检索结果-内蒙古大学图书馆

BlindType: Eyes-free text entry on handheld touchpad by leveraging thumb's muscle memory

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2017年第2期1卷 1–24页

作者： Lu, Yiqin Yu, Chun Yi, Xin Shi, Yuanchun Zhao, Shengdong Department of Computer Science and Technology Tsinghua University Tsinghua National Laboratory for Information Science and Technology Beijing Key Lab of Networked Multimedia China National University of Singapore Singapore

Eyes-free input is desirable for ubiquitous computing, since interacting with mobile and wearable devices often competes for visual attention with other devices and tasks. In this paper, we explore eyes-free typing on a touchpad using one thumb, wherein a user taps on an imaginary QWERTY keyboard while receiving text feedback on a separate screen. Our hypothesis is that users can transfer their typing ability obtained from visible keyboards to eyes-free use. We propose two statistical decoding algorithms to infer users' eyes-free input: the absolute algorithm and the relative algorithm. The absolute algorithm infers user input based on the absolute position of touch endpoints, while the relative algorithm infers based on the vectors between successive touch endpoints. Evaluation results showed users could achieve satisfying performance with both algorithms. Text entry rate was 17-23 WPM (words per minute) depending on the algorithm used. In comparison, a baseline cursor-based text entry method yielded only 7.66 WPM. In conclusion, our research demonstrates for the first time the feasibility of thumb-based eyes-free typing, which provides a new possibility for text entry on ubiquitous computing platforms such as smart TVs and HMDs. © 2017 Association for Computing Machinery.

关键词： Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

On the Performance of CNN and GAN models for Melanoma Classification 2

On the Performance of CNN and GAN models for Melanoma Classi...

引用

2nd International Conference on Artificial Intelligence and Signal Processing, AISP 2022

作者： Joson, Nikhil Nair, Madhu S. Artificial Intelligence & Computer Vision Lab Department of Computer Science Cochin University of Science and Technology Kerala Kochi682022 India

ISBN: (纸本)9781665442909

Melanoma is the most harmful form of skin cancer and they emerge from melanocytes, a type of pigment-producing cells. Melanomas usually occur on the skin;they mostly form around the back for men, whereas the common place for women are legs. Once formed, symptoms of melanoma might include an increase in the size of some mole with irregular edges, or itchiness or changes in its color, etc. This paper reviews the latest research works on melanoma classification using CNN. The performance analysis of the state-of-the-art methods is done focusing only on the binary classification of melanoma. The dataset used for the performance analysis is based on SIIM-ISIC Melanoma Classification Challenge 2020, where the task was to identify melanoma using images of skin lesions by predicting a binary target for each image. The main intent of this study is to review the state-of-the-art deployments which identifies the recent research trends, challenges, and newer domains, like Generative Adversarial Networks (GAN) for melanoma classification and scrutinize the existing solutions for melanoma detection. © 2022 IEEE.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Classification and Comprehension of Software Requirements Using Ensemble Learning

引用

computers, Materials & Continua 2024年第8期80卷 2839-2855页

作者： Jalil Abbas Arshad Ahmad Syed Muqsit Shaheed Rubia Fatima Sajid Shah Mohammad Elaffendi Gauhar Ali School of Computer Science and Technology Anhui UniversityHefei230039China School of Computing Sciences Pak Austria FachhochschuleInstitute of Applied Sciences and TechnologyHaripur22620Pakistan Department of Computer Science and IT University of LahoreLahore55150Pakistan Department of Computer Science Emerson UniversityPunjabMultan60000Pakistan EIAS(Emerging Intelligent Autonomous Systems)Data Science Lab Prince Sultan UniversityRiyad12435Saudi Arabia

The software development process mostly depends on accurately identifying both essential and optional ***,user needs are typically expressed in free-form language,requiring significant time and human resources to translate these into clear functional and non-functional *** address this challenge,various machine learning(ML)methods have been explored to automate the understanding of these requirements,aiming to reduce time and human ***,existing techniques often struggle with complex instructions and large-scale *** our study,we introduce an innovative approach known as the Functional and Non-functional Requirements Classifier(FNRC).By combining the traditional random forest algorithm with the Accuracy Sliding Window(ASW)technique,we develop optimal sub-ensembles that surpass the initial classifier’s accuracy while using fewer *** results demonstrate that our FNRC methodology performs robustly across different datasets,achieving a balanced Precision of 75%on the PROMISE dataset and an impressive Recall of 85%on the CCHIT *** datasets consistently maintain an F-measure around 64%,highlighting FNRC’s ability to effectively balance precision and recall in diverse *** findings contribute to more accurate and efficient software development processes,increasing the probability of achieving successful project outcomes.

关键词： Ensemble learning machine learning non-functional requirements requirement engineering accuracy sliding window

来源：评论

学校读者我要写书评

暂无评论

Tranquility: A low disruptive alternative to quiescence for ensuring safe dynamic updates

Tranquility: A low disruptive alternative to quiescence for ...

引用

作者： Vandewoude, Yves Ebraert, Peter Berbers, Yolande D'Hondt, Theo Department of Computer Science Katholieke Universiteit Leuven Celestijnenlaan 200A 3001 Heverlee Belgium Programming Technology Lab. Vrije Universiteit Brussel Plainlaan 2 B1050 Brussels Belgium

This paper revisits a problem that was identified by Kramer and Magee: placing a system in a consistent state before and after runtime changes. We show that their notion of quiescence as a necessary and sufficient condition for safe runtime changes is too strict and results in a significant disruption in the application being updated. In this paper, we introduce a weaker condition: tranquility. We show that tranquility is easier to obtain and less disruptive for the running application but still a sufficient condition to ensure application consistency. We present an implementation of our approach on a component middleware platform and experimentally verify the validity and practical applicability of our approach using data retrieved from a case study. © 2007 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Optimizing Scene Classification: A Robust Approach with Transfer Learning and Automated Machine Learning Integration

Journal of Engineering Research

引用

Journal of Engineering Research 2025年

作者： Mohamed Hammad Samia A. Chelloug Samah AlShathri Ahmed A. Abd El-Latif Department of Information Technology Faculty of Computers and Information Menoufia University Shibin El Kom 32511 Egypt EIAS Data Science Lab College of Computer and Information Sciences and Center of Excellence in Quantum and Intelligent Computing Prince Sultan University Riyadh 11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia Department of Mathematics and Computer Science Faculty of Science Menoufia University Shebin El-Koom 32511 Egypt

Scene classification is a fundamental challenge in computer vision. Recognizing the complexity of this task is the aim of our study that addresses the need for accurate and robust scene classification by leveraging the capabilities of two widely recognized databases. The motivation behind this research lies in enhancing the accuracy and efficiency of scene classification systems. Therefore, our primary goal is to explore and implement a comprehensive methodology that combines transfer learning and automated machine learning techniques to achieve superior classification results. Our approach commences with a meticulous data loading process, followed by preprocessing steps to ensure the optimal representation of information. We have conducted class distribution analysis to understand the dataset's nuances. Subsequently, we have employed two key models: MobileNetV2 for transfer learning and a custom convolutional neural network (CNN) model featuring batch normalization. This diverse methodology aims to capture intricate patterns within the data. An innovative step of our approach involves employing Tree-based Pipeline Optimization Tool (TPOT), an automated machine learning tool, for model selection and hyperparameter tuning. The results underscore the effectiveness of our methodology, achieving impressive classification accuracy across diverse scenes. This research contributes valuable insights into the integration of transfer learning and automated machine learning for robust and accurate scene recognition, offering a comprehensive approach to address the complexities of scene classification.

关键词： CNN Scene Recognition TPOT MobileNetV2 Transfer Learning Machine Learning

来源：评论

学校读者我要写书评

暂无评论

GreedyJump: A Fast TCAM Update Algorithm

IEEE Networking Letters

引用

IEEE Networking Letters 2022年第1期4卷 25-29页

作者： Wan, Ying Song, Haoyu Liu, Bin Department of Computer Science and Technology Tsinghua University Beijing250000 China Network Technology Lab Futurewei Technologies Santa ClaraCA95050 United States

TCAM is widely used for rule tables in network switches. An efficient update scheme, which requires as few rule moves as possible, is often time-consuming to compute, while the fast computation likely yields a mediocre update scheme. We studied the existing algorithms and found none is satisfactory to the emerging applications. In this letter, we present a simple greedy algorithm, GreedyJump, which achieves fast computation and efficient update scheme at the same time, both with the best-in-class performance. The evaluation qualifies GreedyJump as the default TCAM update algorithm ready for meeting the scalability challenges in various application scenarios. © 2019 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Aircraft Altitude Estimation Using Un-calibrated Onboard Cameras

引用

Journal of The Institution of Engineers (India): Series C 2012年第4期93卷 287-295页

作者： Naidu, V.P.S. Mukherjee, J. MSDF Lab FMCD CSIR—National Aerospace Laboratories Bangalore India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India

In the present study, implementation and study of aircraft altitude estimation using un-calibrated onboard camera is obtained. A camera model has been implemented to simulate the test data. From the results, it was observed that the rounding nature of pixel coordinates creates fluctuations around the true vanishing point (VP) angle and height computations. These fluctuations were smoothened using a Kalman filter based state estimator. The effects of camera tilt and focal length on VP angle and height computations were also studied. It is concluded that the camera should be perpendicular to the runway for there to be no effect of the focal length on the height computation. It is being planned to apply this algorithm for real time imaging data along with Integrated Enhanced Synthetic Vision (IESVS) on HANSA aircraft. © 2012, The Institution of Engineers (India).

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection using Multi-path CNN and Convolutional Attention Mechanism 2

Deepfake Detection using Multi-path CNN and Convolutional At...

引用

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Rineesh Babu, P. Nair, Madhu S. Cochin University of Science and Technology Artificial Intelligence & Computer Vision Lab Department of Computer Science Kerala Kochi682022 India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

Image and video forgery using cutting-edge deep learning techniques has become one of the major issues in the social networking era. Media manipulation in which one person's face is swapped out for another's or has additional features added is referred to as deepfakes. Despite the fact that it has many beneficial purposes, fraudsters generally utilise it to create celebrity porn, revenge porn, and fake news, among other things. One of the biggest risks that deepfake presents is that people's belief in the reality of many things may decline. The motivation behind deepfake detection is the need to prove that the real thing is real and the fake thing is fake. In this paper a multi-CNN approach for detecting deepfakes is being proposed. Here, a multipath convolutional neural network (CNN) with three modules is used, each of which is stacked with a convolutional block attention mechanism. The first two modules in the dual-path paradigm are a Resnet module and a Densenet module. The Resnet component enables for feature reuse while Densenet allows for the investigation of new features. The parallel InceptionResnet module contains a one-dimensional feature reduction module with residual connections. When the performance of the proposed model is compared with that of four deep learning based approaches, it is found that the proposed method gave the best outcomes, with an accuracy and F1-score of 0.940 and 0.939, respectively. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DDoS prevention using third party auditor in cloud computing

引用

Iran Journal of computer science 2019年第4期2卷 231-244页

作者： Saxena, Rajat Dey, Somnath Cloud Computing Lab Department of Computer Science and Engineering Indian Institute of Technology Indore Indore India

Distributed denial of service (DDoS) attack is one of the prominent risk factors for the development of cloud service. It is a very hard task for novice cloud users to identify the real source of DDoS attack because the attacker spoofs the Internet Protocol and Media Access Control addresses. To address this problem, we propose a third party auditor-based packet traceback approach. The method uses Weibull distribution for analyzing the source of the DDoS attack. The approach provides an efficient and fruitful solution because of its strong identification factor. The identification factor depends on the weaknesses left by the intruder. We analyze the traffic pattern to generate attack alert for different cloud users. The advantage of this approach is that it reduces the overhead on the cloud user. With the help of Weibull distribution, we can easily obtain the availability, reliability and median life of DDoS defense in the cloud environment. To demonstrate our approach, we implement an application based on Hadoop and MapReduce framework. We tested this application based on various parameters. Our method has shown the tremendous improvement over the other state of the art methods. The experimental results are included to show the effectiveness of the proposed method for DDoS attack prevention and mitigation. © Springer Nature Switzerland AG 2019.

关键词： Cloud computing Distributed denial of service (DDoS) Attack Packet traceback Third party auditor (TPA) Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

Software transactional memory

引用

Queue 2008年第5期6卷 46-58页

作者： Cascaval, Calin Blundell, Colin Michael, Maged Cain, Harold W. Wu, Peng Chiras, Stefanie Chatterjee, Siddhartha Programming models and tools for scalable systems IBM's T.J. Watson Research Center University of Pennsylvania IBM's Systems and Technology Group Austin Research Laboratory Department of Computer Science University of Texas Austin United States

No abstract available

关键词：

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：