Abstract

Unmanned Aerial Vehicle (UAV)-enabled mobile edge computing (MEC) is considered to offer computational capabilities to the resource-constraints end-users. In this paper, we study the task offloading strategy in UAV-enabled MEC systems, where end-users offload the computation-intensive tasks to the UAV to minimize the overall cost in terms of the weighted delay and energy consumption. The end-users either process the task by itself or offload the tasks to the UAV that acts as a computing access point. However, due to the computation bottleneck and limited channel capacity between UAV and the end-users, it becomes a challenging issue to offload the entire tasks to the UAV. Thus, to find the optimal offloading decision for the tasks generated by the end-users, we build a distributed deep neural network (DNN). In the proposed distributed DNN model, we train multiple DNNs in the same training instance, and finally, for validation, we select the DNN that gives the least training loss. For faster convergence of the training process, we use the optimal generated offloading decision using a Quadratically Constrained Linear Program (QCLP) with Semidefinite Relaxation (SDR). The extensive simulation results show that the offloading decision produced by the trained DNN can achieve near-optimal performance with numerous system parameter settings.

Abstract

With the rising need for reliable and real-time pose estimation in resource constrained environments such as smartphones, IoT devices, and head mounts, we need an efficient and compact pose estimation framework. To this end, we propose PoseFromGraph1, a light-weight 3D pose estimation framework. The inputs to PoseFromGraph are: a graph obtained by skeletonizing the 3D meshes using the prairie-fire analogy and the RGB image, and the output is the 3D pose of the object. The introduction of 3D shapes to the architecture makes our model category-agnostic. Unlike computationally expensive multi-view geometry and point-cloud based representations to estimate pose, our approach uses a message passing network to incorporate local neighborhood information at the same time maintaining global shape property in a graph by optimizing a neighborhood preserving objective. PoseFromGraph surpasses the state-of-the-art pose estimation methods in terms of accuracy achieving, 84.43% on the Pascal3D dataset, and at the same time yields 4 × reduction in the space and time complexity. The compact pose estimation models can then be used to facilitate on-device inference in applications in Augmented Reality and Robotics for 3D virtual model overlay.

Abstract

3While deep learning approaches have shown promising results in Natural Language Processing and Computer Vision domains, they have not yet been able to achieve impressive results in Ontology Alignment, and have typically performed worse than rule-based approaches. Some of the major reasons for this are: a) poor modelling of context, b) overfitting of standard DL models, and c) dataset sparsity, caused by class imbalance of positive alignment pairs wrt negative pairs. To mitigate these limitations, we propose a dual-attention based approach that uses a multi-faceted context representation to compute contextualized representations of concepts, which is then used to discover semantically equivalent concepts.

Abstract

Few-shot segmentation (FSS) methods perform image segmentation for a particular object class in a target (query) image, using a small set of (support) image-mask pairs. Recent deep neural network based FSS methods leverage high-dimensional feature similarity between the foreground features of the support images and the query image features. In this work, we demonstrate gaps in the utilization of this similarity information in existing methods, and present a framework - SimPropNet, to bridge those gaps. We propose to jointly predict the support and query masks to force the support features to share characteristics with the query features. We also propose to utilize similarities in the background regions of the query and support images using a novel foreground-background attentive fusion mechanism. Our method achieves stateof-the-art results for one-shot and five-shot segmentation on the PASCAL-5 i dataset. The paper includes detailed analysis and ablation studies for the proposed improvements and quantitative comparisons with contemporary methods.

Abstract

Software quality has become the lever of differentiation in today’s competitive marketplace. Quality at speed is the customer demand and automation is the biggest bottleneck holding the evolution of quality function. Increased levels of automation and intelligence in software engineering are the emerging trends across the IT field. As systems and software processes guide the life cycle activities and are the vehicles for building quality, it is necessary to look at the process infrastructure for the extent of process automation support provided and the digital enablement. This paper maps out the existing process infrastructure support in industry practice and proposes a roadmap for digital re-imagination of software and systems processes. Harmonizing the quality engineering themes with digital technologies, we propose a framework for building an intelligent software process infrastructure, iSPIN that can help in digital re-imagination of software and systems lifecycle processes. The framework has been implemented using digital technologies and has been piloted with one of the industry business unit for re- imagination of “proposal process”. The proposed iSPIN framework will help in unprecedented automation and quality engineering at each process step and paves the way towards realizing the dictums of “Quality at Speed” and “Digital transformation of Software Process”.

Abstract

OCR for printed classical Indic documents written in Sanskrit is a challenging research problem. It involves complexities such as image degradation, lack of datasets and long-length words. Due to these challenges, the word accuracy of available OCR systems, both academic and industrial, is not very high for such documents. To address these shortcomings, we develop a Sanskrit specific OCR system. We present an attention-based LSTM model for reading Sanskrit characters in line images. We introduce a dataset of Sanskrit document images annotated at line level. To augment real data and enable high performance for our OCR, we also generate synthetic data via curated font selection and rendering designed to incorporate crucial glyph substitution rules. Consequently, our OCR achieves a word error rate of 15.97% and a character error rate of 3.71% on challenging Indic document texts and outperforms strong baselines. Overall, our contributions set the stage for application of OCRs on large corpora of classic Sanskrit texts containing arbitrarily long and highly conjoined words.

Abstract

Off-colour humour is a category of humour which is considered by many to be in poor taste or overly vulgar. Most commonly, off-colour humour contains remarks on particular ethnic group or gender, violence, domestic abuse, acts concerned with sex, excessive swearing or profanity. Blue humour, dark humour and insult humour are types of off-colour humour. Blue and dark humour unlike insult humour are not outrightly insulting in nature but are often misclassified because of the presence of insults and harmful speech. As the primary contributions of this paper we provide an original data-set consisting of nearly 15,000 instances and a novel approach towards resolving the problem of separating dark and blue humour from offensive humour which is essential so that free-speech on the internet is not curtailed. Our experiments show that deep learning methods outperforms other n-grams based approaches like SVM’s, Naive Bayes and Logistic Regression by a large margin.

Abstract

This work presents a highly accurate current reference of 66nA for ultra-low power applications. A very low figureof-merit (FOM) of 1.3501ppm/◦C 2 is achieved on consuming a minimal quiescent current of 199.37nA. To cancel out process variations, the current subtraction technique is employed and a β-multiplier is used to compensate for mobility (µ) and threshold voltage (Vth). In addition, curvature compensation technique backed by PTAT and CTAT current cancellation is adopted to attain a lower temperature coefficient (TC). Hence, an imperceptible variation of accuracy with temperature and supply variations across all process corners is attained. An adopted trimming scheme further minimizes the overall process spread to ±1.515% without compromising on accuracy. Accordingly, a TC of 67.04ppm/◦C over a wide temperature range of -50◦C to 100◦C is obtained. Furthermore, 1.413%/V line sensitivity (LS) in the supply range of 1.38V to 3V is observed. Low power consumption of 275.13nW@1.38V facilitates its use in high-performance low power applications. Index Terms—FOM, curvature compensation, Line Sensitivity, Proportional to Absolute Temperature (PTAT), Complementary to Absolute Temperature (CTAT), ZTC

Abstract

This paper presents a systematic review on thermal comfort studies in Indian residential buildings, to identify the present research scenario, data gaps and policy interventions. Majority of the studies are performed in composite climate (ten), followed by warm-humid (seven) and a very few from cold (two) and hot-dry (two) climates. None thermal comfort study is found in the temperate climate. Seven studies have considered multiple climates for assessment of thermal comfort in residential buildings. This shows that thermal comfort studies in Indian residential buildings are scarce, scattered and unorganized. Further, due to differences in socio-cultural set-up and local adaptations, the prodigious variations in occupant’s comfort requirements are reported. This review argues for the dynamic modifications in individual behaviours due to change in cost of building energy services and comfort requirements. Only four studies have partially considered the occupant behaviour regarding control of indoor thermal environment. The results obtained from these studies indicate that there is strong need of localised thermal comfort model that will not only help in improving comfort requirements but also building energy performance. Importantly this review

Abstract

Product placement in retail stores has a significant impact on the revenue of the retailer. Hence, research efforts are being made to propose approaches for improving item placement in retail stores based on the knowledge of utility patterns extracted from the log of customer purchase transactions. Another strategy to make any retail store interesting from a customer perspective is to cater to the varied requirements and preferences of customers. This can be achieved by placing a wider variety of items in the shelves of the retail store, thereby increasing the diversity of the items that are available for purchase. In this regard, the key contributions of our work are three-fold. First, we introduce the problem of concept hierarchy based diverse itemset placement in retail stores. Second, we present a framework and schemes for facilitating efficient retrieval of the diverse top-revenue itemsets based on a concept hierarchy. Third, we conducted a performance evaluation with a real dataset to demonstrate the overall effectiveness of our proposed schemes.