检索结果-内蒙古大学图书馆

International Conference on software, Knowledge Information, Industrial Management and applications (SKIMA)

作者： Khaled ELKarazle Valliappan Raman Caslon Chua Patrick Then Faculty of Engineering Computing and Science Swinburne University of Technology (Sarawak Campus) Sarawak Malaysia Department of Artificial Intelligence and Data Science Coimbatore Institute of Technology Tamil Nadu India Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia

The urgent need for early detection and intervention in colorectal cancer highlights the importance of automating colorectal polyp detection. Despite the use of deep learning techniques for polyp detection from medical images, these methods often struggle with issues such as skewed data distribution and class imbalances. In this study, we introduce PolyLite, a lightweight transformer-based model designed to balance performance and efficiency. PolyLite features a custom SegFormer encoder that takes advantage of its lightweight design, and a decoder that uses a multi-scale attention network (MA-NET) to achieve an optimal balance between accuracy and efficiency. To improve accuracy and reduce false negatives, we incorporate a reverse attention layer that effectively counteracts input mask attention during training. This refocuses the model's efforts to better learn non-polyp regions. PolyLite undergoes a two-stage training process, beginning with pre-training on the ImageNet dataset and then fine-tuning on the Kvasir-SEG dataset. We conduct rigorous evaluations on three complex datasets: CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB. Empirical results demonstrate PolyLite's superiority over existing techniques, as evidenced by its performance in terms of Intersection over Union and Dice scores. This validates its effectiveness and scalability in polyp segmentation, making complex and computationally intensive architectures unnecessary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative Ground-Space Communications via Evolutionary Multi-objective Deep Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Li, Jiahui Sun, Geng Wu, Qingqing Niyato, Dusit Kang, Jiawen Jamalipour, Abbas Leung, Victor C.M. The College of Computer Science and Technology Jilin University Changchun130012 China The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China The School of Automation Guangdong University of Technology Guangzhou510006 China The School of Electrical and Computer Engineering The University of Sydney SydneyNSW2006 Australia The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Department of Electrical and Computer Engineering The University of British Columbia VancouverV6T 1Z4 Canada

In this paper, we propose a distributed collaborative beamforming (DCB)-based uplink communication paradigm for enabling ground-space direct communications. Specifically, DCB treats the terminals that are unable to establish efficient direct connections with the low Earth orbit (LEO) satellites as distributed antennas, forming a virtual antenna array to enhance the terminal-to-satellite uplink achievable rates and durations. However, such systems need multiple trade-off policies that variously balance the terminal-satellite uplink achievable rate, energy consumption of terminals, and satellite switching frequency to satisfy the scenario requirement changes. Thus, we perform a multi-objective optimization analysis and formulate a long-term optimization problem. To address availability in different terminal cluster scales, we reformulate this problem into an action space-reduced and universal multi-objective Markov decision process. Then, we propose an evolutionary multi-objective deep reinforcement learning algorithm to obtain the desirable policies, in which the low-value actions are masked to speed up the training process. As such, the applicability of a onetime trained model can cover more changing terminal-satellite uplink scenarios. Simulation results show that the proposed algorithm outmatches various baselines, and draw some useful insights. Specifically, it is found that DCB enables terminals that cannot reach the uplink achievable threshold to achieve efficient direct uplink transmission, which thus reveals that DCB is an effective solution for enabling direct ground-space communications. Moreover, it reveals that the proposed algorithm achieves multiple policies favoring different objectives and achieving near-optimal uplink achievable rates with low switching frequency. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review of predictive analytics models for mental illness using machine learning algorithms

引用

Healthcare Analytics 2024年 6卷 100350-100350页

作者： Islam, Md. Monirul Hassan, Shahriar Akter, Sharmin Jibon, Ferdaus Anam Sahidullah, Md. Department of Software Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh Rising Research Lab Sheikh Bari Malancha Melandah Jamalpur Mymensingh 2012 Bangladesh Department of Computer Science and Engineering Gono Bishwabidyalay Savar Dhaka 1344 Bangladesh Department of Computer Science and Engineering Atish Dipankar University of Science and Technology Dhaka Bangladesh Department of Computer Science and Engineering IUBAT - International University of Business Agriculture and Technology Dhaka Bangladesh Department of Computer Science and Engineering Asian University of Bangladesh (AUB) Bangabandhu Road Tongabari Ashulia Dhaka 1349 Bangladesh

Our emotional, psychological, and social well-being are all parts of our mental health, influencing our thoughts, emotions, and behaviors. Mental health also influences how we respond to stress, interact with others, and make good or bad decisions. There has been growing interest in the use of machine learning for the early detection of mental illness. This study reviews the machine learning models, algorithms, and applications for the early detection of mental disease, particularly emphasizing the data modalities. We further propose a comprehensive methodology for assessing mental health that synergistically combines social media monitoring, data analytics from wearable devices, verbal polls, and individualized support. We provide an overview of the field's current state, highlight the potential benefits and challenges of using machine learning in mental health care, and a new taxonomy of mental disorders issues based on five domains of data types. We review existing research on using machine learning to detect and treat mental illness and discuss the implications for future research. Finally, the value of this work lies in its potential to provide a fast and accurate method for predicting the mental health status of a person, which may assist in the diagnosis and treatment of mental illness. © 2024 The Authors

关键词： Diagnosis Healthcare Machine learning classification Mental disorder taxonomy Mental illness prediction Mental illness treatment

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Efficacy of Machine Learning-Based Intrusion Detection Systems on an Imbalanced and Contemporary Dataset

Enhancing the Efficacy of Machine Learning-Based Intrusion D...

引用

Advanced Computing Technologies (ICoACT), International Conference on

作者： A. Kiruthikkumar N. Uma Maheswari D. David Neels Ponkumar A. Niyas Ahamed S. Nazrin Salma R. Saravanakumar Department of Master of Computer Application Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics Engineering (VLSI Technology) R.M.K. Engineering College Thiruvallur Tamil Nadu India General Engineering R.M.K. College of Engineering and Technology Thiruvallur Tamil Nadu India Iconix Software Solution Tirunelveli Tamil Nadu India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

As the Internet has increased in popularity, more computers are networked and becoming part of our daily lives. Common and less evident server vulnerabilities may be used by hackers to access systems and conduct complicated assaults. An Intrusion Detection System (IDs), a popular computer security tool, uses machine learning on a previously acquired dataset. The datasets were generated in distinct networks across brief periods and may not contain the latest information. They're bloated and can't hold enough data to survive an attack. Modern intrusion detection systems are less effective with inconsistent and outdated information for rare attack paths. This paper presents five machine-learning intrusion detection solutions. K Nearest Neighbor (KNN), Decision Tree (DT), Gradient Boosting (GB), Adaboost (AB), and Random Forest (RF) are used. The latest security dataset CSE-CIC-IDS2018 replaces earlier, more often-used datasets to improve Intrusion Detection Systems (IDS). An unbalanced dataset was selected. The imbalance ratio is reduced using the Synthetic Minority Oversampling Technique (SMOTE), a synthetic data model. The approach increases attack type-specific system performance while lowering false alarms and missing incursions. Minor classes increase their data amounts to reach the average data size. Experimental results demonstrate that the recommended strategy greatly enhances uncommon intrusion detection.

关键词： Radio frequency Adaptation models Runtime Intrusion detection Nearest neighbor methods Feature extraction Boosting Decision trees Random forests Testing

来源：评论

学校读者我要写书评

暂无评论

Boundary-Aware Contrastive Learning for Single-Source Domain Generalization in Medical Image Segmentation

Boundary-Aware Contrastive Learning for Single-Source Domain...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chenbin Zhang Zhiqiang Hu Shuyu Dai Qingyuan He Defeng Liu Kun Yan Ping Wang School of Computer Science Peking University Beijing China School of Electronics Engineering and Computer Science Peking University Beijing China Department of Radiology Peking University Third Hospital Beijing China Center for Reproductive Medicine Peking University Third Hospital Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Domain shift is a prevalent issue for medical imaging in both the cross-modality and cross-site manner. As a result, the research of domain generalization meets a significant need that requires no access to any samples in novel target domains. In this paper, we propose BACON, a boundary-aware contrastive learning framework for single-source domain generalization, which enjoys the advantages of both the data-driven methods (e.g. augmentation) and inductive bias methods (e.g. normalization and whitening). BACON designs a novel data augmentation by integrating the bidirectional CutMix with the RandConv and introduces inductive bias through an innovative contrastive learning loss function. Experiments on both the cross-modality and cross-site scenario demonstrate the effectiveness, where BACON achieves a substantial improvement of 33.51% and 33.47% Dice scores over the baseline in the BraTS 2020 dataset and sets the new state of the art on the Prostate Cross-site dataset with an average Dice score of 72.51%.

关键词： Deep learning Image segmentation Adaptation models Contrastive learning Data augmentation Robustness Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fire Detection for Industrial and Environmental Safety Using IoT-Integrated Vision Sensors and Residual Clutch Attention Network and Depthwise Distinguishable Convolutional Neural Networks

Enhanced Fire Detection for Industrial and Environmental Saf...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： D.Christy Sujatha Priyanshu Singh C. Vallikannu Ravi Varman Skanda M G T. Gavaskar Department of Software Engineering Periyar Maniammai Institute of Science & Technology Thanjavur Tamil Nadu India Department of Computer Science and Engineering R.V college of engineering Bangalore Karnataka India Department of Humanities and Sciences Rajalakshmi Engineering College Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Karpagam academy of Higher Education Coimbatore Tamil Nadu India Department of Industrial and Production Engineering SJCE JSS Science and Technology University Mysore Karnataka India Department of Mechanical Engineering St. Joseph's College of Engineering Chennai Tamil Nadu India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Fire detection is an important factor in improved safety in industrial and environmental conditions. The conventional flame detectors, largely relying on heat and smoke detectors, have drawbacks of time lag, low sensitivity, and low coverage when compared with our requirement in large industrial scenes and vast natural terrains vulnerable to fire occurrence. These systems are highly unsuitable for dynamic and high-risk situations as they require a higher accuracy and a faster reaction time for the alarms to be efficient as is now the case due to the aforementioned reasons. In an attempt to remedy these limitations, this research introduces a fire detection system using IoT and vision sensors that combines a RCAN with DDCNN. This architecture is tuned using the Crayfish Optimization Algorithm (COA), which seeks to improve model parameter to improve response time and accuracy. By incorporating feedbacks from sensors placed at its different parts and reading from the environment, the RCAN-DDCNN model can quickly identify the fire patterns and respond by activating the sprinkler systems as well as setting off alarms. The proposed system presents a superior option for fire detecting because it is scalable and adaptive and it provides high degree of precision, making it an optimal development in fire detection technology for industry and environment. The introduced approach attains higher accuracy as 99%.

关键词： Support vector machines Accuracy Vision sensors Sensor systems Stability analysis Safety Convolutional neural networks Time factors Optimization Smoke detectors

来源：评论

学校读者我要写书评

暂无评论

A Novel based Hybrid smart System for detecting the cyber-attacks on IOT’s

A Novel based Hybrid smart System for detecting the cyber-at...

引用

Artificial Intelligence and Smart Communication (AISC), International Conference on

作者： K. Juliana Gnanaselvi Surendra Kumar Shukla Keerthipati Kumar Anita Gehlot Tarun Jaiswal B. T. Geetha Department of Computer Science Rathinam College of Arts and Science Coimbatore Tamil Nadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Information Technology University of Technology and Applied Science- Al Mussnna Oman Uttaranchal Institute of Technology Uttaranchal University India Department of Computer Application National Institute of Technology Raipur (C.G.) Department of ECE Saveetha School of Engineering SIMATS Tamil Nadu India

The Iot technology (IoT) is rapidly advancing sufficiently that it might have a larger effect on huge industrial infrastructure and everyday routines. However, this became the focus of fraudsters, whom made IoT into such a prey for their misbehaviour, thereby potentially opening the door for an assault on the computer systems. Have used a traditional intrusion detection device to manage the Iot network is problematic because of the enormous variety and quantity of IoT devices. A revolutionary aggregation Interdisciplinary Detection System (HIDS) that merges a C5 predictor with the a One Category Classification Algorithm is built to guard IoT devices. It project's goal is to find threats that can be inhibited with high classification certainty and low completely bogus rates, for both storing and accessing and negligible vulnerabilities. The User database, consisting includes include legal IoT data stream and other varieties of assaults, is employed to assess the specified HIDS. Studies show that when combined with SIDS and Assistance methodologies, the proposed hybrid IDS provides a higher accuracy results and a smaller percentage of false positives.

关键词： Fault diagnosis Law Databases Fault detection Stacking Ecosystems Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Distributed Analytics in Smart Grids with Edge Computing and Computational Intelligence

Distributed Analytics in Smart Grids with Edge Computing and...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Apoorva Joshi Preethi D Amandeep Gill Master of Computer Application Noida Institute of Engineering & Technology Greater Noida Uttar Pradesh India Department of Computer Science Jain (Deemed to be University) Bangalore India Department of R&D Cell Vivekananda Global University Jaipur India

Conventional methods like classification or clustering have limits when it comes to handling the complex task for dispersed data mining across heterogeneous sources and divergent data formats. This is especially true in scenarios where stochastic models or mathematical formulas may not be feasible. Data centralization is a prevalent trend that exacerbates problems including communication channel congestion and privacy difficulties related to sensitive data flows. In order to overcome these obstacles, this paper presents the Distributed Academic Engine (DAE), an adaptive edge-based scattered analytic engine designed for distributed networks. The DAE routinely breaks down and divides computations that need data from multiple sources among the nodes that are already in place, enabling the sharing of partial results without disclosing the original data. To get the full expression output, the master node combines these partial results. The expression is decomposed and processing jobs are distributed among nodes using three computational intelligence techniques: genetic algorithm, genetic algorithm using evolution control, the particle swarm optimization. This method's effectiveness is illustrated with a case study on smart grid KPI identification, which shows a noteworthy (over 91%) decrease in communication messages over conventional approaches. This demonstrates how well the suggested method works to reduce the difficulties related to distributed data mining.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Based Advance Image Captioning Improved Feature Attention

Remote Sensing Based Advance Image Captioning Improved Featu...

引用

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Ammara Sattar Muhammad Assam Tahani Jaser Alahmadi Uzair Aslam Bhatti Hao Tang Muhammad Aamir Harbin Engineering University Harbin China Department of Software Engineering University of Science and Technology Bannu KPK Pakistan College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia School of information and communication engineering Hainan University Haikou China College of Computer Science Huanggang Normal University Huanggang China

ISBN: (数字)9798350350890

ISBN: (纸本)9798350350906

In the domain of image description generation, the focal point mechanism is crucial for highlighting the most relevant features within an image, thereby influencing the quality of generated descriptions. To address this challenge, we introduce an innovative optimization module called the Enhanced Focal (EF) mechanism, which builds upon the traditional multi-head focal point mechanism. The EF module is designed to assess the correlation levels between objects within an image, thereby guiding the process of subtitle generation more effectively. The EF mechanism integrates the output of the multi-head focal point mechanism with the current context (i.e., the query) to generate two components: an “information vector” and an “attention gate.” The “attention gate” is then applied to the “information vector” to create a refined focal point mechanism. This refined mechanism undergoes element-wise multiplication with the “information vector,” producing attention information that reveals a strong correlation between the target and the background in the image. This process leverages the Long Short-Term Memory (LSTM) mechanism to enhance the model's capability to capture intricate relationships. Upon training and evaluating our enhanced model on the MS COCO dataset, we observed significant improvements in key evaluation metrics. The BLEU-1 and METEOR scores reached 73.01% and 28.81%, respectively, showcasing the effectiveness of the proposed EF mechanism in improving image description generation.

关键词： Training Correlation Accuracy Logic gates Vectors Stability analysis Pattern recognition Long short term memory Optimization Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Covering

arXiv

引用

arXiv 2023年

作者： Hou, Fei Chen, Xuhui Wang, Wencheng Qin, Hong He, Ying State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Department of Computer Science Stony Brook University New York United States School of Computer Science and Engineering Nanyang Technological University Singapore

In this paper, we propose a new method, called DoubleCoverUDF, for extracting the zero level-set from unsigned distance fields (UDFs). DoubleCoverUDF takes a learned UDF and a user-specified parameter r (a small positive real number) as input and extracts an iso-surface with an iso-value r using the conventional marching cubes algorithm. We show that the computed iso-surface is the boundary of the r-offset volume of the target zero level-set S, which is an orientable manifold, regardless of the topology of S. Next, the algorithm computes a covering map to project the boundary mesh onto S, preserving the mesh's topology and avoiding folding. If S is an orientable manifold surface, our algorithm separates the double-layered mesh into a single layer using a robust minimum-cut post-processing step. Otherwise, it keeps the double-layered mesh as the output. We validate our algorithm by reconstructing 3D surfaces of open models and demonstrate its efficacy and effectiveness on synthetic models and benchmark datasets. Our experimental results confirm that our method is robust and produces meshes with better quality in terms of both visual evaluation and quantitative measures than existing UDF-based methods. The source code is available at https://***/jjjkkyz/DCUDF. © 2023, CC BY-NC-ND.

关键词： Topology

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：