Filters








44 Hits in 8.0 sec

Less is more: Minimizing code reorganization using XTREE

Rahul Krishna, Tim Menzies, Lucas Layman
2017 Information and Software Technology  
Further, XTREE endorses changes to very few code metrics, and the bad smell recommendations (learned from previous studies) are not universal to all software projects.  ...  Evaluation: We evaluate XTREE's recommendations for bad smell improvement against recommendations from previous work (Shatnawi, Alves, and Borges) using multiple data sets of code metrics and defect counts  ...  Acknowledgements The work is partially funded by NSF awards #1506586 and #1302169.  ... 
doi:10.1016/j.infsof.2017.03.012 fatcat:tstuslv26jba3bqkeo6hmbmmta

A Deep Learning-Based Course Recommender System for Sustainable Development in Education

Qinglong Li, Jaekyeong Kim
2021 Applied Sciences  
Therefore, a course recommender system has the essential role of improving the learning efficiency of users.  ...  Therefore, to solve traditional recommendation problems, this study proposes a novel deep learning-based course recommender system (DECOR), which elaborately captures high-level user behaviors and course  ...  This study followed a strategy that is common in current studies because it used too much time to rank all features for all users during the model evaluation [59, 60] .  ... 
doi:10.3390/app11198993 fatcat:kgsypes3tnayffk6sjw4qn266u

Webpage Recommendation for Organization Users via Collaborative Page Weight

Laxmi Rajani, Urjita Thakar
2021 Journal of scientific research  
In this paper, a novel method is presented to make more personalized and effective web page recommendations.  ...  It is observed that more than 90 percent recommendations are matching to the user's requirements and effective as compare to the conventional approaches.  ...  It is observed that more than 90 percent recommendations match to the user's requirements and is effective as compared to the conventional approaches though it takes some computational time to rank and  ... 
doi:10.37398/jsr.2021.650129 fatcat:cndbielvzbf53az6ssrlcvdgq4

Zoomed Ranking: Selection of Classification Algorithms Based on Relevant Performance Information [chapter]

Carlos Soares, Pavel B. Brazdil
2000 Lecture Notes in Computer Science  
Given the wide variety o f a vailable classiaecation algorithms and the volume of data today's organizations need to analyze, the selection of the right algorithm to use on a new problem is an important  ...  The aerst one, zooming, analyzes a given dataset and selects relevant घsimilarङ datasets that were processed by the candidate algoritms in the past.  ...  Also thanks to João Gama for providing his implementations of Linear Discriminant and Naive B a yes and to Rui Pereira for implementing an important part of the methods.  ... 
doi:10.1007/3-540-45372-5_13 fatcat:pivlrzr5lbdhtm47vvoe3vrugi

When recommendation meets mobile

Jinfeng Zhuang, Tao Mei, Steven C.H. Hoi, Ying-Qing Xu, Shipeng Li
2011 Proceedings of the 13th international conference on Ubiquitous computing - UbiComp '11  
We deploy a recommendation application based on the proposed approach on Window Phone 7 devices.  ...  The approach, highly motivated from a large-scale mobile click-through analysis, is able to rank both the entity types and the entities within each type (here an entity is a local business, e.g., "I love  ...  ACKNOWLEDGEMENTS We would like to thank Peng Bai, Zheng Chen, Xuedong Huang, Xin Lin, Xiaochuan Ni, Jian-Tao Sun, Peng Xu, Bo Zhang, and Zhimin Zhang, for their insightful discussions.  ... 
doi:10.1145/2030112.2030134 dblp:conf/huc/ZhuangMHXL11 fatcat:lmullxqsajcyfc3scojszlhh3u

An Efficient Adaptive Attention Neural Network for Social Recommendation

Munan LI, Kenji Tei, Fukazawa Yoshiaki.
2020 IEEE Access  
In addition, we also utilize network embedding to learn more efficient features of each user and incorporate these features into the ANSR to enhance the recommendation results.  ...  Motivated by the above limitations, we designed a neural network model called adaptive attention neural network for social recommendation (ANSR) to study the interaction between a user and his or her social  ...  As it takes time to rank the test item among all the item data, we randomly sampled 300 items that were not in the rating records for each user and ranked the test item among these items.  ... 
doi:10.1109/access.2020.2984340 fatcat:enk5xziaarajlmmkl6hw6mz2ei

Web Page Ranking Using Web Mining Techniques: A Comprehensive Survey

Prem Sagar Sharma, Divakar Yadav, R. N. Thakur, M. Praveen Kumar Reddy
2022 Mobile Information Systems  
In this work, authors presented different approaches/techniques, algorithms and evaluation approaches in previous researches and identified some critical issues in page ranking and web mining, which provide  ...  Web mining plays a vital role in computing the rank of web pages. This article presents web mining types, techniques, tools, algorithms, and their challenges.  ...  is approach was much better and effective, but it took more time to rank.  ... 
doi:10.1155/2022/7519573 fatcat:ii5hv54a75bn7dsoevgli3jzc4

Haptic Feedback to Assist Blind People in Indoor Environment Using Vibration Patterns

Shah Khusro, Babar Shah, Inayat Khan, Sumayya Rahman
2022 Sensors  
The privacy of a blind user can also be compromised with speech feedback. The vibration feedback could effectively be used as an alternative approach to these mediums.  ...  Voice and sonification feedback are effective solutions to convey information. However, these solutions are not applicable in a noisy environment and may occupy the most important auditory sense.  ...  We will develop a real-time mobile application for visually-impaired people upon this tactile feedback module in future work.  ... 
doi:10.3390/s22010361 pmid:35009914 pmcid:PMC8749676 fatcat:mahgcth5uvawfpgflj2uabcnzi

Using Hyperlink Features to Personalize Web Search [chapter]

Mehmet S. Aktas, Mehmet A. Nacar, Filippo Menczer
2006 Lecture Notes in Computer Science  
Given a profile vector, a weighted PageRank is computed assigning a weight to each URL based on the match between the URL and the profile.  ...  Personalized PageRank performed favorably compared to pure similarity based ranking and traditional PageRank.  ...  A weighted PageRank vector is then computed based on URL weights, and used at query time to rank results.  ... 
doi:10.1007/11899402_7 fatcat:ytl6a4urz5hs3euxak2pncw36u

One Size Does Not Fit All: Toward User- and Query-Dependent Ranking for Web Databases

Aditya Telang, Chengkai Li, Sharma Chakravarthy
2012 IEEE Transactions on Knowledge and Data Engineering  
A common thread in most of these approaches is that ranking is done in a user-and/or query-independent manner.  ...  This paper proposes a novel query-and user-dependent approach for ranking query results in Web databases.  ...  ACKNOWLEDGEMENTS We thank the anonymous referees for their extremely useful comments and suggestions on an earlier draft of this paper.  ... 
doi:10.1109/tkde.2011.36 fatcat:is2k42usjjal3eot5cxhcamzra

Setting New Directions for Research in Childhood Nephrotic Syndrome: Results From a National Workshop

Susan M. Samuel, Tomoko Takano, Shannon Scott, Genevieve Benoit, Martin Bitzan, Cherry Mammen, Laurel Ryan, Catherine Morgan, Steven Arora, Heather Beanlands, Geneviève Benoit, Panojot Bifsha (+24 others)
2017 Canadian Journal of Kidney Health and Disease  
Results: Research evaluating glucocorticoid minimization or glucocorticoid-sparing regimens was a consistent theme in the patient and family discussion group.  ...  We report on the proceedings of a national workshop held in Canada with the aims to identify priorities for research in childhood nephrotic syndrome and to develop a national strategy to address these  ...  Funding The author(s) received no financial support for the research, authorship, and/or publication of this article.  ... 
doi:10.1177/2054358117703386 pmid:28491338 pmcid:PMC5405877 fatcat:now4wsnqzzbezdtmu5foavjaai

On the predictive power of meta-features in OpenML

Besim Bilalli, Alberto Abelló, Tomàs Aluja-Banet
2017 International Journal of Applied Mathematics and Computer Science  
There is a need for improving the effectiveness of meta-learning by identifying and designing more predictive meta-features.  ...  Meta-learning is a technique used for assisting non-expert users in this step.  ...  Having defined the latent features, it is time to rank them according to their relevance for predicting the performance of a given algorithm.  ... 
doi:10.1515/amcs-2017-0048 fatcat:eqxkusjmlzbdhniadkdvo4mw3e

Efficient Matching-Based Parallel Task Offloading in IoT Networks

Usman Mahmood Malik, Muhammad Awais Javed, Jaroslav Frnda, Jan Rozhon, Wali Ullah Khan
2022 Sensors  
Parallel offloading, in which a task is split into several sub-tasks and transmitted to different fog nodes for parallel computation, is a promising concept in task offloading.  ...  We develop preference profiles for IoT nodes and fog nodes to reduce the task computation delay.  ...  to rank TN tasks.  ... 
doi:10.3390/s22186906 pmid:36146254 pmcid:PMC9500985 fatcat:kjgyz3dfubgi5p5mld4iwx3g4e

Survey on categorical data for neural networks

John T. Hancock, Taghi M. Khoshgoftaar
2020 Journal of Big Data  
Practitioners working with big data often have a need to encode categorical values in their datasets in order to leverage machine learning algorithms.  ...  Some of these domains are natural language processing, fraud detection, and clinical document automation.  ...  Acknowledgements The authors would like to thank the anonymous reviewers for their constructive evaluation of this paper, and the various members of the Data Mining and Machine Learning Laboratory, Florida  ... 
doi:10.1186/s40537-020-00305-w fatcat:u3rhdtbkd5hljf76265mglrpmy

INNOVATION OF ISLAMIC EDUCATION (PAI) BASED ON MULTIPLE INTELLIGENCES

Abdul Basid
2017 Didaktika Religia  
This article discusses three important things, namely the basic concept of multiple intelligences, the new paradigm of learning Islamic Education, and PAI Learning based on various ideal intelligences.  ...  Multiple intelligence-based learning within the scope of an institution is generally not easy. Recently, Islamic Education as a subject or institution has its own advantages.  ...  For example, a child with high IQ does not necessarily have good emotional intelligence 12 and spiritual intelligence 13 in life. 10 According to Gardner, educators must reduce the time to rank the intelligence  ... 
doi:10.30762/didaktika.v5i2.864 fatcat:boekseeb6bdhnjlyjw6uxkofeq
« Previous Showing results 1 — 15 out of 44 results