检索结果-内蒙古大学图书馆

International Conference on computer Communication and Informatics (ICCCI)

作者： Amu. D Santhi Baskaran Dept of Computer Science and Engineering Puducherry Technological University Puducherry Dept of Information Technology Puducherry Technological University Puducherry

Various algorithms have been employed to enhance the performance of blockchain. Successful algorithms have been developed with the potential to use blockchain technology. In this study, we analyze and explain a list of significant blockchain-based algorithms, including Rivest Shamir Adleman, Advanced Encryption Standard, Data Encryption Standard, Digital Signature, and Elliptic Curve Cryptography. In this article, we examine the Quantum Teleportation security algorithm for Blockchain technology. This technique is based on encryption to provide well *** teleportation compares favorably to RSA, DES, AES, and ECC. This survey document serves as a valuable guide for upcoming research issues in Blockchain technology.

关键词： Surveys Quantum computing Teleportation Elliptic curve cryptography Throughput Blockchains Encryption

来源：评论

学校读者我要写书评

暂无评论

Joint Spectrogram Separation and TDOA Estimation using Optimal Transport

arXiv

引用

arXiv 2025年

作者： Fabiani, Linda Schlecht, Sebastian J. Haasler, Isabel Elvander, Filip Dept. of Information and Communications Engineering Aalto University Finland Dept. of Electrical and Computer Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Dept. of Information Technology Uppsala University Sweden

Separating sources is a common challenge in applications such as speech enhancement and telecommunications, where distinguishing between overlapping sounds helps reduce interference and improve signal quality. Additionally, in multichannel systems, correct calibration and synchronization are essential to separate and locate source signals accurately. This work introduces a method for blind source separation and estimation of the Time Difference of Arrival (TDOA) of signals in the time-frequency domain. Our proposed method effectively separates signal mixtures into their original source spectrograms while simultaneously estimating the relative delays between receivers, using Optimal Transport (OT) theory. By exploiting the structure of the OT problem, we combine the separation and delay estimation processes into a unified framework, optimizing the system through a block coordinate descent algorithm. We analyze the performance of the OT-based estimator under various noise conditions and compare it with conventional TDOA and source separation methods. Numerical simulation results demonstrate that our proposed approach can achieve a significant level of accuracy across diverse noise scenarios for physical speech signals in both TDOA and source separation tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Blind source separation

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection System Using Improved Gloden Jackal optimization for Security and Privacy in Internet of Things

Intrusion Detection System Using Improved Gloden Jackal opti...

引用

Data Science and Information System (ICDSIS), IEEE International Conference on

作者： Naresh Kumar Bhagavatham Mohammed Al-Farouni Komuravelly Sudheer Kumar S Meenakshi Sundaram R P Puneeth Dept of Computer Science and Engineering Vignana Bharathi Institute of Technology Hyderabad India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq School of Computer Science & Artificial Intelligence SR University Warangal Telangana India Department of AI&DS Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering NMAM Institute of Technology Affiliated to NITTE (Deemed to be University) Karnataka India

ISBN: (数字)9798350381665

ISBN: (纸本)9798350381672

technology plays a primary role in rapid growth of service and identifying the quality of life. Recent technology such as Internet of Things (IoT) determines an impressive performance in the development of fast-forward. Intrusion Detection System (IDS) is employed as a lifeline to prevent attacks by categorizing activities as suspicious or normal. However, identifying the most relevant features from large data is challenging to effectively distinguish among suspicious or normal behavior. This research proposes the Improved Gloden Jackal optimization (IGJO) to select the appropriate features in IDS for security and privacy. GJO is improved by using tent mapping reverse learning for initializing populations, sine and cosine techniques are performed for updating prey positions which increases the ability of global exploration, and Cauchy mutation is used to acquire the optimal solutions. Initially, the CIC-IDS2017 dataset is used to evaluate the model performance and min-max normalization is utilized for normalizing the data. Then, IGJO is performed to select the appropriate features and Long Short-Term Memory (LSTM) is employed to classify IDS. The IGJO achieves a high accuracy of 99.95% compared to existing techniques respectively.

关键词： Privacy Accuracy Sociology Intrusion detection Data models Internet of Things Security

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection of Singing Voices With Whisper Encodings

Deepfake Detection of Singing Voices With Whisper Encodings

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Falguni Sharma Priyanka Gupta Centre for Artificial Intelligence Banasthali Vidyapith Jaipur India Dept. of Communication and Computer Engineering The LNM Institute of Information Technology Jaipur India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The deepfake generation of singing vocals is a concerning issue for artists in the music industry. In this work, we propose a singing voice deepfake detection (SVDD) system, which uses noise-variant encodings of open-AI’s Whisper model. As counter-intuitive as it may sound, even though the Whisper model is known to be noise-robust, the encodings are rich in non-speech information, and are noise-variant. This leads us to evaluate Whisper encodings as feature representations for the SVDD task. Therefore, in this work, the SVDD task is performed on vocals and mixtures, and the performance is evaluated in %EER over varying Whisper model sizes and two classifiers-CNN and ResNet34, under different testing conditions.

关键词： Industries Deepfakes Signal processing Encoding Acoustics Noise robustness Speech processing Testing

来源：评论

学校读者我要写书评

暂无评论

CTVAE: Current Task Variational Auto-Encoder with Dynamic Ensemble Loss for Few-Shot Learning

CTVAE: Current Task Variational Auto-Encoder with Dynamic En...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hao-Chin Su Yi-Ling Chen Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan

Few-shot learning is a challenging task in which a classifier needs to quickly adapt to new classes. These new classes are unseen in the training stage, and there are only very few samples (e.g., five images) provided for learning each new class in the testing stage. When the existing methods learn with such a small amount of samples, they could easily be affected by the outliers. Moreover, the category center calculated from those few samples may deviate from the true center. To address these issues, we propose a novel approach called Current Task Variational Auto-Encoder (CTVAE) for few-shot learning. In our framework, a trained feature extractor first produces the features of the current task, and these features are used to repeatedly train the generator in CTVAE. After that, we can use CTVAE to generate additional features of samples, and then find a new center of the category based on these newly generated features. Compared with the original center, the new center tends to be closer to the true center in vector space. CTVAE can break the limitation of traditional few-shot learning methods, which can only fine-tune the model with very few samples in the testing stage. Moreover, by generating the features directly without producing the images first, the training process of the generator in CTVAE is simplified and becomes more efficient, and the features can be generated faster and more precisely. According to the experiments on benchmark datasets (i.e., Mini-ImageNet, CUB, and CIFAR-FS), our proposed framework is able to outperform the state-of-the-art methods and improves the accuracy by 1–4%. We also conduct experiments on the cross-domain tasks, and the results show that the proposed framework can bring 1-5% accuracy improvements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Customer Segmentation using Machine learning Techniques

Customer Segmentation using Machine learning Techniques

引用

Multi-disciplinary Conference in Emerging Research Trends (IMCERT), International

作者： Syed Muhammad Nabeel Mustafa Asad Akhtar Joseph Terence Peter Noronha Muhammad Salman Mirza Ahsan Baig Dept. of Computer Science and I.T NED University of Engineering and Technology Karachi Pakistan

The rapid expansion of e-commerce resulted in the influx of data in the mainstream. The data of customers can lead to better results and can help the stakeholders to take better results and improve their business. Machine learning also found its application in the e-commerce. Machine learning provides a vast collection of algorithms that produce efficient results in segmenting the customers. In this research paper, we explore e-commerce dataset to perform the segmentation of customers. We used ensemble technique to classify the customers using Support vector Machine (SVC), Logistics Regression, KNear st Neighbors, Decision Tree, Random Forest, AdaBoost Classifier and Gradient Boosting Classifier. We performed in dept analysis on the dataset, studying behaviors and forming clusters. In results, the ensemble model of ensembled Random Forest, Gradient Boosting and k-Nearest Neighbors gave 76.83 % precision.

关键词： Support vector machines Static VAr compensators Production Boosting Market research Classification algorithms Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Photonic Signal Transport on Aerospace Platforms: is Analog Signaling Ever Useful?

Photonic Signal Transport on Aerospace Platforms: is Analog ...

引用

IEEE Research and Applications of Photonics In Defense Conference (RAPID)

作者： Michael T. Hoff Stephen E. Ralph Rick C. Stevens Dept. of Electrical and Computer Engineering Advanced Technology Laboratories Georgia Inst of Technology Lockheed Martin Corporation Atlanta GA USA Dept. of Electrical and Computer Engineering Georgia Inst of Technology Atlanta GA USA Advanced Technology Laboratories Lockheed Martin Corporation Eagan MN USA

For photonic signal transport in multi-GHz, waveform-sensitive RF transport applications, it will be shown that digital-over-fiber fundamentally enables superior SNR performance versus analog-over-fiber. However, for ...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impact of Inadequate Mg Activation on Dynamic Threshold Voltage of Schottky-type $p$-GaN Gate HEMTs

Impact of Inadequate Mg Activation on Dynamic Threshold Volt...

引用

International Symposium on Power Semiconductor Devices and Ics (ISPSD)

作者： Jiahui Sun Zheyang Zheng Li Zhang Yat Hon Ng Ji Shu Tao Chen Kevin J. Chen Dept. of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong China

To further reduce the forward gate current of Schottky-type $p$ -GaN gate HEMTs, inadequate Mg activation in $p$ -GaN is deployed in this work, which tends to convert the conventional $p$ -GaN into insulating GaN with high concentration of Mg passivated by hydrogens. The free hole concentration in $p$ -GaN is reduced, and so is the hole deficiency effect that is the main cause of dynamic threshold voltage ( $V_{\text{TH}}$ ) in commercial Schottky-type $p$ -GaN gate HEMTs. However, plenty of electron traps left in $p$ -GaN lead to more significant dynamic $V_{\text{TH}}$ shift (up to 6 V) under reverse gate bias ( $V_{\text{GSQ}}$ , up to -13 V), as revealed by the $V_{\text{TH}}$ recovery processes under different conditions of light illumination and forward gate bias. Fortunately, under forward $V_{\text{GSQ}}$ , the fully depleted $p$ -GaN layer facilitates electron acceleration by the electric field, suppressing the electron trapping and consequent dynamic $V_{\text{TH}}$ shift. Besides, deeper-level electron trapping in AlGaN may account for the slight dynamic $V_{\text{TH}}$ shift under $V_{\text{GSQ}}\geq 7\mathrm{V}$ .

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI Assisted Diagnosis of Dengue Amid Arboviral Diseases, Severity Prediction, and Post Effects

AI Assisted Diagnosis of Dengue Amid Arboviral Diseases, Sev...

引用

International Conference on Information technology Research (ICITR)

作者： Nivasheni B Fernando V.G.S.O. Srihari M Sarah M.I.L. Vishan Jayasinghearachchi Samadhi Chathuranga Rathnayake Dept. of Computer Science Sri Lanka Institute of Information Technology Malabe Sri Lanka Dept. of Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331511425

ISBN: (纸本)9798331511432

This paper aims to examine the applicability of machine learning models for aiding in the diagnosis and management of arboviral illnesses, especially Dengue. The study focuses on three key objectives: Diagnosis of Dengue, prediction of prognosis of severe disease, and the identification of the post dengue effects. Multiple strategies were used to address these challenges. They are feature engineering based multiclass classification of arboviral diseases, enhancement of standard conventional machine learning algorithms for binary classification of severe Dengue and finally MLSOL enhancing ensemble model for drawing future effects of Dengue infections. The comparison of traditional models included both Random Forest, XGBoost, and also ensemble method while applying the feature selection methods of SFA and RFE. This study presents the comparison of traditional individual models and optimal ensemble method for the multiclass classification in arboviral diseases. In the case of binomial classification, the best accuracy level was 0.93 achieved by the Random Forest with RFE feature selection compared to Logistic Regression as well as the Gradient Boosting. Furthermore, the study proposed an MLSOL augmented ensemble approach to handle label imbalance problem in the dataset which in turn substantially enhanced the prediction accuracy. This approach decreased Hamming Loss to 0. 12 and increased the F-measure to 0.82, this has the capability of handling the imbalanced dataset and improving the predictive accuracy and performance. This machine learning framework offers great potential for clinical use in such aspects as early intervention and in effects following Dengue fever. It is meant to help healthcare practitioners and policy makers on how to better prevent and combat Dengue in Sri Lanka.

关键词： Accuracy Machine learning algorithms Medical services Feature extraction Ensemble learning Object recognition Prognostics and health management Viruses (medical) Random forests Standards

来源：评论

学校读者我要写书评

暂无评论

DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units

arXiv

引用

arXiv 2024年

作者： Boyle, Liam Moosmann, Julian Baumann, Nicolas Heo, Seonyeong Magno, Michele Dept. of Information Technology and Electrical Engineering ETH Zurich Zurich8092 Switzerland Dept. of Computer Science and Engineering Kyung Hee University Yongin130-701 Korea Republic of

Advances in lightweight neural networks have revolutionized computer vision in a broad range of Internet of Things (IoT) applications, encompassing remote monitoring and process automation. However, the detection of small objects, which is crucial for many of these applications, remains an underexplored area in current computer vision research, particularly for low-power embedded devices that host resource-constrained processors. To address said gap, this paper proposes an adaptive tiling method for lightweight and energy-efficient object detection networks, including YOLO-based models and the popular Faster Objects More Objects (FOMO) network. The proposed tiling enables object detection on low-power Microcontroller Units (MCUs) with no compromise on accuracy compared to large-scale detection models. The benefit of the proposed method is demonstrated by applying it to FOMO and TinyissimoYOLO networks on a novel RISC-V-based MCU with built-in Machine Learning (ML) accelerators. Extensive experimental results show that the proposed tiling method boosts the F1-score by up to 225% for both FOMO and TinyissimoYOLO networks while reducing the average object count error by up to 76% with FOMO and up to 89% for TinyissimoYOLO. Furthermore, the findings of this work indicate that using a soft F1 loss over the popular binary cross-entropy loss can serve as an implicit non-maximum suppression for the FOMO network. To evaluate the real-world performance, the networks are deployed on the RISC-V based GAP9 microcontroller from GreenWaves Technologies, showcasing the proposed method’s ability to strike a balance between detection performance (58% − 95% F1 score), low latency (0.6 ms/Inference - 16.2 ms/Inference), and energy efficiency (31 µJ/Inference - 1.27 mJ/Inference) while performing multiple predictions using high-resolution images on a MCU. © 2024, CC BY-NC-ND.

关键词： Microcontrollers

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：