Abstract

Active learning is a rapidly growing field of machine learning which aims at reducing the labeling effortof the oracle (human expert) in acquiring informa-tive training samples in domains where the costof labeling is high. Associative classification is a well established prediction method which possesses the advantages of high accuracy and faster learning rates in classification. In this paper, we propose a novel algorithm which unifies associative classification with active learning. The algorithm has two major procedures of Rule generation and rule pruning.The algorithm selects unlabeled instances from the pool of available samples and uses a unique dynamic rule sampling procedure for updating the model.The rules are dynamically sampled class association rules (CAR) which are generated using the mined Minimal infrequent itemsets. The results derived over 10 datasets from the UCI-ML repository for our approach have been compared with those from the ACTIVE-DECORATE algorithm. We also analyze our sampling method against the state of art sampling frameworks and show that our method performs better.

Abstract

Regression algorithms are used for prediction (including forecasting of time-series data), inference, hypothesis testing, and modeling of causal relationships. Statistical approaches although popular, are not generic in that they require the user to make an intelligent guess about the form of the regression equation. In this paper we present a new regression algorithm SEAR – Scalable, Efficient, Accurate kNN-based Regression. In addition to this, SEAR is simple and outlier-resilient. These desirable features make SEAR a very attractive alternative to existing approaches. Our experimental study compares SEAR with fourteen other algorithms on five standard real datasets, and shows that SEAR is more accurate than all its competitors.

Abstract

Fuzzy association rules use fuzzy logic to convert numerical attributes to fuzzy attributes, like ldquoIncome = Highrdquo, thus maintaining the integrity of information conveyed by such numerical attributes. On the other hand, crisp association rules use sharp partitioning to transform numerical attributes to binary ones like ldquoIncome = [100 K and above]rdquo, and can potentially introduce loss of information due to these sharp ranges. Fuzzy A priori and its different variations are the only popular fuzzy association rule mining (ARM) algorithms available today. Like the crisp version of Apriori, fuzzy A priori is a very slow and inefficient algorithm for very large datasets (in the order of millions of transactions). Hence, we have come up with a new fuzzy ARM algorithm meant for fast and efficient performance on very large datasets. As compared to fuzzy A priori, our algorithm is 8-19 times faster for the very large standard real-life dataset we have used for testing with various mining workloads, both typical and extreme ones. A novel combination of features like two-phased multiple-partition tidlist-style processing, byte-vector representation of tidlists, and fast compression of tidlists contribute a lot to the efficiency in performance. In addition, unlike most two-phased ARM algorithms, the second phase is totally different from the first one in the method of processing (individual itemset processing as opposed to simultaneous itemset processing at each k-level), and is also many times faster. Our algorithm also includes an effective preprocessing technique for converting a crisp dataset to a fuzzy dataset

Abstract

We have developed a web based integrated platform for the identification of genomic islands in which various measures that capture bias in nucleotide compositions have been implemented, viz., GC content (both at the whole genome and at three codon positions in genes), genomic signature, k-mer distribution (k=2–6), codon usage bias and amino acid usage bias. The analysis carried out in sliding windows (default size 10Kb) is compared with the genomic average for each measure. The output is displayed in a tabular format for each window which may be filtered if the values of the measures differ by 1.5σ (standard deviations) from the genomic average.

Abstract

Cool roof is one of the important strategies of energy savings in the tropical climate especially for low rise buildings. Standardization of the possible energy savings for a measure like cool roof would be quite difficult due to availability of various technologies and materials, as well as due to difference in building forms and climatic conditions. This paper talks about the development of an online tool for estimating energy saving through cool roof strategy using Energy Plus v4 as the backend simulation engine. Energy savings are calculated through simulating two identical buildings with different roof reflectivity values. Using this tool, simulations are run for the base case roof reflectivity of 0.3 and proposed case roof reflectivity of 0.75 for various major cities in India for a single floor, daytime use building. An average saving of 6.2% in cooling energy and 2.4% in total energy consumption was obtained using this tool.

Abstract

The method of calibrated simulation has been used to estimate the energy savings by application of cool roof for the building of Satyam Learning Centre (SLC) at Hyderabad (India). Energy simulation model of the building was created using ‘DesignBuilder v. 1.95’and the building was monitored for few months. Mismatch between the simulation results and actual energy consumption has been reduced to obtain the calibrated model of the building using the method suggested in IPMVP Option-D. The calibrated model is then used to predict energy saving from the cool roof; the annual cooling energy savings were 19.4 kWh/m2. This saving corresponds to 9% reduction in annual air conditioning load and 5% reduction in overall annual energy consumption. Cost/benefit analysis for cool roof at SLC showed a 2.4 year financial payback period.

Abstract

This paper explores the area of creating smart spaces using mobile Internet devices to develop intelligent classrooms. We propose a suite of applications that leverage the recent progress made in the domains of mobile computers and information access, resulting in a richer classroom experience where knowledge is dispensed with greater efficiency while also making it possible to access it efficiently from the Internet as well as peers. We attempt to achieve this by introducing novel means of classroom teaching and management and an intelligent information access system while harnessing the computational capabilities of mobile Internet devices. Though the current work is still in progress, this paper elaborates on our attempts in reducing the gap between technological progress in various domains and the existing pedagogy.

Abstract

EnergyPlus is an energy simulation tool which models heating, cooling, lighting, ventilation, and other energy flows in buildings. It is based on the popular features of BLAST and DOE-2. Though EnergyPlus is more advanced than DOE-2, it comes with a drawback of larger simulation runtime. A decrease in the simulation runtime of EnergyPlus would increase the usability of the software. In this paper, a concept has been proposed which uses data parallelization to speed up EnergyPlus simulation. Data parallelization is a form of parallelization for computing across multiple processors or multiple computers in a cluster, run under a suitable environment. Data parallelism focuses on distributing the data across different parallel computing nodes by breaking it into smaller chunks, each of which is processed on by the same function, running in parallel on different cores/machines. In the proposed concept, this is …

Abstract

By extending information and communication technologies, a personalizedagricultural advisory system called eSaguTMhas been developed in which the farmersreceive agricultural expert advice for each of their farms at regular intervals. The expertadvice is prepared by agricultural experts based on the crop status information receivedin the form of both digital photographs and text. During 2004-05, the eSaguTMsystemwas operated for 1051 cotton farms covering three villages in the state of AndhraPradesh, India. In eSaguTM, the expert advice had been delivered to every cottonfarm, once in a week. As a result, the data set consisting of about 20,000 such advicetexts had been generated. In this paper, we have carried out the cluster/textualanalysis experiments on the data set and reported interesting results concerning thedynamics of crop problems. Normally, all are cotton farms and belonging to nearbyarea/region should have faced similar problems. However, the cluster analysis of theadvices delivered on each day shows that significant number of farms are suffering fromdistinct crop production problems. The results also indicate that, a cluster of farmswhich face the same crop problem during one week face distinct crop problems duringthe subsequent weeks. Based on the results, we can conclude that it is necessaryto deliver agricultural expert advice to each farm by building agricultural advisorysystems which deliver farm-specific agricultural advices to reduce crop failures andimprove crop productivity.

Abstract

The main issues in processing read-only transactions (ROTs) are correctness, data currency and performance. The popular two-phase locking (2PL) protocol processes the transactions correctly according to serializability criteria, but its performance deteriorates with data contention. To improve the performance, snapshot isolation (SI)-based approaches have been proposed. Even though SI-based approaches improve performance, however they compromise both correctness and data currency aspects. In the literature, an effort has been made to propose improved approaches to process ROTs based on the notion of speculation. The speculation-based approaches improve performance without compromising both correctness and data currency aspects. In this paper, we have extended the speculation-based protocols for processing ROTs in a distributed database systems. It has been identified that an ROT under speculation-based protocols in distributed database systems require a commit phase. In addition, additional messages are required for making speculative versions available to ROTs during the execution phase of an update transaction. In spite of these overheads, the proposed protocols reduce the waiting time of ROTs significantly by increasing the parallelism without violating both correctness and data currency aspects. The simulation experiments show that the proposed protocols significantly improve the performance over 2PL and SI-based protocols.