检索结果-内蒙古大学图书馆

Usability Evaluation of University Websites in Pakistan through User Testing

学校读者我要写书评

暂无评论

Usability Evaluation of University Websites in Pakistan thro...

2022 International Conference on Emerging Technologies in Electronics, Computing and Communication, ICETECC 2022

作者： Nizamani, Sehrish Nizamani, Saad Nizamani, Sarwat Basir, Nazish Khoumbati, Khalil Memon, Shahzad University of Sindh Department of Information Technology Mirpurkhas Pakistan University of Sindh Department of Computer Science Mirpurkhas Pakistan University of Sindh Faculty of Engineering and Technology Jamshoro Pakistan University of Sindh Department of Electronics Engineering Jamshoro Pakistan

ISBN: (纸本)9781665490870

University websites are important mediums of communication that make important information accessible to the stakeholders of university websites. A good user experience of these websites brings the broader population to these websites. Evaluating the usability of university websites is important because it finds possible usability problems. In this regard, this research discusses the experience of the usability evaluation of three official websites of the universities of Pakistan i.e., Lahore University of Management sciences (LUMS), University of Karachi (UoK), and Islamia University, Bahawalpur (IUB) by employing user testing method using thinking aloud approach. The findings of the usability tests are summarized using three measures named effectiveness, efficiency, and satisfaction. The results reflect that the LUMS website scores higher in all three discussed measures. UoK and IUB both have the same effectiveness rating. The UoK website is less efficient than the IUB website, though. Finally, in satisfaction scores, users of the UoK website scored higher as compared to the IUB website. © 2022 IEEE.

关键词： Efficiency

Cost-constrained multi-label group feature selection using shadow features

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Klonecki, Tomasz Teisseyre, Pawel Lee, Jaesung Institute of Computer Science Polish Academy of Sciences Poland Faculty of Mathematics and Information Science Warsaw University of Technology Poland Department of Artificial Intelligence Chung-Ang University Korea Republic of

We consider the problem of feature selection in multilabel classification, considering the costs assigned to groups of features. In this task, the goal is to select a subset of features that will be useful for predicting the label vector, but at the same time, the cost associated with the selected features will not exceed the assumed budget. Solving the problem is of great importance in medicine, where we may be interested in predicting various diseases based on groups of features. The groups may be associated with parameters obtained from a certain diagnostic test, such as a blood test. Because diagnostic test costs can be very high, considering cost information when selecting relevant features becomes crucial to reducing the cost of making predictions. We focus on the feature selection method based on information theory. The proposed method consists of two steps. First, we select features sequentially while maximizing conditional mutual information until the budget is exhausted. In the second step, we select additional cost-free features, i.e., those coming from groups that have already been used in previous steps. Limiting the number of added features is possible using the stop rule based on the concept of so-called shadow features, which are randomized counterparts of the original ones. In contrast to existing approaches based on penalized criteria, in our method, we avoid the need for computationally demanding optimization of the penalty parameter. Experiments conducted on the MIMIC medical database show the effectiveness of the method, especially when the assumed budget is limited. © 2024, CC0.

关键词： Budget control

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Wenbo Wu, Yanan Jiang, Haoran Wang, Yang Wu, Qiang Zhang, Jian Faculty of Engineering and Information Technology University of Technology Sydney Sydney2007 Australia School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

Automatic Detection of Learning Styles on OpenEdx Using Trace Analysis

学校读者我要写书评

暂无评论

Automatic Detection of Learning Styles on OpenEdx Using Trac...

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Youness Chaabi Khadija Lekdioui Yahya Al-Ashmoery Center of Computer Studies Information and Communication Systems (CEISIC) Royal Institute of Amazigh Culture (IRCAM) Rabat Morocco SETIME Laboratory Faculty of Science ENSC Ibn Tofail University Kenitra Morocco Department of Information Technology Al-Razi University Department of Mathematics & Computer Faculty of Science Sana’a University Sana’a Yemen

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

In a learning management system (LMS), the tutor does not interact with the students in person to interpret their reactions and grimaces or to determine the level of course assimilation. As a result, analyzing learners' behavior and traces in an e-learning environment has become necessary for tutors or teachers to assist their students. Many researchers argue that learners' learning styles are an important factor to consider in LMS. These learning styles enable students to tailor their learning to their specific environment. Every learner has a unique learning style and way of perceiving, processing, retaining, and comprehending new information. This approach, which is based on the analysis of learners' interaction traces in LMS, gives teachers a sense of their students' behavior and identifies their learning styles. Our method has demonstrated an accuracy rate of 80% in detecting learning styles, significantly enhancing engagement and motivation. By tailoring content, activities, and assessments to match each student's preferences, we can adapt interventions dynamically.

关键词： Training Learning management systems Adaptation models Electronic learning Accuracy Computational modeling

Improved Distance (Sensitivity) Oracles with Subquadratic Space

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bilò, Davide Chechik, Shiri Choudhary, Keerti Cohen, Sarel Friedrich, Tobias Schirneck, Martin Department of Information Engineering Computer Science and Mathematics University of L'Aquila Italy Department of Computer Science Tel Aviv University Department of Computer Science and Engineering Indian Institute of Technology Delhi India School of Computer Science The Academic College of Tel Aviv-Yaffo Hasso Plattner Institute University of Potsdam Germany Faculty of Computer Science University of Vienna Austria

A distance oracle (DO) for a graph G is a data structure that, when queried with vertices s, t, returns an estimate (Equation presented)(s, t) of their distance in G. The oracle has stretch (α, β) if the estimate satisfies (Equation presented). An f-edge fault-tolerant distance sensitivity oracle (f-DSO) additionally receives a set F of up to f edges and estimates the distance in G−F. Our first contribution is the design of new distance oracles with subquadratic space for undirected graphs. We show that introducing a small additive stretch β > 0 allows one to make the multiplicative stretch α arbitrarily small. This sidesteps a known lower bound of α ≥ 3 (for β = 0 and subquadratic space) [Thorup & Zwick, JACM 2005]. We present a DO for graphs with edge weights in [0, W] that, for any positive integer and any c ∈ (0, /2], has stretch (Equation presented), space (Equation presented), and query time O(nc). These are the first subquadratic-space DOs with (1+Ε, O(1))-stretch generalizing Agarwal and Godfrey's results for sparse graphs [SODA 2013] to general undirected graphs. We also construct alternative DOs with even smaller space at the cost of a higher additive stretch. For any integer k ≥ 1, the DOs have a stretch (Equation presented), space (Equation presented), and query time O(nc). Our second contribution is a framework that turns any (α, β)-stretch DO for unweighted graphs into an (α(1+Ε), β)-stretch f-DSO with sensitivity f = o(log(n)/log log n) and retains subquadratic space. This generalizes a result by Bilò, Chechik, Choudhary, Cohen, Friedrich, Krogmann, and Schirneck [STOC 2023, TheoretiCS 2024] for the special case of stretch (3, 0) and f = O(1). We also derandomize the entire construction. By combining the framework with our new distance oracle, we obtain an f-DSO that, for any γ ∈ (0, (+1)/2], has stretch (Equation presented), space (Equation presented), and query time (Equation presented). This is the first deterministic f-DSO with subquadratic space,

关键词： Undirected graphs

Optimizing Atmospheric Water Generation Through Advanced Weather Prediction Using Solar Energy Data

学校读者我要写书评

暂无评论

Optimizing Atmospheric Water Generation Through Advanced Wea...

International Conference for Convergence of technology (I2CT)

作者： Eman Dar Khadija Rana Muhammad Zunnurain Hussain Muhammad Zulkifl Hasan Aqsa Khalid Arslan Javaid Jawad Altaf Basit Sattar Saad Hussain Chuhan Muhammad Atif Yaqub Ali Moiz Qureshi Zaima Mubarak Computer Engineering Department Information Technology University Lahore Pakistan Dept. of Computer Science Bahria University Lahore Campus Lahore Pakistan Faculty of Information Technology University of Central Punjab Lahore Pakistan Department of Computer Science National College of Business Adm. & Economics Lahore Pakistan Department of Computer Science National College of Ireland NCI Department of AI UMT Lahore Pakistan Department of Computer Science National College of Business Administration and Economics Lahore Pakistan

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

This research focuses on enhancing the efficiency of Atmospheric Water Generation (AWG) systems through the development of an accurate weather prediction model. Leveraging solar energy data, the project aims to forecast key weather parameters such as solar radiation, temperature, and humidity. The objective is to optimize the performance of the AWG device across diverse weather conditions. By integrating advanced weather prediction, the study endeavors to enable proactive adjustments in the AWG operation, ensuring optimal water production. This research contributes to the sustainable utilization of solar energy for atmospheric water generation, addressing water scarcity challenges with a forward-thinking and adaptive approach.

关键词： Performance evaluation Temperature distribution Atmospheric modeling Weather forecasting Solar energy Production Humidity

Adaptive Query Prompting for Multi-Domain Landmark Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wei, Qiusen Huang, Guoheng Yuan, Xiaochen Chen, Xuhang Zhong, Guo Huang, Jianwen Huang, Jiajie School of Automation Guangdong University of Technology Guangzhou China School of Computer Science and Technology Guangdong University of Technology Guangzhou China Faculty of Applied Sciences Macao Polytechnic University China School of Computer Science and Engineering Huizhou University Huizhou China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China

Medical landmark detection is crucial in various medical imaging modalities and procedures. Although deep learning-based methods have achieve promising performance, they are mostly designed for specific anatomical regions or tasks. In this work, we propose a universal model for multi-domain landmark detection by leveraging transformer architecture and developing a prompting component, named as Adaptive Query Prompting (AQP). Instead of embedding additional modules in the backbone network, we design a separate module to generate prompts that can be effectively extended to any other transformer network. In our proposed AQP, prompts are learnable parameters maintained in a memory space called prompt pool. The central idea is to keep the backbone frozen and then optimize prompts to instruct the model inference process. Furthermore, we employ a lightweight decoder to decode landmarks from the extracted features, namely Light-MLD. Thanks to the lightweight nature of the decoder and AQP, we can handle multiple datasets by sharing the backbone encoder and then only perform partial parameter tuning without incurring much additional cost. It has the potential to be extended to more landmark detection tasks. We conduct experiments on three widely used X-ray datasets for different medical landmark detection tasks. Our proposed Light-MLD coupled with AQP achieves SOTA performance on many metrics even without the use of elaborate structural designs or complex frameworks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

A hybrid technique for intelligent bank security system based on blink gesture recognition 1

学校读者我要写书评

暂无评论

A hybrid technique for intelligent bank security system base...

1st International Conference on Engineering and technology, ICoEngTech 2021

作者： Bakunah, Raed Awadh Mohammed Baneamoon, Saeed Department of Information Technology Faculty of Engineering and Information Technology Al-Rayan University Yemen Department of Computer Engineering College of Engineering and Petroleum Hadhramout University Yemen Department of Computer Science College of Computers and Information Technology Hadhramout University Yemen

Enhancement of bank security system plays an important role at the present time due to increasing attempts to expose it to many infringements by criminals. This paper proposes a hybrid technique of amplitude and duration to recognize its blink gestures to increase the accuracy of the human security system's interaction for intelligent bank security, as this hybrid technique implemented analyzing of face, facial landmark detection, and the duration of the eye aspect ratio (EAR) for blink processes. The proposed hybrid technique is evaluated by experimenting a number of blink gesture with two eyes obtained from web camera and the results shows better and more effective analysis and provide high security bank system. © Published under licence by IOP Publishing Ltd.

关键词： Gesture recognition

Cybersecurity Threats in the Era of AI: Detection of Phishing Domains Through Classification Rules

学校读者我要写书评

暂无评论

Cybersecurity Threats in the Era of AI: Detection of Phishin...

Electrical, Energy, and Artificial Intelligence (EICEEAI), International Engineering Conference on

作者： Mohammad Aljaidi Ayoub Alsarhan Dimah Al-Fraihat Ahmed Al-Arjan Bashar Igried Subhieh M. El-Salhi Muhammad Khalid Qais Al-Na'amneh Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Department of Information Technology The Hashemite University Jordan Department of Software Engineering Faculty of Information Technology Isra University Amman Jordan Department of Information Technology Faculty of Prince AL-Hussein bin Abdullah II of Information Technology The Hashemite University Jordan Department of Computer Science and Applications The Hashemite University Zarqa Jordan The Hashemite University Zarqa Jordan Department of Computer Sciences and Technology University of Hull Kingston upon Hull UK Dep. of Cyber Security Applied Science Private University Amman Jordan

ISBN: (数字)9798350373363

ISBN: (纸本)9798350373370

Phishing is a cyber threat where attackers create deceptive websites or emails to exploit individuals for fraudulent purposes such as providing sensitive information like usernames, passwords, or financial details. Hence, detecting phishing emails is of paramount importance to protect sensitive information, preventing financial losses, protecting against identity theft, and maintaining trust. This study employs machine learning techniques to classify and categorize websites that are used for phishing attacks. To achieve this, we proposed a classification model for the detection of phishing domains based on classification rules. These rules were formulated based on analyzing and distributing them into three classifiers: domain name features, search engine opinion (SEO) information of the domain, and security scans by security vendors. A total of eleven classification rules were formulated which were distributed as follows: six rules for the first classifier, four rules for the second classifier, and one rule for the third classifier. Each classifier feeds its results to the main classifier, which then evaluates the received results based on its rules. Domain names from 222 confirmed phishing URLs were used to test the suggested model. The model demonstrated exceptional performance, achieving an impressive accuracy rate of 99.1% during testing.

关键词： Adaptation models Accuracy Phishing Identity theft Refining Machine learning Passwords