Department of Electrical and Electronics Engineering

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1925

Browse

Subject: search.filters.subject.Machine learning (ML)

Search Results

Now showing 1 - 10 of 26
  • No Thumbnail Available
    Item
    LPNet: a DNN based latency prediction technique for application mapping in Network-on-Chip design
    (Elsevier, 2021-11) Sambangi, Ramesh
    Analytical models used for latency estimation of Network-on-Chip (NoC) are not producing reliable accuracy. This makes these analytical models difficult to use in optimization of design space exploration. In this paper, we propose a learning based model using deep neural network (DNN) for latency predictions. Input features for DNN model are collected from analytical model as well as from Booksim simulator. Then this DNN model has been adopted in mapping optimization loop for predicting the best mapping of given application and NoC parameters combination. Our simulations show that using the proposed DNN model, prediction error is less than 12% for both synthetic and application specific traffic. More than 108 times speedup could be achieved using DPSO with DNN model compared to DPSO using Booksim simulator.
  • No Thumbnail Available
    Item
    Future of connectivity: a comprehensive review of innovations and challenges in 7G smart networks
    (IEEE, 2025-04) Chamola, Vinay
    The evolution from 1G to 6G networks has transformed global communication, progressing from basic voice calls in 1G to the immersive, AI-enabled experiences of 6G. As emerging AI-driven applications like autonomous systems, the Internet of Everything (IoE), and immersive technologies demand unprecedented capabilities, 7G networks are set to redefine connectivity by overcoming the limitations of earlier generations. This paper comprehensively reviews the innovations and challenges in 7G networks, focusing on integrating advanced AI and machine learning paradigms such as meta-learning, incremental learning, distributed intelligence, and reinforcement learning to enhance adaptability, resource allocation, and edge performance. The review also examines the role of Large Language Models (LLMs) in enabling real-time actionable intelligence and optimizing edge devices within 7G. The paper highlights the use of technologies, including blockchain for decentralized security, quantum computing for robust encryption, terahertz communication for ultra-fast data transfer, zero-energy solutions for sustainability, and generative AI for intelligent network optimization and automation. By addressing these challenges and exploring cutting-edge strategies, this paper envisions 7G networks as the foundation for a secure, intelligent, and sustainable digital future, equipped to combat emerging cyber warfare threats, enhance resilience against technological disruptions, and support innovations across smart cities, autonomous systems, healthcare, and industrial IoT.
  • No Thumbnail Available
    Item
    Unveiling the future: A comprehensive analysis of 6G technology and its transformative potential
    (Springer, 2025-06) Chamola, Vinay
    Sixth-generation (6G) technology signifies a major leap in mobile communications, offering ultra-reliable, low-latency, and high-throughput connectivity. This review investigates the foundational technologies underpinning 6G, including Terahertz (THz) communication and ultra-massive multiple input, multiple output (MIMO), and explores their capabilities in enabling high-speed, consistent, and scalable communication infrastructures. A key focus of this study is the application of machine learning (ML) and deep learning (DL) in optimizing network slicing and addressing security challenges within 6G networks. While network slicing allows for flexible, service-specific logical network partitions, it also introduces technical challenges such as dynamic resource allocation, secure slice isolation, and real-time threat detection. To mitigate these, we assess ML-driven approaches—including reinforcement learning (RL), federated learning, and anomaly detection models—that facilitate intelligent orchestration and adaptive security. Furthermore, we highlight practical deployment barriers such as data privacy concerns, computational limitations at the edge, and the need for interpretable models and standardization. This comprehensive review provides insights into the current state, challenges, and potential solutions for integrating ML-based mechanisms to enhance the efficiency, scalability, and security of next-generation communication systems.
  • No Thumbnail Available
    Item
    A study of machine learning algorithms for hand gesture classification of sEMG signals Available to Purchase
    (Emerald, 2025-04) Yenuganti, Sujan
    This paper presents a cost-effective signal acquisition circuitry (SAC) for capturing surface electromyography (sEMG) data to classify different hand movements using advanced machine learning algorithms. The SAC, comprising an instrumentation amplifier, a Sallen–Key band-pass filter and a noninverting amplifier, is designed and tested on a portable printed circuit board. The purpose of this paper is to perform feature extraction and data segmentation for effective analysis and processing of the recorded sEMG signals.
  • No Thumbnail Available
    Item
    A multi-modal smart switching based image transmission using semantic communication
    (IEEE, 2025-02) Tripathi, Sharda; Joshi, Sandeep
    The conventional paradigm of communication primarily concentrates on the transmission of raw data, often disregarding its contextual meaning. However, to tackle the exponential growth in data demands along with the limited availability of transmission bandwidth, there is an increasing need to transition from Shannon’s classical information-theoretic communication to a more advanced framework centered on semantics. This work presents a multi-modal semantic-based communication method for the transmission of high-definition images aimed at optimizing the transmitted data volume while maintaining a high throughput and mean intersection over union score. To this end, two architectural models are explored: a denser ResNet-based and a lightweight U-Net-based. Depending on the required QoS and resource availability, the raw image is either semantically segmented to obtain a fine-grained, pixel-level classification of the image or represented as label semantics, which provides only a higher-level, object-based, or region-based classification prior to its transmission. The experimental results show that such an adaptive semantic image processing approach leads to around 63% reduction in the transmitted data volume without compromising on the quality of image reconstruction.
  • No Thumbnail Available
    Item
    A comprehensive survey on data converters for IOT applications: scope, issues, and future directions
    (IEEE, 2025-03) Gupta, Anu; Shekhar, Chandra; Chamola, Vinay
    Data converters significantly contribute to efficient and accurate data processing in Internet of Things (IoT) systems. As IoT expands into agriculture, industrial automation, and healthcare (AIH), precise and low-power data conversion has become crucial to support longer battery life and reliable performance in IoT devices. Efficient data converters are key to reducing energy use, especially in components like comparator circuits, which consume significant energy in successive approximation register analog-to-digital converters (SAR ADCs). This survey provides an in-depth review of recent developments in low-power data converter design, examining techniques that help reduce power consumption at various stages. It emphasizes advancements, such as energy scaling, dynamic voltage references, and architectural optimizations that enhance efficiency without compromising performance. A specific analysis of emerging technology trends, such as the application of machine learning in data converter design, is explored to stimulate further innovation. Machine learning (ML)-based optimization, including adaptive calibration, noise reduction, and real-time performance optimization, presents new opportunities for enhancing efficiency and accuracy while addressing critical design constraints in IoT applications. While quantum encryption offers promising advancements in securing IoT data transmission, a broader security perspective beyond encryption is necessary, including concerns, such as attack detection and data integrity, ensuring the robustness of IoT systems. This review also examines latency, signal integrity, and accuracy issues, offering a roadmap for next-generation converter designs and reducing power consumption in data converters, which are fundamental to enhancing the performance and lifespan of IoT devices.
  • No Thumbnail Available
    Item
    A detailed comparative analysis of automatic neural metrics for machine translation: bleurt & bertscore
    (IEEE, 2025-04) Chamola, Vinay; Gupta, Karunesh Kumar
    Bleurt a recently introduced metric that employs Bert, a potent pre-trained language model to assess how well candidate translations compare to a reference translation in the context of machine translation outputs. While traditional metrics like Bleu rely on lexical similarities, Bleurt leverages Bert's semantic and syntactic capabilities to provide more robust evaluation through complex text representations. However, studies have shown that Bert, despite its impressive performance in natural language processing tasks can sometimes deviate from human judgment, particularly in specific syntactic and semantic scenarios. Through systematic experimental analysis at the word level, including categorization of errors such as lexical mismatches, untranslated terms, and structural inconsistencies, we investigate how Bleurt handles various translation challenges. Our study addresses three central questions: What are the strengths and weaknesses of Bleurt, how do they align with Bert's known limitations, and how does it compare with the similar automatic neural metric for machine translation, BERTScore? Using manually annotated datasets that emphasize different error types and linguistic phenomena, we find that Bleurt excels at identifying nuanced differences between sentences with high overlap, an area where BERTScore shows limitations. Our systematic experiments, provide insights for their effective application in machine translation evaluation.
  • No Thumbnail Available
    Item
    Automated Designing of Single Stage Operational Amplifier and Its Teleportation Among Different Technology Nodes
    (IEEE, 2020-06) Bhatt, Upendra Mohan
    Analog circuits play a vital role in advanced electronic systems and they cannot be replaced because of their need to provide an interface with the natural analog world. In this paper we have presented an analog design flow for Automated Designing and Teleportation (ADT) of analog circuits, Further ADT for a single-stage operational amplifier (single-stage op-Amp, i.e., differential amplifier) has been presented to demonstrate the complete process flow which provides accurate results in a shorter span of time using the trained machine learning models.
  • No Thumbnail Available
    Item
    Application of Deep Neural Networks for Weed Detection and Classification
    (IEEE, 2023-06) Bhatt, Upendra Mohan
    Weeds compete for natural resources both in forest areas, harming the development of native vegetation, and in agricultural areas, affecting crop quality. The need then arises to classify these species, so that mechanical or chemical methods can be applied appropriately to contain the pests. This research presents the application and comparison of machine learning techniques, with the aim of automating the classification of images for agricultural challenges, such as the detection of defective seeds, and weeds and the category between these and native vegetation, while finally, the architecture of a convolutional neural network is presented. As a differential, the network's self-learning ability stands out, as images are captured in less than ideal conditions at varying heights and lighting levels in most cases. This research is expected to provide important information on artificial intelligence techniques that can be used in the classification of weed images, a factor that will contribute to the forestry and agricultural sector.
  • No Thumbnail Available
    Item
    Optimal Machine Learning Model for the Relationship Between Grain Size, Channel Thickness, and Grain Boundary Trap Density in 3D NAND Strings
    (IEEE, 2024-01) Bhatt, Upendra Mohan
    The rapid growth of the semiconductor industry has resulted in the development of three-dimensional NAND (3D NAND) strings, which offer increased memory density and greater performance over classical planar NAND designs. In this work, we look at the critical aspects that determine the performance and reliability of 3D NAND strings. Using simulation results and machine learning algorithms we focus on the effects of grain size, channel thickness, and grain boundary trap density. We address their individual and cumulative effects on memory cell behavior, with the current state-of-the-art strategies used to optimize these characteristics. This work will be helpful in the ongoing development of 3D NAND flash technology.