Lakshmish Ramaswamy

Prof. Lakshmish Ramaswamy

Department of Computer Science, University of Georgia, Athens, GA 30602, USA

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2023 in ACM Transactions on Internet Technology
Verified
Journal Article
Open access
JHJianwei Hao
Jianwei Hao
PSPiyush Subedi
Piyush Subedi
Lakshmish RamaswamyLakshmish Ramaswamy
Lakshmish Ramaswamy
In kee KimIn kee Kim
In kee Kim
The wide adoption of smart devices and Internet-of-Things (IoT) sensors has led to massive growth in data generation at the edge of the Internet over the past decade. Intelligent real-time analysis of such a high volume of data, particularly leveraging highly accurate deep learning (DL) models, often requires the data to be processed as close to the data sources (or at the edge of the Internet) to minimize the network and processing latency. The advent of specialized, low-cost, and power-efficient edge devices has greatly facilitated DL inference tasks at the edge. However, limited research has been done to improve the inference throughput (e.g., number of inferences per second) by exploiting various system techniques. This study investigates system techniques, such as batched inferencing, AI multi-tenancy, and cluster of AI accelerators, which can significantly enhance the overall inference throughput on edge devices with DL models for image classification tasks. In particular, AI multi-tenancy enables collective utilization of edge devices’ system resources (CPU, GPU) and AI accelerators (e.g., Edge Tensor Processing Units; EdgeTPUs). The evaluation results show that batched inferencing results in more than 2.4× throughput improvement on devices equipped with high-performance GPUs like Jetson Xavier NX. Moreover, with multi-tenancy approaches, e.g., concurrent model executions (CME) and dynamic model placements (DMP), the DL inference throughput on edge devices (with GPUs) and EdgeTPU can be further improved by up to 3× and 10×, respectively. Furthermore, we present a detailed analysis of hardware and software factors that change the DL inference throughput on edge devices and EdgeTPUs, thereby shedding light on areas that could be further improved to achieve high-performance DL inference at the edge.

26 March 2007 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
Lakshmish RamaswamyLakshmish Ramaswamy
Lakshmish Ramaswamy
LLLing Liu
Ling Liu
AIArun Iyengar
Arun Iyengar
In recent years, edge computing has emerged as a popular mechanism to deliver dynamic Web content to clients. However, many existing edge cache networks have not been able to harness the full potential of edge computing technology. In this paper, we argue and experimentally demonstrate that cooperation among the individual edge caches coupled with scalable server-driven document consistency mechanisms can significantly enhance the capabilities and performance of edge cache networks in delivering fresh dynamic content. However, designing large-scale cooperative edge cache networks presents many research challenges. Toward addressing these challenges, this paper presents cooperative edge cache grid (cooperative EC grid, for short)-a large-scale cooperative edge cache network for efficiently delivering highly dynamic Web content with varying server update frequencies. The design of the cooperative EC grid focuses on the scalability and reliability of dynamic content delivery in addition to cache hit rates, and it incorporates several novel features. We introduce the concept of cache clouds as a generic framework of cooperation in large-scale edge cache networks. The architectural design of the cache clouds includes dynamic hashing-based document lookup and update protocols, which dynamically balance lookup and update loads among the caches in the cloud. We also present cooperative techniques for making the document lookup and update protocols resilient to the failures of individual caches. This paper reports a series of simulation-based experiments which show that the overheads of cooperation in the cooperative EC grid are very low, and our architecture and techniques enhance the performance of the cooperative edge networks.

1 September 2018
Verified
Conference Paper
Closed access
NTNavid Hashemi Tonekaboni
Navid Hashemi Tonekaboni
SKSujeet Kulkarni
Sujeet Kulkarni
Lakshmish RamaswamyLakshmish Ramaswamy
Lakshmish Ramaswamy
Crowdsensing temperature data have enabled a paradigm shift in the ways we collect data and analyze the heat exposure effects on individuals and communities. The use of low-cost sensors has helped in gathering granular spatiotemporal temperature data and capturing ever-changing ambient environmental conditions. However, this practice poses challenges such as sensor failures and data integrity. One of the main concerns of the participatory sensing approach is the misplacement of temperature sensors in a way that they are not exposed to the natural outdoor environment. We propose a novel approach to detect anomalous sensor placement in a semi-real-time manner at the edge of the Internet. We introduce a sliding window technique in conjunction with supervised learning classifiers to detect anomalously-placed sensors effectively. This approach is based on the empirical observation that temperature readings show more frequent fluctuations while exposed to the outdoor environment. We also conduct a series of comparative performance analysis of different classifiers including SVM, Logistic Regression, and Random Forest.

5 September 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
AGAbdulrahman Gharawi
Abdulrahman Gharawi
MAMohammad D. Alahmadi
Mohammad D. Alahmadi
Lakshmish RamaswamyLakshmish Ramaswamy
Lakshmish Ramaswamy
Skin cancer poses a significant health risk, affecting multiple layers of the skin, including the dermis, epidermis, and hypodermis. Melanoma, a severe type of skin cancer, originates from the abnormal proliferation of melanocytes in the epidermis. Current methods for skin lesion segmentation heavily rely on large annotated datasets, which are costly, time-consuming, and demand specialized expertise from dermatologists. To address these limitations and improve logistics in dermatology practices, we present a self-supervised strategy for accurate skin lesion segmentation in dermatologist images, eliminating the need for manual annotations. Unlike the traditional appraoch, our proposed approach integrates a hybrid CNN/Transformer model, harnessing the complementary strengths of both architectures. The Transformer module captures long-range contextual dependencies, enabling a comprehensive understanding of image content, while the CNN encoder extracts local semantic information. To dynamically recalibrate the representation space, we introduce a contextual attention module that effectively combines hierarchical features and pixel-level information. By incorporating local and global dependencies among image pixels, we perform a clustering process that organizes the image content into a meaningful space. Furthermore, as another contribution, we incorporate a spatial consistency loss to promote the gradual merging of clusters with similar representations, thereby improving the segmentation quality. Experimental evaluations conducted on two publicly available skin lesion segmentation datasets demonstrate the superiority of our proposed method, outperforming both unsupervised and self-supervised strategies, and achieving state-of-the-art performance in this challenging task.

1 October 2010 in International Journal of Web Services Research
Verified
Journal Article
Closed access
PDF file
OHOsama Al-Haj Hassan
Osama Al-Haj Hassan
Lakshmish RamaswamyLakshmish Ramaswamy
Lakshmish Ramaswamy
JMJohn Miller
John Miller
In recent years, Web 2.0 applications have experienced tremendous growth in popularity. Mashups are a key category of Web 2.0 applications, which empower end-users with a highly personalized mechanism to aggregate and manipulate data from multiple sources distributed across the Web. Surprisingly