About

Richard P. Martin is an Associate Professor in the Department of Computer Science at Rutgers University. His research activities are centered around wireless technologies, as evidenced by his involvement with WINLAB, a laboratory dedicated to wireless research. He maintains a comprehensive curriculum vitae and provides detailed explanations of his research interests, along with a list of his publications and talks available through external links. In addition to his research, Professor Martin is engaged in teaching, offering courses such as CS 505: Computer Structures during the Spring 2024 semester. He is not hiring research assistants for the Spring 2024 semester but provides opportunities for grader or recitation PTL positions. Professor Martin's office is located in CoRE 304 at Rutgers University, where he is available by appointment.

Research topics

• Computer Science
• Artificial Intelligence
• Embedded system
• Operating system
• Information Retrieval
• Database
• Machine Learning
• Computer hardware
• Algorithm
• Mathematics
• Distributed computing
• Parallel computing
• Computational science

Selected publications

• An Irish Odyssey : Tradition and Autofiction in Pádraig de Brún’s An Odaisé

  2025-11-21

  other1st authorCorresponding
  PublisherDOI

• The Archilochus Diet: Comedy and Empty Calories in Pythian 2

  2024-10-07

  book-chapter1st authorCorresponding
  PublisherDOI

• Poster Abstract: A Radar Based User Discrimination System for Medication Adherence Monitoring

  2023-05-05

  article

  Medication non-adherence is a major healthcare challenge globally, with over half of patients with chronic conditions in developed countries failing to follow their prescribed medication regimen. This can lead to poor disease outcomes, increased hospital visits, and a significant financial burden on healthcare systems [1]. These issues have driven a recent wave of research, including the development of smart adherence products [6] that can be incorporated into a patient’s daily life to monitor medication adherence. In this work, we present a radar-based system for user identification while taking medication, which extends our recent work [5]. we conducted preliminary experiments examining semi-medication-taking activities executed by 6 subjects. Our system achieved 80% accuracy in identifying who has taken the medication in a group of 3 subjects.

  PublisherDOI

• Bearing Error Diagnosis Using Deep Learning and Convolution Neural Network

  2023-03-03 · 3 citations

  article1st authorCorresponding

  Fault diagnostics and prognostics are essential issues. Industrial plants will be under a huge amount of pressure that maintains unpredictable interruption, system failures, and safety issues to a minimum, that necessitates identifying and eliminating potential issues as quickly as possible. Intelligent problem diagnosis is a promising technique because of its capacity to handle gathered signals quickly and effectively while also offering reliable diagnosis findings. Numerous authors have validated deep learning and machine learning approaches for identifying bearings failures, the findings have mostly been confined to tiny train and test datasets, with the input data modified to achieve high accuracy. In this article, original data of accelerometer sensor was loaded into unique periodic sequencing prediction algorithm that develops an edge fault diagnosis technique. We utilize identical frequency patterns as inputs to an innovative deep neural Long-Short-Term-Memory, Recurrent Neural Network to diagnosis bearings insufficiency at excellent accuracy inside the least time (CRNN). Without the use of database adjustment, the technique would acquire the maximum level of competence in the industry. The fault diagnostic method’s efficacy and applicability are demonstrated by comparing the findings to those of other intelligent fault detection systems using two widely known benchmark real vibration datasets.

  PublisherDOI

• An Accelerator for Sparse Convolutional Neural Networks Leveraging Systolic General Matrix-matrix Multiplication

  ACM Transactions on Architecture and Code Optimization · 2022 · 26 citations

  • Computer Science
  • Computer Science
  • Parallel computing

  This article proposes a novel hardware accelerator for the inference task with sparse convolutional neural networks (CNNs) by building a hardware unit to perform Image to Column ( Im2Col ) transformation of the input feature map coupled with a systolic-array-based general matrix-matrix multiplication (GEMM) unit. Our design carefully overlaps the Im2Col transformation with the GEMM computation to maximize parallelism. We propose a novel design for the Im2Col unit that uses a set of distributed local memories connected by a ring network, which improves energy efficiency and latency by streaming the input feature map only once. The systolic-array-based GEMM unit in the accelerator can be dynamically configured as multiple GEMM units with square-shaped systolic arrays or as a single GEMM unit with a tall systolic array. This dynamic reconfigurability enables effective pipelining of Im2Col and GEMM operations and attains high processing element utilization for a wide range of CNNs. Further, our accelerator is sparsity aware, improving performance and energy efficiency by effectively mapping the sparse feature maps and weights to the processing elements, skipping ineffectual operations and unnecessary data movements involving zeros. Our prototype, SPOTS, is on average 2.16 \( \times \) , 1.74 \( \times \) , and 1.63 \( \times \) faster than Gemmini, Eyeriss, and Sparse-PE, which are prior hardware accelerators for dense and sparse CNNs, respectively. SPOTS is also 78 \( \times \) and 12 \( \times \) more energy-efficient when compared to CPU and GPU implementations, respectively.

  PublisherOA PDFDOI

• MedBuds: In-Ear Inertial Medication Taking Detection Using Smart Wireless Earbuds

  2022-05-01 · 2 citations

  article

  Wireless earbuds are gaining in popularity these days, especially for smart mobile phone pairing. Some of these devices are getting smart as they embed motion sensors to monitor head and mouth movements. The embodiment of these sensors can enable important mobile health applications such as medication adherence monitoring. Existing solutions are often focused on capturing hand gestures associated with medication retrieval and thus they are inaccurate and do not detect med-ication ingestion. Other solutions use neck-worn systems which make them uncomfortable and socially unacceptable. In this paper, we present MedBuds, a smart system for medication-taking activity detection using earbud embedded IMUs and a pairing device (e.g., a smartphone). To evaluate our approach, we conducted preliminary experiments examining semi-medication-taking activities (i.e. swallowing) and non-medication-taking activities (speaking and chewing). Our results show the possibility of distinguishing between these activities with more than 84 % accuracy. We believe that by coupling MedBuds with other monitoring techniques (e.g. smart pill bottles), the overall performance of medication adherence monitoring systems can be improved.

  PublisherDOI

• Near-Storage Processing for Solid State Drive Based Recommendation Inference with SmartSSDs®

  2022 · 18 citations

  • Computer Science
  • Computer Science
  • Artificial Intelligence

  Deep learning-based recommendation systems are extensively deployed in numerous internet services, including social media, entertainment services, and search engines, to provide users with the most relevant and personalized content. Production scale deep learning models consist of large embedding tables with billions of parameters. DRAM-based recommendation systems incur a high infrastructure cost and limit the size of the deployed models. Recommendation systems based on solid-state drives (SSDs) are a promising alternative for DRAM-based systems. Systems based on SSDs can offer ample storage required for deep learning models with large embedding tables. This paper proposes SmartRec, an inference engine for deep learning-based recommendation systems that utilizes Samsung SmartSSD, an SSD with an on-board FPGA that can process data in-situ. We evaluate SmartRec with state-of-the-art recommendation models from Facebook and compare its performance and energy efficiency to a DRAM-based system on a CPU. We show SmartRec improves the energy efficiency of the recommendation inference task up to 10x in comparison to the baseline CPU implementation. In addition, we propose a novel application-specific caching system for SmartSSDs that allows the kernel on the FPGA to use its DRAM as a cache to minimize high latency SSD accesses. Finally, we demonstrate the scalability of our design by offloading the computation to multiple SmartSSDs to further improve performance.

  PublisherDOI

• Monitoring Technologies for Quantifying Medication Adherence

  Health informatics · 2022-01-01 · 7 citations

  book-chapterOpen accessSenior author

  Abstract Medication non-adherence is a prevalent, complex problem. Failure to follow medication schedules may lead to major health complications, which could reduce quality of life. Proper medication adherence is thus required in order to gain the greatest possible drug benefit during a patient’s treatment. Interventions have been proven to improve medication adherence if deviations are detected. This review focuses on recent advances in the field of technology-based medication adherence approaches and pays particular attention to their technical monitoring aspects. The taxonomy space of this review spans multiple techniques including sensor systems, proximity sensing, vision systems, and combinations of these. As each technique has unique advantages and limitations, this work describes their trade-offs in accuracy, energy consumption, acceptability and user’s comfort, and user authentication.

  PublisherOA PDFDOI

• The performance of the Dharan-Dhankuta Road, east Nepal, in the context of the Fookes et al. (1985) mountain model: a tribute to the late Professor PG Fookes

  Bulletin of Engineering Geology and the Environment · 2022-03-03 · 6 citations

  articleSenior author
  PublisherDOI

• A Simplified Machine Learning Approach to Classifying Individual Websites

  GLOBECOM 2022 - 2022 IEEE Global Communications Conference · 2022-12-04

  articleSenior author

  We quantify the classification accuracy of Neural Networks (NNs) to specific websites using only the packet size and difference in inter-packet arrival time, which are easily observable via passive attackers in the network. Our flow classification work with NNs is unique in that we do not classify traffic by application type. Rather, we observe the accuracy of various NNs classifying specific web sites using HTTP traffic over TCP. We test a diverse set of neural network structures including a fully connected network (FCN), a convolutional neural network (CNN), a long short-term memory network (LSTM), and an autoencoder network (AE). We found that CNNs consistently had the highest accuracy, typically 80-90% when using 20 million packets as training data. We suspect that individual websites generate unique traffic patterns which are discoverable using NN techniques. Our work has important privacy implications. In particular, our work supports that both packet sizes and inter-packet timing must be randomized to obtain strong web browsing privacy. Many privacy preserving techniques, such as VPNs, will require additional enhancements.

  PublisherDOI

Recent grants

• CAREER: Unified Probabilistic Localization for Sensor Networks: Theoretic and Practical Foundations

  NSF · $448k · 2005–2011

Frequent coauthors

• Paolo Madeddu

  NIHR Bristol Cardiovascular Biomedical Research Unit

  294 shared

• Costanza Emanueli

  Imperial College London

  245 shared

• Rajesh Katare

  University of Otago

  196 shared

• M. Meloni

  University of Sassari

  168 shared

• Lucie Carrier

  Universität Hamburg

  147 shared

• David M. Poitz

  TU Dresden

  147 shared

• Claude Delcayre

  Hôpital Lariboisière

  147 shared

• Jolanda van der Velden

  Vrije Universiteit Amsterdam

  126 shared

Education

• Ph.D., Computer Science

  Rutgers, The State University of New Jersey

• M.S., Computer Science

  Rutgers, The State University of New Jersey

• B.S., Computer Science

  Rutgers, The State University of New Jersey