Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (5624)
- Computer Sciences (5609)
- Databases and Information Systems (2339)
- Software Engineering (1250)
- Artificial Intelligence and Robotics (1175)
-
- Engineering (730)
- Numerical Analysis and Scientific Computing (724)
- Information Security (687)
- Graphics and Human Computer Interfaces (582)
- Business (504)
- Social and Behavioral Sciences (501)
- Operations Research, Systems Engineering and Industrial Engineering (356)
- Computer Engineering (349)
- Theory and Algorithms (341)
- Programming Languages and Compilers (241)
- OS and Networks (219)
- Communication (186)
- Public Affairs, Public Policy and Public Administration (184)
- Transportation (167)
- Medicine and Health Sciences (163)
- Education (150)
- Social Media (148)
- Management Information Systems (140)
- E-Commerce (116)
- Data Storage Systems (109)
- Health Information Technology (98)
- International and Area Studies (87)
- Asian Studies (86)
- Digital Communications and Networking (82)
- Higher Education (78)
- Keyword
-
- Deep learning (90)
- Machine learning (88)
- Artificial intelligence (55)
- Reinforcement learning (53)
- Cloud computing (51)
-
- Privacy (49)
- Data mining (47)
- Online learning (44)
- Security (44)
- Social media (43)
- Empirical study (42)
- Optimization (42)
- Training (42)
- Visualization (41)
- Task analysis (39)
- Access control (38)
- Feature extraction (37)
- Neural networks (37)
- Deep Learning (34)
- Software engineering (34)
- Blockchain (33)
- Large Language Models (31)
- Machine Learning (31)
- Twitter (31)
- Anomaly detection (30)
- Privacy-preserving (30)
- Natural language processing (29)
- Singapore (29)
- Clustering (28)
- Collaboration (28)
- Publication Year
Articles 4561 - 4590 of 5741
Full-Text Articles in Entire DC Network
Finding Robust-Under-Risk Solutions For Flowshop Scheduling, Steven O. Kimbrough, Ann Kuo, Hoong Chuin Lau
Finding Robust-Under-Risk Solutions For Flowshop Scheduling, Steven O. Kimbrough, Ann Kuo, Hoong Chuin Lau
Research Collection School Of Computing and Information Systems
We propose and explore, in the context of benchmark problems for flowshop scheduling, a risk-based concept of robustness for optimization problems. This risk-based concept is in distinction to, and complements, the uncertainty-based concept employed in the field known as robust optimization. Implementation of our concept requires problem solution methods that sample the solution space intelligently and that produce large numbers of distinct sample points. With these solutions to hand, their robustness scores are easily obtained and heuristically robust solutions found. We find evolutionary computation to be effective for this purpose on these problems.
Trust Network Inference For Online Rating Data Using Generative Models, Freddy Tat Chua Chua, Ee Peng Lim
Trust Network Inference For Online Rating Data Using Generative Models, Freddy Tat Chua Chua, Ee Peng Lim
Research Collection School Of Computing and Information Systems
In an online rating system, raters assign ratings to objects contributed by other users. In addition, raters can develop trust and distrust on object contributors depending on a few rating and trust related factors. Previous study has shown that ratings and trust links can influence each other but there has been a lack of a formal model to relate these factors together. In this paper, we therefore propose Trust Antecedent Factor (TAF)Model, a novel probabilistic model that generate ratings based on a number of rater’s and contributor’s factors. We demonstrate that parameters of the model can be learnt by Collapsed …
Query Weighting For Ranking Model Adaptation, Peng Cai, Wei Gao, Aoying Zhou, Kam-Fai Wong
Query Weighting For Ranking Model Adaptation, Peng Cai, Wei Gao, Aoying Zhou, Kam-Fai Wong
Research Collection School Of Computing and Information Systems
We propose to directly measure the importance of queries in the source domain to the target domain where no rank labels of documents are available, which is referred to as query weighting. Query weighting is a key step in ranking model adaptation. As the learning object of ranking algorithms is divided by query instances, we argue that it’s more reasonable to conduct importance weighting at query level than document level. We present two query weighting schemes. The first compresses the query into a query feature vector, which aggregates all document instances in the same query, and then conducts query weighting …
Smoothly Varying Affine Stitching, Wen-Yan Lin, Siying Liu, Yasuyuki Matsuhita, Tian-Tsong Ng, Loong-Fah Cheong
Smoothly Varying Affine Stitching, Wen-Yan Lin, Siying Liu, Yasuyuki Matsuhita, Tian-Tsong Ng, Loong-Fah Cheong
Research Collection School Of Computing and Information Systems
Traditional image stitching using parametric transforms such as homography, only produces perceptually correct composites for planar scenes or parallax free camera motion between source frames. This limits mosaicing to source images taken from the same physical location. In this paper, we introduce a smoothly varying affine stitching field which is flexible enough to handle parallax while retaining the good extrapolation and occlusion handling properties of parametric transforms. Our algorithm which jointly estimates both the stitching field and correspondence, permits the stitching of general motion source images, provided the scenes do not contain abrupt protrusions.
On Combining State Space Reductions With Global Fairness Assumptions, Shao Jie Zhang, Jun Sun, Jun Pang, Yang Liu, Jin Song Dong
On Combining State Space Reductions With Global Fairness Assumptions, Shao Jie Zhang, Jun Sun, Jun Pang, Yang Liu, Jin Song Dong
Research Collection School Of Computing and Information Systems
Model checking has established itself as an effective system analysis method, as it is capable of proving/dis-proving properties automatically. Its application to practical systems is however limited by state space explosion. Among effective state reduction techniques are symmetry reduction and partial order reduction. Global fairness often plays a vital role in designing self-stabilizing population protocols. It is known that combining fairness and symmetry reduction is nontrivial. In this work, we first show that global fairness, unlike weak/strong fairness, can be combined with symmetry reduction. We extend the PAT model checker with the technique and demonstrate its usability by verifying recently …
Getting To Global Yes! Designing A Distributed Student Collaboration, Selma Limam Mansar, Randy Weinberg, Benjamin Kok Siew Gan
Getting To Global Yes! Designing A Distributed Student Collaboration, Selma Limam Mansar, Randy Weinberg, Benjamin Kok Siew Gan
Research Collection School Of Computing and Information Systems
The authors have taught a course called 'Global Project Management' for four years, engaging students in three international locations in hands-on distance projects. The distance projects are intended to provide students with enriching, realistic global project experience. With experience, improved planning and better coordination, each iteration of the distance projects has improved. In this paper, the authors present lessons learned and a mind map demonstrating key aspects of design of global hands-on projects.
A Quality Metric For Sustainable Innovations, Arcot Desai Narasimhalu
A Quality Metric For Sustainable Innovations, Arcot Desai Narasimhalu
Research Collection School Of Computing and Information Systems
Sustainability has become a major concern for nations and firms especially since the Kyoto Protocol was defined in 1997. While there have been several studies on benchmarks for national innovation systems and effectiveness of innovation management within firms there is as yet no reasonable metric for determining the quality of an innovation much less its quality relating to sustainability? Similarly, there have been several studies on sustainability but that such research groups have also not focused on developing a metric for denoting the quality of sustainable innovations. This paper offers a metric that defines the quality of an innovation, especially …
Cio Reporting Structure, Strategic Positioning, And Firm Performance, Rajiv D Banker, Nan Hu, Paul A Pavlou, Jerry Luftman
Cio Reporting Structure, Strategic Positioning, And Firm Performance, Rajiv D Banker, Nan Hu, Paul A Pavlou, Jerry Luftman
Research Collection School Of Computing and Information Systems
Almost 30 years after the introduction of the CIO position, the ideal CIO reporting structure (whether the CIO should report to the CEO or the CFO) is yet to be identified. There is an intuitive assumption among some proponents of IT that the CIO should always report to the CEO to promote the importance of IT and the CIO's clout in the firm, while some adversaries of IT call for a CIO—CFO reporting structure to keep a tab on IT spending. However, we challenge these two ad hoc prescriptions by arguing that neither CIO reporting structure is necessarily optimal, and …
Towards Human-Like Social Multi-Agents With Memetic Automaton, Liang Feng, Yew-Soon Ong, Ah-Hwee Tan, Xian-Shun Chen
Towards Human-Like Social Multi-Agents With Memetic Automaton, Liang Feng, Yew-Soon Ong, Ah-Hwee Tan, Xian-Shun Chen
Research Collection School Of Computing and Information Systems
Memetics is a new science that has attracted increasing attentions in the recent decades. Beyond the formalism of simple hybrids, adaptive hybrids and memetic algorithms, the notion of memetic automaton as an adaptive entity that is self-contained and uses memes as building blocks of information is recently conceptualized in the context of computational intelligence as potential tools for effective problem-solving [1]. Taking this cue, this paper embarks a study on Memetic Multiagent system (MeM) towards human-like social agents with memetic automaton. Particularly, we introduce a potentially rich meme-inspired design and operational model, with Darwin’s theory of natural selections and Dawkins’ …
Using Service Responsibility Tables To Supplement Uml In Analyzing E-Service Systems, Xin Tan, Steven Alter, Keng Siau
Using Service Responsibility Tables To Supplement Uml In Analyzing E-Service Systems, Xin Tan, Steven Alter, Keng Siau
Research Collection School Of Computing and Information Systems
This paper proposes using Service Responsibility Tables (SRTs) as a tool in analyzing e-service systems. First it discusses difficulties and deficiencies of using formal modeling languages such as UML in analyzing e-service systems. It proposes using SRTs as an informal language and lightweight analytical tool to be used by business professionals in analyzing e-service systems. SRTs are based on a service value chain framework but do not rely on abstract concepts and constructs, and therefore can be used by business professionals to supplement UML. We suggest a set of heuristics for transforming SRTs into two key UML diagrams, thereby illustrating …
Supervisory Evolutionary Optimization Strategy For Adaptive Maintenance Schedules, Zhaoxia Wang, C. S. Chang
Supervisory Evolutionary Optimization Strategy For Adaptive Maintenance Schedules, Zhaoxia Wang, C. S. Chang
Research Collection School Of Computing and Information Systems
No abstract provided.
Guest Editorial: Special Issue On Game Theory In Communication Networks, Tansu Alpcan, Rachid El-Azouzi, Nahum Shimkin, Laura Wynter
Guest Editorial: Special Issue On Game Theory In Communication Networks, Tansu Alpcan, Rachid El-Azouzi, Nahum Shimkin, Laura Wynter
Research Collection School Of Computing and Information Systems
The distributed nature of wireline and wireless communication networks gives rise to many challenges in their analysis, control, and management. Development of decentralized control mechanisms that achieve fair allocation of system resources despite the selfish nature of the users is among the major issues in networks research. Consequently, game theoretic methods and approaches have been increasingly utilized to gain a deeper analytical understanding of these complex problems and systems.
Preserving Transparency And Accountability In Optimistic Fair Exchange Of Digital Signatures, Xinyi Huang, Yi Mu, Willy Susilo, Jianying Zhou, Robert H. Deng
Preserving Transparency And Accountability In Optimistic Fair Exchange Of Digital Signatures, Xinyi Huang, Yi Mu, Willy Susilo, Jianying Zhou, Robert H. Deng
Research Collection School Of Computing and Information Systems
Optimistic fair exchange (OFE) protocols are useful tools for two participants to fairly exchange items with the aid of a third party who is only involved if needed. A widely accepted requirement is that the third party's involvement in the exchange must be transparent, to protect privacy and avoid bad publicity. At the same time, a dishonest third party would compromise the fairness of the exchange and the third party thus must be responsible for its behaviors. This is achieved in OFE protocols with another property called accountability. It is unfortunate that the accountability has never been formally studied in …
Continuous Visible Nearest Neighbor Query Processing In Spatial Databases, Yunjun Gao, Baihua Zheng, Gencai Chen, Qing Li, Xiaofa Guo
Continuous Visible Nearest Neighbor Query Processing In Spatial Databases, Yunjun Gao, Baihua Zheng, Gencai Chen, Qing Li, Xiaofa Guo
Research Collection School Of Computing and Information Systems
In this paper, we identify and solve a new type of spatial queries, called continuous visible nearest neighbor (CVNN) search. Given a data set P, an obstacle set O, and a query line segment q in a two-dimensional space, a CVNN query returns a set of $${\langle p, R\rangle}$$ tuples such that $${p \in P}$$ is the nearest neighbor to every point r along the interval $${R \subseteq q}$$ as well as pis visible to r. Note that p may be NULL, meaning that all points in P are invisible to all points in R due to the obstruction of …
A Solution With Security Concern For Rfid-Based Track And Trace Services In Epcglobal-Enabled Supply Chains, Wei He, Yingjiu Li, Kevin Chiew, Tieyan Li, Eng Wah Lee
A Solution With Security Concern For Rfid-Based Track And Trace Services In Epcglobal-Enabled Supply Chains, Wei He, Yingjiu Li, Kevin Chiew, Tieyan Li, Eng Wah Lee
Research Collection School Of Computing and Information Systems
A supply chain represents the flow of materials, information, and finance as they move through supply chain partners such as manufacturers, suppliers, distributors, retailers, and consumers. The track & trace services in supply chains can help improve supply chain visibility and efficiency, and prevent counterfeiting and stealing of products thus enhance security. Track & trace services in supply chains require identification of items, capture of events as items move through supply chains, and query of events of items. RFID (radio frequency identification) is a technology that allows to identify objects simultaneously in a fully automated manner via radio waves. This …
Leveraging Complex Event Processing For Smart Hospitals Using Rfid, Wen Yao, Chao-Hsien Chu, Zang Li
Leveraging Complex Event Processing For Smart Hospitals Using Rfid, Wen Yao, Chao-Hsien Chu, Zang Li
Research Collection School Of Computing and Information Systems
RFID technology has been examined in healthcare to support a variety of applications such as patient identification and monitoring, asset tracking, and patient–drug compliance. However, managing the large volume of RFID data and understanding them in the medical context present new challenges. One effective solution for dealing with these challenges is complex event processing (CEP), which can extract meaningful events for context-aware applications. In this paper, we propose a CEP framework to model surgical events and critical situations in an RFID-enabled hospital. We have implemented a prototype system with the proposed approach for surgical management and conducted performance evaluations to …
Double Updating Online Learning, Peilin Zhao, Steven C. H. Hoi, Rong Jin
Double Updating Online Learning, Peilin Zhao, Steven C. H. Hoi, Rong Jin
Research Collection School Of Computing and Information Systems
In most kernel based online learning algorithms, when an incoming instance is misclassified, it will be added into the pool of support vectors and assigned with a weight, which often remains unchanged during the rest of the learning process. This is clearly insufficient since when a new support vector is added, we generally expect the weights of the other existing support vectors to be updated in order to reflect the influence of the added support vector. In this paper, we propose a new online learning method, termed Double Updating Online Learning, or DUOL for short, that explicitly addresses this problem. …
A Simple Curious Agent To Help People Be Curious, Han Yu, Zhiqi Shen, Chunyan Miao, Ah-Hwee Tan
A Simple Curious Agent To Help People Be Curious, Han Yu, Zhiqi Shen, Chunyan Miao, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Curiosity is an innately rewarding state of mind that, over the millennia, has driven the human race to explore and discover. Many researches in pedagogical science have confirmed the importance of being curious to the students' cognitive development. However, in the newly popular virtual world-based learning environments (VLEs), there is currently a lack of attention being paid to enhancing the learning experience by stimulating the learners' curiosity. In this paper, we propose a simple model for curious agents (CAs) which can be used to stimulate learners' curiosity in VLEs. Potential future research directions will be discussed.
Fragile Online Relationship: A First Look At Unfollow Dynamics In Twitter, Haewoon Kwak, Hyunwoo Chun, Sue. Moon
Fragile Online Relationship: A First Look At Unfollow Dynamics In Twitter, Haewoon Kwak, Hyunwoo Chun, Sue. Moon
Research Collection School Of Computing and Information Systems
We analyze the dynamics of the behavior known as 'unfollow' in Twitter. We collected daily snapshots of the online relationships of 1.2 million Korean-speaking users for 51 days as well as all of their tweets. We found that Twitter users frequently unfollow. We then discover the major factors, including the reciprocity of the relationships, the duration of a relationship, the followees' informativeness, and the overlap of the relationships, which affect the decision to unfollow. We conduct interview with 22 Korean respondents to supplement the quantitative results.They unfollowed those who left many tweets within a short time, created tweets about uninteresting …
Incremental Dcop Search Algorithms For Solving Dynamic Dcop Problems, William Yeoh, Pradeep Varakantham, Xiaoxun Sun, Sven Koenig
Incremental Dcop Search Algorithms For Solving Dynamic Dcop Problems, William Yeoh, Pradeep Varakantham, Xiaoxun Sun, Sven Koenig
Research Collection School Of Computing and Information Systems
Distributed constraint optimization problems (DCOPs) are well-suited for modeling multi-agent coordination problems. However, most research has focused on developing algorithms for solving static DCOPs. In this paper, we model dynamic DCOPs as sequences of (static) DCOPs with changes from one DCOP to the next one in the sequence. We introduce the ReuseBounds procedure, which can be used by any-space ADOPT and any-space BnB-ADOPT to find cost-minimal solutions for all DCOPs in the sequence faster than by solving each DCOP individually. This procedure allows those agents that are guaranteed to remain unaffected by a change to reuse their lower and upper …
Configuring Global Software Teams: A Multi-Company Analysis Of Productivity, Quality, And Profits, Narayanasamy Ramasubbu, Marcelo Cataldo, Rajesh Krishna Balan, James Herbsleb
Configuring Global Software Teams: A Multi-Company Analysis Of Productivity, Quality, And Profits, Narayanasamy Ramasubbu, Marcelo Cataldo, Rajesh Krishna Balan, James Herbsleb
Research Collection School Of Computing and Information Systems
In this paper, we examined the impact of project-level configurational choices of globally distributed software teams on project productivity, quality, and profits. Our analysis used data from 362 projects of four different firms. These projects spanned a wide range of programming languages, application domain, process choices, and development sites spread over 15 countries and 5 continents. Our analysis revealed fundamental tradeoffs in choosing configurational choices that are optimized for productivity, quality, and/or profits. In particular, achieving higher levels of productivity and quality require diametrically opposed configurational choices. In addition, creating imbalances in the expertise and personnel distribution of project teams …
Beespace Navigator: Exploratory Analysis Of Gene Function Using Semantic Indexing Of Biological Literature, Moushumi Sen Sarma, David Arcoleo, Radhika S. Khetani, Brant Chee, Xu Ling, Xin He, Jing Jiang, Qiaozhu Mei, Chengxiang Zhai, Bruce Schatz
Beespace Navigator: Exploratory Analysis Of Gene Function Using Semantic Indexing Of Biological Literature, Moushumi Sen Sarma, David Arcoleo, Radhika S. Khetani, Brant Chee, Xu Ling, Xin He, Jing Jiang, Qiaozhu Mei, Chengxiang Zhai, Bruce Schatz
Research Collection School Of Computing and Information Systems
With the rapid decrease in cost of genome sequencing, the classification of gene function is becoming a primary problem. Such classification has been performed by human curators who read biological literature to extract evidence. BeeSpace Navigator is a prototype software for exploratory analysis of gene function using biological literature. The software supports an automatic analogue of the curator process to extract functions, with a simple interface intended for all biologists. Since extraction is done on selected collections that are semantically indexed into conceptual spaces, the curation can be task specific. Biological literature containing references to gene lists from expression experiments …
Continuous Nearest Neighbor Search In The Presence Of Obstacles, Yunjun Gao, Baihua Zheng, Gang Chen, Chun Chen, Qing Li
Continuous Nearest Neighbor Search In The Presence Of Obstacles, Yunjun Gao, Baihua Zheng, Gang Chen, Chun Chen, Qing Li
Research Collection School Of Computing and Information Systems
Despite the ubiquity of physical obstacles (e.g., buildings, hills, and blindages, etc.) in the real world, most of spatial queries ignore the obstacles. In this article, we study a novel form of continuous nearest-neighbor queries in the presence of obstacles, namely continuous obstructed nearest-neighbor (CONN) search, which considers the impact of obstacles on the distance between objects. Given a data setP, an obstacle set O, and a query line segment q, in a two-dimensional space, a CONN query retrieves the nearest neighbor p ∈ P of each point p′ on q according to the obstructed distance, the shortest path between …
Design And Performance Analysis Of Mac Schemes For Wireless Sensor Networks Powered By Ambient Energy Harvesting, Zhi Ang Eu, Hwee-Pink Tan, Winston K. G. Seah
Design And Performance Analysis Of Mac Schemes For Wireless Sensor Networks Powered By Ambient Energy Harvesting, Zhi Ang Eu, Hwee-Pink Tan, Winston K. G. Seah
Research Collection School Of Computing and Information Systems
Energy consumption is a perennial issue in the design of wireless sensor networks (WSNs) which typically rely on portable sources like batteries for power. Recent advances in ambient energy harvesting technology have made it a potential and promising alternative source of energy for powering WSNs. By using energy harvesters with supercapacitors, WSNs are able to operate perpetually until hardware failure and in places where batteries are hard or impossible to replace. In this paper, we study the performance of different medium access control (MAC) schemes based on CSMA and polling techniques for WSNs which are solely powered by ambient energy …
Interactivity-Constrained Server Provisioning In Large-Scale Distributed Virtual Environments, Nguyen Binh Duong Ta, Thang Nguyen, Suiping Zhou, Xueyan Tang, Wentong Cai, Rassul Ayani
Interactivity-Constrained Server Provisioning In Large-Scale Distributed Virtual Environments, Nguyen Binh Duong Ta, Thang Nguyen, Suiping Zhou, Xueyan Tang, Wentong Cai, Rassul Ayani
Research Collection School Of Computing and Information Systems
Maintaining interactivity is one of the key challenges in distributed virtual environments (DVE), e.g., online games, distributed simulations, etc., due to the large, heterogeneous Internet latencies; and the fact that clients in a DVE are usually geographically separated. In this paper, we consider a new problem, termed the interactivity-constrained server provisioning problem, whose goal is to minimize the number of distributed servers needed to achieve a pre-determined level of interactivity. We identify and formulate two variants of this new problem and show that they are both NP-hard via reductions to the set covering problem. We then propose several computationally efficient …
A Family Of Simple Non-Parametric Kernel Learning Algorithms From Pairwise Constraints, Jinfeng Zhuang, Ivor W. Tsang, Steven C. H. Hoi
A Family Of Simple Non-Parametric Kernel Learning Algorithms From Pairwise Constraints, Jinfeng Zhuang, Ivor W. Tsang, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Previous studies of Non-Parametric Kernel Learning (NPKL) usually formulate the learning task as a Semi-Definite Programming (SDP) problem that is often solved by some general purpose SDP solvers. However, for N data examples, the time complexity of NPKL using a standard interior-point SDP solver could be as high as O(N6.5), which prohibits NPKL methods applicable to real applications, even for data sets of moderate size. In this paper, we present a family of efficient NPKL algorithms, termed "SimpleNPKL", which can learn non-parametric kernels from a large set of pairwise constraints efficiently. In particular, we propose two efficient SimpleNPKL algorithms. One …
Heterogeneous Signcryption With Key Privacy, Qiong Huang, Duncan S. Wong, Guomin Yang
Heterogeneous Signcryption With Key Privacy, Qiong Huang, Duncan S. Wong, Guomin Yang
Research Collection School Of Computing and Information Systems
A signcryption scheme allows a sender to produce a ciphertext for a receiver so that both confidentiality and non-repudiation can be ensured. It is built to be more efficient and secure, for example, supporting insider security, when compared with the conventional sign-then-encrypt approach. In this paper, we propose a new notion called heterogeneous signcryption in which the sender has an identity-based secret key while the receiver is holding a certificate-based public key pair. Heterogeneous signcryption is suitable for practical scenarios where an identity-based user, who does not have a personal certificate or a public key, wants to communicate securely with …
Action Learning: Reflections Of A First-Time Coach, Siu Loon Hoe
Action Learning: Reflections Of A First-Time Coach, Siu Loon Hoe
Research Collection School Of Computing and Information Systems
PurposeIn recent years, action learning has been widely adopted as a problem solving and leadership development tool. The purpose of the article is to reflect on key learning points when initiating action learning sessions and provide tips on what to expect from such sessions.Design/methodology/approachDocumentation of the author's initial first‐hand action learning coaching experience and sharing of lessons learnt in organizing and coaching action learning sessions.FindingsThe paper offers a view on how action learning practitioners can overcome initial coaching issues to run more effective sessions.Originality/valueThis article contributes to the existing action learning literature by providing a deeper understanding of key factors …
Weight-Based Boosting Model For Cross-Domain Relevance Ranking Adaptation, Peng Cai, Wei Gao, Kam-Fai Wong, Aoying Zhou
Weight-Based Boosting Model For Cross-Domain Relevance Ranking Adaptation, Peng Cai, Wei Gao, Kam-Fai Wong, Aoying Zhou
Research Collection School Of Computing and Information Systems
Adaptation techniques based on importance weighting were shown effective for RankSVM and RankNet, viz., each training instance is assigned a target weight denoting its importance to the target domain and incorporated into loss functions. In this work, we extend RankBoost using importance weighting framework for ranking adaptation. We find it non-trivial to incorporate the target weight into the boosting-based ranking algorithms because it plays a contradictory role against the innate weight of boosting, namely source weight that focuses on adjusting source-domain ranking accuracy. Our experiments show that among three variants, the additive weight-based RankBoost, which dynamically balances the two types …
Learning Feature Dependencies For Noise Correction In Biomedical Prediction, Ghim-Eng Yap, Ah-Hwee Tan, Hwee Hwa Pang
Learning Feature Dependencies For Noise Correction In Biomedical Prediction, Ghim-Eng Yap, Ah-Hwee Tan, Hwee Hwa Pang
Research Collection School Of Computing and Information Systems
The presence of noise or errors in the stated feature values of biomedical data can lead to incorrect prediction. We introduce a Bayesian Network-based Noise Correction framework named BN-NC. After data preprocessing, a Bayesian Network (BN) is learned to capture the feature dependencies. Using the BN to predict each feature in turn, BN-NC estimates a feature's error rate as the deviation between its predicted and stated values in the training data, and allocates the appropriate uncertainty to its subsequent findings during prediction. BN-NC automatically generates a probabilistic rule to explain BN prediction on the class variable using the feature values …