检索结果-内蒙古大学图书馆

IEEE Conference on Energy internet and Energy System Integration (EI2)

作者： Harriet Agobah Olusola Bamisile Dongsheng Cai Delanyo Kwame Bensah Kulevome Benjamin Darkwa Nimo Qi Huang Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Technology Research Center Chengdu University of Technology Chengdu China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

This work proposes a Convolutional neural network (CNN)-based framework for estimating basic facial expressions, which achieves state-of-the-art results and runs in real-time on an android-based device to fulfill the target of intelligent human-computer interaction (HCI). A new CNN architecture is modeled using MobileNetV1 for the facial expression recognition task. CNN training often necessitates a large amount of data. However, most current facial expression datasets fall short of this requirement, making it difficult to train a deep CNN with insufficient data. Using a model pre-trained on ImageNet, and a supplementary dataset (such as FER-2013) in supervised two-stage transfer learning addresses the issue of small datasets (such as JAFFE and CK+) to a great extent. Furthermore, to improve the framework's performance, a center loss is used in conjunction with the softmax loss as a joint supervision signal for CNN training optimization. Validation is carried out on two publicly available datasets, JAFFE and CK+. The model is evaluated based on the average accuracy, precision, recall, F1-score, and confusion matrix. An evaluation baseline for the CK+ dataset includes eight scenarios. As a whole, the proposed method outperforms current state-of-the-art methods on both JAFFE and CK+.

关键词： Training Human computer interaction Face recognition Transfer learning System integration Real-time systems Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MACCoM: A multiple attention and convolutional cross-mixer framework for detailed 2D biomedical image segmentation

引用

Computers in Biology and Medicine 2024年 179卷 108847-108847页

作者： Ejiyi, Chukwuebuka Joseph Qin, Zhen Ejiyi, Makuachukwu Bennedith Ukwuoma, Chiagoziem Ejiyi, Thomas Ugochukwu Muoka, Gladys Wavinya Gyarteng, Emmanuel S.A. Bamisile, Olusola O. Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Sichuan Chengdu China Pharmacy Department University of Nigeria Nsukka Enugu State Nsukka Nigeria Department of Pure and Industrial Chemistry University of Nigeria Nsukka Enugu State Nsukka Nigeria School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Research Center Chengdu University of Technology Chengdu China

The UNet architecture, which is widely used for biomedical image segmentation, has limitations like blurred feature maps and over- or under-segmented regions. To overcome these limitations, we propose a novel network architecture called MACCoM (Multiple Attention and Convolutional Cross-Mixer) – an end-to-end depthwise encoder-decoder fully convolutional network designed for binary and multi-class biomedical image segmentation built upon deeperUNet. We proposed a multi-scope attention module (MSAM) that allows the model to attend to diverse scale features, preserving fine details and high-level semantic information thus useful at the encoder-decoder connection. As the depth increases, our proposed spatial multi-head attention (SMA) is added to facilitate inter-layer communication and information exchange, enabling the network to effectively capture long-range dependencies and global context. MACCoM is also equipped with a convolutional cross-mixer we proposed to enhance the feature extraction capability of the model. By incorporating these modules, we effectively combine semantically similar features and reduce artifacts during the early stages of training. Experimental results on 4 biomedical datasets crafted from 3 datasets of varying modalities consistently demonstrate that MACCoM outperforms or matches state-of-the-art baselines in the segmentation tasks. With Breast Ultrasound Image (BUSI), MACCoM recorded 99.06 % Jaccard, 77.58 % Dice, and 93.92 % Accuracy, while recording 99.50 %, 98.44 %, and 99.29 % respectively for Jaccard, Dice, and Accuracy on the Chest X-ray (CXR) images used. The Jaccard, Dice, and Accuracy for the High-Resolution Fundus (HRF) images are 95.77 %, 74.35 %, and 95.95 % respectively. The findings here highlight MACCoM's effectiveness in improving segmentation performance and its valuable potential in image analysis. © 2024 Elsevier Ltd

关键词： Mixers (machinery)

来源：评论

学校读者我要写书评

暂无评论

A Tokenized Blockchain-Based Energy Eco-System Over Integrated Automated Market Makers

SSRN

引用

SSRN 2024年

作者： Adjei-Arthur, Bonsu Bamisile, Olusola Xia, Qi da Silva Tavares, Eliezer Eliezer Gao, Jianbin Xia, Hu Chengdu611731 China Blockchain Research Institute of UESTC-Chengdu Jiaozi Financial Holding Group Co.Ltd Chengdu610095 China Sichuan Provincial Key Lab for Power Systems Wide-Area Measurements and Control University of Electronic Science and Technology of China Sichuan Chengdu China Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Research Center Chengdu University of Technology Sichuan 610059 China

In a complex system of multiple entities coming together and transacting energy from various sources, incentivization and energy utilization are difficult to achieve due to inefficiencies in current mechanisms set up to generate, distribute, utilize, and manage energy within varying ecosystems. We provide a solution to this by proposing a tokenized blockchain-based renewable/non-renewable energy ecosystem built on Automated Market Makers with an underlying Constant Function *** this work, we proved the feasibility of achieving a more efficient means of trading, controlling, and managing energy from multiple RE/NRE energy sources using AMMs. In this approach, we remove the need for buyers and sellers’ influence in the energy market and provide an automated means of ensuring energy flow, pricing, and regulation without the need for third parties. We were able to maintain the decarbonization degree of the entire system through the deployment of the decarbonization mechanism at a cost of 584,213 Wei, proving a self-realizing decarbonization mechanism. We observed a cost of 1,255,219 Wei for both RE/NRE participants to engage the network, showing a faster means of transacting among energy parties. A cheaper cost of 2,497,561 Wei was achieved for setting up the network for trading, a cost of 2,500,666 Wei for rebalancing energy prices, and a cost of 1,836,918 Wei for the management of the entire network. Our results thus prove the ability of our proposed idea to ensure the effective generation, control, and distribution of energy across energy ecosystems. It also offers flexibility to address the complexity within energy ecosystems. Its incentivization mechanism ensures the continuous generation of rewards, ensuring the continuity of energy systems achieved by leveraging the transparency inherent in token mechanisms in blockchain technology. © 2024, The Authors. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Polynomial-SHAP analysis of liver disease markers for capturing of complex feature interactions in machine learning models

引用

Computers in Biology and Medicine 2024年 182卷 109168-109168页

作者： Ejiyi, Chukwuebuka Joseph Cai, Dongsheng Ejiyi, Makuachukwu B. Chikwendu, Ijeoma A. Coker, Kenneth Oluwasanmi, Ariyo Bamisile, Oluwatoyosi F. Ejiyi, Thomas U. Qin, Zhen College of Nuclear Technology and Automation Engineering Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Research Center Chengdu University of Technology Sichuan Chengdu China Pharmacy Department University of Nigeria Nsukka Enugu State Nsukka Nigeria School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China Department of Electrical and Electronic Engineering Ho Technical University Ghana Ghana Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Sichuan Chengdu China Department of Pure and Industrial Chemistry University of Nigeria Nsukka Enugu State Nsukka Nigeria

Liver disease diagnosis is pivotal for effective patient management, and machine learning techniques have shown promise in this domain. In this study, we investigate the impact of Polynomial-SHapley Additive exPlanations analysis on enhancing the performance and interpretability of machine learning models for liver disease classification. Our results demonstrate significant improvements in accuracy, precision, recall, F1_score, and Matthews correlation coefficient across various algorithms when polynomial- SHapley Additive exPlanations analysis is applied. Specifically, the Light Gradient Boosting Machine model achieves exceptional performance with 100 % accuracy in both scenarios. Furthermore, by comparing the results obtained with and without the approach, we observe substantial differences in the performance, highlighting the importance of incorporating Polynomial-SHapley Additive exPlanations analysis for improved model performance. The Polynomial features and SHapley Additive exPlanations values also enhance the interpretability of machine learning models by capturing complex feature interactions, enabling users to gain deeper insights into the underlying mechanisms driving the diagnosis. Moreover, data rebalancing using Synthetic Minority Over-sampling Technique and parameter tuning were employed to optimize the performance of the models. These findings underscore the significance of employing this analytical approach in machine-learning-based diagnostic systems for liver diseases, offering superior performance and enhanced interpretability for informed decision-making in clinical practice. © 2024 Elsevier Ltd

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Rethinking Image Generation From Scene Graphs With Attention Mechanism

Rethinking Image Generation From Scene Graphs With Attention...

引用

Computer Communication and Information Systems (CCCIS), International Conference on

作者： Chikwendu Ijeoma Amuche Xiaoling Zhang Chiagoziem Chima Ukwuoma Isaac Adjei-Mensah Assila Abdallah Abdou Chikwendu Chinyere Onyedikachi School of Information and Communication Engineering dept. University of Electronic Science and Technology of China Chengdu China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan P.R. China School of Management and Economics University of Electronic Science and Technology of China Chengdu China Department of Guidance and Counseling University of Port Harcourt Port Harcourt Nigeria

ISBN: (数字)9798350389548

ISBN: (纸本)9798350389555

The paper titled “Rethinking Image Generation from Scene Graphs with Attention Mechanism” addresses the limitation of existing methods that generate images from scene graphs. While the previous method serves as the network backbone to recent architectures, when applied alone, it struggles to accurately reproduce complex sentences with multiple objects and relationships, thus weakening the accurate prediction when used as a network backbone to a new model. In addressing this limitation, this paper proposes a new method that explicitly reasons about objects and their relationships by generating images from scene graphs. Just like the initial approach, the proposed model utilizes graph convolution to process input graphs and predicts bounding boxes and segmentation masks for objects to create a scene layout. In contrast, however, it converts the layout into an image using an attention-based cascaded refinement network. The proposed attention mechanism helps to selectively focus on certain parts of the refined image, enhancing their importance. Furthermore, to help maintain the fidelity and quality of the generated images, the proposed model is trained adversarialy against a pair of discriminators. Generated results - qualitative and quantitative results demonstrate the effectiveness of the method in generating complex images with multiple objects based on Visual Genome and COCO-Stuff datasets. The proposed method shows promising results in generating complex images and addresses the limitation of previous methods in faithfully reproducing scenes with multiple objects.

关键词： Training Visualization Image segmentation Attention mechanisms Accuracy Image synthesis Layout

来源：评论

学校读者我要写书评

暂无评论

Fracture Analysis of Fractured Sandstone Based on Multiple Parameters

SSRN

引用

SSRN 2024年

作者： Zhu, Xing He, Chunlei Zhu, Hao Fan, Jie State Key Laboratory of Geohazard Prevention and Geoenvironment Protection Chengdu University of Technology Chengdu610059 China College of Environment and Civil Engineering Chengdu University of Technology Chengdu610059 China College of Computer and Cyber Security Chengdu University of Technology Chengdu610059 China Sichuan Engineering Technology Research Center of Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Chengdu610059 China

To understand the deformation and fracture characteristics of fractured rock masses, a systematic experimental study was carried out on sandstone samples with various prefabricated cracks. Acoustic emission and digital image correlation technology were employed to analyze the failure mechanism and instability precursor of the fractured rock masses. The results indicate that the sandstone samples with double fractures exhibit stress drop behavior prior to failure, with the timing and magnitude of these drops varying according to fracture angle. Analysis of acoustic emission count rate and energy indicates that acoustic emission activity begins to fluctuate before 70% of peak stress is reached, with the count rate being particularly sensitive to the internal changes within the fractured rock mass. Five types of crack development were observed: wing cracks, oblique secondary cracks, coplanar secondary cracks, out-of-plane shear cracks, and out-of-plane tensile cracks. An image coefficient of variation (GCV), based on image gray characteristics, was introduced using the characteristic parameter of the image gray histogram. The GCV curve demonstrates a sudden change prior to the instability of fractured sandstone. For sandstone samples with fracture dip angles of 30°, 45°, 60°, and 75°, the time differences between the abrupt change point of GCV curve and the final failure is 43s, 36s, 28s, and 4s, respectively. This characteristic behavior can be used for effective short-term prediction of rock fracture instability. © 2024, The Authors. All rights reserved.

关键词： Image correlation

来源：评论

学校读者我要写书评

暂无评论

MuTCELM: An optimal multi-TextCNN-based ensemble learning for text classification

引用

Heliyon 2024年第19期10卷 e38515页

作者： Agbesi, Victor Kwaku Chen, Wenyu Yussif, Sophyani Banaamwini Ukwuoma, Chiagoziem C. Gu, Yeong Hyeon Al-antari, Mugahed A. School of Computer Science and Engineering University of Electronic Science and Technology of China No. 2006 Xiyuan Ave West Hi-Tech Zone Sichuan Chengdu China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology No. 610059 Sichuan Chengdu China Department of Artificial Intelligence and Data Science College of AI Convergence Daeyang AI Center Sejong University Seoul 05006 South Korea

Feature extraction plays a critical role in text classification, as it converts textual data into numerical representations suitable for machine learning models. A key challenge lies in effectively capturing both semantic and contextual information from text at various levels of granularity while avoiding overfitting. Prior methods have often demonstrated suboptimal performance, largely due to the limitations of the feature extraction techniques employed. To address these challenges, this study introduces Multi-TextCNN, an advanced feature extractor designed to capture essential textual information across multiple levels of granularity. Multi-TextCNN is integrated into a proposed classification model named MuTCELM, which aims to enhance text classification performance. The proposed MuTCELM leverages five distinct sub-classifiers, each designed to capture different linguistic features from the text data. These sub-classifiers are integrated into an ensemble framework, enhancing the overall model performance by combining their complementary strengths. Empirical results indicate that MuTCELM achieves average improvements across all datasets in accuracy, precision, recall, and F1-macro scores by 0.2584, 0.2546, 0.2668, and 0.2612, respectively, demonstrating significant performance gains over baseline models. These findings underscore the effectiveness of Multi-TextCNN in improving model performance relative to other ensemble methods. Further analysis reveals that the non-overlapping confidence intervals between MuTCELM and baseline models indicate statistically significant differences, suggesting that the observed performance improvements of MuTCELM are not attributable to random chance but are indeed statistically meaningful. This evidence indicates the robustness and superiority of MuTCELM across various languages and text classification tasks. © 2024 The Author(s)

关键词： Deep learning Ensemble learning Feature extraction Multi-TextCNN Text classification

来源：评论

学校读者我要写书评

暂无评论

Towards renewables development: Review of optimization techniques for energy storage and hybrid renewable energy systems

引用

Heliyon 2024年第19期10卷 e37482页

作者： Bamisile, Oluwatoyosi Cai, Dongsheng Adun, Humphrey Dagbasi, Mustafa Ukwuoma, Chiagoziem C. Huang, Qi Johnson, Nathan Bamisile, Olusola College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Engineering Technology Research Centre for Industrial Internet Intelligent Monitoring and Application Sichuan 610059 China Energy Systems Engineering Department Cyprus International University Haspolat-Lefkosa Mersin 10 Turkey Centre for Environmental Policy Imperial College London United Kingdom Energy and Environmental Science Division CEPMLP University of Dundee Scotland United Kingdom

As global energy demand and warming increase, there is a need to transition to sustainable and renewable energy sources. Integrating different systems to create a hybrid renewable system enhances the overall adoption and deployment of renewable energy resources. Given the intermittent nature of solar and wind, energy storage systems are combined with these renewable energy sources, to optimize the quantity of clean energy used. Thus, various optimization strategies have been developed for the integration and operation of these hybrid renewable energy systems. Existing studies have either reviewed hybrid renewable energy systems or energy storage systems, however, these studies ignored energy storage systems integrated with hybrid renewable energy systems. This study offers a comprehensive analysis of the optimization methods used in hybrid renewable energy systems (HRES) integrated with energy storage systems (ESS). We examined the optimization models used in the integration of HRES and ESS, their objectives, and the common constraints. Based on our review, capacity and CO₂ emissions constraints were frequently used in hybrid optimization techniques that are effective approaches for integrating HRES and ESS. This research supports the move towards sustainable, clean energy solutions by combining an analysis of energy storage techniques with the optimization of hybrid renewable energy systems. © 2024 The Authors

关键词： Energy storage Energy storage techniques Hybrid energy System Intermittent energy sources Optimization

来源：评论

学校读者我要写书评

暂无评论

ResfEANet: ResNet-fused External Attention Network for Tuberculosis Diagnosis using Chest X-ray Images

引用

Computer Methods and Programs in Biomedicine Update 2024年 5卷

作者： Ejiyi, Chukwuebuka Joseph Qin, Zhen Nnani, Ann O Deng, Fuhu Ejiyi, Thomas Ugochukwu Ejiyi, Makuachukwu Bennedith Agbesi, Victor Kwaku Bamisile, Olusola Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China College of Environmental Science and Engineering Hohai University Nanjing China Department of Pure and Industrial Chemistry University of Nigeria Nsukka Enugu Nigeria Pharmacy Department University of Nigeria Nsukka Enugu Nigeria School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Technology Research Centre Chengdu University of Technology Chengdu China

Pulmonary tuberculosis (TB), the most prevalent form of TB, remains a major global public health concern, contributing to more than a million deaths each year. The accurate and timely diagnosis of this disease is of paramount importance for effective control and treatment. Chest X-ray (CXR) images have emerged as a valuable tool for screening lung diseases, including TB, owing to their cost-effectiveness and non-invasiveness. Despite advancements in technology, the challenges associated with interpreting CXR images persist, primarily due to the scarcity of trained radiologists. This underscores the pressing need for an automated and cost-effective computer-aided system capable of diagnosing TB, assisting medical practitioners in distinguishing between TB-positive and negative CXR scans. In response to this need, we introduce an innovative approach called ResNet-fused External Attention Network (ResfEANet). This network excels in accurately classifying TB from CXR images, achieving remarkable levels of accuracy and sensitivity. ResfEANet is built upon ResNet and incorporates an External Attention mechanism, albeit with fewer residual network blocks than ResNet-50 resulting in a relatively shallow network with fewer layers. This approach proves highly effective in feature extraction and yields competitive results in the classification of TB. Our method was employed to train a model that demonstrated an impressive accuracy rate of 97.59% and a remarkable sensitivity of 100% in binary classification tasks with optimal computational cost. These outcomes suggest that our proposed approach has the potential to serve as a valuable secondary tool in clinical decision-making, providing crucial assistance to radiologists and healthcare professionals. © 2023

关键词： Chest X-ray images External Attention ResfEANet ResNet Tuberculosis

来源：评论

学校读者我要写书评

暂无评论

The complementary role of carbon dioxide removal: A catalyst for advancing the COP28 pledges towards the 1.5 °C Paris Agreement target

引用

Science of the Total Environment 2024年 947卷 174302页

作者： Acen, Caroline Bamisile, Olusola Cai, Dongsheng Ukwuoma, Chiagoziem C. Obiora, Sandra Huang, Qi Uzun Ozsahin, Dilber Adun, Humphrey College of Nuclear Science and Automation Engineering Sichuan Industrial Internet Intelligent Monitoring and Application Research Center Chengdu University of Technology Sichuan Chengdu China Centre for Environmental Policy Imperial College London United Kingdom Leeds Business School Leeds Beckett University LeedsLS1 3HE United Kingdom Electrical Engineering Department Southwest University of Science and Technology Sichuan Maiyang China Department of Medical Diagnostic Imaging College of Health Science University of Sharjah Sharjah United Arab Emirates Research Institute for Medical and Health Sciences University of Sharjah Sharjah United Arab Emirates Operational Research Centre in Healthcare Near East University TRNC Nicosia Mersin 1099138 Turkey Energy and Environmental Science Division University of Dundee Scotland United Kingdom

As the imperative to address climate change becomes more pressing, there is an increasing focus on limiting global temperature increase to 1.5 °C by the end of the century relative to pre-industrial levels. During the recent Conference of Parties (COP28), nations committed to tripling renewable energy generation to a minimum of 11,000 GW by 2030 and increasing the global annual energy efficiency from 2 % to 4 % annually until 2030. Additionally, the Food and Agricultural Organization (FAO) introduced a roadmap to transition the Agri-food system from a net emitter to a carbon sink. The role of carbon dioxide removal (CDR) is important;first to accelerate the near-term reduction in net emissions, counterbalance residual emissions at the point of net-zero by mid-century, and sustain large net negative emissions beyond mid-century to return warming to safe levels after decades of temporal overshoot. This paper assesses the impact of the COP 28 agreements, alongside the complementary role of CDR on emission levels, energy structure, land use, and global warming temperature. The findings indicate that implementing the COP28 pledges and FAO roadmap leads to a warming temperature of 2 °C, falling short of the ambitious 1.5 °C temperature limit. Likewise, more stringent actions on transitioning away from fossil plants is a high-priority mitigation action which drives significant emissions reduction. The modelled result shows that Agricultural soil carbon and biochar contribute 47–58 % share of the total CDR deployed in the stylized scenarios. In conclusion, CDR can expedite climate goals but must complement emission reduction efforts;hence, the transition away from fossil fuels should prompt the development of detailed roadmaps. Also, more global efforts should be placed on nature-based CDR methods, as they offer diverse co-benefits. © 2024 Elsevier B.V.

关键词： Global warming

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：