检索结果-内蒙古大学图书馆

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

作者： Hessa Alfalahi Ahsan H. Khandoker Leontios J. Hadjileontiadis Department of Biomedical Engineering Khalifa University of Science and Technology Abu Dhabi UAE Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Greece

While machines struggle to cope with acoustical variability and noise, humans show remarkable robustness to recognize speech content under different conditions of environmental noise. The tonotopic organization of the spiral human cochlea has motivated the signal processing community for its superb frequency tuning capabilities. In this work, we design and evaluate a novel spiral cochlear cepstrum space, as a novel, directional feature engineering framework, using a cochlear transform approach, that results in tonotopically organized, orthogonal cochlear modes. Such cochlear modes are then transformed to the spiral cochlear cepstral space, yielding cochlear filterbank cepstral coefficients (CFCCs). As opposed to previous works that define the bio-inspired cepstral features based on Mel-, Equivalent Rectangular Bandwidth (ERB) or linear scales, we define the scaling based on the cochlear spiral geometry that spans from θ = 0° at the base to θ = 990° at the apex. We then compute the log function and the discrete cosine transform of the cochlear modes energy yielding spatially supported cepstral features along the spiral cochlear space, spaced by θ = 45°. We assess the impact of noise on the CFCCs and compare the performance to that of Mel-Frequency Cepstral Coefficients (MFCCs) and Gammatone Filterbank Cepstral Coefficients (GFCCs) using the NOIZEUS dataset. We report, for the first time, that the superiority of the CFCCs noise-robustness stems from the geometrical organization of the cochlea (i.e., its tonotopic map) when evaluated on speech signals contaminated with different noise conditions at different SNRs. The proposed CFCCs constitute a platform for a new class, bio-inspired and noise-robust feature extraction for many applications such as speaker recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time-Interpolated Vernier Digital-to-Time Converter with Applications in Time-Mode SAR TDC

Time-Interpolated Vernier Digital-to-Time Converter with App...

引用

Annual IEEE Northeast Workshop on Circuits and Systems (NEWCAS)

作者： Daniel Junehee Lee Fei Yuan Yushi Zhou Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto ON> Canada Department of Electrical and Computer Engineering Lakehead University Thunder Bay ON Canada

This paper proposes an 8 bit time-interpolated Vernier digital-to-time converter (DTC) consisting of a 4-bit Vernier delay line coarse DTC and a 4 bit time interpolator fine DTC with applications in a time-based successive approximation register time-to-digital converter (SAR TDC) for power and area efficiency. The design, operation, calibration, and error analysis of the DTC are presented. The DTC is designed in a TSMC 130 nm 1.2 V CMOS technology and analyzed using Spectre with BSIM3 device models. Simulation results show that the DTC achieves a resolution of 0.57-0.69 ps, a dynamic range of 145.4-176 ps, and DNL and INL of 0.5 LSB and 0.52 LSB, respectively and consumes 1.1 mW.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Performance Study of Selected Machine Learning Techniques for Predicting Heart Diseases 2nd

A Performance Study of Selected Machine Learning Techniques ...

引用

2nd International Conference on Security and Information Technologies with AI, Internet Computing and Big-data Applications, SITAIBA 2023

作者： Olorunfemi, Blessing Oluwatobi Ogunde, Adewale Opeoluwa Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Imoize, Agbotiname Lucky Li, Chun-Ta Faculty of Natural Sciences Department of Computer Science Redeemer’s University Osun Nigeria Department of Computer Science Bowen University Iwo Nigeria Faculty of Information and Communication Sciences Department of Computer Science University of Ilorin Ilorin240003 Nigeria Faculty of Engineering Department of Electrical and Electronics Engineering University of Lagos Lagos Akoka100213 Nigeria Bachelor’s Program of Artificial Intelligence and Information Security Fu Jen Catholic University New Taipei City24206 Taiwan

ISBN: (纸本)9789819777853

Heart Disease remains a leading cause of mortality worldwide. It alarmingly rises at a quick rate, making early heart disease prediction crucial for effective prevention and timely intervention. Heart disease diagnosis is a difficult process that requires technical skills and accuracy to complete. With improvements in technology, computing has lent its voice to simplify the diagnosis of various health problems. Machine learning uses past or existing history to predict future results. Various machine learning techniques have been developed over the years and used in predicting heart diseases with various levels of performance. Identifying the best-suited machine learning technique to use for prediction purposes can be a challenging task. This research work analyses the performance of seven (7) machine learning techniques, comprising AdaBoost Algorithm, KNN, Logistic Regression, Naïve Bayes Classifier, Random Forest, SVM, and XGBoost. The heart disease dataset was downloaded from the UCI repository and analysed using Python programming language in the Jupyter Notebook environment. A comparative analysis of the seven (7) techniques was performed based on Accuracy, Precision, and Recall. From the results obtained, KNN, Random Forest, and XGBoost showed superior performance over the others with an accuracy of 100%, AdaBoost Algorithm followed with an accuracy of 92.2%, SVM followed with an accuracy of 91.71%, Naïve Bayes Classifier followed with an accuracy of 88.29% while Logistic Regression has the least accuracy of 86.34%. KNN, RF, and XGBoost outperformed AdaBoost, SVN, and LR. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Micromolded honeycomb scaffold design to support the generation of a bilayered RPE and photoreceptor cell construct

引用

Bioactive Materials 2023年第12期30卷 142-153页

作者： In-Kyu Lee Ruosen Xie Agustin Luz-Madrigal Seunghwan Min Jingcheng Zhu Jiahe Jin Kimberly L.Edwards M.Joseph Phillips Allison L.Ludwig David M.Gamm Shaoqin Gong Zhenqiang Ma Department of Electrical and Computer Engineering University of Wisconsin-MadisonMadisonWI53706USA Wisconsin Institute for Discovery University of Wisconsin-MadisonMadisonWI53715USA Department of Ophthalmology and Visual Sciences University of Wisconsin-MadisonMadisonWI53705USA Department of Biomedical Engineering University of Wisconsin-MadisonMadisonWI53706USA McPherson Eye Research Institute University of Wisconsin-MadisonMadisonWI53705USA Waisman Center University of Wisconsin-MadisonMadisonWI53705USA Department of Comparative Biomedical Sciences University of Wisconsin–MadisonMadisonWI53706USA Department of Materials Science and Engineering University of Wisconsin-MadisonMadisonWI53706USA Department of Engineering Physics University of Wisconsin-MadisonMadisonWI53706USA Grainger Institute for Engineering University of Wisconsin-MadisonMadisonWI53706USA

Age-related macular degeneration(AMD)causes blindness due to loss of retinal pigment epithelium(RPE)and photoreceptors(PRs),which comprise the two outermost layers of the *** the small size of the macula and the importance of direct contact between RPE and PRs,the use of scaffolds for targeted reconstruction of the outer retina in later stage AMD and other macular dystrophies is particularly *** developed microfabricated,honeycomb-patterned,biodegradable poly(glycerol sebacate)(PGS)scaffolds to deliver organized,adjacent layers of RPE and PRs to the subretinal ***,an optimized process was developed to photocure PGS,shortening scaffold production time from days to *** resulting scaffolds robustly supported the seeding of human pluripotent stem cell-derived RPE and PRs,either separately or as a dual celllayered *** advanced,economical,and versatile scaffolds can accelerate retinal cell transplantation efforts and benefit patients with AMD and other retinal degenerative diseases.

关键词： Microfabrication Retina Scaffolds Stem cells Tissue engineering

来源：评论

学校读者我要写书评

暂无评论

Longitudinal Missing Data Imputation for Predicting Disability Stage of Patients with Multiple Sclerosis

arXiv

引用

arXiv 2025年

作者： Vazifehdan, Mahin Bosoni, Pietro Pala, Daniele Tavazzi, Eleonora Bergamaschi, Roberto Bellazzi, Riccardo Dagliati, Arianna Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy IRCCS Mondino Foundation Pavia Italy

Multiple Sclerosis (MS) is a chronic disease characterized by progressive or alternate impairment of neurological functions (motor, sensory, visual, and cognitive). Predicting disease progression with a probabilistic and time-dependent approach might help in suggesting interventions that can delay the progression of the disease. However, extracting informative knowledge from irregularly collected longitudinal data is difficult, and missing data pose significant challenges. MS progression is measured through the Expanded Disability Status Scale (EDSS), which quantifies and monitors disability in MS over time. EDSS assesses impairment in eight functional systems (FS). Frequently, only the EDSS score assigned by clinicians is reported, while FS sub-scores are missing. Imputing these scores might be useful, especially to stratify patients according to their phenotype assessed over the disease progression. This study aimed at i) exploring different methodologies for imputing missing FS sub-scores, and ii) predicting the EDSS score using complete clinical data. Results show that Exponential Weighted Moving Average achieved the lowest error rate in the missing data imputation task;furthermore, the combination of Classification and Regression Trees for the imputation and SVM for the prediction task obtained the best accuracy. Copyright © 2025, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Evolution of Wavelet Higher-Order Dynamics in Atrial Fibrillation 44

Investigation of the Evolution of Wavelet Higher-Order Dynam...

引用

44th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2022

作者： Zisou, Charilaos A. Apostolidis, Georgios K. Hadjileontiadis, Leontios J. School of Electrical & Computer Engineering Aristotle University of Thessaloniki GR 54124 Greece Khalifa University Department of Biomedical Engineering PO Box 127788 United Arab Emirates

ISBN: (数字)9781728127828

ISBN: (纸本)9781728127828

Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with significant morbidity and mortality. Owing to the advances in sensor technology and the emergence of wearable devices that enable daily self-monitoring, ECG signal processing methods for the automatic detection of AF are more pertinent than ever. In this paper, we investigate the use of wavelet higher-order statistics (WHOS) for feature extraction and differentiation between normal sinus rhythm and AF. The proposed approach captures the evolution of the WHOS dynamics and quantifies the changes in the time-varying characteristics of the frequency couplings caused by AF. Results obtained from the statistical analysis of a dataset of 5834 single-lead ECG recordings, reveal 46/50 statistically significant features and provide insight into the complexity of the evolution of the ECG non-linearities during AF. © 2022 IEEE.

关键词： Higher order statistics

来源：评论

学校读者我要写书评

暂无评论

Enhanced programmability of Reconfigurable Intelligent Surfaces for Smart Cities using Application-Specific Integrated Circuits

Enhanced Programmability of Reconfigurable Intelligent Surfa...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Loukas Petrou Thorsten Brandt Yorgos Stratakos Marco A. Antoniades Panos Megerditchian Konstantinos Michail Anastasis Kounoudes Julius Georgiou Department of Electrical and Computer Engineering Holistic Electronics Research Laboratory University of Cyprus Nicosia Cyprus Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto Canada SignalGeneriX Ltd. Limassol Cyprus

ISBN: (数字)9798350356830

ISBN: (纸本)9798350356847

Reconfigurable Intelligent Surfaces (RISs) are emerging as a key technology for enhancing wireless communications in smart city environments, offering robust, low-latency connectivity. This paper presents the design of an adaptive control system based on high-voltage, mixed-signal integrated circuits for controlling tunable RISs, tailored for wireless cellular communications in urban areas. The proposed system enables enhanced programmability by dynamically steering beams and fine-tuning signal reflections through the precise control of varactor diodes embedded within the RIS unit cells. This flexible system architecture supports real-time software reconfiguration, allowing RIS units to adapt to varying network conditions and scale seamlessly across smart city infrastructures. Simulated results on a 0.35 μm CMOS high voltage process technology demonstrate the circuit's ability to achieve low power consumption and high reconfiguration speed across a wide temperature range. The control electronics are separated from the RIS panels, this way enabling tiling of multiple surfaces for scalable, cost-effective deployment. This approach offers a promising pathway to meeting the growing demand for seamless, high-speed, and energy-efficient connectivity in next-generation smart city applications, including vehicular networks, Internet of Things, smart traffic management and smart infrastructure.

关键词： Wireless communication Integrated circuits Varactors Temperature distribution Smart cities High-voltage techniques Reconfigurable intelligent surfaces Real-time systems Low latency communication Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Less is More: Optimizing Function Calling for LLM Execution on Edge Devices

arXiv

引用

arXiv 2024年

作者： Paramanayakam, Varatheepan Karatzas, Andreas Anagnostopoulos, Iraklis Stamoulis, Dimitrios School of Electrical Computer and Biomedical Engineering Southern Illinois University CarbondaleIL United States Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX United States

The advanced function-calling capabilities of foundation models open up new possibilities for deploying agents to perform complex API tasks. However, managing large amounts of data and interacting with numerous APIs makes function calling hardware-intensive and costly, especially on edge devices. Current Large Language Models (LLMs) struggle with function calling at the edge because they cannot handle complex inputs or manage multiple tools effectively. This results in low task-completion accuracy, increased delays, and higher power consumption. In this work, we introduce Less-is-More, a novel fine-tuning-free function-calling scheme for dynamic tool selection. Our approach is based on the key insight that selectively reducing the number of tools available to LLMs significantly improves their function-calling performance, execution time, and power efficiency on edge devices. Experimental results with state-of-the-art LLMs on edge hardware show agentic success rate improvements, with execution time reduced by up to 70% and power consumption by up to 40%. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

ITNR: Inversion Transformer-based Neural Ranking for cancer drug recommendations

引用

computers in Biology and Medicine 2024年 172卷 108312-108312页

作者： Sotudian, Shahabeddin Paschalidis, Ioannis Ch. Department of Electrical and Computer Engineering Division of Systems Engineering Boston University BostonMA United States Department of Biomedical Engineering and Faculty of Computing and Data Sciences Boston University BostonMA United States

Personalized drug response prediction is an approach for tailoring effective therapeutic strategies for patients based on their tumors’ genomic characterization. While machine learning methods are widely employed in the literature, they often struggle to capture drug-cell line relations across various cell lines. In addressing this challenge, our study introduces a novel listwise Learning-to-Rank (LTR) model named Inversion Transformer-based Neural Ranking (ITNR). ITNR utilizes genomic features and a transformer architecture to decipher functional relationships and construct models that can predict patient-specific drug responses. Our experiments were conducted on three major drug response data sets, showing that ITNR reliably and consistently outperforms state-of-the-art LTR models. © 2024 Elsevier Ltd

关键词： Cell culture

来源：评论

学校读者我要写书评

暂无评论

Control Loop Architectures for High-Frequency Switching-Mode DC-DC Buck Converters

Control Loop Architectures for High-Frequency Switching-Mode...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Filippo Boera Elisabetta Moisello Cristian Garbossa Edoardo Bonizzoni Infineon Pavia Italy Department of Electrical Computer and Biomedical Engineering University of Pavia Italy Infineon Padova Italy

ISBN: (数字)9798350356830

ISBN: (纸本)9798350356847

This paper tackles the issue of control loops in high-frequency switching-mode DC-DC buck converters for post-regulation in automotive applications. Two different control loop implementations, designed in a 120-nm BCD process, are proposed and verified through simulations. Both solutions exploit the advantages of standard voltage mode control (VMC), while improving the transient response by including a one cycle (OC) and a feed forward (FF) loop, respectively. The OC VMC loop achieves 0.92 mV/V line regulation and 0.6 mV/A load regulation, whereas the FF VMC attains 0.17 mV/V line regulation and 4.8 mV/A load regulation, thus both outperforming the state-of-the-art of high-frequency switching-mode buck converters.

关键词： Transient response Buck converters Process control Switches Control systems Regulation Transistors Voltage control Integrated circuit modeling Standards

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：