检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3384-3392页

作者： Alkhouri, Ismail R. Jha, Sumit Beckus, Andre Atia, George Jha, Susmit Ewetz, Rickard Velasquez, Alvaro OrlandoFL32816 United States Michigan State University Computational Mathematics Science and Engineering Department East LansingMI48824 United States University of Michigan Electrical Engineering and Computer Science Department Ann ArborMI48109 United States Florida International University Knights Foundation School of Computing and Information Sciences MiamiFL33199 United States Air Force Research Laboratory Rome Information Directorate NY13441 United States Department Computer Science Department OrlandoFL32816 United States SRI International Computer Science Laboratory Menlo ParkCA94025 United States Electrical and Computer Engineering Department OrlandoFL32816 United States University of Colorado Computer Science Department BoulderCO80309 United States

Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been fully explored. This is particularly relevant given the broad social implications of such technologies and the fact that biologically small perturbations to noncritical residues of a protein sequence do not typically lead to drastic changes in the protein structure. Our study demonstrates that, similar to adversarial methods in machine learning, small changes to protein sequences can result in significant differences in the predicted protein structures using AlphaFold as determined by large distance measures. Despite this, our findings using multiple protein sequences suggest that AlphaFold is able to accurately predict the domain structure and folding regions of a protein. To gauge structural differences, we employ two alignment-based measures [root-mean-square deviation (RMSD) and the global distance test (GDT) similarity], and one alignment-free measure, which is an effective graph-based structure representation (GraSR) method. We prove that the problem of minimally perturbing protein sequences is NP-complete. Based on the well-established block substitution matrices (BLOSUM62) sequence alignment scoring matrix, we generate adversarial sequences. In our experimental evaluation, we consider 111 proteins (including 29 COVID-19 sequences) in the Universal Protein resource (UniProt), a central resource for protein data. Our findings suggest that, despite the high RMSD values returned by AlphaFold, it is capable of handling the BLOSUM adversarial sequences considered in our analysis, as evidenced by the preservation of the folded regions and the GraSR results. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals 41

SleepFM: Multi-modal Representation Learning for Sleep Acros...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Thapa, Rahul He, Bryan Kjær, Magnus Ruud Moore, Hyatt Ganjoo, Gauri Mignot, Emmanuel Zou, James Department of Biomedical Data Science Stanford University United States Department of Computer Science Stanford University United States Department of Health Technology Technical University of Denmark Denmark Department of Psychiatry and Behavioral Sciences Stanford University United States

Sleep is a complex physiological process evaluated through various modalities recording electrical brain, cardiac, and respiratory activities. We curate a large polysomnography dataset from over 14,000 participants comprising over 100,000 hours of multi-modal sleep recordings. Leveraging this extensive dataset, we developed SleepFM, the first multi-modal foundation model for sleep analysis. We show that a novel leave-one-out approach for contrastive learning significantly improves downstream task performance compared to representations from standard pairwise contrastive learning. A logistic regression model trained on SleepFM’s learned embeddings outperforms an end-to-end trained convolutional neural network (CNN) on sleep stage classification (macro AUROC 0.88 vs 0.72 and macro AUPRC 0.72 vs 0.48) and sleep disordered breathing detection (AUROC 0.85 vs 0.69 and AUPRC 0.77 vs 0.61). Notably, the learned embeddings achieve 48% top-1 average accuracy in retrieving modality clip pairs from 90,000 candidates. This work demonstrates the value of holistic multi-modal sleep modeling to fully capture the richness of sleep recordings. SleepFM is open source and available at https://***/rthapa84/sleepfmcodebase. Copyright 2024 by the author(s)

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Optimization of Character Classes in Devanagari Ancient Manuscripts and dataset Generation 3rd

Optimization of Character Classes in Devanagari Ancient Manu...

引用

The 3rd International Conference on Frontiers in Computing and Systems (COMSYS 2022)

作者： Narang, Sonika Rani Kumar, Munish Jindal, M.K. Department of Computer Science DAV College Punjab Abohar India Department of Computational Sciences Maharaja Ranjit Singh Punjab Technical University Bathinda India Department of Computer Science and Applications Panjab University Regional Centre Punjab Muktsar India

ISBN: (纸本)9789819926794

In any OCR system, the character classes define the set of characters or shapes to be recognized during the recognition process. So, it is necessary to identify character classes for an OCR system. The Devanagari script consists of several basic characters (vowels and consonants), half-forms of characters, modifiers, diacritics, and conjuncts. An analysis of the characters in Devanagari ancient documents has been presented in this chapter. Based on the analysis of such documents, two sets of character classes have been categorized in this work. One set contains only basic characters (vowels and consonants) of the Devanagari script. It does not contain any modifier, conjunct or diacritical symbols and is labeled as dataSET-A. dataSET-A contains 33-character classes. The other set contains all identifiable shapes of Devanagari ancient manuscripts and is labeled as dataSET-B. A total of 236-character classes have been identified in dataSET-B. In this work, the character class count for dataSET-B has been optimized to 116 characters. In this work, a character dataset of 22,522 characters has been used. Discrete Cosine Transform (DCT) zigzag features have been extracted and a Support Vector Machine (SVM) classifier has been used for the recognition of ancient Devanagari characters. A maximum accuracy of 88.69% has been obtained with the above-mentioned setup. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Forensic Investigation of Malicious Activities in Digital Environments 4

Forensic Investigation of Malicious Activities in Digital En...

引用

4th IEEE International Conference on data Engineering and Communication Systems, ICDECS 2024

作者： Pasumpon Pandian, A. Anakath, A.S. Kannadasan, R. Ravikumar, K. Abdul Kareem, D. Care College of Engineering Department of Computer Science and Engineering Trichy India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India School of Computer Science and Engineering Department of Software Systems Tamil Nadu Vellore India Rrase College of Engineering Padappai Department of Computer Science & Engineering Chennai India Grt Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Tamil Nadu Tiruttani India

ISBN: (纸本)9798350393354

Several digital dangers were investigated. Malware dominated analysis with 45 attacks. We found 30 phishing attacks. 22 data breaches, 15 cyber espionage, 18 identity theft. This indicates the kind and frequency of harassment digital forensic specialists endure. Digital evidence was crucial to the case. 65 pieces of evidence were collected on computers. 42 incidents showed smartphones and tablets' digital investigative potential. There were 55 examples of communication patterns requiring network logs. In 28 and 12, cloud services and removable media provided proof. A wide range of evidence sources stresses the need for extensive collecting. Digital forensics were essential to the inquiry. In 70% of cases, disk imaging software created forensic copies of metadata-and timestamp-containing storage media. Network packet analyzers examined 48 traffic logs and communication patterns. To analyze volatile memory, 35 cases used memory forensics. In 25 cases, malware analysis platforms decrypted malware. In 60 situations, file recovery software recovered lost or hidden files. Digital forensic specialists' diverse arsenal for thorough investigations is shown here. Legal and ethical considerations dominated the study. The law was important, and all inquiries followed norms. A strong chain of custody protects evidence integrity and admissibility. The data privacy rules were respected. Legal evidence is admissible in court. Ethics ensured objective investigations. This underlines digital forensic investigations' legal and ethical foundation. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Evolving Safety Protocols: Deep Learning-Enabled Detection of Personal Protective Equipment 1

引用

4th International Conference on computer Vision, High-Performance Computing, Smart Devices, and Networks, CHSN 2023

作者： Alahmid, Mustafa Bhimani, Kishankumar Saradva, Khushbu Ghildiyal, Sushil Saeedi, Sayed Aryan Ali, Saraa Yan, Han Filippov, Evgeny Faculty of Computer Science and Technology Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia Laboratory on AI for Computational Biology Faculty of Computer Science HSE University Moscow Russia Department of Computer Science and Engineering Indian Institute of Technology Ropar Punjab India Laboratory of Methods for Big Data Analysis Faculty of Computer Science HSE University Moscow Russia Deggendorf Institute of Technology Bavaria Germany

ISBN: (数字)9789819777945

ISBN: (纸本)9789819777938

To give shift in safety protocols, we have employed advanced deep learning algorithms and frameworks (Shrestha and Mahmood in IEEE Access 7:53,040–53,065, 2019 [25]) to construct an innovative AI model. The designed model detects the usage of personal protective equipment (PPE) (Personal protective equipment. Geneva: World Health Organization, 2020 [18]) by workers in high-risk industries such as construction and manufacturing. We have used Google’s TensorFlow object detection API (Sai and Sasikala in Object detection and count of objects in image using tensor flow object detection API, pp 542–546, 2019 [22]) to modify and train a model for dual purposes: PPE detection and face recognition. The state-of-the-art of this research is to substantially enhance safety compliance by addressing the prevalent issue of PPE non-compliance. To emphasis this, we have developed a pioneering software prototype that synergizes PPE detection with a face recognition-based clock-in system. This prototype demonstrates impressive object detection metrics with a mean average precision (mAP) of 0.9 for vests and 0.85 for helmets. Moreover, it exhibited efficient face recognition with a successful threshold range of 17–20%. The implementation of AI in our system promises significant enhancements to worker safety, while concurrently reducing the financial burden associated with big hazards and accidents. Beyond the development and performance of the system, this paper provides a thorough exploration of the encountered challenges, potential real-world applications (particularly in employee monitoring and clock-in systems), and the future implications of this study on research and practical applications in the field of AI-integrated safety compliance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Software prototyping

来源：评论

学校读者我要写书评

暂无评论

A Lightweight, Mobility-Aware, Geospatial & Temporal data Store for Multi-UAV Systems

A Lightweight, Mobility-Aware, Geospatial & Temporal Data St...

引用

Cluster, Cloud and Internet Computing Workshops (CCGridW), IEEE/ACM International Symposium on

作者： Shashwat Jaiswal Suman Raj Subhajit Sidhanta Yogesh Simmhan Department of Computer Science Indian Institute of Technology Bhilai India Department of Computational and Data Sciences Indian Institute of Science India

The meteoric rise in cutting-edge research in the area of cyber-physical systems has made it possible for UAVs to serve as computing infrastructure for processing the data collected from on-board sensors as well as ground-based IoT (Internet of Things) devices. To enable UAVs to perform edge computing tasks on the data received from cameras and other sensors in a near real-time manner, the input data or its associated metadata needs to be stored and processed locally, i.e., on the UAVs themselves. To that end, we present the design of DroneDB - a lightweight data storage engine that can process geospatial and time series data on a multi-UAV system comprising: A) a swarm of UAVs fitted with onboard computers, and B) ground-based fog servers. DroneDB is mobility-aware and has been optimized to perform efficient processing of different possible combinations of spatial and temporal queries, which are typically performed on time series data by real-world applications such as pollution, weather, and traffic monitoring.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification

引用

computers, Materials & Continua 2023年第3期74卷 6335-6349页

作者： Ibrar Amin Saima Hassan Samir Brahim Belhaouari Muhammad Hamza Azam Institute of Computing Kohat University of Science and TechnologyKohat26000K.P.KPakistan College of Science and Engineering Hamad bin Khalifa UniversityDohaQatar Centre of Research in Data Science Computer and Information Sciences DepartmentUniversiti Teknologi PETRONASSeri Iskandar32610PerakMalaysia

Malaria is a lethal disease responsible for thousands of deaths worldwide every *** methods of malaria diagnosis are timeconsuming that require a great deal of human expertise and *** automated diagnosis of diseases is progressively becoming *** deep learning models show high performance in the medical field,it demands a large volume of data for training which is hard to acquire for medical ***,labeling of medical images can be done with the help of medical experts *** recent studies have utilized deep learning models to develop efficient malaria diagnostic system,which showed promising ***,the most common problem with these models is that they need a large amount of data for *** paper presents a computer-aided malaria diagnosis system that combines a semi-supervised generative adversarial network and transfer *** proposed model is trained in a semi-supervised manner and requires less training data than conventional deep learning *** of the proposed model is evaluated on a publicly available dataset of blood smear images(with malariainfected and normal class)and achieved a classification accuracy of 96.6%.

关键词： Generative adversarial network transfer learning semi-supervised malaria VGG16

来源：评论

学校读者我要写书评

暂无评论

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion 38

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusi...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Han, Xing Nguyen, Huy Harris, Carl Ho, Nhat Saria, Suchi Department of Computer Science Johns Hopkins University United States Department of Statistics and Data Sciences The University of Texas Austin United States Department of Biomedical Engineering Johns Hopkins University United States

As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and sparsity of collected samples. Successfully leveraging this complex data, while overcoming the scarcity of high-quality training samples, is key to improving these models' predictive performance. We introduce "FuseMoE", a mixture-of-experts framework incorporated with an innovative gating function. Designed to integrate a diverse number of modalities, FuseMoE is effective in managing scenarios with missing modalities and irregularly sampled data trajectories. Theoretically, our unique gating function contributes to enhanced convergence rates, leading to better performance in multiple downstream tasks. The practical utility of FuseMoE in the real world is validated by a diverse set of challenging prediction tasks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Invertibility of Discrete-Time Linear Systems with Sparse Inputs 63

Invertibility of Discrete-Time Linear Systems with Sparse In...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Poe, Kyle Mallada, Enrique Vidal, Rene University of Pennsylvania Applied Mathematics and Computational Science Group PA19104 United States Johns Hopkins University Mallada Is with the Department of Electrical and Computer Engineering MD21218 United States University of Pennsylvania Radiology Computer and Information Science Statistics and Data Science Departments of Electrical and Systems Engineering PA19104 United States

ISBN: (纸本)9798350316339

One of the fundamental problems of interest for discrete-time linear systems is whether its input sequence may be recovered given its output sequence, a.k.a. the left inversion problem. Many conditions on the state space geometry, dynamics, and spectral structure of a system have been used to characterize the well-posedness of this problem, without assumptions on the inputs. However, certain structural assumptions, such as input sparsity, have been shown to translate to practical gains in the performance of inversion algorithms, surpassing classical guarantees. Establishing necessary and sufficient conditions for left invertibility of systems with sparse inputs is therefore a crucial step toward understanding the performance limits of system inversion under structured input assumptions. In this work, we provide the first necessary and sufficient characterizations of left invertibility for linear systems with sparse inputs, echoing classic characterizations for standard linear systems. The key insight in deriving these results is in establishing the existence of two novel geometric invariants unique to the sparseinput setting, the weakly unobservable and strongly reachable subspace arrangements. By means of a concrete example, we demonstrate the utility of these characterizations. We conclude by discussing extensions and applications of this framework to several related problems in sparse control. © 2024 IEEE.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Language Disorders in Children Using NLP and Machine Learning

Automated Detection of Language Disorders in Children Using ...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Malathi, P. Legapriyadharshini, N. Nair, Shruthi S Sujatha, M.P. Sadaieswaran, R. Thirumalaikumari, T. Simats Deemed to Be University Saveetha College of Liberal Arts and Sciences Department of Data Analytics Tamil Nadu Chennai India Simats Deemed to Be University Saveetha College of Liberal Arts and Sciences Department of Computer Application Tamil Nadu Chennai India Saveetha Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Agni College of Technology Department of Computer Science and Engineering Chennai India Tagore College of Arts and Science Department of Computer Applications Chennai India Simats Deemed to Be University Saveetha College of Liberal Arts and Sciences Department of Computer Science Chennai India

ISBN: (纸本)9798350309140

The purpose of the study is to address the essential need for a more efficient and objective technique for detecting language disorders in children, overcoming the constraints of standard manual evaluation systems. Existing systems, which utilize subjective evaluations and manual scoring, frequently result in lengthy processes and possible errors. To solve these issues, the proposed system automates the identification process by combining Natural Language Processing (NLP) and Machine Learning (ML). The system achieves a breakthrough in accuracy by normalizing text and extracting a comprehensive collection of linguistic features using advanced NLP techniques. The implementation involves difficult data preprocessing, extensive feature extraction, and the application of a cutting-edge Support Vector Machine (SVM) classifier. The proposed system achieves a 15% increase in accuracy, a 12% increase in precision, a 10% increase in recall, and an 11% increase in F1 score over existing systems. The confusion matrices show improved prediction skills, while accuracy across varied linguistic samples demonstrates the system's adaptability. Finally, the proposed system not only speeds up the detection of language disorders but also provides the groundwork for deeper insights into linguistic development, with revolutionary potential in educational and therapeutic settings. © 2024 IEEE.

关键词： Adversarial machine learning

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：