Abstract

Visual data obtained during driving scenarios usually con-tain large amounts of text that conveys semantic information necessary to analyse the urban environment and is integral to the traffic control plan. Yet, research on autonomous driving or driver assistance systems typically ignores this information. To advance research in this direction, we present RoadText-3K, a large driving video dataset with fully anno-tated text. RoadText-3K is three times bigger than its predecessor and contains data from varied geographical locations, unconstrained driving conditions and multiple languages and scripts. We offer a comprehensive analysis of tracking by detection and detection by tracking methods ex-ploring the limits of state-of-the-art text detection. Finally, we propose a new end-to-end trainable tracking model that yields state-of-the-art results on this challenging dataset. Our experiments demonstrate the complexity and variability of RoadText-3K and establish a new, realistic benchmark for scene text tracking in the wild.

Abstract

Information Security in the cyber world is a major cause for concern, with significant increase in the number of attack surfaces. Existing information on vulnerabilities, attacks, controls, and advisories available on web provides an opportunity to represent knowledge and perform security analytics to mitigate some of the concerns. Representing security knowledge in the form of ontology facilitates anomaly detection, threat intelligence, reasoning and relevance attribution of attacks, and many more. This necessitates dynamic and automated enrichment of information security ontologies. However, existing ontology enrichment algorithms based on natural language processing and ML models have issues with contextual extraction of concepts in words, phrases and sentences. This motivates the need for sequential Deep Learning architectures that traverse through dependency paths in text and extract embedded vulnerabilities, threats, controls, products and other security related concepts and instances from learned path representations. In the proposed approach, Bidirectional LSTMs trained on a large DBpedia dataset and Wikipedia corpus of 2.8 GB along with Universal Sentence Encoder is deployed to enrich ISO 27001 [1] based information security ontology. The model is trained and tested on an high performance computing (HPC) environment to handle Wiki text dimensionality. The approach yielded a test accuracy of over 80% when tested with knocked out concepts from ontology and web page instances to validate the robustness. Index Terms—Ontology Enrichment, Information Security, Bidirectional LSTM, Universal Sentence Encoder

Abstract

nd optimizing an electromechanical system, instinctively affecting its performance. In this study, design optimization, finite element analysis, and experimental evaluation of capacitive pressure sensors were conducted. The air pressure sensing application was demonstrated to characterize different sensors, which include a combination of multiple rectangular cantilevers and diaphragms (square and circular-shaped). After the design improvement, we found that the square and circular diaphragms each with two trapezoidal cantilevers exhibited highest sensitivity to air pressure monitoring among the different investigated designs which combine the square and circular diaphragms with cantilevers. These designs were then selected for further analysis for acoustic pressure monitoring. The sensors were fabricated using the do- it-yourself technique with household materials such as post-it paper, posted tape, and foil. Our approach offers an alternative to the conventional cleanroom fabrication technique and uses easily available materials to fabricate affordable sensors. Therefore, this is the first step toward the development of democratized and sustainable electronic devices that are affordable and available to everyone on the internet.

Abstract

This paper presents a fast and efficient optimization engine with multi-directional, multi-objective algorithms based on a robust transistor sizing approach to improve digital circuit performance. However, such optimization processes are highly simulator-dependent and computationally expensive tasks. Therefore, we propose developing machine learning-based reliable models considering process and operating variations to speed up the optimization procedure by running them on developed Residual Neural Network (ResNN) models instead of running expensive circuit simulations. Results on 22nm Metal Gate HighK digital cells show a reduction in delay and leakage up to 36.7% and 18.8%, respectively improving computational efficiency by several orders.

Abstract

This paper aims to provide an unsupervised modelling approach that allows for a more flexible representation of text embeddings. It jointly encodes the words and the paragraphs as individual matrices of arbitrary column dimension with unit Frobenius norm. The representation is also linguistically motivated with the introduction of a novel similarity metric. The proposed modelling and the novel similarity metric exploits the matrix structure of embeddings. We then go on to show that the same matrices can be reshaped into vectors of unit norm and transform our problem into an optimization problem over the spherical manifold. We exploit manifold optimization to efficiently train the matrix embeddings. We also quantitatively verify the quality of our text embeddings by showing that they demonstrate improved results in document classification, document clustering, and semantic textual similarity benchmark tests.

Abstract

AI is adept at using large quantities of data, sometimes sensitive personal data, and can adversely affect individuals’ privacy. Data privacy concerns significantly impact the course of next-generation AI. Users do not trust anyone withholding their data and need privacy-preserving intelligent systems. In addition, several regulations mandate that organizations handle users’ data in ways that do not affect their privacy and provide them control on their data. Federated Learning emerged as a privacy-preserving technology for data-intensive machine learning by training the models on-site or on-device. However, several concerns related to federated learning emerged due to: (i) dynamic, distributed, heterogeneous, and collaborative nature of client devices, (ii) membership inference and model inversion attacks affecting the overall privacy and security of FL systems, (iii) the need for strict compliance to data privacy and protection laws, (iv) the vulnerabilities at local client devices leading to data leakage, and (iv) diversity and ubiquity of smart devices collecting real-time multimodal data leading to lack of standardization efforts for security and privacy management framework. In this paper, we discuss (a) how federated learning can help us withholding privacy, (b) the need for improving security and privacy in federated learning systems, (c) the privacy regulations and their application to federated learning in various business domains, (d) proposed a federated recommender system and demonstrated the performance that matches the central setting.

Abstract

The exact determination of settlement and the time required to complete that settlement is very important from the safety point of view. There are several methods available to find the rate of consolidation that is highly dependent on the settlement versus time curve. Here, it has been attempted to identify the suitable method for the determination of the rate of consolidation of coal ash. After analyzing the value of the coefficient of consolidation (Cv) estimated from various methods, the rectangular hyperbola method (RH method) is found to be in best linear correlation between the measured Cv and calculated Cv. The coal ash shows an increment in Cv with the increase in effective pressure. The Cv obtained from the RH method is higher than the Cv obtained from Taylor’s and Casagrande method that helps in close approximation with field Cv. The precise determination of Cv helps in better prediction of the time required for the consolidation settlement that will increase the performance of the structure.

Abstract

In many Asian countries with unconstrained road traffic conditions, driving violations such as not wearing helmets and triple-riding are a significant source of fatalities involving motorcycles. Identifying and penalizing such riders is vital in curbing road accidents and improving citizens’ safety. With this motivation, we propose an approach for detecting, tracking, and counting motorcycle riding violations in videos taken from a vehicle-mounted dashboard camera. We employ a curriculum learning-based object detector to better tackle challenging scenarios such as occlusions. We introduce a novel trapezium-shaped object boundary representation to increase robustness and tackle the rider-motorcycle association. We also introduce an amodal regressor that generates bounding boxes for the occluded riders. Experimental results on a large-scale unconstrained driving dataset demonstrate the superiority of our approach compared to existing approaches and other ablative variants.

Abstract

In recent years, semi-transparent building-integrated photovoltaics (BIPV) technology has attracted attention for its renewable energy utilization. This research aims to develop a methodology for assessing the energy-saving potential of semi-transparent photovoltaic (STPV) window, which has a complex relationship with daylighting and air conditioning (AC) electricity consumption. A case study has been developed for the composite climate of Hyderabad, India. The study examines four commercially available single and double pane STPV windows and similar non-photovoltaic windows. For evaluation, an automated parametric simulation tool was developed to compute the net electricity consumption (NEC) for a representative model building with different window systems, and several window-to-wall ratios (WWR) and orientations. The result shows benefit in adopting the STPV window system across all directions and higher optimal WWR in STPV window as compared to normal window with the same opto-thermal characteristics.

Abstract

Clause recommendation is the problem of recommending a clause to a legal contract, given the context of the contract in question and the clause type to which the clause should belong. With not much prior work being done toward the generation of legal contracts, this problem was proposed as a first step toward the bigger problem of contract generation. As an open-ended text generation prob-lem, the distinguishing characteristics of this problem lie in the nature of legal lan-guage as a sublanguage and the considerable similarity of textual content within the clauses of a specific type. This similarity aspect in legal clauses drives us to investi-gate the importance of similar contracts’ representation for recommending clauses. In our work, we experiment with generating clauses for 15 commonly occurring clause types in contracts expanding upon the previous work on this problem and analyzing clause recommendations in varying settings using information derived from similar contracts.