Abstract

The problem of data exchange between multiple nodes with storage and communication capabilities models several current multi-user communication problems like Coded Caching, Data Shuffling, Coded Computing, etc. The goal in such problems is to design communication schemes which accomplish the desired data exchange between the nodes with the optimal (minimum) amount of communication load. In this work, we present a converse to such a general data exchange problem. The expression of the converse depends only on the number of bits to be moved between different subsets of nodes, and does not assume anything further specific about the parameters in the problem. Specific problem formulations, such as those in Coded Caching, Coded Data Shuffling, and Coded Distributed Computing, can be seen as instances of this generic data exchange problem. Applying our generic converse, we can efficiently recover known important converses in these formulations. Further, for a generic coded caching problem with heterogeneous cache sizes at the clients with or without a central server, we obtain a new general converse, which subsumes some existing results. Finally we relate a “centralized” version of our bound to the known generalized independence number bound in index coding and discuss our bound’s tightness in this context.

Abstract

This paper analyses patch antennas operating at 16 GHz on flexible Kapton polyimide substrate in various shapes, namely rectangular, circular, pentagon, hexagon, heptagon, and octagon. Their applications in medical areas, more particularly in wearable devices for E-health, are targeted. The bending effects of these antennas are studied, more specifically on gain, return loss, radiation characteristics, bandwidth, and beamwidth. A detailed comparison results showed that the rectangular patch had better performance even under the bending when the diameter of the surface is varied from 40mm to 120mm and maintains a gain of 4.8 dB at the given frequency. Under such extreme bending, the antennas operate satisfactorily with an efficiency of 43.424% to 47.41%

Abstract

Localization of multiple speakers using microphone arrays remains a challenging problem, especially in the presence of noise and reverberation. State-of-the-art localization algorithms generally exploit the sparsity of speech in some representation for this purpose. Whereas the broadband approaches exploit time-domain sparsity for multi-speaker localization, narrowband approaches can additionally exploit sparsity and disjointness in the time-frequency representation. Broadband approaches are robust to spatial aliasing but do not optimally exploit the frequency domain sparsity, leading to poor localization performance for arrays with short inter-microphone distances. Narrowband approaches, on the other hand, are vulnerable to spatial aliasing, making them unsuitable for arrays with large inter-microphone spacing. Proposed here is an approach that decomposes a signal spectrum into a weighted sum of broadband spectral components (atoms) and then exploits signal sparsity in the time-atom representation for simultaneous multiple source localization. The decomposition into atoms is performed in situ using non-negative

Abstract

Sexism, a permeate form of oppression, causes profound sufering through various manifestations. Given the increasing number of experiences of sexism shared online, categorizing these recollections automatically can support the battle against sexism, since it can promote successful evaluations by gender studies researchers and government representatives engaged in policy making. In this paper, we examine the fne-grained, multi-label classifcation of accounts (reports) of sexism. To the best of our knowledge, we consider substantially more categories of sexism than any related prior work through our 23-class problem formulation. Moreover, we present the frst semi-supervised work for the multi-label classifcation of accounts describing any type(s) of sexism. We devise self-training-based techniques tailor-made for the multi-label nature of the problem to utilize unlabeled samples for augmenting the labeled set. We identify high textual diversity with respect to the existing labeled set as a desirable quality for candidate unlabeled instances and develop methods for incorporating it into our approach. We also explore ways of infusing class imbalance alleviation for multi-label classifcation into our semisupervised learning, independently and in conjunction with the method involving diversity. In addition to data augmentation methods, we develop a neural model which combines biLSTM and attention with a domain-adapted BERT model in an endto-end trainable manner. Further, we formulate a multi-level training approach in which models are sequentially trained using

Abstract

Residential electricity consumption (REC) in India has tripled in the past two decades accounting for 24% of the overall electricity consumption during 2018-19. Residential air conditioning (AC) usage is responsible for about 20%-40% of REC in India. This paper investigates the relationship of residential AC use with indoor temperature and relative humidity (RH) using concurrent time-series monitoring data gathered in eight dwellings during summer and monsoon seasons. Contextual data about the dwelling (physical) and household characteristics were gathered using face-to-face interview based surveys. The dwellings were located in Hyderabad representing the composite climate of India. The mean daily electricity consumption was found to be higher in summer (11.5kWh) possibly due to the higher usage of AC (because of higher ambient conditions) as compared to 6.5kWh/day during monsoon season. Binary logistic regression identified the trigger indoor temperature and RH at which AC was likely to be switched on in the summer as 29 °C - 31.9 °C for indoor temperature and 36%-38.9% RH. In the monsoon season AC was predicted to come on sooner at 26°C-28.9°C but at higher RH range of 59%-61.9%. These empirical findings can be used to reduce residential cooling energy demand through smart management of ACs in Indian dwellings

Abstract

A smart city is a collection of a variety of smart devices representing several disparate infrastructural verticals. The data gathered by these smart devices helps bring a strong integration of human, collective, and artificial intelligence within the city operation. With the advent and proliferation of electric vehicles (EVs), the EV charge point is a relatively new addition to this plethora of smart devices. We believe that the EV charge point can acquire enhanced functionality if it can be seamlessly integrated with the rest of the smart city infrastructure. For example, charging services can be stopped if smart grid or smart fire alarms sense an electrical overload or fire hazard in the vicinity. However, the interaction of an EV charge point with the smart city infrastructure requires seamless information exchange across various verticals. This horizontal flow of information is enabled by making the charge point complaint with the oneM2M platform. To this end, we present the design and fabrication of an EV charge point based on the OCPP communication standard and complaint with the oneM2M platform. Further, we discuss various use cases showing an increased functional capability of the EV charger due to access to data from other IoT devices.

Abstract

Natural Language Understanding has made recent advancements where context-aware token representation and word disambiguation have become possible to a large extent. In this scenario, comprehension of phrasal semantics particularly in the context of multi word expressions (MWE) and idioms, is the subsequent task to be addressed. Word level metaphor detection is unable to handle phrases or MWE(s) which occur in both literal and idiomatic context. State of the art transformer architectures can be useful in this context, but the absence of a large comprehensive dataset is a bottleneck. In this paper, we present a labelled EPIE dataset containing 3136 occurrences for 358 formal idioms. To prove the efficacy of our dataset, we also train a sequence classification model effectively and perform cross-dataset evaluation on three independent datasets. Our method achieves good results on all datasets with F1 score of 96% on our test data, and 82%, 74% and 76% F1 score on SemEval All Words, SemEval Lex Sample, and PIE Corpus datasets respectively.

Abstract

Conventional approaches for addressing road safety rely on manual interventions or immobile CCTV infras-tructure. Such methods are expensive in enforcing compliance to traffic rules and do not scale to large road networks. This paper proposes a simple mobile imaging setup to address several common problems in road safety at scale. We use recent computer vision techniques to identify possible irregularities on roads, the absence of street lights, and defective traffic signs using videos from a moving camera-mounted vehicle. Beyond the inspection of static road infrastructure, we also demonstrate the mobile imaging solution’s applicability to spot traffic violations. Before deploying our system in the real-world, we investigate the strengths and shortcomings of computer vi- sion techniques on thirteen condition-based hierarchical labels. These conditions include different timings, road type, traffic density, and state of road damage. Our demonstrations are then carried out on 2000 km of unconstrained road scenes, captured across an entire city. Through this, we quantitatively measure the overall safety of roads in the city through carefully constructed metrics. We also show an interactive dashboard for visually inspecting and initiating action in a time, labor and cost-efficient manner. Code, models, and datasets used in this work will be publicly released

Abstract

3D reconstruction of human body model from a monocular image is an under-constrained and challenging yet desired research problem in computer vision. Recently proposed multi-layered shape repre-sentation called PeeledHuman attempted a sparse non-parametric 2D representation that can handle severe self-occlusion. However, the key limitation of their PeeledHuman model is that the predicted depth maps of self-occluded parts are sparse and noisy, and hence after back-projection lead to distorted body parts and sometimes with discontinuity between them. In this work, proposed to intro- duce Peeled Segmentation map representation in a coarse-to-fine refinement framework which consist of a cascade three networks namely, PeelGAN, PSegGAN and RefGAN. At first, we use original PeeledHuman as baseline model to predict initial coarse estimation of peeled depth maps from input RGB image. These peeled maps are subsequently fed as input along with monocular RGB image to our novel PSegGAN which predict Peeled Segmentation maps in a gen- erative fashion. Finally, we feed these peeled segmentation maps as additional context along with monocular input image to our Ref-GAN which predicts the refined peeled RBG and Depth maps. This also provides an additional output of 3D semantic segmentation of the reconstructed shape. We perform thorough empirical evaluation over four publicly available datasets to demonstrate superiority of our model.

Abstract

This paper presents a learning assistant that tests one’s knowledge and gives feedback that helps a person learn at a faster pace. A learning assistant (based on automated question generation) has extensive uses in education, information websites, self-assessment, FAQs, testing ML agents, research, etc. Multiple researchers, and companies have worked on Virtual Assistance, but majorly in English. We built our learning assistant for Telugu language to help with teaching in the mother tongue, which is the most efficient way of learning. Our system is built primarily based on Question Generation in Telugu. Many experiments were conducted on Question Generation in English in multiple ways. We have built the first hybrid machine learning and rule-based solution in Telugu, which proves efficient for short stories or short passages in children’s books. Our work covers the fundamental question forms with question types: adjective, yes/no, adverb, verb, when, where, whose, quotative, and quantitative (how many/how much). We constructed rules for question generation using Part of Speech (POS) tags and Universal Dependency (UD) tags along with linguistic information of the surrounding relevant context of the word. We used keyword matching, multilingual sentence embedding to evaluate the answer. Our system is primarily built on question generation in Telugu, and is also capable of evaluating the user’s answers to the generated questions.