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

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

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

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

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

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

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

Software-as-a-Service (SaaS) product companies have brought in significant changes in how we build software from architecture and engineering process perspective. SaaS products are large, dis- tributed software systems hosted in cloud and built using collabo- rating services (or micro-services). The software releases happen in days and weeks, necessitating an agile development process. Novice engineers (those who join the company fresh from college) need to become comfortable with complex systems and proficient in agile delivery with high quality, otherwise they fall behind in productivity. The paper posits that, to be successful at these SaaS product companies, the novice engineers need good modeling and design skills. While this has been for all software development, the changes driven by SaaS products have made this need more acute. Such skills will allow them to capture their feature behaviors (in context of their understanding of the larger product) in an implementation- independent manner and any knowledge gaps can be identified and bridged by their collaborators. We propose a modeling language that is easy for them to learn and use, and which has characteristics suitable for the kind of engineering work they need to do in their early years in a SaaS product company. This modeling language is based on the notion of Transition Systems. The paper demonstrates the usage and value of this language by creating a model for a real feature. The modeling language is quite general and transcends abstraction boundaries. We also present a modeling process that should be used with this language for better results. This is a short position paper that presents an idea about a new modeling language for a specific purpose (helping novice engineers design well at SaaS product companies). Validation studies for the language and the design process is a work in progress and the results will be shared in a full paper later.

Abstract

Sparse neural networks have been proven to generate efficient and better runtimes when compared to dense neural networks. Accelera- tion in runtime is better achieved with structured sparsity. However, generating an efficient sparsity structure to maintain both runtime and accuracy is a challenging task. In this paper, we implement the RBGP4 sparsity pattern derived from the Ramanujan Bipartite Graph Product (RBGP) framework on various Computer Vision tasks and test how well it performs w.r.t accuracy and runtime. Us- ing this approach, we generate structured sparse neural networks which has multiple levels of block sparsity that generates good connectivity due to the presence of Ramanujan bipartite graphs. We benchmark our approach on Semantic Segmentation and Pose Estimation tasks on an edge device (Jetson Nano 2GB) as well as server (V100) GPUs. We compare the results obtained for RBGP4 sparsity pattern with the unstructured and block sparsity patterns. When compared to sparsity patterns like unstructured and block, we obtained significant speedups while maintaining accuracy. KEYWORDS Sparse Neural Networks, Ramanujan Graphs, Semantic Segmenta- tion, Pose Detection ACM Reference Format: Thejasvi Konduru, Furqan Ahmed Shaik, Girish Varma, and Kishore Kotha- palli. 2023. Accelerating Computer Vision Tasks on GPUs using Ramanujan Graph Product Framework. In 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD) (CODS-COMAD 2023), January 4–7, 2023, Mumbai, India. ACM, New York, NY, USA, 5 pages. https://doi.org/10.1145/3570991.3571044

Abstract

Invertible convolutions have been an essential element for building expressive normalizing flow-based generative models since their introduction in Glow. Several attempts have been made to design invertible k × k convolutions that are efficient in training and sampling passes. Though these attempts have improved the expressivity and sampling efficiency, they severely lagged behind Glow which used only 1×1 convolutions in terms of sampling time. Also, many of the approaches mask a large number of parameters of the underlying convolution, resulting in lower expressivity on a fixed run-time budget. We propose a k × k convolutional layer and Deep Normalizing Flow architecture which i.) has a fast parallel inversion algorithm with running time O(nk2 ) (n is height and width of the input image and k is kernel size), ii.) masks the minimal amount of learnable parameters in a layer. iii.) gives better forward pass and sampling times comparable to other k ×k convolution-based models on real-world benchmarks. We provide an implementation of the proposed parallel algorithm for sampling using our invertible convolutions on GPUs. Benchmarks on CIFAR-10, ImageNet, and CelebA datasets show comparable performance to previous works regarding bits per dimension while significantly improving the sampling time.