Abstract

Political propaganda in recent times has been amplified by media news portals through bi- ased reporting, creating untruthful narratives on serious issues causing misinformed public opinions with interests of siding and helping a particular political party. This issue pro- poses a challenging NLP task of detecting po- litical bias in news articles. We propose a transformer-based transfer learning method to fine-tune the pre-trained network on our data for this bias detection. As the required dataset for this particular task was not available, we created our dataset comprising 1388 Hindi news articles and their headlines from various Hindi news media outlets. We marked them on whether they are biased towards, against, or neutral to BJP, a political party, and the current ruling party at the centre in India.

Abstract

This paper presents our solutions for Task4 at SemEval2022: Patronizing and Condescend- ing Language Detection. This shared task con- tains two sub-tasks. The first sub-task is a bi- nary classification task whose goal is to predict whether a given paragraph contains any form of patronising or condescending language(PCL). For the second sub-task, given a paragraph, we have to find which PCL categories express the condescension. Here we have a total of 7 overlapping sub-categories for PCL. Our pro- posed solution uses BERT based ensembled models with hard voting and techniques applied to take care of class imbalances. Our paper de- scribes the system architecture of the submitted solution and other experiments that we con- ducted. Our best performing models achieve an F1 score of 59.4 and 15.7 on sub-tasks 1 and 2 respectively.

Abstract

We investigate Referring Image Segmentation (RIS), which outputs a segmentation map corresponding to the natural language description. Addressing RIS efficiently requires considering the interactions happening across visual and linguistic modalities and the interactions within each modality. Existing methods are limited because they either compute different forms of interactions sequentially (leading to error propagation) or ignore intramodal interactions. We address this limitation by performing all three interactions simultaneously through a Synchronous Multi-Modal Fusion Module (SFM). Moreover, to produce refined segmentation masks, we propose a novel Hierarchical Cross-Modal Aggregation Module (HCAM), where linguistic features facilitate the exchange of contextual information across the visual hierarchy. We present thorough ablation studies and validate our approach’s performance on four benchmark datasets, showing considerable performance gains over the existing state-of-the-art (SOTA) methods.

Abstract

Bluetooth technology has enabled short-range wireless communication for billions of devices. Bluetooth Low-Energy (BLE) variant aims at improving power consumption on battery-constrained devices. BLE-enabled devices broadcast information (e.g., as beacons) to nearby devices via advertisements. Unfortunately, such functionality can become a double-edged sword at the hands of attackers. In this paper, we primarily show how an attacker can exploit BLE advertisements to exfiltrate information from BLE-enable devices. In particular, our attack establishes a communication medium between two devices without requiring any prior authentication or pairing. We develop a proof-of-concept attack framework on the Android ecosystem and assess its performance via a thorough set of experiments. Our results indicate that such an exfiltration attack is indeed possible though with a limited data rate. Nevertheless, we also demonstrate potential use cases and enhancements to our attack that can further its severeness. Finally, we discuss possible countermeasures to prevent such an attack.

Abstract

We propose a novel Riemannian method called “RXML" for solving the Extreme multi-label classification problem that exploits the geometric structure of the sparse low-dimensional local embedding models. A constrained optimization problem is formulated as an optimization problem on a matrix manifold and solved using a Riemannian optimization method. A proof of convergence for the proposed Riemannian optimization method is stated. The proposed approach is tested on several real-world large scale multi-label datasets, and its usefulness is demonstrated through numerical experiments. Experimental results show that RXML improves the trade-off between train time and accuracy. At the similar level of accuracy, the train time of RXML was 1.5 to 4 times faster than that of AnnexML and EXMLDS-4, which are the state-of-the-art embedding- based methods.

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

The emergence of vehicle connectivity technologies and associated applications have paved the way for increased consumer interest in connected vehicles. These modern day vehicles are now capable of sending/receiving vast amounts of data and offloading computation (which is one possible service) to servers thereby improving safety, comfort, driving experience, etc. In the early stages of connectivity, all the data communication and computation offloading happened between the cloud server and the vehicles. However, this is not feasible in scenarios having strict timing requirements and bandwidth cost constraints. Vehicular Edge Computing (VEC) demonstrated an efficient way to tackle the above problem. In order to optimally utilize the resources of the edge servers for data delivery, an efficient edge resource allocation framework needs to be developed. In a recent work, data/service delivery to connected vehicles assumed a worst-case scenario that all vehicles with routes passing through an edge appear in the edge coverage region simultaneously. However, this worst-case scenario is very pessimistic, which results in overestimation of edge resources. We address this by precisely computing the set of vehicles which simultaneously appear in the coverage region of an edge (which we call textit{vehicle overlaps}). In this work, we first propose an optimization framework for edge resource allocation that minimizes the bandwidth cost of data delivery to connected vehicles while considering the traffic flow and vehicle overlaps. Then, we propose an efficient heuristic to deliver data based on minimizing global edge bandwidth cost gradient under vehicle overlaps. We demonstrate the improvement in resource allocation considering vehicle overlaps. Using real world traffic data, we also demonstrate reduction in data delivery times using the proposed heuristic.

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

In this paper, we propose a predictive and cooperative optimal control based autonomous navigation and collision avoidance for multiple fixed-wing aircraft (FWA) that also takes into account the physical constraints of the aircraft. The proposed method is implemented in a cooperative framework, analogous to the Reciprocal Velocity Obstacle (RVO) framework for autonomous navigation and collision avoidance for FWA swarm moving in a three dimensional (3D) space. Also, the change in performance with respect to varying prediction horizon is analyzed through numerical simulations. As a result of predictive optimal control and cooperation, we get less conservative maneuvers, reduced path lengths, and less deviation from the shortest path when compared to the conventional method without prediction and cooperation. Simulation results are provided, highlighting the advantages of the proposed method when compared to a popular method (Optimal reciprocal collision avoidance) for collision avoidance in 3D for FWA swarm and also against FGA algorithm (Fast geometric avoidance algorithm).