Avi Deb Raha

Avi Deb Raha

Auto-generated profile, based on publicly available information

Avi Deb Raha

Department of Computer Science and Engineering, School of Computing, Kyung Hee University, Yongin, Republic of Korea

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
3 October 2025 in IEEE Communications Surveys & Tutorials
Verified
Journal Article
Open access
LNLoc X. Nguyen
Loc X. Nguyen
ARAvi Deb Raha
Avi Deb Raha
PAPyae Sone Aung
Pyae Sone Aung
DNDusit Niyato
Dusit Niyato
ZHZhu Han
Zhu Han
Choong Seon HongChoong Seon Hong
Choong Seon Hong
Semantic communication is emerging as a key pillar of wireless communication technology, owing to its capabilities in reducing communication overhead, enhancing resilience to channel noise, and supporting a large number of users. However, it still encounters various challenging obstacles that need to be solved before real-world deployment. The major challenge is the lack of standardization across different directions, leading to variations in interpretations and objectives. In the survey, we provide detailed explanations of three leading directions in semantic communications, namely Theory of Mind, Generative AI, Deep Joint Source-Channel Coding. These directions have been widely studied, developed, and verified by institutes worldwide, and their effectiveness has increased along with the advancement in technology. We provide explanations of the concepts and background for each direction. Firstly, we introduce the Theory of Mind-based semantic communication, in which communication agents gradually develop a shared, minimal-length language through interactions within a shared environment. Subsequently, we present works on Generative AI-based semantic communication, which leverage the creativity of generative models to produce high-quality data for goal-oriented tasks, as well as their powerful data encoding capabilities to represent transmitted information with minimal redundancy. For the final direction, we highlight the importance of deep learning (DL) models in jointly optimizing source and channel coding, demonstrating their ability to overcome the cliff effect associated with traditional separate coding approaches. Then, we present a comprehensive survey of existing works in each direction, thereby offering readers an overview of past achievements and potential avenues for further contribution. Moreover, for each direction, we identify and discuss the existing challenges that must be addressed before these approaches can be effectively deployed in real-world scenarios. These challenges encompass a range of technical, computational, and practical issues. For instance, scalability and adaptability remain critical barriers in real-world deployment, particularly in dynamic environments with diverse user demands. Additionally, the possibility of applying emerging technology, specifically quantum computing, in semantic communication is discussed in this survey.

10 June 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
AAApurba Adhikary
Apurba Adhikary
ARAvi Deb Raha
Avi Deb Raha
YQYu Qiao
Yu Qiao
Walid SaadWalid Saad
Walid Saad
ZHZhu Han
Zhu Han
Choong Seon HongChoong Seon Hong
Choong Seon Hong
Sixth-generation wireless networks are required to satisfy the ever-increasing demands of diverse applications to guarantee power savings, energy efficiency, and mass connectivity. To accomplish these goals, in this paper, an artificial intelligence (AI)-based holographic MIMO (HMIMO)-empowered cell-free (CF) network is proposed while leveraging integrated sensing and communication (ISAC). The proposed AI-based framework allocates the desired power for beamforming by activating the required number of grids from the serving HMIMO base stations (BSs) in the CF network to serve the users. An optimization problem is formulated that maximizes the sensing utility function, which in turn maximizes the signal-to-interference-plus-noise ratio (SINR) of the received signal, the sensing SINR of the reflected echo signal, and energy efficiency, ensuring efficient power allocation. To solve the optimization problem, an AI-based framework is proposed to enable a decomposition of the NP-hard problem into two subproblems: a sensing subproblem and a power allocation subproblem. Initially, a variational autoencoder (VAE)-based scheme is utilized to solve the sensing subproblem that identifies the current location of the users with the sensing information. Then, a transformer-based mechanism is devised to allocate the desired power to users by activating the required grids from the serving HMIMO BSs in the CF network based on the sensing information achieved with the VAE-based scheme. Simulation results demonstrate that the proposed AI-based framework outperforms the long short-term memory and gated recurrent unit-based mechanisms, with cumulative power savings of 8.64% and 16.02%, and cumulative energy efficiency of 14.49% and 16.61%, accordingly, considering the ground truth values.

29 May 2025 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
ARAvi Deb Raha
Avi Deb Raha
KKKitae Kim
Kitae Kim
AAApurba Adhikary
Apurba Adhikary
MGMrityunjoy Gain
Mrityunjoy Gain
ZHZhu Han
Zhu Han
Choong Seon HongChoong Seon Hong
Choong Seon Hong
Advancements in 6 G wireless technology have elevated the importance of beamforming, especially for attaining ultra-high data rates via millimeter-wave (mmWave) frequency deployment. Although promising, mmWave bands require substantial beam training to achieve precise beamforming. While initial deep learning models that use RGB camera images demonstrated promise in reducing beam training overhead, their performance suffers due to sensitivity to lighting and environmental variations. Due to this sensitivity, Quality of Service (QoS) fluctuates, eventually affecting the stability and dependability of networks in dynamic environments. This emphasizes a critical need for robust solutions. This paper proposes a robust beamforming technique to ensure consistent QoS under varying environmental conditions. An optimization problem has been formulated to maximize users' data rates. To solve the formulated NP-hard optimization problem, we decompose it into two subproblems: the semantic localization problem and the optimal beam selection problem. To solve the semantic localization problem, we propose a novel method that leverages the K-means clustering and YOLOv8 model. To solve the beam selection problem, we propose a novel lightweight hybrid architecture that combines a lightweight transformer with a CNN architecture through a weighted entropy mechanism. This hybrid architecture utilizes multimodal data sources to dynamically predict the optimal beams. For maintaining QoS, rapid and accurate beam predictions are needed. To quantify this, a novel metric, Accuracy-Complexity Efficiency (ACE), which combines both the model complexity and accuracy, has been proposed. Six testing scenarios have been developed to evaluate the robustness of the proposed model. Finally, the simulation result demonstrates that the proposed model outperforms several state-of-the-art baselines regarding beam prediction accuracy, received power, and ACE in the developed test scenarios.

9 January 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
MGMrityunjoy Gain
Mrityunjoy Gain
AAAsadov Amirjon
Asadov Amirjon
SDSumit Kumar Dam
Sumit Kumar Dam
AAApurba Adhikary
Apurba Adhikary
Anupam Kumar BairagiAnupam Kumar Bairagi
Anupam Kumar Bairagi
ARAvi Deb Raha
Avi Deb Raha

4 March 2026 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
ARAvi Deb Raha
Avi Deb Raha
Md. Shirajum MunirMd. Shirajum Munir
Md. Shirajum Munir
AAApurba Adhikary
Apurba Adhikary
MGMrityunjoy Gain
Mrityunjoy Gain
YQYu Qiao
Yu Qiao
Choong Seon HongChoong Seon Hong
Choong Seon Hong
This work designs a novel semantic communication (SemCom) framework for next-generation wireless networks to tackle high bandwidth consumption, latency, and degraded quality of service (QoS). These challenges, caused by transmitting vast amounts of unnecessary data, hinder real-time applications like intelligent transportation systems (ITS), metaverse, and mixed reality. The proposed framework aims to reduce this communication overhead and maintain QoS for these emerging systems. First, an intelligent semantic transmitter is designed to capture meaningful information (e.g., roadside image in ITS) by designing a domain-specific Mobile Segment Anything Model (MSAM)-based mechanism to reduce the potential communication traffic while QoS remains intact. Second, the concept of generative AI is introduced at the receiver for building the SemCom framework to reconstruct and denoise the received semantic data frames. In particular, the Generative Adversarial Network (GAN) mechanism is designed to maintain high-quality reconstruction under different signal-to-noise (SNR) channel conditions. To support edge deployment, a lightweight knowledge-distilled GAN is proposed for efficient reconstruction with minimal quality loss. Finally, we have evaluated the proposed semantic communication (SemCom) framework in a real-world 6 G scenario of ITS; in particular, the base station equipped with an RGB camera and a mmWave phased array. Experimental results demonstrate the effectiveness of the proposed SemCom framework by achieving high-quality reconstruction across various SNR channel conditions, resulting in 89.45% data reduction in communication.

2 April 2025 in PLOS ONE
Verified
Journal Article
Open access
NDNiloy Das
Niloy Das
BHBipul Hossain
Bipul Hossain
AAApurba Adhikary
Apurba Adhikary
ARAvi Deb Raha
Avi Deb Raha
YQYu Qiao
Yu Qiao
Anupam Kumar BairagiAnupam Kumar Bairagi
Anupam Kumar Bairagi
Hepatitis is a widespread inflammatory condition of the liver, presenting a formidable global health challenge. Accurate and timely detection of hepatitis is crucial for effective patient management, yet existing methods exhibit limitations that underscore the need for innovative approaches. Early-stage detection of hepatitis is now possible with the recent adoption of machine learning and deep learning approaches. With this in mind, the study investigates the use of traditional machine learning models, specifically classifiers such as logistic regression, support vector machines (SVM), decision trees, random forest, multilayer perceptron (MLP), and other models, to predict hepatitis infections. After extensive data preprocessing including outlier detection, dataset balancing, and feature engineering, we evaluated the performance of these models. We explored three modeling approaches: machine learning with default hyperparameters, hyperparameter-tuned models using GridSearchCV, and ensemble modeling techniques. The SVM model demonstrated outstanding performance, achieving 99.25% accuracy and a perfect AUC score of 1.00 with consistency in other metrics with 99.27% precision, and 99.24% for both recall and F1-measure. The MLP and Random Forest proved to be in pace with the superior performance of SVM exhibiting an accuracy of 99.00%. To ensure robustness, we employed a 5-fold cross-validation technique. For deeper insight into model interpretability and validation, we employed an explainability analysis of our best-performed models to identify the most effective feature for hepatitis detection. Our proposed model, particularly SVM, exhibits better prediction performance regarding different performance metrics compared to existing literature.