Ansuman Banerjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ansuman Banerjee has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
- Kaustabha Ray
IBM Research, Bangalore, India
6 shared publications - Krishnendu Chakrabarty
Arizona State University
4 shared publications - Soumi Chattopadhyay
Department of Computer Science and Engineering, Indian Institute of Technology Indore, Indore, India
4 shared publications - Swarup Kumar Mohalik
Ericsson India, Bangalore, Karnataka, India
4 shared publications Bhaskar Sardar
Jadavpur University, India
3 shared publications- Rajarshi Ray
Indian Association for the Cultivation of Science, Kolkata, India
3 shared publications
Latest Publications
- Open Access
- 4 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 40-41
Towards Verification of Spiking Neural Networks for Next-Generation AI Systems
- 4 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 40-41
Open AccessTowards Verification of Spiking Neural Networks for Next-Generation AI Systems
- 2 January 2026
- Published by Springer Nature
- p. 591-613
Collection Scheduling with Memory Constraints for Low Earth Orbit Satellite Constellations
- 2 January 2026
- Published by Springer Nature
- p. 591-613
Collection Scheduling with Memory Constraints for Low Earth Orbit Satellite Constellations
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 40-50
Modeling and Verification of Sigma Delta Neural Networks using Satisfiability Modulo Theory
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 40-50
Open AccessModeling and Verification of Sigma Delta Neural Networks using Satisfiability Modulo Theory
- Open Access
- 11 April 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Modeling and Computer Simulation
- Vol. 35 (2) , 1-28
Computation Offloading and Band Selection for IoT Devices in Multi-Access Edge Computing
The advent of Multi-Access Edge Computing (MEC) has enabled service providers to mitigate high network latencies often encountered in accessing cloud services. The key idea of MEC involves service providers deploying containerized application services on MEC servers situated near Internet-of-Things (IoT) device users. The users access these services via wireless base stations with ultra low latency. Computation tasks of IoT devices can then either be executed locally on the devices or on the MEC servers. A key cornerstone of the MEC environment is an offloading policy utilized to determine whether to execute computation tasks on IoT devices or to offload the tasks to MEC servers for processing. In this work, we propose a two-phase Probabilistic Model Checking-based offloading policy catering to IoT device user preferences. The first stage evaluates the tradeoffs between local vs. server execution while the second stage evaluates the tradeoffs between choice of wireless communication bands for offloaded tasks. We present experimental results in practical scenarios on data gathered from an IoT test-bed setup with benchmark applications to show the benefits of an adaptive preference-aware approach over conventional approaches in the MEC offloading context.
- 11 April 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Modeling and Computer Simulation
- Vol. 35 (2) , 1-28
Open AccessComputation Offloading and Band Selection for IoT Devices in Multi-Access Edge Computing
The advent of Multi-Access Edge Computing (MEC) has enabled service providers to mitigate high network latencies often encountered in accessing cloud services. The key idea of MEC involves service providers deploying containerized application services on MEC servers situated near Internet-of-Things (IoT) device users. The users access these services via wireless base stations with ultra low latency. Computation tasks of IoT devices can then either be executed locally on the devices or on the MEC servers. A key cornerstone of the MEC environment is an offloading policy utilized to determine whether to execute computation tasks on IoT devices or to offload the tasks to MEC servers for processing. In this work, we propose a two-phase Probabilistic Model Checking-based offloading policy catering to IoT device user preferences. The first stage evaluates the tradeoffs between local vs. server execution while the second stage evaluates the tradeoffs between choice of wireless communication bands for offloaded tasks. We present experimental results in practical scenarios on data gathered from an IoT test-bed setup with benchmark applications to show the benefits of an adaptive preference-aware approach over conventional approaches in the MEC offloading context.
- Open Access
- 13 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 29 (5) , 1-37
MAB-BMC: A Formal Verification Enhancer by Harnessing Multiple BMC Engines Together
In recent times, Bounded Model Checking (BMC) engines have gained wide prominence in formal verification. Different BMC engines exist, differing in their optimization, representations and solving mechanisms used to represent and navigate the underlying state transition of the given design to be verified. The objective of this article is to examine if combinations of BMC engines can help to combine their strengths. We propose an approach that can create a sequencing of BMC engines that can reach better depth in formal verification, as opposed to executing them alone for a specified time. Our approach uses machine learning, specifically, the Multi-Armed Bandit paradigm of reinforcement learning, to predict the best-performing BMC engine for a given unrolling depth of the underlying circuit design. We evaluate our approach on a set of benchmark designs from the Hardware Model Checking Competition (HWMCC) benchmarks and show that it outperforms the state-of-the-art BMC engines in terms of the depth reached or time taken to deduce a property violation. The synthesized BMC engine sequences reach better depths than HWMCC results and the state-of-the-art technique, super_deep, for more than 80% of the cases. It also outperforms single engine runs for more than 92% of the cases where a property violation is not found within a given time duration. For designs where property violations are found within the given time duration, the synthesized sequences found the property violation in a lesser time than HWMCC for all the designs and outperformed both super_deep and single engine runs for more than 87% of the designs.
- 13 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 29 (5) , 1-37
Open AccessMAB-BMC: A Formal Verification Enhancer by Harnessing Multiple BMC Engines Together
In recent times, Bounded Model Checking (BMC) engines have gained wide prominence in formal verification. Different BMC engines exist, differing in their optimization, representations and solving mechanisms used to represent and navigate the underlying state transition of the given design to be verified. The objective of this article is to examine if combinations of BMC engines can help to combine their strengths. We propose an approach that can create a sequencing of BMC engines that can reach better depth in formal verification, as opposed to executing them alone for a specified time. Our approach uses machine learning, specifically, the Multi-Armed Bandit paradigm of reinforcement learning, to predict the best-performing BMC engine for a given unrolling depth of the underlying circuit design. We evaluate our approach on a set of benchmark designs from the Hardware Model Checking Competition (HWMCC) benchmarks and show that it outperforms the state-of-the-art BMC engines in terms of the depth reached or time taken to deduce a property violation. The synthesized BMC engine sequences reach better depths than HWMCC results and the state-of-the-art technique, super_deep, for more than 80% of the cases. It also outperforms single engine runs for more than 92% of the cases where a property violation is not found within a given time duration. For designs where property violations are found within the given time duration, the synthesized sequences found the property violation in a lesser time than HWMCC for all the designs and outperformed both super_deep and single engine runs for more than 87% of the designs.
- Open Access
Configuring Safe Spiking Neural Controllers for Cyber-Physical Systems through Formal Verification
Spiking Neural Networks (SNNs) are a subclass of neuromorphic models that have great potential to be used as controllers in Cyber-Physical Systems (CPSs) due to their energy efficiency. They can benefit from the prevalent approach of first training an Artificial Neural Network (ANN) and then translating to an SNN with subsequent hyperparameter tuning. The tuning is required to ensure that the resulting SNN is accurate with respect to the ANN in terms of metrics like Mean Squared Error (MSE). However, SNN controllers for safety-critical CPSs must also satisfy safety specifications, which are not guaranteed by the conversion approach. In this paper, we propose a solution which tunes the $temporal$ $window$ hyperparameter of the translated SNN to ensure both accuracy and compliance with the safe range specification that requires the SNN outputs to remain within a safe range. The core verification problem is modelled using mixed-integer linear programming (MILP) and is solved with Gurobi. When the controller fails to meet the range specification, we compute tight bounds on the SNN outputs as feedback for the CPS developer. To mitigate the high computational cost of verification, we integrate data-driven steps to minimize verification calls. Our approach provides designers with the confidence to safely integrate energy-efficient SNN controllers into modern CPSs. We demonstrate our approach with experimental results on five different benchmark neural controllers.Open AccessConfiguring Safe Spiking Neural Controllers for Cyber-Physical Systems through Formal Verification
Spiking Neural Networks (SNNs) are a subclass of neuromorphic models that have great potential to be used as controllers in Cyber-Physical Systems (CPSs) due to their energy efficiency. They can benefit from the prevalent approach of first training an Artificial Neural Network (ANN) and then translating to an SNN with subsequent hyperparameter tuning. The tuning is required to ensure that the resulting SNN is accurate with respect to the ANN in terms of metrics like Mean Squared Error (MSE). However, SNN controllers for safety-critical CPSs must also satisfy safety specifications, which are not guaranteed by the conversion approach. In this paper, we propose a solution which tunes the $temporal$ $window$ hyperparameter of the translated SNN to ensure both accuracy and compliance with the safe range specification that requires the SNN outputs to remain within a safe range. The core verification problem is modelled using mixed-integer linear programming (MILP) and is solved with Gurobi. When the controller fails to meet the range specification, we compute tight bounds on the SNN outputs as feedback for the CPS developer. To mitigate the high computational cost of verification, we integrate data-driven steps to minimize verification calls. Our approach provides designers with the confidence to safely integrate energy-efficient SNN controllers into modern CPSs. We demonstrate our approach with experimental results on five different benchmark neural controllers. - Open Access
- 22 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-5
A Contrastive Explanation Tool for Plans in Hybrid Domains
This paper presents a tool for generating contrastive explanations of plans in hybrid domains. The tool offers a collection of contrastive questions over a plan, such as "Why use action A?", for users to select. An explanation of the user question is produced by contrasting the original plan against an alternative that meets the user’s expectation implicit from the question. The tool has the provision to contrast with the best alternative that the underlying planner can generate in terms of plan makespan (duration of a plan) and length. The current version supports two planners in the hybrid domain, namely SMTPlan+, and ENHSP, which a tool user can select. The tool consists of (1) A web-based interactive GUI for selecting questions, viewing contrastive plans and the generated explanations, and (2) A back-end implementing an iterative re-modeling and re-planning algorithm. We demonstrate the working of the tool over two case studies.
- 22 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessA Contrastive Explanation Tool for Plans in Hybrid Domains
This paper presents a tool for generating contrastive explanations of plans in hybrid domains. The tool offers a collection of contrastive questions over a plan, such as "Why use action A?", for users to select. An explanation of the user question is produced by contrasting the original plan against an alternative that meets the user’s expectation implicit from the question. The tool has the provision to contrast with the best alternative that the underlying planner can generate in terms of plan makespan (duration of a plan) and length. The current version supports two planners in the hybrid domain, namely SMTPlan+, and ENHSP, which a tool user can select. The tool consists of (1) A web-based interactive GUI for selecting questions, viewing contrastive plans and the generated explanations, and (2) A back-end implementing an iterative re-modeling and re-planning algorithm. We demonstrate the working of the tool over two case studies.
- 19 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 21 (2) , 1969-1982
Learning-Based Microservice Placement and Migration for Multi-Access Edge Computing
In Multi-Access Edge Computing (MEC), a number of mechanisms exist to determine the optimal placement of monolithic service workflows. For applications designed as microservice workflow architectures, service placement schemes need to be revisited owing to the inherent interdependencies which exist between microservices. The dynamic environment, with stochastic user movement and service invocations, along with a large placement configuration space makes microservice placement in MEC a challenging task. Additionally, owing to user mobility, a placement scheme may need to be recalibrated, triggering service migrations to maintain the advantages offered by MEC. Existing microservice placement and migration schemes consider on-demand strategies. In this work, we take a different route and propose a Reinforcement Learning (RL) based proactive mechanism using a Learning Automata (LA) for microservice placement and migration that on one hand, keeps track of user mobility and resorts to migration when necessary, while on the other hand, keeps track of server residual capacities so that no server is overloaded. We use the San Francisco Taxi dataset to validate our approach. Experimental results show the effectiveness of our approach in comparison to other methods.
- 19 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 21 (2) , 1969-1982
Learning-Based Microservice Placement and Migration for Multi-Access Edge Computing
In Multi-Access Edge Computing (MEC), a number of mechanisms exist to determine the optimal placement of monolithic service workflows. For applications designed as microservice workflow architectures, service placement schemes need to be revisited owing to the inherent interdependencies which exist between microservices. The dynamic environment, with stochastic user movement and service invocations, along with a large placement configuration space makes microservice placement in MEC a challenging task. Additionally, owing to user mobility, a placement scheme may need to be recalibrated, triggering service migrations to maintain the advantages offered by MEC. Existing microservice placement and migration schemes consider on-demand strategies. In this work, we take a different route and propose a Reinforcement Learning (RL) based proactive mechanism using a Learning Automata (LA) for microservice placement and migration that on one hand, keeps track of user mobility and resorts to migration when necessary, while on the other hand, keeps track of server residual capacities so that no server is overloaded. We use the San Francisco Taxi dataset to validate our approach. Experimental results show the effectiveness of our approach in comparison to other methods.
- Open Access
- 19 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 132-139
A Framework for Tile Processing on Edge Servers for Roadside Traffic Surveillance
- 19 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 132-139
Open AccessA Framework for Tile Processing on Edge Servers for Roadside Traffic Surveillance