previous day
next day
all days

View: session overviewtalk overviewside by side with other conferences

10:00-10:20Coffee Break
11:20-12:20 Session 12G: Deployed Application of Machine Learning
Deployed: An Antimicrobial Prescription Surveillance System that Learns from Experience
SPEAKER: unknown

ABSTRACT. Inappropriate prescribing of antimicrobials is a major clinical and health concern, as well as a financial burden, in hospitals worldwide. In this paper, we describe a deployed automated antimicrobial prescription surveillance system that has been assisting hospital pharmacists in identifying and reporting inappropriate antimicrobial prescriptions. One of the key characteristics of this system is its ability to learn new rules for detecting inappropriate prescriptions based on previous false alerts. The supervised learning algorithm combines instance-based learning and rule induction techniques. It exploits temporal abstraction to extract a meaningful time interval representation from raw clinical data, and applies nearest neighbor classification with a distance function on both temporal and non-temporal parameters. The learning capability is valuable both in configuring the system for initial deployment and improving its long term use. We give an overview of the application, point to lessons learned so far and provide insight into the machine learning capability.

Deployed: GRADE: Machine Learning Support for Graduate Admissions
SPEAKER: unknown

ABSTRACT. This paper describes GRADE, a statistical machine learning system developed to support the work of the graduate admissions committee in the University of Texas at Austin Department of Computer Science (UTCS). In recent years, UTCS has received increasingly large pools of PhD applicants that are unwieldy to manage with a traditional review process. GRADE uses a dataset of historical admissions data to predict how likely each new applicant is to be admitted to the graduate program. Its predictions are reported to the admissions committee along with a human-readable explanation. GRADE makes the review process more efficient, in part, by enabling reviewers to identify very high- and low-quality applicants quickly, leaving more time to deliberate on borderline applicants. An evaluation over two seasons of PhD admissions indicates that the system leads to dramatic time savings, reducing the total time spent on reviews by at least 74%.

12:30-13:45Lunch Break
14:45-15:45 Session 16F: Monitoring and Response Systems
Emerging: Timed Probabilistic Automaton: A Bridge between Raven and Song Scope for Automatic Species Recognition
SPEAKER: unknown

ABSTRACT. Raven and Song Scope are two state-of-the-art auto-mated sound analysis tools based on machine learning techniques for environmental monitoring. Many research works have been conducted upon them, however, no or rare exploration mentions about the performance and comparison between them. This paper compares the tools from six aspects: theory, software interface, ease of use, detection targets, detection accuracy, and potential applications. Through deep exploration one critical gap is identified that there is a lack of approach to detect both syllables and call structures, since Raven only aims to detect syllables while Song Scope targets call structures. Therefore, a Timed Probabilistic Automata (TPA) system is proposed which separates syllables first and clusters them into complex structures after.

Emerging: Multiagent Router Throttling: Decentralized Coordinated Response against DDoS Attacks
SPEAKER: unknown

ABSTRACT. Distributed denial of service (DDoS) attacks constitute a rapidly evolving threat in the current Internet. In this paper we introduce Multiagent Router Throttling, a decentralized DDoS response mechanism in which a set of upstream routers independently learn to throttle traffic towards a victim server. We compare our approach against a baseline and a popular throttling technique from the literature, and we show that our proposed approach is more secure, reliable and cost-effective. Furthermore, our approach outperforms the baseline technique and either outperforms or has the same performance as the popular one.

Emerging: Scalable Randomized Patrolling for Securing Rapid Transit Networks
SPEAKER: unknown

ABSTRACT. Mass Rapid Transit using rail is a popular mode of transport employed by millions of people in many urban cities across the world. Typically, these networks are massive and can be a soft target for criminals. In this paper, we consider the problem of scheduling randomised patrols for improved security of rail networks. Similar to existing work in randomised patrols for protecting critical infrastructure, we also employ Stackelberg Games to represent the problem. Towards addressing this problem in massive rail networks, our contributions in this paper are two fold: (1) An approach called RaPtoR for computing randomized strategies in patrol teams, which guarantees (i) Strong Stackelberg equilibrium (SSE); and (ii) Optimality in terms of distance travelled by the patrol teams for certain constraints on schedules. (2) Secondly, we demonstrate this approach on a real world data set corresponding to the rail network in Singapore. Further, we also show that the algorithm scales easily to large rail networks while providing randomized strategies in SSE.

15:45-16:15Coffee Break
16:45-17:55 Session 19G: Constraint-Based Scheduling
Deployed: The Deployment of a Constraint-Based Dental School Timetabling System
SPEAKER: unknown

ABSTRACT. We describe a constraint-based timetabling system that was developed for the dental school based at Cork University Hospital in Ireland. This system has been deployed since 2010. Dental school timetabling differs from other university course scheduling in that certain clinic sessions can be used by multiple courses at the same time, provided a limit on room capacity is satisfied. Starting from a constraint programming solution using a web interface, we have moved to a mixed integer programming-based solver to deal with multiple objective functions, along with a dedicated Java application, which provides a rich user interface. Solutions for the years 2010, 2011 and 2012 have been used in the dental school, replacing a manual timetabling process, which could no longer cope with increasing student numbers and resulting resource bottlenecks. The use of the automated system allowed the dental school to increase student numbers to the maximum possible given the available resources. It also provides the school with a valuable "what-if" analysis tool.

Emerging: Train Outstable Scheduling as Constraint Satisfaction
SPEAKER: unknown

ABSTRACT. This paper outlines the design of a constraint satisfaction problem (CSP) scheduling algorithm that allocates outstabling locations to railway trains. From time to time railway trains may need to be outstabled to temporary locations, such as stations, sidings, depots, etc., until they are needed for regular operations. This is common for urban rail transit, and especially so for those that do not operate 24 hours. During non-traffic hours (NTH), trains are outstabled to various locations along the rail network so that when operations start again next day, the trains will be nearby their originating station or conveniently located so that they can be put into service whenever needed. This is the case for Hong Kong. However, this is complicated by the fact that engineering works, such as rail testing, installation, regular maintenance, etc. are all done during the NTH. Therefore, the outstabling algorithm must allocate passenger trains in such a way that they do not interfere with night-time engineering works and the movements of associated engineering trains. This paper shows how we modeled the outstabling problem as a constraint-satisfaction problem and implemented into an ├ČOutstabling System├« (OSS) for MTR.

Emerging: Balancing the Traveling Tournament Problem for Weekday and Weekend Games
SPEAKER: unknown

ABSTRACT. The Traveling Tournament Problem (TTP) is a complex problem in sports scheduling, involving constraint programming to create a schedule of home and away games that meet the feasibility requirements, as well as integer programming to minimize total travel. In this paper, we tackle the TTP from a graph-theoretic perspective, by generating a "canonical" schedule in which each team's three-game road trips match up with the underlying graph's minimum-weight P_3-packing. We apply this canonical schedule to produce a new TTP approximation algorithm, and generate solutions for the three-dimensional n-team Galaxy benchmark data set, producing feasible tournaments for n \in {22, 28, 34, 40} that beat all previously-known solutions.