526 publications from this institution
We present a new concept - Wikiometrics - the derivation of metrics and indicators from Wikipedia. Wikipedia provides an accurate representation of the real world due to its size, structure, editing policy and popularity. We demonstrate an innovative mining methodology, where different elements of Wikipedia - content, structure, editorial actions and reader reviews - are used to rank items in a manner which is by no means inferior to rankings produced by experts or other methods. We test our proposed method by applying it to two real-world ranking problems: top world universities and academic journals. Our proposed ranking methods were compared to leading and widely accepted benchmarks, and were found to be extremely correlative but with the advantage of the data being publically available.
This paper introduces BagStacking, a novel ensemble learning method designed to enhance the detection of Freezing of Gait (FOG) in Parkinson's Disease (PD) by using a lower-back sensor to track acceleration. Building on the principles of bagging and stacking, BagStacking aims to achieve the variance reduction benefit of bagging's bootstrap sampling while also learning sophisticated blending through stacking. The method involves training a set of base models on bootstrap samples from the training data, followed by a meta-learner trained on the base model outputs and true labels to find an optimal aggregation scheme. The experimental evaluation demonstrates significant improvements over other state-of-the-art machine learning methods on the validation set. Specifically, BagStacking achieved a MAP score of 0.306, outperforming LightGBM (0.234) and classic Stacking (0.286). Additionally, the run-time of BagStacking was measured at 3828 seconds, illustrating an efficient approach compared to Regular Stacking's 8350 seconds. BagStacking presents a promising direction for handling the inherent variability in FOG detection data, offering a robust and scalable solution to improve patient care in PD.
This paper examines a decision-tree framework for instance-space decomposition. According to the framework, the original instance-space is hierarchically partitioned into multiple subspaces and a distinct classifier is assigned to each subspace. Subsequently, an unlabeled, previously-unseen instance is classified by employing the classifier that was assigned to the subspace to which the instance belongs. After describing the framework, the paper suggests a novel splitting-rule for the framework and presents an experimental study, which was conducted, to compare various implementations of the framework. The study indicates that using the novel splitting-rule, previously presented implementations of the framework, can be improved in terms of accuracy and computation time.
No abstract is provided for this article.
Driving under the influence of alcohol is a widespread phenomenon in the US where it is considered a major cause of fatal accidents. In this research, we present Virtual Breathalyzer, a novel approach for detecting intoxication from the measurements obtained by the sensors of smartphones and wrist-worn devices. We formalize the problem of intoxication detection as the supervised machine learning task of binary classification (drunk or sober). In order to evaluate our approach, we conducted a field experiment and collected 60 free gait samples from 30 patrons of three bars using a Microsoft Band and Samsung Galaxy S4. We validated our results against an admissible breathalyzer used by the police. A system based on this concept successfully detected intoxication and achieved the following results: 0.97 AUC and 0.04 FPR, given a fixed TPR of 1.0. Our approach can be used to analyze the free gait of drinkers when they walk from the car to the bar and vice versa, using wearable devices which are ubiquitous and more widespread than admissible breathalyzers. This approach can be utilized to alert people, or even a connected car, and prevent people from driving under the influence of alcohol.
Machine learning techniques are widely used in many fields. One of the applications of machine learning in the field of information security is classification of a computer behavior into malicious and benign. Antiviruses consisting of signature-based methods are helpless against new (unknown) computer worms. This paper focuses on the feasibility of accurately detecting unknown worm activity in individual computers while minimizing the required set of features collected from the monitored computer. A comprehensive experiment for testing the feasibility of detecting unknown computer worms, employing several computer configurations, background applications, and user activity, was performed. During the experiments 323 computer features were monitored by an agent that was developed. Four feature selection methods were used to reduce the number of features and four learning algorithms were applied on the resulting feature subsets. The evaluation results suggest that by using classification algorithms applied on only 20 features the mean detection accuracy exceeded 90%, and for specific unknown worms accuracy reached above 99%, while maintaining a low level of false positive rate.
In recent years, keystroke dynamics has gained popularity as a reliable means of verifying user identity in remote systems. Due to its high performance in verification and the fact that it does not require additional effort from the user, keystroke dynamics has become one of the most preferred second factor of authentication. Despite its prominence, it has one major limitation: keystroke dynamics algorithms are good at fitting a model to one user and one user only. When such algorithms try to fit a model to more than one user, the verification accuracy decreases dramatically. However, in real-world applications it is common practice for two or more users to use the same credentials, such as in shared bank accounts, shared social media profiles, and shared streaming licenses which allow multiple users in one account. In these cases, keystroke dynamics solutions become unreliable. To address this limitation, we propose a method that can leverage existing keystroke dynamics algorithms to automatically determine the number of users sharing the account and accurately support accounts that are shared with multiple users. We evaluate our method using eight state-of-the-art keystroke dynamics algorithms and three public datasets, with up to five different users in one model, achieving an average improvement in verification of 9.2% for the AUC and 8.6% for the EER in the multi-user cases, with just a negligible reduction of 0.2% for the AUC and 0.3% for the EER in the one-user cases.
In this chapter we discuss how fuzzy logic extends the envelop of the main data mining tasks: clustering, classification, regression and association rules. We begin by presenting a formulation of the data mining using fuzzy logic attributes. Then, for each task, we provide a survey of the main algorithms and a detailed description (i.e. pseudo-code) of the most popular algorithms. There are two main types of uncertainty in supervised learning: statistical and cognitive. Statistical uncertainty deals with the random behavior of nature and all existing data mining techniques can handle the uncertainty that arises (or is assumed to arise) in the natural world from statistical variations or randomness. Cognitive uncertainty, on the other hand, deals with human cognition. Fuzzy set theory, first introduced by Zadeh in 1965, deals with cognitive uncertainty and seeks to overcome many of the problems found in classical set theory. For example, a major problem faced by researchers of control theory is that a small change in input results in a major change in output. This throws the whole control system into an unstable state. In addition there was also the problem that the representation of subjective knowledge was artificial and inaccurate. Fuzzy set theory is an attempt to confront these difficulties and in this chapter we show how it can be used in data mining tasks.
Many leading e-commerce retailers adopt a consistent pricing strategy to build customer trust and promote just a small portion of their catalog each week. Promotion optimization for consistent pricing retailers is a challenging problem, as they need to decide which products to promote, with no historical price elasticity information for the candidate products. In this paper, we introduce a novel approach for predicting product price elasticity impact for e-commerce retailers who use a consistent pricing strategy. We combine the commonly used operation research-based log–log demand model with the nonlinear gradient boosting machines algorithm to predict the price elasticity impact of products with no historical price elasticity information. A pessimistic prediction interval measure is used to accelerate the learning period and reduce the probability of selecting low impact promotions due to high model prediction uncertainty. We demonstrate the effectiveness of our approach on a real-world dataset collected from an online European department store.
Pre-distortion for an optical transmitter modeled with complex frequency selective nonlinearity applicable to different system architecture, based on recurrent neural network is proposed. Several architectures are compared and above 20dB performance gain is presented.
Item-based Collaborative Filtering (CF) models offer good recommendations with low latency. Still, constructing such models is often slow, requiring the comparison of all item pairs, and then caching for each item the list of most similar items. In this paper we suggest methods for reducing the number of item pairs comparisons, through simple clustering, where similar items tend to be in the same cluster. We propose two methods, one that uses Locality Sensitive Hashing (LSH), and another that uses the item consumption cardinality. We evaluate the two methods demonstrating the cardinality based method reduce the computation time dramatically without damage the accuracy.
Multi-level logic synthesis is a problem of immense practical significance, and is a key to developing circuits that optimize a number of parameters, such as depth, energy dissipation, reliability, etc. The problem can be defined as the task of taking a collection of components from which one wants to synthesize a circuit that optimizes a particular objective function. This problem is computationally hard, and there are very few automated approaches for its solution. To solve this problem we propose an algorithm, called Circuit-Decomposition Engine (CDE), that is based on learning decision trees, and uses a greedy approach for function learning. We empirically demonstrate that CDE, when given a library of different component types, can learn the function of Disjunctive Normal Form (DNF) Boolean representations and synthesize circuit structure using the input library. We compare the structure of the synthesized circuits with that of well-known circuits using a range of circuit similarity metrics.
No abstract is provided for this article.
