Abstract

Rare association rules are the association rules consisting ofrare items. It is difficult to mine rare association rules withthe single minimum support based approaches such as Apri-ori and FP-growth as they suffer fromrare item problem. Inthe literature, efforts has been made to extract rare associa-tion rules with multiple minimum supports. It was observedthat the multiple minimum supports-based approach stillsuffers from performance problems. As a part of proposedwork, we have analyzed the multiple minimum supports-based approach and proposed improved approaches for ex-tracting rare association rules. Experimental results showthat the proposed approaches are efficient

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.

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

Rare association rules (or rules) are the association rules involving rare items (low frequent items). To minerare association rules efficiently, an effort has been made in CFP-growth approach to mine frequent patternsusing multiple minimum support (minsup) values. This approach is an extension of FP-growth approach tomultiple minsup values. This approach involves construction of MIS-tree and generating frequent patternsfrom the MIS-tree. The issue in CFP-growth is constructing the compact MIS-tree because CFP-growth con-siders certain items which will generate neither frequent patterns nor rules. In this paper, we propose an effi-cient approach for constructing the compact MIS-tree. To do so, the proposed approach explores the notions“least minimum support” and “infrequent child node pruning”. Experimental results on both synthetic andreal world datasets show that the proposed approach improves the performance over CFP-growth approach.

Abstract

In this paper we have proposed an improved ap-proach to extract rare association rules. Rare association rulesare the association rules containing rare items. Rare items are lessfrequent items. For extracting rare itemsets, the single minimumsupport (minsup) based approaches like Apriori approach sufferfrom “rare item problem” dilemma. At high minsup value, rareitemsets are missed, and at low minsup value, the number offrequent itemsets explodes. To extract rare itemsets, an effort hasbeen made in the literature in which minsup of each item is fixedequal to the percentage of its support. Even though this approachimproves the performance over single minsup based approaches,it still suffers from “rare item problem” dilemma. If minsup forthe item is fixed by setting the percentage value high, the rareitemsets are missed as the minsup for the rare items becomes closeto their support, and if minsup for the item is fixed by setting thepercentage value low, the number of frequent itemsets explodes.In this paper, we propose an improved approach in which minsupis fixed for each item based on the notion of “support difference”.The proposed approach assigns appropriate minsup values forfrequent as well as rare items based on their item supportsand reduces both “rule missing” and “rule explosion” problems.Experimental results on both synthetic and real world datasetsshow that the proposed approach improves performance overexisting approaches by minimizing the explosion of number offrequent itemsets involving frequent items and without missingthe frequent itemsets involving rare items.

Abstract

For clustering, cosine similarity method is apopular approach to compute the similarity between twodocument vectors where each document vector consists ofweighted terms. It can be noted that, the value of theweight assigned to the terms influences the similarity value.Generally, the weight for each term is calculated by using thepopular TF-IDF method. In the TF-IDF method, the weightof a term is a function of its frequency in the document andin overall document collection. However, it can be observedthat, TF-IDF weighting method ignores the semantic asso-ciation between the terms. In this paper, we have proposedan improved term weighting method calledBoostWeightbyconsidering the semantic association between the terms. Forthis, we exploit the generalization ability of hierarchicalknowledge repositories such as “Open Web Directory” tosemantically associate the terms. The proposedBoostWeightmethod increases the weight of terms if they have commongeneralized term. The clustering experiments on the realdata-set show thatBoostWeightimproves both entropy andpurity values over traditional term weighting approaches.

Abstract

Despite the growing importance of other sectors, agriculture continues to hold the key to the growth of GDP, food security, employment and income in India. Over a period of time, agriculture is undergoing a change towards high value crops, livestock, fisheries etc. Along with it substantial changes have occurred in seed varieties, use of chemical inputs, cultivation practices. Such a process has also culminated in distress conditions in the farm sector. Studies1 undertaken in the states of Andhra Pradesh, Karnataka, Maharastra and Punjab have revealed the serious crisis among the farming community. It is pertinent to note that net income is negative in some states( Narayan Moorthy: 2006) and nearly two thirds of the farmers are frustrated with their profession ( Desh

Abstract

In the E-commerce environment, a customer faces several difficul-ties for selecting the product. The technology like recommendationsystem is being developed to improve the performance of productselection. In this paper, we have investigated the problem of ‘se-lecting a product from group of similar products’ faced by the cus-tomer. For example, when a customer wants to buy a Sony camerathrough E-commerce Web site, the customer has to go through theinformation of several Sony camera models to select the appropri-ate one. In this paper, we have proposed an improved approachto help the customers to select the appropriate product. We haveexploited the fact that every product possesses some specialness,which is exhibited through few special features. The proposed ap-proach identifies the special features and organizes the features ofthe product in an effective manner. We have conducted the experi-ments on three real world data-sets related to Nokia-mobile phones,Sony-cameras and HP-laptops. The results indicate that the pro-posed approach has a potential to improve the performance of theproduct selection.

Abstract

The eSaguTMsystem is an IT-based personalized agro advisory system. In this system, the agricultural experts generate the advice by using the latest information about the crop situation received in the form of both photographs and text. The agricultural expert advice is delivered to each farm on a regular basis (typically once in a week/two weeks depending on the type of crop) from the sowing stage to the harvesting stage to the farmer without farmer asking a question. Since 2004, the eSagu system is being developed by operating on several crops and farms in Andhra Pradesh state of India. It has been found that the agriculture expert can prepare the expert advice in an efficient manner based on the crop photographs and the related information. The impact results show that the expert advices helped the farmers to achieve significant savings in the capital investment and improvement in the yield. Encouraged by the results of eSagu experiment, a country-wide integrated agri-service program is planned by Media Lab Asia to provide expert advice and other agri-related services to Indian farming community. In this paper we briefly explain the development of eSagu system, advantages and future plan.

Abstract

Information systems receive data through theuser interface forms. Improperly designed user interface formincreases navigational burden which in turn increases data-entry cost and data-entry errors. Research efforts are goingon to investigate the improved methods for user interfacedesign. Normally, context-based approach is followed to designuser interfaces. In this approach, the input attributes aredivided into several contexts based on the functionality anduser interface form is designed for each context. It can beobserved that, in some information systems, some attributesreceive values only during certain time duration. We termthis property as temporality of the attribute. In this paper,we have proposed an approach to exploit the temporality ofattributes for identifying the active-contexts to design improveduser interface. The implementation results on a real systemshow that the proposed method reduces the navigationalburden significantly as compared to the existing context-basedapproach