arXiv subjects

Adil Khan

Publications and source records attributed to Adil Khan.

25 records · Page 2Linked to original sources

arXiv2019

A Survey of Methods to Leverage Monolingual Data in Low-resource Neural Machine Translation

Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora. However, the quality of machine translation for low-resource languages leaves much to be desired. There are several approaches to mitigate this problem, such as transfer learning, semi-supervised and unsupervised learning techniques. In this paper, we review the existing methods, where the main idea is to exploit the power of monolingual data, which, compared to parallel, is usually easier to obtain and significantly greater in amount.

cs.CL↗

arXiv2019

An Accurate Fault Location Algorithm for Meshed Power Networks Utilizing Hybrid Sparse Voltage and Current Measurements

This paper proposes an accurate fault location algorithm technique based on hybrid synchronized sparse voltage and sparse current phasor measurements. The proposed algorithm addresses the performance limitation of fault location algorithms based on only synchronized sparse voltage measurements (SSVM) and on only synchronized sparse current measurements (SSCM). In the proposed method, bus voltage phasor of faulty line or close to the faulty line and branch current phasor of the adjacent line is utilized. The paper contributes to improve the accuracy of fault location and deter the effect of CT saturation by using hybrid voltage and current measurements. The proposed algorithm has been tested on four bus two area power system and IEEE 14 bus system with the typical features of an actual distribution system. The robustness of algorithm has been tested by variation in fault location, fault resistance, load switching. The simulation results demonstrate the accuracy of the proposed algorithm and ensure a reliable fault detection and location method.

eess.SP↗

arXiv2019

SART - Similarity, Analogies, and Relatedness for Tatar Language: New Benchmark Datasets for Word Embeddings Evaluation

There is a huge imbalance between languages currently spoken and corresponding resources to study them. Most of the attention naturally goes to the "big" languages: those which have the largest presence in terms of media and number of speakers. Other less represented languages sometimes do not even have a good quality corpus to study them. In this paper, we tackle this imbalance by presenting a new set of evaluation resources for Tatar, a language of the Turkic language family which is mainly spoken in Tatarstan Republic, Russia. We present three datasets: Similarity and Relatedness datasets that consist of human scored word pairs and can be used to evaluate semantic models; and Analogies dataset that comprises analogy questions and allows to explore semantic, syntactic, and morphological aspects of language modeling. All three datasets build upon existing datasets for the English language and follow the same structure. However, they are not mere translations. They take into account specifics of the Tatar language and expand beyond the original datasets. We evaluate state-of-the-art word embedding models for two languages using our proposed datasets for Tatar and the original datasets for English and report our findings on performance comparison.

cs.CL↗

arXiv2018

Teaching Programming and Design-by-Contract

This paper summarizes the experience of teaching an introductory course to programming by using a correctness by construction approach at Innopolis University, Russian Federation. In this paper we claim that division in beginner and advanced groups improves the learning outcomes, present the discussion and the data that support the claim.

cs.SE↗

arXiv2018

Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks

Automatic analysis of the video is one of most complex problems in the fields of computer vision and machine learning. A significant part of this research deals with (human) activity recognition (HAR) since humans, and the activities that they perform, generate most of the video semantics. Video-based HAR has applications in various domains, but one of the most important and challenging is HAR in sports videos. Some of the major issues include high inter- and intra-class variations, large class imbalance, the presence of both group actions and single player actions, and recognizing simultaneous actions, i.e., the multi-label learning problem. Keeping in mind these challenges and the recent success of CNNs in solving various computer vision problems, in this work, we implement a 3D CNN based multi-label deep HAR system for multi-label class-imbalanced action recognition in hockey videos. We test our system for two different scenarios: an ensemble of $k$ binary networks vs. a single $k$-output network, on a publicly available dataset. We also compare our results with the system that was originally designed for the chosen dataset. Experimental results show that the proposed approach performs better than the existing solution.

cs.CV↗

arXiv2018

Open source platform Digital Personal Assistant

Nowadays Digital Personal Assistants (DPA) become more and more popular. DPAs help to increase quality of life especially for elderly or disabled people. In this paper we develop an open source DPA and smart home system as a 3-rd party extension to show the functionality of the assistant. The system is designed to use the DPA as a learning platform for engineers to provide them with the opportunity to create and test their own hypothesis. The DPA is able to recognize users' commands in natural language and transform it to the set of machine commands that can be used to control different 3rd-party application. We use smart home system as an example of such 3rd-party. We demonstrate that the system is able to control home appliances, like lights, or to display information about the current state of the home, like temperature, through a dialogue between a user and the Digital Personal Assistant.

cs.HC↗

arXiv2010

Scintillator-Based Electromagnetic Calorimeter Prototype and Beam Test Results at FNAL

A prototype Scintillator-Tungsten electromagnetic calorimeter (ScECAL) for the ILC detector was tested in 2008 at the Fermilab test beam. Data were collected with electron, pion and muon beams in the energy range 1 to 32GeV combined with hadronic calorimeter and Tail catcher. One of the main objectives of the CALICE program is to establish the technology of Scintillator-based electromagnetic calorimeter and validate the prformance of the calorimeter. From preliminary results of the first approach of analysis with electron beam, we obtain the ScECAL energy resolution σstochastic = 15.15+/-0.03% and σconstant = 1.44+/-0.02% . The deviation from the linear response is calculated to be less than 6%.

physics.ins-det↗