A notable amount of work has been done to find sentence embeddings using compositional models in recent years. These works have shown that one of the simplest and most effective approaches to obtaining sentence embeddings is simple vector averaging of off-the-shelf word embeddings trained on large corpora. Recent literature introduced word weighting schemes based on the words frequency distribution into the simple averaging model. The frequency-based weighted averaging models augmented with the denoising steps are shown to outperform many complex deep learning models. However, these frequency-based weighting schemes derive the word weights solely based on their raw counts and ignore the diversity of contexts in which these words occur. This paper proposes an alternative weighting scheme that captures the contextual diversity in the word embedding space. The proposed weighting algorithm is simple, unsupervised, and non-parametric. Experimental results on semantic textual similarity tasks show that the proposed weighting method outperforms all the baseline models with significant margins and performs competitively to the current frequency-based state-of-the-art weighting approach. Furthermore, as the frequency distribution-based approaches and the proposed word embeddings geometry-based weighting approach capture two different properties of the words, we define hybrid weighting schemes to combine both the varieties. We also empirically demonstrate that the hybrid weighting methods perform consistently better than the corresponding individual weighting schemes.

High utility itemset mining is an important model in data mining. It involves discovering all itemsets in a quantitative transactional database that satisfy a user-specified minimum utility (minUtil) constraint. MinUtil controls the minimum value that an itemset must maintain in a database. Since the model evaluates an itemset’s interestingness using only the minUtil constraint, it implicitly assumes that all items in the database have similar utility values. However, some items have high utility, while others may have relatively low utility in a database. If minUtil is set too high, the user will miss all itemsets containing low utility items. To find itemsets that involve both high and low utility items, minUtil has to be set very low. However, this may cause a combinatorial explosion as the items with high utility may combine with others in all possible ways. This dilemma is called the low utility item problem. This paper proposes a flexible model of relative high utility itemset to address this problem. We introduce a new null-invariant measure, called utility ratio, to evaluate the interestingness of an itemset in the database. We also present a fast single scan algorithm to find all desired itemsets in the database. Experimental results demonstrate that the proposed algorithm is efficient. Finally, a case study on Yahoo! JAPAN retail data shows that the proposed model is useful.

Spatial High Utility Itemset Mining (SHUIM) is an important knowledge discovery technique with many real-world applications. It involves discovering all itemsets that satisfy the user-specified m inimum u tility (minUtil) i n a q uantitative spatiotemporal database. The popular adoption and the successful industrial application of this technique have been hindered by the following two limitations: (i) Since the rationale of SHUIM is to find all itemsets that satisfy the minUtil constraint, it often produces too many patterns, most of which may be redundant or uninteresting to the user. (ii) Specifying a right minUtil value is an open research problem in SHUIM. This paper tackles these two problems by proposing a novel model of top-k spatial high utility itemsets that may exist in a database. A new constraint, called dynamic minimum utility (dMinUtil), was explored to reduce the search space effectively. This constraint is based on a greedy search, where we raise its value through five thresholdraising strategies. An efficient single scan algorithm that employs depth-first search to find all top-k spatial high utility itemsets was also presented in this paper. Experimental results demonstrate that our algorithm is memory and runtime efficient. We will also demonstrate the usefulness of our algorithm with two real-world case studies.

Placement of items on the shelf space of retail stores significantly impacts the revenue of the retailer. Since customers typically tend to buy sets of items (i.e., itemsets) together, several research efforts have been undertaken towards facilitating itemset placement in retail stores for improving retailer revenue. However, they fail to consider that the time-period of expiry can vary across items i.e., some items expire sooner than others. This leads to loss of opportunity towards improving retailer revenue. Hence, we propose PEAR, which is a Product Expiry-Aware and Revenue-conscious itemset placement scheme for improving retailer revenue. Our key contributions are three-fold. First, we introduce the problem of addressing retail itemset placement when the items can be associated with different time-periods of expiry. Second, we propose the expiry-aware PEAR scheme for efficiently identifying and placing high-revenue itemsets for improving retailer revenue. Third, we conduct a performance study with two real datasets to demonstrate that PEAR is indeed effective in improving retailer revenue w.r.t. a reference scheme.

Product placement in retail has a significant impact on the sales revenue of retailers. Hence, research efforts are being made to improve retailer revenue using high-utility pattern mining based product placement approaches. However, none of these existing approaches has explored generalized high-utility itemset mining for determining product placement in retail. The knowledge of generalized high-utility itemsets extracted from user purchase transactional database in conjunction with a product taxonomy can provide new insights about customer purchase behaviour. This work proposes the generalized utility itemset (GUI) index for retrieving generalized high-utility (revenue) itemsets. We also present a framework, which leverages the GUI index towards retail product placement to improve revenue. Our performance study using real datasets shows the effectiveness of our proposed scheme w.r.t. two existing schemes.

Finding partial periodic patterns in very large databases is a challenging problem of great importance in many real-world applications. Most previous work focused on finding these patterns in temporal (or transactional) databases and did not recognize the spatial characteristics of items. In this paper, we propose a more flexible model of partial periodic spatial pattern that may be present in spatiotemporal database. Three constraints, maximum inter-arrival time(maxIAT), minimum period-support(minPS) and maximum distance(maxDist), have been employed to determine the interestingness of a pattern in a spatiotemporal database. The maxIAT controls the maximum duration in which a pattern must reappear to consider its occurrence as periodic within the data. The minPS controls the minimum number of periodic occurrences of a pattern within the data. The maxDist controls the maximum distance between the items in a pattern. All patterns satisfying these three constraints are returned. An efficient algorithm, called SpatioTemporal-Equivalence CLAss Transformation (ST-ECLAT), has also been described to discover all partial periodic spatial patterns in a spatiotemporal database. This algorithm employs a novel smart depth-first search technique to discover desired patterns effectively. Experimental results demonstrate that the proposed algorithm is efficient. We also present a case study in which we apply our model to find useful information in the air pollution database.

Pattern mining is an important task of data mining and involves the extraction of interesting associations from large databases. Typically, pattern mining is carried out from huge databases, which tend to get updated several times. Consequently, as a given database is updated, some of the patterns discovered may become invalid, while some new patterns may emerge. This has motivated significant research efforts in the area of Incremental Mining. The goal of incremental mining is to efficiently and incrementally mine patterns when a database is updated as opposed to mining all of the patterns from scratch from the complete database. Incidentally, research efforts are being made to develop incremental pattern mining algorithms for extracting different kinds of patterns such as frequent patterns, sequential patterns and utility patterns. However, none of the existing works addresses incremental mining in the context of coverage patterns, which has important applications in areas such as banner advertising, search engine advertising and graph mining. In this regard, the main contributions of this work are three-fold. First, we introduce the problem of incremental mining in the context of coverage patterns. Second, we propose the IncCMine algorithm for efficiently extracting the knowledge of coverage patterns when incremental database is added to the existing database. Third, we performed extensive experiments using two real-world click stream datasets and one synthetic dataset. The results of our performance evaluation demonstrate that our proposed IncCMine algorithm indeed improves the performance significantly w.r.t. the existing CMine algorithm.

In real-world databases, high utility itemset (HUI) is an important class of regularities. Most previous studies have focused on mining HUIs in transactional databases and did not consider the spatiotemporal characteristics of items. In this study, a more flexible model of spatial HUIs (SHUIs) that exist in spatiotemporal databases is proposed. In a spatiotemporal database (STD), an itemset is said to be an SHUI if its utility is not less than a user-specified minimum utility and the distance between any two of its items is not more than a user-specified maximum distance. Identifying SHUIs is very challenging because the generated itemsets do not satisfy the anti-monotonic property. In this study, we present two novel pruning techniques for reducing computational costs. Moreover, a fast single scan algorithm is presented for effectively evaluating all SHUIs in a STD. Furthermore, two case studies are presented, in which the proposed model is used to identify useful information in traffic congestion data and air pollution data.

Weighted Frequent Itemset (WFI) mining is an important model in data mining. The popular adoption and successful industrial application of this model has been hindered by the following two obstacles: (i) finding WFIs is a computationally expensiveness process as these itemsets do not satisfy the downward closure property and (ii) lack of parallel algorithms to find WFIs in very large databases (e.g. astronomical data and twitter data). This paper makes an effort to address these two obstacles. Two pattern-growth algorithms, Sequential Weighted Frequent Pattern-growth and Parallel Weighted Frequent Pattern-growth, have been introduced to discover WFIs efficiently. Both algorithms employ three novel pruning techniques to reduce the computational cost effectively. The first pruning technique prunes some of the uninteresting items by employing a criterion known as cutoff weight. The second pruning technique, called conditional pattern base elimination, eliminates the construction of conditional pattern bases if a suffix item is an uninteresting item. The third pruning technique, called pattern-growth termination, defines a new terminating condition for the pattern-growth technique. Experimental results demonstrate that the proposed algorithms are memory and runtime efficient, and highly scalable as well.

Advertising through web search engines is one of the modes of online advertising and is described as Adwords problem. In Adwords, advertisers bid on keywords to display advertisements along with corresponding search results. During keyword auction, there is very high competition for the frequent keywords while little to no competition for the less frequent ones. In this paper, we have proposed an approach to utilize the advertisement space related to infrequent keywords to meet the demands of more advertisers by employing the notions of coverage and concept taxonomy. We employed the notion of coverage to form the multiple distinct groups of infrequent keywords. We also employed concept taxonomy to ensure that each group of keywords is semantically related. We have conducted experiments on the search queries dataset of AOL search engine. The results show that the proposed approach has a potential to meet the advertising demands of more number of advertisers over the existing approach.

Protein-protein interaction (PPI) networks are valuable biological data source which contain rich information useful for protein function prediction. The PPI network data set obtained from high-throughput experiments is known to be noisy and incomplete. By modeling PPI data as a graph, research efforts are being made in the literature to improve the performance of protein function prediction by extending common neighbor, clustering, and classification based approaches. These approaches exploit the fact that protein shares function with other proteins which are connected through common neighbours. As PPI data is modeled as a graph, it contains prominent nodes which establish relatively high connectivity with other modes. In this paper we propose an improved approach for protein function prediction by exploiting the connectivity properties of prominent proteins. Experimental results on real-world data sets demonstrate the effectiveness of proposed approach.

In banner advertisement scenario, advertiser expects his advertisement should be displayed to certain percentage of visitors. He also expects the advertisement to be relevant to the content of web page. On the other hand, to generate more revenue for a given website, publisher has to meet the coverage demands of several advertisers by providing appropriate sets of pages. Coverage patterns (CPs) are a set of web pages visited by certain percentage of visitors. The model of CPs does not reflect the real world scenario as they do not capture the aspect of relevance of web pages to the advertisement. In this paper, we propose a model of content-specific CPs and a methodology to extract content-specific CPs from click-through data, given keywords describing every web page. Content-specific CP is a set of web pages visited by certain percentage of users interested in particular content of the web pages. Experimental results show that the proposed model extracts CPs relevant to the topics of interest of advertiser over the previous model.

Frequent patterns are an important class of regularities that exist in a transaction database. Certain frequent patterns with low minimum support (minsup) value can provide useful information in many real-world applications. However, extraction of these frequent patterns with single minsupbased frequent pattern mining algorithms such as Apriori and FP-growth leads to “rare item problem. ” That is, at high minsup value, the frequent patterns with low minsup are missed, and at low minsup value, the number of frequent patterns explodes. In the literature,“multiple minsups framework” was proposed to discover frequent patterns. Furthermore, frequent pattern mining techniques such as Multiple Support Apriori and Conditional Frequent Pattern-growth (CFP-growth) algorithms have been proposed. As the frequent patterns mined with this framework do not satisfy downward closure property, the algorithms follow different types of pruning techniques to reduce the search space. In this paper, we propose an efficient CFP-growth algorithm by proposing new pruning techniques. Experimental results show that the proposed pruning techniques are effective.

In this paper we have proposed an improved approach to extract rare association rules. Rare association rules are the association rules containing rare items. Rare items are less frequent items. For extracting rare itemsets, the single minimum support (minsup) based approaches like Apriori approach suffer from ldquorare item problemrdquo dilemma. At high minsup value, rare itemsets are missed, and at low minsup value, the number of frequent itemsets explodes. To extract rare itemsets, an effort has been made in the literature in which minsup of each item is fixed equal to the percentage of its support. Even though this approach improves the performance over single minsup based approaches, it still suffers from ldquorare item problemrdquo dilemma. If minsup for the item is fixed by setting the percentage value high, the rare itemsets are missed as the minsup for the rare items becomes close to their support, and if minsup for the item is fixed by setting the percentage value low, the number of frequent itemsets explodes. In this paper, we propose an improved approach in which minsup is fixed for each item based on the notion of ldquosupport differencerdquo. The proposed approach assigns appropriate minsup values for frequent as well as rare items based on their item supports and reduces both ldquorule missingrdquo and ldquorule explosionrdquo problems. Experimental results on both synthetic and real world datasets show that the proposed approach improves performance over existing approaches by minimizing the explosion of number of frequent itemsets involving frequent items and without missing the frequent itemsets involving rare items.

In this paper, we explain a personalized agricultural advisory system called eSagu, which has been developed to improve the performance and utilization of agriculture technology and help Indian farmers. In eSagu, rather than visiting the crop in person, the agricultural expert delivers the expert advice at regular intervals (once in one or two weeks) to each farm by getting the crop status in the form of digital photographs and other information. During 2004-06, through eSagu, agricultural expert advices delivered for about 6000 farms covering six crops. The results show that the expert advices helped the farmers to achieve savings in capital investment and improved the crop yield. Mainly, the data warehouse of farm histories has been developed which is providing the crop related information to the agricultural expert in an integrated manner for generating a quality agricultural expert advice. In this paper, after explaining eSagu and its advantages, we discuss how data warehouse of farm histories is enabling agricultural expert to deliver a quality expert advice. We also discuss some research issues to improve the performance of eSagu.

We have proposed speculative locking (SL) protocols to improve the performance of distributed database systems (DDBSs) by trading extra processing resources. In SL, a transaction releases the lock on the data object whenever it produces corresponding after-image during its execution. By accessing both before and after-images, the waiting transaction carries out speculative executions and retains one execution based on the termination (commit or abort) mode of the preceding transactions. By carrying out multiple executions for a transaction, SL increases parallelism without violating serializability criteria. Under the naive version of SL, the number of speculative executions of the transaction explodes with data contention. By exploiting the fact that a submitted transaction is more likely to commit than abort, we propose the SL variants that process transactions efficiently by significantly reducing the number of speculative executions. The simulation results indicate that even with manageable extra resources, these variants significantly improve the performance over two-phase locking in the DDBS environments where transactions spend longer time for processing and transaction-aborts occur frequently.

Insect pests are a major cause of crop loss globally. Pest management will be effective and efficient if we can predict the occurrence of peak activities of a given pest. Research efforts are going on to understand the pest dynamics by applying analytical and other techniques on pest surveillance data sets. We make an effort to understand pest population dynamics using neural networks by analyzing pest surveillance data set of Helicoverpa armigera or Pod borer on chickpea (Cicer arietinum L.) crop. The results show that neural network method successfully predicts the pest attack incidences for one week in advance.

Distributed locking is commonly adopted for performing concurrency control in distributed systems. It incorporates additional steps for handling deadlocks. This activity is carried out by methods based on wait-for-graphs or probes. The present study examines detection of conflicts based on enhanced local processing for distributed concurrency control. In the proposed "edge detection" approach, a graph-based resolution of access conflicts has been adopted. The technique generates a uniform wait-for precedence order at distributed sites for transactions to execute. The earlier methods based on serialization graph testing are difficult to implement in a distributed environment. The edge detection approach is a fully distributed approach. It presents a unified technique for locking and deadlock detection exercises. The technique eliminates many deadlocks without incurring message overheads.

The Web harbors a large number of community structures. Early detection of community structures has many purposes such as reliable searching and selective advertising. In this paper we investigate the problem of extracting and relating the web community structures from a large collection of Web-pages by performing hyper-link analysis. The proposed algorithm extracts the potential community signatures by extracting the corresponding dense bipartite graph (DBG) structures from the given data set of web pages. Further, the proposed algorithm can also be used to relate the extracted community signatures. We report the experimental results conducted on 10 GB TREC (Text REtrieval Conference) data collection that contains 1.7 million pages and 21.5 million links. The results demonstrate that the proposed approach extracts meaningful community signatures and relates them.

The authors propose an improved concurrency control protocol based on speculation for nested transactions and explain how it increases both intraand inter-transaction concurrency as compared to J.E.B. Moss's (1985) nested locking protocol. In the proposed speculative nested locking (SNL) protocol, whenever a sub-transaction finishes work with a data object (produces after-image), it's parent inherits the lock. The waiting sub-transaction carries out speculative executions by accessing both before- and after-images of preceding sub-transaction and selects appropriate execution after the termination of the preceding subtransaction. In this way, SNL allows multiple executions to be carried out for a transaction by trading extra processing and main memory resources to increase concurrency.

Replicated data management systems adopt the 1-copy serializability criteria for processing transactions. In order to achieve this goal, many approaches rely on obtaining votes from other sites for processing update requests. In the proposed approach, a technique for generation of precedence graphs for each transaction execution is analyzed. The transaction data flow graph approach is a fully distributed approach. The proposed technique, is free from deadlocks, and avoids resubmission of transactions.>