Abstract

Location-based services (LBS), which provide personalized and timely information, entail privacy concerns such as unwanted leaks of current user locations to potential stalkers. In this regard, existing works have proposed dummy generation techniques by creating a cloaking region (CR) such that the user’s location is at a fixed distance from the centre of CR. Hence, if the adversary somehow knows the location of the centre of CR, the user’s location would be vulnerable to attacks. Moreover, in case of the existing approaches, infeasible regions are assumed to have no relationship with time. However, this assumption is typically not valid in real-world scenarios. For example, a supermarket can be considered to be an infeasible region from 9 pm to 9 am since it would be closed at that time. Thus, if a dummy is placed at this location at that particular time, the attacker would know that it is a dummy, thereby reducing the user’s location privacy. In this regard, our key contributions are three-fold. First, we propose an improved dummy generation approach, which we designate as Annulus-based Gaussian Dummy Generation (AGDG), for facilitating improved location privacy for mobile users. Second, we introduce the notion of time-dependent infeasible regions to further improve the dummy generation approach by considering infeasible regions that change with time. Third, we conducted experiments to demonstrate that the AGDG effectively provides improved location privacy, including for regions with time-dependent infeasible regions w.r.t. existing approaches.

Abstract

Retailer revenue is significantly impacted by item placement. Given the prevalence and popularity of medium-to-large-sized retail stores, several research efforts have been made towards facilitating item/itemset placement for improving retailer revenue. However, they fail to consider the issue of inventory of the items w.r.t. itemset placement. Notably, the inventory of a given item refers to the number of instances of that item that are available to the retailer for sales purposes. Moreover, efficient retrieval and placement of top-revenue itemsets in the retail store slots cannot be performed by existing approaches. Our key contributions are summarized as follows. First, we introduce the notion of inventory in retail itemset placement. Second, we propose an inventory-aware indexing scheme, designated as IRIS, for efficiently retrieving high-revenue itemsets. Moreover, we propose the IRPS inventory-aware itemset placement scheme, which exploits the IRIS indexing scheme, for facilitating improved retailer revenue. Third, we conduct a performance study with two real datasets to demonstrate the effectiveness of our proposed itemset indexing and placement schemes in improving retailer revenue.

Abstract

It is a well-established fact that strategic placement of items on the shelves of a retail store significantly impacts the revenue of the retailer. Consumer goods sold in retail stores can be classified into essential and typically low-priced convenience items, and non-essential and high-priced shopping items. Notably, the lower-priced convenience items are critical to ensuring consumer foot-traffic, thereby also driving the sales of shopping items. Moreover, users typically buy multiple items together (i.e., itemsets) to facilitate one-stop shopping. Hence, it becomes a necessity to strategically index and place itemsets that contain both convenience items and shopping items. In this regard, we propose a consumer-good-type aware and revenue-conscious itemset indexing scheme for efficiently retrieving high-revenue itemsets containing both convenience and shopping items. Moreover, we propose an itemset placement …

Abstract

Location-based services (LBSs) in a mobile network environment that provide personalized and timely information to users entail privacy concerns due to the leakage of user locations to adversaries. In the literature, several cloaking-based privacy preservation approaches have been proposed by considering the P2P environment. However, existing spatial cloaking approaches form a large cluster of mobile users to cloak the user query location. Maintaining such structures in a highly dynamic mobile- P2P network is challenging. In addition to user’s location, the user’s intent is also an important concern and needs to be preserved from an adversary. This paper proposes a location privacy and intent privacy preservation scheme, especially for spatial range queries. The key contributions of our work are three-fold. First, we introduce the concept of ijk-anonymity to achieve improved location privacy. Second, we propose a location- based privacy-preservation approach, which we designate as ijkCloak, for spatial range queries in a mobile network environ- ment. The proposed approach preserves user location and intent information from the LBS provider and nearby peers. Third, we conduct theoretical analysis and experiments on resistance to attacks. We show that ijkCloak effectively facilitates improved user location privacy and intent privacy by employing fewer peers w.r.t. existing approaches. Index Terms—Mobile computing, location-based services, loca- tion privacy, spatial cloaking, spatial queries, peer-to-peer, spatial range queries

Abstract

Link forecasting in a temporal Knowledge Graph (tKG) in- volves predicting a future event from a given set of past events. Most previous studies suffered from reduced performance as they disregarded acyclic rules and enforced a tight constraint that all past events must exist in a strict temporal order. This paper proposes a novel explainable rule-based link forecasting framework by introducing two new concepts, namely ‘relaxed temporal cyclic and acyclic random walks’ and ‘link-star rules’. The former concept involves generating rules by performing cyclic and acyclic random walks on a tKG by taking into account the real-world phenomenon that the order of any two events may be ignored if their oc- currence time gap is within a threshold value. Link-star rules are a special class of acyclic rules generated based on the natural phenomenon that history repeats itself after a particular time. Link-star rules eliminate the problem of combinatorial rule explosion, thereby making our frame- work practicable. Experimental results demonstrate that our framework outperforms the state-of-the-art by a substantial margin. The evaluation measures hits@1 and mean reciprocal rank were improved by 45% and 23%, respectively. Keywords: Knowledge Graphs · Graph Analytics · Forecasting

Abstract

No Results Found

Abstract

Developing methods for extracting relevant legal information to aid legal practitioners is an active research area. In this regard, research efforts are being made by leveraging different kinds of information, such as meta-data, citations, keywords, sentences, paragraphs, etc. Similar to any text document, legal documents are composed of paragraphs. In this paper, we have analyzed the resourcefulness of paragraph-level information in capturing similarity among judgments for improving the performance of precedence retrieval. We found that the paragraph-level methods could capture the similarity among the judgments with only a few paragraph interactions and exhibit more discriminating power over the baseline document-level method. Moreover, the comparison results on two benchmark datasets for the precedence retrieval on the Indian supreme court judgments task show that the paragraph-level methods exhibit comparable performance with the state-of-the-art methods.

Abstract

Periodic pattern mining is an emerging technique for knowledge discovery. Most previous approaches have aimed to find only those patterns that exhibit full (or perfect) periodic behavior in databases. Consequently, the existing approaches miss interesting patterns that exhibit partial periodic behavior in a database. With this motivation, this paper proposes a novel model for finding partial periodic patterns that may exist in temporal databases. An efficient pattern-growth algorithm, called Partial Periodic Pattern-growth (3P-growth), is also presented, which can effectively find all desired patterns within a database. Substantial experiments on both real-world and synthetic databases showed that our algorithm is not only efficient in terms of memory and runtime, but is also highly scalable. Finally, the effectiveness of our patterns is demonstrated using two case studies. In the first case study, our model was employed to identify the highly polluted areas in Japan. In the second case study, our model was employed to identify the road segments on which people regularly face traffic congestion.

Abstract

Alongside revenue maximization, retailers seek to offer a diverse range of items to facilitate sustainable revenue generation in the long run. Moreover, customers typically buy sets of items, i.e., itemsets, as opposed to individual items. Therefore, strategic placement of diversified and high-revenue itemsets is a priority for the retailer. Research efforts made towards the extraction and placement of high-revenue itemsets in retail stores do not consider the notion of diversification. Further, candidate itemsets generated using existing utility mining schemes usually explode; which can cause memory and retrieval- time issues. This work makes three key contributions. First, we propose an efficient framework for retrieval of high-revenue itemsets with a varying size and a varying degree of diversification. A higher degree of diversification is indicative of fewer repetitive items in the top-revenue itemsets. Second, we propose the kUI (k Utility Itemset) index for quick and efficient retrieval of diverse top-λ high-revenue itemsets. We also propose the HUDIP (High-Utility and Diversified Itemset Placement) scheme, which exploits our proposed kUI index for placement of high-revenue and diversified itemsets. Third, our extensive performance study with both real and synthetic datasets demonstrates the effectiveness of our proposed HUDIP scheme in efficiently determining high-revenue and diversified itemsets.

Abstract

India Meteorological Department (IMD) has started block-level level agromet advisory (AA) service from the year 2015 and is currently operating in a few blocks of each state across India. In a block-level AA service, on every Tuesday and Friday, AA is being prepared for each block based on the block-level Medium Range weather Forecast (MRF). In this paper, we propose a framework to improve the preparation of block- level AA by modeling a weather situation as “Category-based Weather Condition (CWC)” and exploiting both “temporal reuse” and “spatial reuse” of AA based on the similarity among CWCs. The weather data analysis for 12 blocks of Telangana by considering the phenophase-specific CWCs of Rice crop showed that there is a scope to improve the efficiency of block-level AA bulletin preparation process by exploiting reuse