检索结果-内蒙古大学图书馆

Breast cancer detection and classification: A study on the specification and implementation of multilayer perceptron analog artificial neural networks

引用

computers in Biology and Medicine 2025年 190卷 110060-110060页

作者： Silas, Koagne Longpa T. Djimeli-Tsajio Alain, B. Thierry, Noulamo Jean-Pierre, Lienou T. Ejuh, Geh Wilson Research Unit of Automation and Applied Computer Science URAIA IUT-FV University of Dschang P.O. Box 134 Bandjoun Cameroon Department of Telecommunication and Network Engineering IUT-FV University of Dschang P.O. Box 134 Bandjoun Cameroon Department of Computer Engineering IUT-FV University of Dschang P.O. Box 134 Bandjoun Cameroon Department of General and Scientific Studies IUT-FV University of Dschang P.O. Box 134 Bandjoun Cameroon Department of Electrical and Electronic Engineering National Higher Polytechnic Institute University of Bamenda P. O. Box 39 Bambili Cameroon

Breast cancer is a leading cause of mortality worldwide. Screening therefore remains the best defense against this disease, highlighting the need for accurate and efficient diagnostic methods. Previous authors addressed this issue by implementing digital hardware with low processing speed and high power consumption constraints. Moreover, a similar approach was developed focusing on implementing an off-chip learning on-chip inference methodology resulting in a high complexity of the proposed systems and complex communication between modules regarding the operations performed by each circuit. This research presents a fully integrated multilayer perceptron analog artificial neural network, classifying breast tumor cells as benign or malignant. A novel analog network architecture and fundamental analog circuit blocks realized by dint of the 90 nm complementary metal-oxide semiconductor technology are developed in this work for breast cancer analysis. The model's reliability findings are confirmed through comprehensive evaluation metrics, achieving sensitivity, specificity, accuracy, F1-Scoree, Intersection-over-Union, and Matthew's correlation coefficient of 0.9668, 0.9869, 0.9800, 0.9708, 0.9433, and 0.9556, respectively. Monte Carlo analysis further validates a 98.00 % accuracy on the Wisconsin Breast Cancer Dataset, with a power consumption of 23.06 mW, using 122 MB of memory while operating at a power supply rail of ±900 mV per analog circuit component and 27 °C computational unit temperature. These findings suggest a significant opportunity for integrating the proposed model into clinical practice, thereby improving patient care in medical diagnostics. © 2025 Elsevier Ltd

关键词： Oxide semiconductors

来源：评论

学校读者我要写书评

暂无评论

Real-time deep learning for multi-label retinal disease diagnosis with embedded system

Computational and Structural Biotechnology Reports

引用

Computational and Structural Biotechnology Reports 2025年 2卷

作者： Feudjio Ghislain Saha Tchinda Beaudelaire Romain Atangana Tchiotsop Daniel Research Unit of Automation and Applied Computer (UR-AIA) Electrical Engineering Department of IUT-FV University of Dschang P.O. Box: 134 Bandjoun Cameroon Research Unit of Condensed Matter of Electronics and Signal Processing (UR‑MACETS) Department of Physics Faculty of Sciences University of Dschang P.O. Box 67 Dschang Cameroon Department of Computer Science Higher Teacher Training College University of Bertoua-Cameroon P.O.Box 652 Bertoua Cameroon

Background Ophthalmological consultations are essential for the early detection of retinal pathologies. The development of advanced diagnostic devices that combine portability, ease of access, and energy efficiency offers significant benefits, especially in rural or peri-urban areas, which often struggle with limited medical resources and time constraints. Method In this study, we develop a classification platform for various retinal diseases using a Raspberry Pi 4 board. The system relies on a lightweight deep learning model based on convolutional neural networks (CNNs). To enhance the model's efficiency, we integrate biorthogonal wavelet transforms, which facilitate the effective extraction of relevant features from the input images. This approach reduces computational complexity while maintaining the quality of the extracted information. The model, optimized for real-time deployment, was trained on a dataset containing 4303 retinal images, representing four classes of pathologies. Results The proposed embedded model achieves an accuracy of 0.9806 across the four classes of pathologies collected from the two public databases ODIR (Ocular Disease Intelligence Recognition) and RFMiD (Retinal Fundus Multi-Disease Image Dataset). Conclusions Compared to several state-of-the-art methods published to date, the outstanding performance of the proposed embedded system demonstrates its potential as a valuable tool for clinicians to diagnose various ocular diseases in underprivileged healthcare settings.

关键词： Embedded board Real-time classification Lightweight CNN model Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Dynamic Analysis of a Hyperchaotic Hyperjerk Circuit, FPGA Implementation and Its Application in RNG for Medical Images Encryption

引用

Transactions of the Indian National Academy of Engineering 2022年第3期7卷 753-773页

作者： Feudjio, E. R. Tamba, V. Kamdoum Tagne, F. Kapche Tchendjeu, A. E. Tchahou Djatche, G. P. Biamou, A. L. Mbanda Fotsin, H. B. Research Unit of Automation and Applied Computer (URAIA) Department of Electrical Engineering IUT-FV Bandjoun University of Dschang Bandjoun Cameroon Research Unit of Condensed Matter Electronics and Signal Processing (URMACETS) Department of Physics University Of Dschang Dschang Cameroon Department of Computer Engineering National Polytechnic Institute University of Bamenda Bambili Cameroon

Nonlinear systems with high dimension have received considerable attention recently due to their possibility to exhibit complex dynamics including chaos, hyperchaos, pattern formation, self-organization, and other related dynamics. In this work, a novel four dimensional autonomous hyperchaotic hyperjerk circuit with hyperbolic sine and quintic nonlinearities is proposed and its corresponding dynamics is analyzed theoretically, numerically and experimentally. Using Kirchhoff’s laws, the state equations of the proposed hyperchaotic hyperjerk circuit are described. Some fundamental properties of the model including symmetry, dissipation, equilibrium points and their stability are examined. Bifurcation diagrams, Lyapunov exponent spectrum and phase portraits are plotted to point out the complex dynamical behaviors exhibited by the system. The numerical results are validated using PSpice-based circuit simulations and Field-Programmable Gate Array (FPGA) implementations. In addition, to use the proposed hyperchaotic hyperjerk circuit for medical images encryption, a random number generator (RNG) is designed. The resulting random number generator (RNG) successfully passes the National Institute of Standards and Technology (NIST-800-22) statistical tests. This confirms that the proposed hyperchaotic hyperjerk circuit is effective in showing randomness. Finally, a medical images encryption algorithm is developed based on the generated random bits. The security performances analyses are performed and the results show that the proposed algorithm can effectively encrypt and decrypt medical images with better security performances.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effects of the Flatness Network Parameter Threshold on the Performance of the Rectified Linear unit Memristor-Like Activation Function in Deep Learning

引用

SN computer science 2024年第8期5卷 1-10页

作者： Tchepgoua Mbakop, Marcelle Mboupda Pone, Justin Roger Chassem Kamdem, Priva Kengne, Romanic Research Unit of Condensed Matter Electronics and Signal Processing (RU-MACETS) Department of Physics Faculty of Science University of Dschang P. O. Box 67 Dschang Cameroon Research Unit of Automation and Applied Computer (RU-AIA) Electrical Engineering Department of IUT-FV University of Dschang P.O. Box 134 Bandjoun Cameroon Research Unit of Fundamental Computer Sciences and Artificial Intelligence (RU-FCSAI) Department of Computer Sciences Faculty of Science University of Dschang P. O. Box 67 Dschang Cameroon

In this contribution, we improve of the performance of the Rectified Linear unit Memristor Like Activation Function with the implication to help training process of CNN without a lot of epochs by computing the best value of the flatness network parameter (p). In this regards the flatness network parameter threshold (p) has been investigated and a good performance of the activation function has been discovered at p = 4.5. We firstly used the MNIST and the CIFAR-10 datasets to trained and test the Alex-Net architecture model of convolutional neural network (CNN) and we showed better performances of Rectified Linear unit Memristor-like Activation Function compared to those of the literature. We noticed that the performance of Alex-Net also improved and the better performance was recorded when p = 4.5 with 99.50%, 99.25%, 98.81% for training, validation and testing accuracy respectively when using the MNIST. These results open the outcome to reduce the training time of neural networks when this activation function is used. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Activation function Artificial intelligence Deep learning Flatness network parameter threshold Memristive windows function Neural network

来源：评论

学校读者我要写书评

暂无评论

An Effective Networks Intrusion Detection Approach Based on Hybrid Harris Hawks and Multi-Layer Perceptron

arXiv

引用

arXiv 2024年

作者： Alazab, Moutaz Khurma, Ruba Abu Castillo, Pedro A. Abu-Salih, Bilal Martı´n, Alejandro Camacho, David Faculty of Artificial Intelligence Al-Balqa Applied University Amman Jordan Computer Science Department Faculty of MEU Research Unit Middle East University Amman Jordan Department of Computer Engineering Automation and Robotics University of Granada Granada Spain King Abdullah II School of Information Technology The University of Jordan Amman Jordan Department of Computer Systems Engineering Universidad Politécnica de Madrid Madrid Spain

This paper proposes an Intrusion Detection System (IDS) employing the Harris Hawks Optimization algorithm (HHO) to optimize Multilayer Perceptron learning by optimizing bias and weight parameters. HHO-MLP aims to select optimal parameters in its learning process to minimize intrusion detection errors in networks. HHO-MLP has been implemented using EvoloPy NN framework, an open-source Python tool specialized for training MLPs using evolutionary algorithms. For purposes of comparing the HHO model against other evolutionary methodologies currently available, specificity and sensitivity measures, accuracy measures, and mse and rmse measures have been calculated using KDD datasets. Experiments have demonstrated the HHO MLP method is effective at identifying malicious patterns. HHO-MLP has been tested against evolutionary algorithms like Butterfly Optimization Algorithm (BOA), Grasshopper Optimization Algorithms (GOA), and Black Widow Optimizations (BOW), with validation by Random Forest (RF), XGBoost. HHO-MLP showed superior performance by attaining top scores with accuracy rate of 93.17%, sensitivity level of 89.25%, and specificity percentage of 95.41%. © 2024, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Analysis, circuit realization and controls of an autonomous Morse jerk oscillator

引用

SeMA Journal 2021年第3期78卷 415-433页

作者： Ainamon, Cyrille Tamba, Victor Kamdoum Pone, Justin Roger Mboupda Kingni, Sifeu Takougang Malwe, Hubert Boudoue Orou, Jean Bio Chabi Institut de Mathématiques et de Sciences Physiques Université d’Abomey-Calavi B.P. 613 Porto Novo Benin Department of Telecommunication and Network Engineering IUT-Fotso Victor of Bandjoun University of Dschang PO Box 134 Bandjoun Cameroon Electrical Engineering Department of IUT-Fotso Victor of Bandjoun Research Unit of Automation and Applied Computer (RU-AIA) University of Dschang PO Box 134 Bandjoun Cameroon Department of Mechanical Petroleum and Gas Engineering Faculty of Mines and Petroleum Industries University of Maroua PO Box 46 Maroua Cameroon Department of Physics Faculty of Science University of Maroua PO Box 814 Maroua Cameroon

In this paper, an autonomous Morse jerk oscillator which is designed by converting an autonomous two-dimensional Morse oscillator to a jerk oscillator, is analysed. The stability of its unique equilibrium point reveals the existence of Hopf bifurcation. Periodic and chaotic oscillations, antimonotonicity, chaotic bubbles and coexisting attractors are generated in the proposed jerk oscillator. Then, this proposed jerk oscillator is implemented in PSIM software and realized in a printed circuit board to verify the numerical results. The experimental/PSIM results agree well with the numerical simulations. Moreover, it is possible to control partially or totally the amplitude of its signals by introducing two additional parameters in the rate-equations describing the proposed jerk oscillator. Furthermore based on the Routh–Hurwitz conditions and using a single linear feedback controller, the proposed jerk oscillator is controlled to its unique equilibrium point. Finally, the coexistence between periodic and chaotic attractors is destroyed and controlled to a desired trajectory thank to the linear augmentation method. © 2021, The Author(s), under exclusive licence to Sociedad Española de Matemática Aplicada.

关键词： Antimonotonicity Chaotic and coexisting attractors Control Electronic circuit realization Hopf bifurcation Morse jerk oscillator

来源：评论

学校读者我要写书评

暂无评论

Choosing a Suitable Requirement Prioritization Method: A Survey

arXiv

引用

arXiv 2024年

作者： Alhenawi, Esraa Awawdeh, Shatha Khurma, Ruba Abu García-Arenas, Maribel Castillo, Pedro A. Hudaib, Amjad Faculty of Information Technology Zarqa University Zarqa Jordan Applied Science Private University Amman Jordan MEU Research Unit Faculty of Information Technology Middle East University Amman11831 Jordan Department of Computer Engineering Automation and Robotics University of Granada Granada Spain King Abdullah II School for Information Technology The University of Jordan Amman Jordan

Software requirements prioritization plays a crucial role in software development. It can be viewed as the process of ordering requirements by determining which requirements must be done first and which can be done later. Powerful requirements prioritization techniques are of paramount importance to finish the implementation on time and within budget. Many factors affect requirement prioritization such as stakeholder expectations, complexity, dependency, scalability, risk, and cost. Therefore, finding the proper order of requirements is a challenging process. Hence, different types of requirements prioritization techniques have been developed to support this task. In this survey, we propose a novel classification that can classify the prioritization techniques under two major classes: relative and exact prioritization techniques class, where each class is divided into two subclasses. We depend in our classification on the way the value of ranking is given to the requirement, either explicitly as a specific value in the case of the exact prioritization techniques class, or implicitly in the case of the Relative prioritization technique class. An overview of fifteen different requirements prioritization techniques are presented and organized according to the proposed classification criteria’s. Moreover, we make a comparison between methods that are related to the same subclass to analyze their strengths and weaknesses. Based on the comparison results, the properties for each proposed subclass of techniques are identified. Depending on these properties, we present some recommendations to help project managers in the process of selecting the most suitable technique to prioritize requirements based on their project characteristics (number of requirements, time, cost, and accuracy). © 2024, CC BY.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Josephson junction based on high critical-temperature superconductors: analysis, microcontroller implementation, and suppression of coexisting and chaotic attractors

引用

The European Physical Journal B 2022年第9期95卷 1-13页

作者： Ngongiah, Isidore Komofor Ramakrishnan, Balamurali Natiq, Hayder Pone, Justin Roger Mboupda Kuiate, Gaetan Fautso Department of Physics Faculty of Science University of Bamenda Bamenda Cameroon Center for Nonlinear Systems Chennai Institute of Technology Chennai India Information Technology College Imam Ja’afar Al-Sadiq University Baghdad Iraq Research Unit of Automation and Applied Computer (RUAIA) Electrical Engineering Department of IUT-FV University of Dschang Bandjoun Cameroon Department of Physics Higher Teacher Training College University of Bamenda Bamenda Cameroon Department of Mechanical and Industrial Engineering National Higher Polytechnic Institute University of Bamenda Bamenda Cameroon

A Josephson junction (JJ) based on high critical-temperature superconductors described by a linear resistive–capacitive–inductance shunted junction (LRCLSJ) model with unharmonic current-phase relation (UCPR) is theoretically and experimentally investigated in this paper. The numerical simulations indicate that JJ based on high critical-temperature superconductors exhibits excitable mode, regular spiking, periodic bursting, relaxation oscillations, chaotic attractors, and coexisting attractors. The theoretical investigations are verified experimentally through the microcontroller implementation. In addition, the coexistence between chaotic and limit cycle attractors found in JJ based on high critical-temperature superconductors is controlled to the desired trajectory using the linear augmentation control method. Finally, analytical calculations and numerical simulations are carried out to show the serviceableness of the two designed single controllers in suppressing chaos in JJ based on high critical-temperature superconductors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A survey of power system coordinated control algorithms for stability enhancement

Progress in Engineering Science

引用

Progress in Engineering science 2024年第4期1卷

作者： Muluh, Fombu Andrew Sonfack, Lionel Leroy Pesdjock, Mathieu Jean Pierre Department of Electrical and Electronic Engineering National Higher Polytechnic Institute University of Bamenda P.O. Box 39 Bambili North West Region Cameroon Department of Electrical and Power Engineering Research Unit of Automation and Applied Computer Science IUT-FV Bandjoun University of Dschang P.O. Box 134 West Region Cameroon Cameroonian Association for Research and Innovation in Energy Technology and Environment P.O. Box 59 Ebolowa South Region Cameroon

In recent years, the increasing integration of renewable energy sources has led to the expansion of power grids and the increased proliferation of various types of controls. As a consequence, complications related to stability issues have increased. Hence, to sustain stability in future power grids, the present uncoordinated control approaches based on decentralized local control actions have to be abandoned for new methods based on the coordination of sub-controllers distributed across the power system. Within this new control paradigm, control is no longer based on purely localized tasks but rather a set of coordinated actions across different controllers within a local or wide area in which interplant communication is of paramount importance. This paper aims at reviewing and summarizing the vast variety of coordination strategies implemented in the design of power system controls for enhancing stability. The coordinated strategies are categorized based on their design techniques into conventional (linear analysis), optimization and artificial intelligence based algorithms. A second classification based on control architecture equally categorizes them into decentralized, centralized, distributed and hierarchical controls. A qualitative comparison of the coordinated strategies is presented and future outlooks are discussed. This state-of-the-art review on coordinated control presented in this paper is not reported in any of the published works with a similar level of details. © 2024 Elsevier B.V.

关键词： Control architecture Control techniques Coordinated control Power system control Power system stability

来源：评论

学校读者我要写书评

暂无评论

Roadmap on Quantum Thermodynamics

arXiv

引用

arXiv 2025年

作者： Campbell, Steve D’Amico, Irene Ciampini, Mario A. Anders, Janet Ares, Natalia Artini, Simone Auffèves, Alexia Oftelie, Lindsay Bassman Bettmann, Laetitia P. Bonança, Marcus V.S. Busch, Thomas Campisi, Michele Cavalcante, Moallison F. Correa, Luis A. Cuestas, Eloisa Dag, Ceren B. Dago, Salambô Deffner, Sebastian Del Campo, Adolfo Deutschmann-Olek, Andreas Donadi, Sandro Doucet, Emery Elouard, Cyril Ensslin, Klaus Erker, Paul Fabbri, Nicole Fedele, Federico Fiusa, Guilherme Fogarty, Thomás Folk, Joshua Guarnieri, Giacomo Hegde, Abhaya S. Hernández-Gómez, Santiago Hu, Chang-Kang Iemini, Fernando Karimi, Bayan Kiesel, Nikolai Landi, Gabriel T. Lasek, Aleksander Lemziakov, Sergei Monaco, Gabriele Lo Lutz, Eric Lvov, Dmitrii Maillet, Olivier Mehboudi, Mohammad Mendonça, Taysa M. Miller, Harry J.D. Mitchell, Andrew K. Mitchison, Mark T. Mukherjee, Victor Paternostro, Mauro Pekola, Jukka Perarnau-Llobet, Martí Poschinger, Ulrich Rolandi, Alberto Rosa, Dario Sánchez, Rafael Santos, Alan C. Sarthour, Roberto S. Sela, Eran Solfanelli, Andrea Souza, Alexandre M. Splettstoesser, Janine Tan, Dian Tesser, Ludovico Van Vu, Tan Widera, Artur Halpern, Nicole Yunger Zawadzki, Krissia School of Physics University College Dublin Belfield Dublin 4 Ireland Centre for Quantum Engineering Science and Technology University College Dublin Dublin 4 Ireland School of Physics Engineering and Technology University of York York United Kingdom York Centre for Quantum Technologies University of York York United Kingdom Boltzmanngasse 5 ViennaA-1090 Austria Institute of Physics and Astronomy University of Potsdam Potsdam14476 Germany Department of Physics and Astronomy University of Exeter ExeterEX4 4QL United Kingdom Department of Engineering Science University of Oxford Parks Road OxfordOX1 3PJ United Kingdom Università degli Studi di Palermo Dipartimento di Fisica e Chimica - Emilio Segrè via Archirafi 36 PalermoI-90123 Italy MajuLab CNRS-UCA-SU-NUS-NTU International Joint Research Laboratory France Centre for Quantum Technologies National University of Singapore Singapore117543 Singapore NEST Istituto Nanoscienze-CNR and Scuola Normale Superiore Pisa56127 Italy School of Physics Trinity College Dublin College Green Dublin 2 Ireland Gleb Wataghin Physics Institute The University of Campinas Campinas São Paulo13083-859 Brazil Quantum Systems Unit OIST Graduate University Okinawa Onna904-0495 Japan Department of Physics University of Maryland Baltimore County BaltimoreMD21250 United States Quantum Science Institute University of Maryland Baltimore County BaltimoreMD21250 United States Universidad de La Laguna La Laguna38203 Spain Departamento de Física Universidad de La Laguna La Laguna38203 Spain Jülich54245 Germany Department of Physics Indiana University BloomingtonIN47405 United States Department of Physics Harvard University 17 Oxford Street CambridgeMA02138 United States National Quantum Laboratory College ParkMD20740 United States Department of Physics and Materials Science University of Luxembourg LuxembourgL-1511 Luxembourg Donostia International Physics Center San SebastianE-20018 Spain Au

The last two decades has seen quantum thermodynamics become a well established field of research in its own right. In that time, it has demonstrated a remarkably broad applicability, ranging from providing foundational advances in the understanding of how thermodynamic principles apply at the nano-scale and in the presence of quantum coherence, to providing a guiding framework for the development of efficient quantum devices. Exquisite levels of control have allowed state-of-the-art experimental platforms to explore energetics and thermodynamics at the smallest scales which has in turn helped to drive theoretical advances. This Roadmap provides an overview of the recent developments across many of the field’s sub-disciplines, assessing the key challenges and future prospects, providing a guide for its near term progress. Copyright © 2025, The Authors. All rights reserved.

关键词： Temperature

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：