1,721,192 research outputs found
Emerging Architectures for Global System Science
No full textOur society is organized around a number of (interdependent) global systems. Logistic and supply chains, health services, energy networks, financial markets, computer networks, and cities are just a few examples of such global, complex systems. These global systems are socio-technical and involve interactions between complex infrastructures, man-made processes, natural phenomena, multiple stakeholders, and human behavior. For the first time in the history of manking, we have access to data sets of unprecedented scale and accuracy about these infrastructures, processes, natural phenomena, and human behaviors. In addition, progress in high-performancing computing, data mining, machine learning, and decision support opens the possibility of looking at these problems more holistically, capturing many of these aspects simultaneously. This paper addresses emergent architectures enabling controlling, predicting and reaoning on these systems
Crowdsourcing contest dilemma
No full textCrowdsourcing offers unprecedented potential for solving tasks efficiently by tapping into the skills of large groups of people. A salient feature of crowdsourcing—its openness of entry—makes it vulnerable to malicious behaviour. Such behaviour took place in a number of recent popular crowdsourcing competitions. We provide game-theoretic analysis of a fundamental trade-off between the potential for increased productivity and the possibility of being set back by malicious behaviour. Our results show that in crowdsourcing competitions malicious behaviour is the norm, not the anomaly—a result contrary to the conventional wisdom in the area. Counterintuitively, making the attacks more costly does not deter them but leads to a less desirable outcome. These findings have cautionary implications for the design of crowdsourcing competitions
Depth-k Sharing and Freeness
Full text linkAnalyses for variable sharing and freeness are important both in the automatic parallelisation and in the optimisation of sequential logic programs. In this paper, a new analysis is described which can infer sharing and freeness information to an unusually high degree of accuracy. By encoding structural properties of substitutions in a sharing group fashion, a powerful depth-k sharing and freeness analysis is synthesised which exploits the synergy between tracing sharing information and tracking term structure. The analysis propagates groundness with the accuracy of sharing groups and yet can precisely infer sharing and freeness. Correctness is formally proven
Performance of social network sensors during Hurricane Sandy
No full textInformation flow during catastrophic events is a critical aspect of disaster management. Modern communication platforms, in particular online social networks, provide an opportunity to study such flow and derive early-warning sensors, thus improving emergency preparedness and response. Performance of the social networks sensor method, based on topological and behavioral properties derived from the "friendship paradox", is studied here for over 50 million Twitter messages posted before, during, and after Hurricane Sandy. We find that differences in users' network centrality effectively translate into moderate awareness advantage (up to 26 hours); and that geo-location of users within or outside of the hurricaneaffected area plays a significant role in determining the scale of such an advantage. Emotional response appears to be universal regardless of the position in the network topology, and displays characteristic, easily detectable patterns, opening a possibility to implement a simple "sentiment sensing" technique that can detect and locate disasters.Yury Kryvasheyeu, Haohui Chen, Pascal Van Hentenryck and Manuel Cebrian acknowledge the support of the Australian Government represented by the Department of Broadband, Communications and Digital Economy; and the Australian Research Council through the ICT Centre of Excellence program. Esteban Moro acknowledges the support of Spanish Ministry of Science and Technology under grant FIS2013-47532-C3-3-P. This research was also supported by the Army ResearchPeer reviewe
Nearest-neighbour-induced isolation similarity and its impact on density-based clustering
Full text linkA recent proposal of data dependent similarity called Isolation Kernel/Similarity has enabled SVM to produce better classification accuracy. We identify shortcomings of using a tree method to implement Isolation Similarity; and propose a nearest neighbour method instead. We formally prove the characteristic of Isolation Similarity with the use of the proposed method. The impact of Isolation Similarity on density-based clustering is studied here. We show for the first time that the clustering performance of the classic density-based clustering algorithm DBSCAN can be significantly uplifted to surpass that of the recent density-peak clustering algorithm DP. This is achieved by simply replacing the distance measure with the proposed nearest-neighbour-induced Isolation Similarity in DBSCAN, leaving the rest of the procedure unchanged. A new type of clusters called mass-connected clusters is formally defined. We show that DBSCAN, which detects density-connected clusters, becomes one which detects mass-connected clusters, when the distance measure is replaced with the proposed similarity. We also provide the condition under which mass-connected clusters can be detected, while density-connected clusters cannot.</p
Structured two‐stream attention network for video question answering
Full text linkTo date, visual question answering (VQA) (i.e., image QA and video QA) is still a holy grail in vision and language understanding, especially for video QA. Compared with image QA that focuses primarily on understanding the associations between image region-level details and corresponding questions, video QA requires a model to jointly reason across both spatial and long-range temporal structures of a video as well as text to provide an accurate answer. In this paper, we specifically tackle the problem of video QA by proposing a Structured Two-stream Attention network, namely STA, to answer a free-form or open-ended natural language question about the content of a given video. First, we infer rich longrange temporal structures in videos using our structured segment component and encode text features. Then, our structured two-stream attention component simultaneously localizes important visual instance, reduces the influence of background video and focuses on the relevant text. Finally, the structured two-stream fusion component incorporates different segments of query and video aware context representation and infers the answers. Experiments on the large-scale video QA dataset TGIF-QA show that our proposed method significantly surpasses the best counterpart (i.e., with one representation for the video input) by 13.0%, 13.5%, 11.0% and 0.3 for Action, Trans., TrameQA and Count tasks. It also outperforms the best competitor (i.e., with two representations) on the Action, Trans., TrameQA tasks by 4.1%, 4.7%, and 5.1%
Recommended from our members
Decision-Focused Learning for the Masses With Applications to Public Health
Full text linkIn this thesis, I aim to better understand how to best train Machine Learning models for decision-making under uncertainty. Specifically, I focus on the ``Predict-then-Optimize'' framework, in which uncertain quantities are predicted using ML models, and decisions are made by solving optimization problems parameterized by these predictions. While past Decision-Focused Learning (DFL) methods show that optimizing directly for decision quality leads to improved outcomes, existing approaches typically require extensive manual effort—such as designing differentiable surrogate optimization tasks—limiting their applicability to arbitrary problems. Moreover, evaluating the real-world impact of these models in resource-constrained settings poses additional challenges.
This thesis, therefore, addresses the central question: Can we create generalizable methods to train and evaluate decision-focused learning models on arbitrary decision-making tasks so that DFL can be more practically useful? In response, I introduce methods that distill task-specific decision-making structures into a learned, differentiable ``decision loss,'' eliminating the need for handcrafted surrogates. I first propose Locally Optimized Decision Losses (LODLs), demonstrating their improved performance across multiple domains. I then extend this approach via Efficient Global Losses (EGLs), significantly enhancing generalization, efficiency, and theoretical robustness.
Additionally, I develop rigorous statistical estimators for accurately evaluating DFL models in resource allocation scenarios. Applying these estimators to real-world randomized control trials reveals insights previously hidden by existing methods. Collectively, these contributions establish a broadly applicable, reliable framework for decision-focused learning, making DFL more practically viable across diverse decision-making contexts.Engineering and Applied Sciences - Computer Scienc
Robust anomaly detection in videos using multilevel representations
Full text linkDetecting anomalies in surveillance videos has long been an important but unsolved problem. In particular, many existing solutions are overly sensitive to (often ephemeral) visual artifacts in the raw video data, resulting in false positives and fragmented detection regions. To overcome such sensitivity and to capture true anomalies with semantic significance, one natural idea is to seek validation from abstract representations of the videos. This paper introduces a framework of robust anomaly detection using multilevel representations of both intensity and motion data. The framework consists of three main components: 1) representation learning using Denoising Autoencoders, 2) level-wise representation generation using Conditional Generative Adversarial Networks, and 3) consolidating anomalous regions detected at each representation level. Our proposed multilevel detector shows a significant improvement in pixel-level Equal Error Rate, namely 11.35%, 12.32% and 4.31% improvement in UCSD Ped 1, UCSD Ped 2 and Avenue datasets respectively. In addition, the model allowed us to detect mislabeled anomalies in the UCDS Ped 1.</p
- …
