检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Si, Wenwen Park, Sangdon Lee, Insup Dobriban, Edgar Bastani, Osbert Department of Computer & Information Science University of Pennsylvania United States Graduate School of AI and Computer Science & Engineering POSTECH Korea Republic of Department of Statistics and Data Science University of Pennsylvania United States

Prediction sets capture uncertainty by predicting sets of labels rather than individual labels, enabling downstream decisions to conservatively account for all plausible outcomes. Conformal inference algorithms construct prediction sets guaranteed to contain the true label with high probability. These guarantees fail to hold in the face of distribution shift, which is precisely when reliable uncertainty quantification can be most useful. We propose a novel algorithm for constructing prediction sets with PAC guarantees in the label shift setting, where the probabilities of labels can differ between the source and target distributions. Our algorithm relies on constructing confidence intervals for importance weights by propagating uncertainty through a Gaussian elimination algorithm. We evaluate our approach on four datasets: the CIFAR-10 and ChestX-Ray image datasets, the tabular CDC Heart Dataset, and the AGNews text dataset. Our algorithm satisfies the PAC guarantee while producing smaller prediction set sizes compared to several baselines. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Securing Tuberculosis Disease Detection with IoT-Driven Improved AlexNet and RSA Encryption 2

Securing Tuberculosis Disease Detection with IoT-Driven Impr...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Kavitha, S. Nagamani, H.S. Rallapalli, Sreekanth Sumanth, S. Pareek, Piyush Kumar Nitte Meenakshi Institute of Echnology Department of Mca Bangalore India Govt. Smt Vhd Central Institute of Home Science Department of Computer Science Bengaluru India Government College for Women Department of Computer Science and Applictaions Kolar India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bangalore India

ISBN: (纸本)9798350382952

This study provides tuberculosis (TB) disease detection method that protects patient data and is accurate. It uses homomorphic filtering to improve chest X-ray images using the Shenzhen dataset, which rallies classification. The advised Improved AlexNet model extracts complex features from pre-processed images to detect tuberculosis. In addition to image processing and classification advances, this paper incorporates Rivest-Shamir-Adleman (RSA) encryption to secure patient data. This RSA algorithms. Guaranteeing patient record confidentiality and integrity ensures ethical and privacy compliance. This method has a Peak Signal-to-Noise Ratio (PSNR) of 49.84, a minimized Bit Error Rate (BER) of 0.39, an SSI of 0.93, model. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

EnSKM-FTOPSIS: Enhanced Secure Key Management Framework in Dynamic Mobile Wireless Sensor Networks

引用

SN computer science 2024年第8期5卷 1115页

作者： Kusha, K.R. Shrinivasacharya, Purohit Department of Machine Learning (AI & amp ML) B.M.S College of Engineering Bangalore & amp Visvesvaraya Technological University Karnataka Belagavi India Department of Information Science & amp Engineering Siddaganga Institute of Technology Karnataka Tumkur India

Applications for WSN are numerous and include medical status monitoring, military sensing and tracking, and traffic flow monitoring, where sensory devices are frequently moving between different sites. An appropriate encryption key protocol is needed to secure data and connections. The energy, memory, transmission range, communication, and processing capacity of the sensor nodes are severely limited. Energy is considered to be a significant influence in extending the network's lifetime when compared to all of these other resources. Key management is one tactic for preserving these networks' security. For secure communication in dynamic WSNs with node mobility, this article suggests an Enhanced Secure Key Management (EnSKM) Framework. The proposed network model is a WSN that is heterogeneous and hierarchical and consists of a base station, cluster-head nodes, and several mobile sensor nodes. The Improved K-Means Algorithm is used to cluster the mobile sensor nodes. A CH is in charge of each cluster and has the ability to broadcast messages to other clusters as well as to all of the sensors inside the clusters. The best node is chosen as the CH using a novel metaheuristic optimization approach called Red Panda Optimization. The suggested system uses a hybrid fuzzy TOPSIS decision-making approach for both creation of path keys and addition of additional nodes to the network. It improved the efficiency of the proposed system and since it reduces energy consumption, it also elongates the network lifetime. The proposed Selfish Herd Optimization combined with ElGamal (SH-mEEG) encryption technique and modified elliptic curve cryptography improves network security. By eliminating cryptanalyzed nodes, the network's security is improved and its resilience to cryptanalysis attacks is increased. The suggested method is implemented on NS2 platform and contrasted with alternative key management methods. The proposed model achieves lowest encryption time of 2.654 s, decryption tim

关键词： Dynamic mobile wireless sensor networks ElGamal Improved K-means algorithm Red panda optimization Secure key management Selfish herd optimization

来源：评论

学校读者我要写书评

暂无评论

How do benefits and challenges influence students’ satisfaction with online education? The mediation effect of awareness

引用

International Social science Journal 2024年第252期74卷 299-318页

作者： Chawla, Udit Sondhi, Sundeep Singh Jabbar, Meerja Akhil Mishra, Varsha Singh, Harsh Vikram Department of Business Administration University of Engineering & Management Kolkata India Department of CSE(AI & ML) Vardhaman College of Engineering Hyderabad India Digital Marketing Royal Holloway University of London Egham United Kingdom Computer Application Techno India University Kolkata India

Traditional education is shifting towards online instruction, and the temporary closure of educational institutions due to COVID-19 has prompted its dramatic increase in the last couple of years. With additional benefits, such as flexible schedule, low cost and anywhere learning, online education will determine the near future of education. Due to the increase in Internet reach in India, face-to-face instructional methods to which students are habituated to can be substituted. This study aims to analyse students’ satisfaction with the parameters of awareness, challenges and benefits of using new technologies to learn online. With the help of a structured questionnaire and interactions with local inhabitants, the researchers obtained 430 samples from the outskirts of five different cities (Kolkata, Mumbai, Delhi, Chennai and Bengaluru) in India. A conceptual model was built around the constructs of awareness, challenges, benefits and student satisfaction, and their relationship was established and empirically tested. It is found that factors like challenges, benefits and awareness have a significant influence on student satisfaction with online learning. We also find that awareness helps in decreasing the challenges faced and increasing the value of benefits of online education for students. © 2023 John Wiley & Sons Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition and Identification of COVID-19 from Chest X-Rays for Earlier Diagnosis 4

Recognition and Identification of COVID-19 from Chest X-Rays...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Kavitha, P. Sharma, Manish Pradeep Kumar, G.M. Barve, Amit Patil, Harshal Maranan, Ramya CMR Institute of Technology Department of Computer Science and Engineering Karnataka Bengaluru560037 India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India BMS Institute of Technology and Management Department of AI & ML Karnataka Bangalore560064 India Parul Institute of Technology Parul University Faculty of Engineering and Technology Department of Computer Science and Engineering P.O. Limda Gujarat 391760 India Computer Science and Engineering Maharashtra Pune412115 India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350385793

Early detection is critical for controlling the spread and death of the COVID-19 worldwide pandemic, which affects global health care and lifestyle. The gold standard diagnosis, Reverse Transcription Polymerase Chain Reaction (RT-PCR) is both costly and has a lengthy process time. So more readily available and fast diagnostic methods are necessary. Many researchers proved that COVID-19 data can be effectively detected by Chest X-rays (CXR). However, diagnosing chest X-ray images for COVID-19 is difficult and error-prone. The only way to improve the COVID-19 diagnosis is to use DL algorithms. In this research, a novel deep learning model Convolutional Neural Network and Autoencoder (CNN-AE) tuned by Bat Optimization Algorithm (BOA) is proposed. The proposed approach would identify whether the CXR images were positive or negative for COVID. We received the CXR images from Kaggle. The pre-processing phases in the proposed technique assist with providing relevant information and reducing biased outputs. This is followed by the classification model. We were able to evaluate the performance of our proposed model by using Kaggle datasets. Our proposed model is evaluated using Kaggle datasets and achieved an average accuracy, True Positive Rate (TPR), True Negative Rate (TNR), precision, F1-score, False Positive Rate (FPR), and False Negative Rate (FNR) of 99.28%, 99.42%, 99.14%, 99.42%, 99.28%, 0.85%, and 0.57% respectively. The outcome of the proposed method is compared with the existing and similar research. A comparative study shows that our proposed method outperforms the state-of-art methods. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An Examination of the Compositionality of Large Generative Vision-Language Models

An Examination of the Compositionality of Large Generative V...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Ma, Teli Li, Rong Liang, Junwei AI Thrust The Hong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798891761148

With the success of Large Language Models (LLMs), many Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning. However, the performance of GVLMs in multimodal compositional reasoning remains under-explored. In this paper, we examine both the evaluation metrics (VisualGPTScore, etc.) and current benchmarks for evaluating the compositionality of GVLMs. We identify the syntactical bias in current benchmarks, which is exploited by the linguistic capability of GVLMs. The bias renders VisualGPTScore an insufficient metric for assessing GVLMs. To combat this, we first introduce a SyntaxBias Score, leveraging LLMs to quantify such bias for mitigation. A challenging new task is subsequently added to evaluate the robustness of GVLMs against inherent inclination toward syntactical correctness. Using the bias-mitigated datasets and the new task, we propose a novel benchmark, namely SyntActically DE-biased benchmark (SADE). Our study provides an unbiased benchmark for the compositionality of GVLMs, facilitating future research in this direction. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning to Identify Synergistic Drug Combinations for Effective Cancer Treatment 7

Leveraging Machine Learning to Identify Synergistic Drug Com...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Sujatha, P. Saravanan, K. Sohail, Mohammed Ali Basi Reddy, A. Dixit, Rohit R. Krishnaiah, Nallam Amrita Vishwa Vidyapeetham Department of AI/ML Guntur Amaravati India R.M.K Engineering College Department of Information Technology Tamil Nadu Tiruvallur District India Jazan University College of Computer Science & Information Technology Department of Computer & Network Engineering Jazan Saudi Arabia Mohan Babu University School of Computing Department of Computer Science And Engineering Andhra Pradesh Tirupati India Siemens Healthineers NH03755 United States St.Martin's Engineering College Department of Ai&ml Secunderabad Telangana Dhulapally500100 India

ISBN: (纸本)9798350371406

The potential of drug combinations to treat and overcome medication resistance complex genetic diseases is evident. Synergistic drug combinations offer a promising way to enhance drug therapy efficacy and reduce the required medication dosage. However, developing effective combination medication therapies with synergistic effects has been challenging, despite numerous ongoing clinical investigations. Current models and approaches to detect medication synergy outlined in the literature lack the expected consistency in outcomes. to better comprehend the impact of particular medication combinations, it is essential to be familiar with the vocabulary used to describe synergy. In this study, a combinational drug screen is utilized to identify useful features for locating synergistic or efficient drug combinations. The feature selection algorithm (Boruta) helps select the most relevant features, and machine learning models are then trained using the selected feature dataset. Performance assessment metrics like sensitivity, accuracy, and specificity are used to compare the trained models, and the Random Forest model stands out for its significantly better performance compared to other models. © 2023 IEEE.

关键词： Drug dosage

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of ai Models for Accurate Early Diabetes Detection

Comparative Analysis of AI Models for Accurate Early Diabete...

引用

Machine Learning and Autonomous Systems (ICmlAS), International Conference on

作者： Ratnam Dodda Mohd Miskeen Ali Prateeka Munugala Roshini Rajan Desu Om Keerthi Computer Science & Engineering (AI&ML) CVR College of Engineering Hyderabad India Computer Science & Engineering Sphoorthy Engineering College Hyderabad India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Diabetes is a common long-term disease with significant health implications, necessitating early and accurate diagnosis to manage and mitigate its impact. The use of deep learning (DL) and machine learning (ml) algorithms is investigated in this study to predict diabetes based on patient-specific factors, including medical history and lifestyle habits. By leveraging various algorithms, the research evaluates and compares their prediction accuracy to identify the most effective model. The findings aim to improve the early detection of diabetes, providing insights into the performance and feasibility of ai-driven diagnostic approaches in healthcare. In the experimental study we have compared machine learning and deep learning algorithms with the same dataset and found that convolutional neural network outperformed other algorithms.

关键词： Deep learning Accuracy Machine learning algorithms Gaussian processes Prediction algorithms Diabetes Convolutional neural networks Decision trees Random forests Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

EBMDOCK: NEURAL PROBABILISTIC PROTEIN-PROTEIN DOCKING VIA A DIFFERENTIABLE ENERGY-BASED MODEL 12

EBMDOCK: NEURAL PROBABILISTIC PROTEIN-PROTEIN DOCKING VIA A ...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Wu, Huaijin Liu, Wei Bian, Yatao Wu, Jiaxiang Yang, Nianzu Yan, Junchi Department of Computer Science and Engineering Shanghai Jiao Tong University China Tencent AI Lab China XVERSE China

Protein complex formation, a pivotal challenge in contemporary biology, has recently gained interest from the machine learning community, particularly concerning protein-ligand docking tasks. In this paper, we delve into the equally crucial but comparatively under-investigated domain of protein-protein docking. Specifically, we propose a geometric deep learning framework, termed EBMDock, which employs statistical potential as its energy function. This approach produces a probability distribution over docking poses, such that the identified docking pose aligns with a minimum point in the energy landscape. We employ a differential algorithm grounded in Langevin dynamics to efficiently sample from the docking pose distribution. Additionally, we incorporate energy-based training using contrastive divergence, enhancing both performance and stability. Empirical results demonstrate that our approach achieves superior performance on two benchmark datasets DIPS and DB5.5. Furthermore, the results suggest EBMDock can serve as an orthogonal enhancement to existing methods. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Cerebral cortex contributions to Parkinson's disease tremor:what exactly generates the tremor?

引用

Neural Regeneration Research 2025年第12期20卷 3535-3536页

作者： Manuel Bange Hao Ding Muthuraman Muthuraman Informatics for Medical Technology Institute of Computer ScienceUniversity AugsburgAugsburgGermany Department of Neurology Neural Engineering with Signal Analytics and Artificial Intelligence(NESA-AI)University Clinic WürzburgWürzburgGermany

Pathological tremor is one of the cardinal symptoms in Parkinson's disease (PD).Tremor is comprised of involuntary,rhythmic,a nd oscillating movements that can vary according to the circumstances under which they occur,the body parts that are involved,and the frequency at which they *** example,tremors can be mild to severe,are stress sensitive,and can affect arms,legs,or the head (Dirkx and Bologna,2022).

关键词： tremor cortex exactly

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：