness and viscosity variation on the couple stress squeeze film characteristics between a cylinder and a rough plate with slip velocity. Two distinct one-dimensional roughness patterns—longitudinal and transverse—are considered. Using Christensen's theory, the stochastic modified Reynolds equation is derived for Stokes couple stress fluid, incorporating viscosity variation with pressure. The standard perturbation technique is applied to solve the average Reynolds equation, yielding closed-form expressions for the mean fluid film pressure, load-carrying capacity, and squeeze film time. Various parameters are varied, and the results are discussed through graphical representations in 2D and 3D. This study highlights the importance of viscosity variation, couple stresses, and surface roughness in optimizing squeeze film performance. While increased viscosity and couple stresses enhance load-bearing capacity and film time, slip velocity detracts from these properties. Additionally, surface roughness has a significant impact, with transverse roughness improving, and longitudinal roughness reducing, the squeeze film characteristics. Applications of this study include improving the design and performance of bearing systems, lubrication in mechanical seals, and hydraulic systems where surface roughness and viscosity variation play a significant role in operational efficiency. © 2025

关键词： Couple stress fluid Rough surface Slip velocity Squeeze-film Viscosity variation

6-regular partitions: New combinatorial properties, congruences, and linear inequalities

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ballantine, Cristina Merca, Mircea Department of Mathematics and Computer Science College of the Holy Cross WorcesterMA01610 United States Department of Mathematical Methods and Models Fundamental Sciences Applied in Engineering Research Center University Politehnica of Bucharest BucharestRO-060042 Romania

We consider the number of the 6-regular partitions of n, b6(n), and give infinite families of congruences modulo 3 (in arithmetic progression) for b6(n). We also consider the number of the partitions of n into distinct parts not congruent to ±2 modulo 6, Q2(n), and investigate connections between b6(n) and Q2(n) providing new combinatorial interpretations for these partition functions. In this context, we discover new infinite families of linear inequalities involving Euler's partition function p(n). Infinite families of linear inequalities involving the 6-regular partition function b6(n) and the distinct partition function Q2(n) are proposed as open *** Codes 11P81, 11P82, 05A19, 05A20 © 2023, CC BY.

关键词： Combinatorial mathematics