Abstract

Blockchains have proven to provide a high level of performance in terms of security and reliability for various applications like cryptocurrencies and Internet-of-Things (IoT). Prism is a recent blockchain algorithm that achieves the physical limit on throughput and latency without compromising security. In recent days, reinforcement learning approaches are investi- gated in traditional blockchains, to improve performance. In this work, we apply Deep Reinforcement Learning (DRL) to one of the promising blockchain protocols, Prism, to optimize its performance. We propose a Deep Reinforcement Learning- based Prism Blockchain (DRLPB) scheme which dynamically optimizes the parameters of the Prism blockchain and helps in achieving a better performance. In DRLPB, we apply two widely used DRL algorithms, Dueling Deep Q Networks (DDQN) and Proximal Policy Optimization (PPO). This work presents a novel approach to applying DDQN and PPO to a blockchain protocol and comparing the performance. The DRLPB scheme adapts the Prism blockchain parameters to enhance the number of votes upto 84% more than Prism, while still preserving the security and latency performance guarantees of Prism.

Abstract

Integrating scalability, interoperability, and security has become crucial with the widespread adoption of Internet of Things (IoT)-enabled smart city solutions. In this context, the oneM2M provides promising technical specifications for an interoperable and secure IoT/M2M system. This paper focuses on the potential threats and their impact on oneM2M standardbased smart city deployments. Further, configurations for baseline security of the oneM2M open-source implementation, called eclipse OM2M, are presented. Recommendations are proposed based on actual on-ground tests conducted on OM2M-based smart city deployment of IIIT Hyderabad (IIIT-H) in India. The tests cover passive eavesdropping, performing replay attacks, brute force on credentials, denial of service, and analysis of access control policies. Index Terms—Eclipse OM2M, Internet of Things (IoT) security, IoT security standardisation, oneM2M, smart city

Abstract

Cognitive brain mapping is enjoying its growth with the availability of large open data sharing efforts as well as the application of modern machine learning and deep learning methods. In this article, we review some of the current practices in cognitive neuroscience predominantly focusing on functional imaging and highlight the tremendous opportunities fostered by the unprecedented scale of datasets in cognitive neuroscience. We also point out challenges and limitations to keep in mind while working with these datasets.

Abstract

The construction of a decision tree on a given data set involves certain features. In case these features have NULL values during the production environment, the decision tree performance suffers. In this work, we develop a methodology to generate subspace deci- sion tree classifiers, where each decision tree uses non-overlapping subsets of feature sets. We build an ensemble classifier over these subspace classifiers to get better performance. We consider different levels of missing data in our ensemble classifier, to show that it is resilient to missing data and can also give better performance even in cases of incomplete data (that is, data with missing values). We show the viability of our methodology using real-life and synthetic data sets. Our approach delivers a simple yet effective missing data resilient decision tree classifier

Abstract

Retailer revenue is significantly impacted by item placement. Given the prevalence and popularity of medium-to-large-sized retail stores, several research efforts have been made towards facilitating item/itemset placement for improving retailer revenue. However, they fail to consider the issue of inventory of the items w.r.t. itemset placement. Notably, the inventory of a given item refers to the number of instances of that item that are available to the retailer for sales purposes. Moreover, efficient retrieval and placement of top-revenue itemsets in the retail store slots cannot be performed by existing approaches. Our key contributions are summarized as follows. First, we introduce the notion of inventory in retail itemset placement. Second, we propose an inventory-aware indexing scheme, designated as IRIS, for efficiently retrieving high-revenue itemsets. Moreover, we propose the IRPS inventory-aware itemset placement scheme, which exploits the IRIS indexing scheme, for facilitating improved retailer revenue. Third, we conduct a performance study with two real datasets to demonstrate the effectiveness of our proposed itemset indexing and placement schemes in improving retailer revenue.

Abstract

Location-based services (LBS), which provide personalized and timely information, entail privacy concerns such as unwanted leaks of current user locations to potential stalkers. In this regard, existing works have proposed dummy generation techniques by creating a cloaking region (CR) such that the user’s location is at a fixed distance from the centre of CR. Hence, if the adversary somehow knows the location of the centre of CR, the user’s location would be vulnerable to attacks. Moreover, in case of the existing approaches, infeasible regions are assumed to have no relationship with time. However, this assumption is typically not valid in real-world scenarios. For example, a supermarket can be considered to be an infeasible region from 9 pm to 9 am since it would be closed at that time. Thus, if a dummy is placed at this location at that particular time, the attacker would know that it is a dummy, thereby reducing the user’s location privacy. In this regard, our key contributions are three-fold. First, we propose an improved dummy generation approach, which we designate as Annulus-based Gaussian Dummy Generation (AGDG), for facilitating improved location privacy for mobile users. Second, we introduce the notion of time-dependent infeasible regions to further improve the dummy generation approach by considering infeasible regions that change with time. Third, we conducted experiments to demonstrate that the AGDG effectively provides improved location privacy, including for regions with time-dependent infeasible regions w.r.t. existing approaches.

Abstract

In the healthcare domain, medical and patient interactions form a crucial part of the diagnosis. Initially, the AI models developed for healthcare centered only on monolingual data. However, such models do not cater to the multilingual regions, where most conversations are Code-Mixed. We present the Code-Mixed Medical Task-Oriented Dialog Dataset to facilitate the research and development of Code-Mixed medical dialog systems. We analyzed the dataset using medical, conversational, and linguistic theories. The dataset contains 3005 Telugu–English Code-Mixed dialogs between patients and doctors with 29 k utterances covering ten specializations with an average code-mixing index (CMI) of 33.3%. We manually annotated the conversational dataset with intents and slot labels. We also present baselines to establish benchmarks on the dataset using existing state-of-the-art Natural Language Understanding …

Abstract

Open-domain question qnswering (OpenQA) involves a retriever for selecting relevant passages from large text corpora (e.g. Wikipedia) and a reading comprehension (RC) model for extracting answers from these retrieved passages. The retrieved passages are often noisy. Since OpenQA relies heavily on efficient passages for better answer prediction, many passage ranker models have been pro- posed to filter out noisy passages. However, their performance is limited because their ranker model scores each passage separately by modelling only the relationship between query and passage. Thus, they could not capture local context information. Their ranker model also ignored the rich initial rank of passages ranked by a search engine. This paper presents a Passage Ranker model that captures local-context information through cross-passage interac- tion. Our ranker model integrates initial ranking and uses modified attention in the cross-passage interaction to compute a better confi- dence score for each passage. Moreover, we integrate SRL into our passage reader and train it on proposed sampled data. Our semantic reader can absorb contextual semantics. Experimental results on four public OpenQA datasets show that o

Abstract

Multilingual Automatic Speech Recognition (ASR) for Indian lan- guages is an obvious technique for leveraging their similarities. We present a detailed analysis of how phonological similarities and differences between languages affect Time Delay Neural Net- work (TDNN) and End-to-End (E2E) ASR. To study this, we select genealogically similar pairs from five Indian languages and train bilingual acoustic models. We compare these against corresponding monolingual acoustic models and find similar phoneme distribu- tions within speech to be the primary factor for improving model performance, with phoneme overlap being secondary. The influ- ence of phonological properties on performance is visible in both cases. Word Error Rate (WER) of E2E decreased by a median of 2.35%, and upto 8.5% when the phonological similarity was great- est. WER of TDNN increased by 11.69% when the similarity was lowest. Thus, it is clear that the choice of supplementary language is important for model performance. Index Terms— Phonetics and Phonology, Analysis, Automatic Speech Recognition, Low-Resource Languages, Multilingual Sys-

Abstract

Autonomous systems are often deployed in the open world where it is hard to obtain complete specifications of objectives and constraints. Operating based on an incomplete model can produce negative side effects (NSEs), which affect the safety and reliability of the system. We focus on mitigating NSEs in environments modeled as Markov decision processes (MDPs). First, we learn a model of NSEs using observed data that contains state-action trajectories and the severity of the associated NSEs. Unlike previous works that associate NSEs with state-action pairs, our framework associates NSEs with entire trajectories, which is more general and captures non-Markovian dependence on states and actions. Second, we learn finite state controllers (FSCs) that predict the NSE severity for a given trajectory and generalize well to unseen data. Finally, we develop a constrained MDP model that uses information from both the underlying MDP and the learned FSC for planning while avoiding NSEs. Our empirical evaluation demonstrates the effectiveness of our approach in learning and mitigating Markovian and non-Markovian NSEs.