Abstract

In this paper, we address the problem of active learning using the notion of in uence sets based on Reverse Nearest Neighbor. Active learning is an area of machine learning which emphasizes on achiev-ing optimal classi cation performance using as few labeled samples as possible. Reverse nearest neighbors have been used in domains such a sclustering and outliers detection in the past e ectively. In this paper, we devise a new sampling method for instances based on the knowledge pro-vided from RNN in uence sets. To demonstrate the eectiveness of our sampling method, we compare its performance against existing sampling methods on few real life datasets. The experimental results show that our technique outperforms existing methods, particularly on multi-class datasets

Abstract

The thermostat control variable in conventional HVAC System is air temprature Ta

Abstract

The study, conducted in composite climate of India, exhibits improvement in energy efficiency of a conditioned building block with the use of energy conservation measures (ECMs) recommended by National Energy Conservation Building Code (ECBC). In first part of it, subject building model was individually applied with five ECMs and two combinations of these ECMs by using constant thermostat settings. Similarly in second part of the study the same was done with adaptive thermostat settings. Sensitivity analysis showed that the effect of ECMs get reduced with increase in building footprint and internal loads. Analysis of thermal comfort in an unconditioned building using same set of ECMs was also carried out to see improvement in comfort hours.

Abstract

This article presents an approach for speeding EnergyPlus simulations. The computing run time of an energy simulation depends on several variables and is directly proportional to the simulation RunPeriod. In the proposed approach, data parallelization is achieved by breaking an annual simulation into several segments of smaller RunPeriod, each handled by a separate computer/processor. The speed gain achieved by running 12 one-month RunPeriod segments in parallel as compared to single simulation of 12 months is between three and six times. Segmentation of simulation has resulted in minor deviations between the results obtained through segmented simulations and annual simulations. Methods for reducing these deviations on annual and monthly basis are presented in this article using 12 benchmark models each simulated for five cities. On annual basis, a maximum deviation of 0.06% was observed …

Abstract

Recently, temporal occurrences of the frequent patterns in a transactional database has been exploited as an interestingness criterion to discover a class of user-interest-based frequent patterns, called periodic-frequent patterns. Informally, a frequent pattern is said to be periodic-frequent if it occurs at regular intervals specified by the user throughout the database. The basic model of periodic-frequent patterns is based on the notion of “single constraints.” The use of this model to mine periodic-frequent patterns containing both frequent and rare items leads to a dilemma called the “rare item problem.” To confront the problem, an alternative model based on the notion of “multiple constraints” has been proposed in the literature. The periodic-frequent patterns discovered with this model do not satisfy downward closure property. As a result, it is computationally expensive to mine periodic-frequent patterns with the model. Furthermore, it has been observed that this model still generates some uninteresting patterns as periodic-frequent patterns. With this motivation, we propose an efficient model based on the notion of “multiple constraints.” The periodic-frequent patterns discovered with this model satisfy downward closure property. Hence, periodic-frequent patterns can be efficiently discovered. A pattern-growth algorithm has also been discussed for the proposed model. Experimental results show that the proposed model is effective.

Abstract

In this paper, we have made an effort to propose approachesto find similar legal judgements by extending the popu-lar techniques used in information retrieval and search en-gines. Legal judgements are complex in nature and re-fer other judgements. We have analyzed all-term, legal-term, co-citation and bibliographic coupling-based similaritymethods to find similar judgements. The experimental re-sults show that the legal-term cosine similarity method per-forms better than all-term cosine similarity method. Also,the results show that bibliographic coupling similarity methodimproves the performance over co-citation approach.

Abstract

Recommender systems employ the popular K-nearest neigh-bor collaborative filtering (K-CF) methodology and its vari-ations for recommending the products. In K-CF approach,recommendation for a given user is computed based on theratings of K-nearest neighbors. In K-CF approach, it can benoted that, the system identifiesKneighbors for each userirrespective of the number of products he/she has rated.As a result, the user who have rated few products may getthe less-similar neighbors and the user who have rated moreproducts may miss the genuine neighbors. In the literature,the notion of lower-bound similarity has been proposed toimprove the clustering performance in which the clusters areextracted by fixing the similarity threshold. In this paper,we have extended the notion of lower-bound similarity torecommender systems to improve the performance of K-CFapproach. In the proposed approach, instead of fixingKfor finding the neighborhood, the similarity threshold valueis fixed to extract the neighbors for each user. As a re-sult, each user gets appropriate number of neighbors basedon the number of products rated by him/her in a dynamicmanner. The experimental results, on MovieLens dataset,show that the proposed lower bound similarity CF approachimproves the performance of recommender systems over K-CF approach.

Abstract

Frequent patterns are an important class of regularities thatexist in a transaction database. Certain frequent patternswith low minimum support (minsup) value can provide use-ful information in many real-world applications. However,extraction of these frequent patterns with singleminsup-based frequent pattern mining algorithms such as Aprioriand FP-growth leads to “rare item problem.” That is, athighminsupvalue, the frequent patterns with lowminsupare missed, and at lowminsupvalue, the number of frequentpatterns explodes. In the literature,“multipleminsupsframe-work” was proposed to discover frequent patterns. Further-more, frequent pattern mining techniques such as MultipleSupport Apriori and Conditional Frequent Pattern-growth(CFP-growth) algorithms have been proposed. As the fre-quent patterns mined with this framework do not satisfydownward closure property, the algorithms follow differenttypes of pruning techniques to reduce the search space. Inthis paper, we propose an efficient CFP-growth algorithmby proposing new pruning techniques. Experimental resultsshow that the proposed pruning techniques are effective.

Abstract

MapReduce framework has received a wide acclaim over the past few years for large scale computing. It has become a standard paradigm for batch oriented workloads. As the adoption of this paradigm has increased rapidly, scheduling of these MapReduce jobs has become a problem of great interest in research community. We propose an approach which tries to maintain harmony among the jobs running on the cluster, and in turn decrease their runtime. In our model, the scheduler is made aware of different types of jobs running on the cluster. The scheduler tries to allocate a task on a node if the incoming task does not affect the tasks already running on that node. From the list of available pending tasks, our algorithm selects the one that is most compatible with the tasks already running on that node. We bring up heuristic and machine learning based solutions to our approach and try to maintain a resource balance on the cluster by not overloading any of the nodes, thereby reducing the overall runtime of the jobs. The results show a saving of runtime of around 21% in the case of heuristic based approach and around 27% in the case of machine learning based approach when compared to Yahoo's Capacity scheduler.

Abstract

In this report, we present details about the participation of IIIT Hyderabad in Guided Summarization and Knowledge Base Population tracks at TAC 2011. we have enhanced our summarization system with knowledge based measures. Wikipedia based extraction methods and topic modelling are used to score sentences in guided summarization track. For multilingual summarization task, we investigated the HAL (Hyperspace Analogue to Language Model) where we created a semantic space from word co-occurrences. We show that the results obtained with this unsupervised language independent method are competitive with other state-of-the-art systems. For monolingual and multilingual entity linking task, we extended our previous year’s model to a light weight language independent system without utilizing any other external knowledge or resource.