Change search
Link to record
Permanent link

Direct link
Publications (10 of 26) Show all publications
Shrestha, R., Mishra, A., Bajracharya, R., Sinaei, S. & Kim, S. (2023). 6G Network for Connecting CPS and Industrial IoT (IIoT): Chapter 2. In: Gunasekaran Manogaran, Nour Eldeen Mahmoud Khalifa, Mohamed Loey, Mohamed Hamed N. Taha (Ed.), Cyber-Physical Systems for Industrial Transformation: . CRC Press
Open this publication in new window or tab >>6G Network for Connecting CPS and Industrial IoT (IIoT): Chapter 2
Show others...
2023 (English)In: Cyber-Physical Systems for Industrial Transformation / [ed] Gunasekaran Manogaran, Nour Eldeen Mahmoud Khalifa, Mohamed Loey, Mohamed Hamed N. Taha, CRC Press, 2023Chapter in book (Other academic)
Abstract [en]

The IoT comprises billions of intelligent devices that interact, gather, and share data via sensors and actuators. The Industrial IoT (IIoT), specifically used in industry and production, is used in automation and rapid production of goods based on machine learning techniques. Similarly, Cyber-Physical System (CPS) plays a vital role in the next-generation industry. The CPSs are intelligent systems that interconnect the physical world through embedded systems, sensors, actuators with the cyberworld. We require a communication backbone for interconnecting and information processing, which 6G networks can fulfill. The 6G has a higher capacity and improved characteristics than previous cellular networks, accelerating the applications and deployments of 6G-based IIoT networks in industry platforms. This chapter discusses how the 6G networks can help interconnect the CPS and IIoT through smart connection, digital twinning, and immersive technology.

Place, publisher, year, edition, pages
CRC Press, 2023
National Category
Computer Engineering
Identifiers
urn:nbn:se:ri:diva-67487 (URN)10.1201/9781003262527 (DOI)9781003262527 (ISBN)
Available from: 2023-10-02 Created: 2023-10-02 Last updated: 2023-12-27Bibliographically approved
Mohammadi, M., Shrestha, R., Sinaei, S., Salcines, A., Pampliega, D., Clemente, R. & Sanz, A. L. (2023). Anomaly Detection Using LSTM-Autoencoder in Smart Grid: A Federated Learning Approach. In: ACM International Conference Proceeding Series: . Paper presented at 7th International Conference on Cloud and Big Data Computing, ICCBDC 2023. Manchester, UK. 17 August 2023 through 19 August 2023 (pp. 48-54). Association for Computing Machinery
Open this publication in new window or tab >>Anomaly Detection Using LSTM-Autoencoder in Smart Grid: A Federated Learning Approach
Show others...
2023 (English)In: ACM International Conference Proceeding Series, Association for Computing Machinery , 2023, p. 48-54Conference paper, Published paper (Refereed)
Abstract [en]

ABSTRACT. Anomaly detection is critical in industrial systems such as smart grid systems to guarantee their safe and effective operation. The smart grid stations contain sensitive data, and they are concerned about sharing it with a third-party server to establish a centralized anomaly detection system. Federated Learning (FL) is a feasible solution to these problems for enhancing anomaly detection in smart grid systems. This study describes a method for developing an unsupervised anomaly detection based on FL system using a synthetic dataset based on real-world grid system behavior. The paper investigates the usage of FL’s long short-term memory autoencoder (LSTM-AE) for anomaly detection. For more accurate identification, this research explores the performance of integrating LSTM-AE with one-class support vector machine (OC-SVM) and isolation forest (IF) and compares their results with a threshold-based anomaly detection approach. Moreover, an approach is described for generating synthetic anomalies with different levels of difficulty to evaluate the robustness of the anomaly detection FL model. The FL models results are compared with the centralized version of the models as a baseline and the results show that FL models outperformed the centralized approach by detecting higher outlier data by achieving 99% F1-Score.

Place, publisher, year, edition, pages
Association for Computing Machinery, 2023
Keywords
Anomaly detection; Learning systems; Long short-term memory; Sensitive data; Smart power grids; Additional key word and phrase: autoencoder; Anomaly detection; Auto encoders; Federated learning; Isolation forest; Key words; Key-phrase; LSTM; One-class support vector machine; Smart grid; Support vectors machine; Support vector machines
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-67956 (URN)10.1145/3616131.3616138 (DOI)2-s2.0-85176004408 (Scopus ID)
Conference
7th International Conference on Cloud and Big Data Computing, ICCBDC 2023. Manchester, UK. 17 August 2023 through 19 August 2023
Note

This work was partially supported by EU ECSEL project DAIS that has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No.101007273

Available from: 2023-11-27 Created: 2023-11-27 Last updated: 2023-12-27Bibliographically approved
Mohammadi, S., Mohammadi, M., Sinaei, S., Balador, A., Nowroozi, E., Flammini, F. & Conti, M. (2023). Balancing Privacy and Accuracy in Federated Learning for Speech Emotion Recognition. Paper presented at 2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS). ACSIS Annals of Computer Science and Information Systems, 35, 191-199
Open this publication in new window or tab >>Balancing Privacy and Accuracy in Federated Learning for Speech Emotion Recognition
Show others...
2023 (English)In: ACSIS Annals of Computer Science and Information Systems, Vol. 35, p. 191-199Article in journal (Refereed) Published
Abstract [en]

Context: Speech Emotion Recognition (SER) is a valuable technology that identifies human emotions from spoken language, enabling the development of context-aware and personalized intelligent systems. To protect user privacy, Federated Learning (FL) has been introduced, enabling local training of models on user devices. However, FL raises concerns about the potential exposure of sensitive information from local model parameters, which is especially critical in applications like SER that involve personal voice data. Local Differential Privacy (LDP) has prevented privacy leaks in image and video data. However, it encounters notable accuracy degradation when applied to speech data, especially in the presence of high noise levels. In this paper, we propose an approach called LDP-FL with CSS, which combines LDP with a novel client selection strategy (CSS). By leveraging CSS, we aim to improve the representatives of updates and mitigate the adverse effects of noise on SER accuracy while ensuring client privacy through LDP. Furthermore, we conducted model inversion attacks to evaluate the robustness of LDP-FL in preserving privacy. These attacks involved an adversary attempting to reconstruct individuals' voice samples using the output labels provided by the SER model. The evaluation results reveal that LDP-FL with CSS achieved an accuracy of 65-70%, which is 4% lower than the initial SER model accuracy. Furthermore, LDP-FL demonstrated exceptional resilience against model inversion attacks, outperforming the non-LDP method by a factor of 10. Overall, our analysis emphasizes the importance of achieving a balance between privacy and accuracy in accordance with the requirements of the SER application.

National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-68535 (URN)10.15439/2023F444 (DOI)
Conference
2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS)
Note

This work was partially supported by EU ECSEL projectDAIS that has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No.101007273.

Available from: 2023-12-13 Created: 2023-12-13 Last updated: 2023-12-13Bibliographically approved
Balador, A., Sinaei, S., Pettersson, M. & Kaya, I. (2023). DAIS Project - Distributed Artificial Intelligence Systems: Objectives and Challenges. ACM SIGAda Ada Letters, 42(2), 96-98
Open this publication in new window or tab >>DAIS Project - Distributed Artificial Intelligence Systems: Objectives and Challenges
2023 (English)In: ACM SIGAda Ada Letters, ISSN 1094-3641, E-ISSN 1557-9476, Vol. 42, no 2, p. 96-98Article in journal (Refereed) Published
Abstract [en]

DAIS is a step forward in the area of artificial intelligence and edge computing. DAIS intends to create a complete framework for self-organizing, energy efficient and private-by-design distributed AI. DAIS is a European project with a consortium of 47 partners from 11 countries coordinated by RISE Research Institute of Sweden.

Place, publisher, year, edition, pages
Association for Computing Machinery, 2023
Keywords
dais, federated learning, kdt ju, eu project, edge computing, distributed ai
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-65763 (URN)10.1145/3591335.3591348 (DOI)
Available from: 2023-08-14 Created: 2023-08-14 Last updated: 2023-08-21Bibliographically approved
Mishchenko, K., Mohammadi, S., Mohammadi, M. & Sinaei, S. (2023). Hyperparameters Optimization for Federated Learning System: Speech Emotion Recognition Case Study. In: 2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC): . Paper presented at 2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC) (pp. 80-86). IEEE
Open this publication in new window or tab >>Hyperparameters Optimization for Federated Learning System: Speech Emotion Recognition Case Study
2023 (English)In: 2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC), IEEE, 2023, p. 80-86Conference paper, Published paper (Refereed)
Abstract [en]

Context: Federated Learning (FL) has emerged as a promising, massively distributed way to train a joint deep model across numerous edge devices, ensuring user data privacy by retaining it on the device. In FL, Hyperparameters (HP) significantly affect the training overhead regarding computation and transmission time, computation and transmission load, as well as model accuracy. This paper presents a novel approach where Hyperparameters Optimization (HPO) is used to optimize the performance of the FL model for Speech Emotion Recognition (SER) application. To solve this problem, both Single-Objective Optimization (SOO) and Multi-Objective Optimization (MOO) models are developed and evaluated. The optimization model includes two objectives: accuracy and total execution time. Numerical results show that optimal Hyperparameters (HP) settings allow for improving both the accuracy of the model and its computation time. The proposed method assists FL system designers in finding optimal parameters setup, allowing them to carry out model design and development efficiently depending on their goals.

Place, publisher, year, edition, pages
IEEE, 2023
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-68573 (URN)10.1109/FMEC59375.2023.10306052 (DOI)
Conference
2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC)
Note

This work was supported by EU ECSEL project DAIS which has received funding from the ECSEL Joint Under-taking (JU) under grant agreement No.101007273.

Available from: 2023-12-13 Created: 2023-12-13 Last updated: 2023-12-13Bibliographically approved
Mohammadi, S., Sinaei, S., Balador, A. & Flammini, F. (2023). Optimized Paillier Homomorphic Encryption in Federated Learning for Speech Emotion Recognition. In: 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC): . Paper presented at IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC) (pp. 1021-1022).
Open this publication in new window or tab >>Optimized Paillier Homomorphic Encryption in Federated Learning for Speech Emotion Recognition
2023 (English)In: 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), 2023, p. 1021-1022Conference paper, Published paper (Refereed)
Abstract [en]

Federated Learning is an approach to distributed machine learning that enables collaborative model training on end devices. FL enhances privacy as devices only share local model parameters instead of raw data with a central server. However, the central server or eavesdroppers could extract sensitive information from these shared parameters. This issue is crucial in applications like speech emotion recognition (SER) that deal with personal voice data. To address this, we propose Optimized Paillier Homomorphic Encryption (OPHE) for SER applications in FL. Paillier homomorphic encryption enables computations on ciphertext, preserving privacy but with high computation and communication overhead. The proposed OPHE method can reduce this overhead by combing Paillier homomorphic encryption with pruning. So, we employ OPHE in one of the use cases of a large research project (DAIS) funded by the European Commission using a public SER dataset.

National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-66346 (URN)10.1109/compsac57700.2023.00156 (DOI)
Conference
IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)
Note

This work was partially supported by EU ECSEL project DAIS that has received funding from the ECSEL JU under grant agreement No.101007273.

Available from: 2023-09-06 Created: 2023-09-06 Last updated: 2023-09-06Bibliographically approved
Mohammadi, M., Allocca, R., Eklund, D., Shrestha, R. & Sinaei, S. (2023). Privacy-preserving Federated Learning System for Fatigue Detection. Paper presented at 3rd IEEE International Conference on Cyber Security and Resilience, CSR 2023Hybrid, Venice31 July 2023 through 2 August 2023. Proceedings of the 2023 IEEE International Conference on Cyber Security and Resilience, CSR 2023, 624-629
Open this publication in new window or tab >>Privacy-preserving Federated Learning System for Fatigue Detection
Show others...
2023 (English)In: Proceedings of the 2023 IEEE International Conference on Cyber Security and Resilience, CSR 2023, p. 624-629Article in journal (Refereed) Published
Abstract [en]

Context:. Drowsiness affects the driver’s cognitive abilities, which are all important for safe driving. Fatigue detection is a critical technique to avoid traffic accidents. Data sharing among vehicles can be used to optimize fatigue detection models and ensure driving safety. However, data privacy issues hinder the sharing process. To tackle these challenges, we propose a Federated Learning (FL) approach for fatigue-driving behavior monitoring. However, in the FL system, the privacy information of the drivers might be leaked. In this paper, we propose to combine the concept of differential privacy (DP) with Federated Learning for the fatigue detection application, in which artificial noise is added to parameters at the drivers’ side before aggregating. This approach will ensure the privacy of drivers’ data and the convergence of the federated learning algorithms. In this paper, the privacy level in the system is determined in order to achieve a balance between the noise scale and the model’s accuracy. In addition, we have evaluated our models resistance against a model inversion attack. The effectiveness of the attack is measured by the Mean Squared Error (MSE) between the reconstructed data point and the training data. The proposed approach, compared to the non-DP case, has a 6% accuracy loss while decreasing the effectiveness of the attacks by increasing the MSE from 5.0 to 7.0, so a balance between accuracy and noise scale is achieved.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2023
Keywords
Learning algorithms; Mean square error; Privacy-preserving techniques; Cognitive ability; Critical technique; Differ-ential privacy; Differential privacies; Fatigue detection; Federated learning; Federated learning system; Mean squared error; Privacy preserving; Safe driving; Learning systems
National Category
Computer Sciences
Identifiers
urn:nbn:se:ri:diva-67444 (URN)10.1109/CSR57506.2023.10224953 (DOI)2-s2.0-85171804331 (Scopus ID)
Conference
3rd IEEE International Conference on Cyber Security and Resilience, CSR 2023Hybrid, Venice31 July 2023 through 2 August 2023
Note

This work was partially supported by EU ECSEL projectDAIS that has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No.101007273. 

Available from: 2023-10-02 Created: 2023-10-02 Last updated: 2023-12-27Bibliographically approved
Mohammadi, S., Sinaei, S., Balador, A. & Flammini, F. (2023). Secure and Efficient Federated Learning by Combining Homomorphic Encryption and Gradient Pruning in Speech Emotion Recognition. In: Weizhi Meng, Zheng Yan & Vincenzo Piuri (Ed.), ISPEC 2023: Information Security Practice and Experience: International Conference on Information Security Practice and Experience (pp. 1-16). Springer Nature Singapore
Open this publication in new window or tab >>Secure and Efficient Federated Learning by Combining Homomorphic Encryption and Gradient Pruning in Speech Emotion Recognition
2023 (English)In: ISPEC 2023: Information Security Practice and Experience: International Conference on Information Security Practice and Experience / [ed] Weizhi Meng, Zheng Yan & Vincenzo Piuri, Springer Nature Singapore , 2023, p. 1-16Chapter in book (Refereed)
Abstract [en]

Speech Emotion Recognition (SER) detects human emotions expressed in spoken language. SER is highly valuable in diverse fields; however, privacy concerns arise when analyzing speech data, as it reveals sensitive information like biometric identity. To address this, Federated Learning (FL) has been developed, allowing models to be trained locally and just sharing model parameters with servers. However, FL introduces new privacy concerns when transmitting local model parameters between clients and servers, as third parties could exploit these parameters and disclose sensitive information. In this paper, we introduce a novel approach called Secure and Efficient Federated Learning (SEFL) for SER applications. Our proposed method combines Paillier homomorphic encryption (PHE) with a novel gradient pruning technique. This approach enhances privacy and maintains confidentiality in FL setups for SER applications while minimizing communication and computation overhead and ensuring model accuracy. As far as we know, this is the first paper that implements PHE in FL setup for SER applications. Using a public SER dataset, we evaluated the SEFL method. Results show substantial efficiency gains with a key size of 1024, reducing computation time by up to 25% and communication traffic by up to 70%. Importantly, these improvements have minimal impact on accuracy, effectively meeting the requirements of SER applications.

Place, publisher, year, edition, pages
Springer Nature Singapore, 2023
Series
Lecture Notes in Computer Science ; 14341
National Category
Computer Sciences Telecommunications
Identifiers
urn:nbn:se:ri:diva-68451 (URN)10.1007/978-981-99-7032-2_1 (DOI)9789819970315 (ISBN)9789819970322 (ISBN)
Note

This work was partially supported by EU ECSEL project DAIS which has received funding from the ECSEL JU under grant agreement No.101007273.

Available from: 2023-12-12 Created: 2023-12-12 Last updated: 2023-12-13Bibliographically approved
Balador, A., Sinaei, S. & Pettersson, M. (2022). Artificial Intelligence Enabled Distributed Edge Computing for Internet of Things. ERCIM News (129), 41-42
Open this publication in new window or tab >>Artificial Intelligence Enabled Distributed Edge Computing for Internet of Things
2022 (English)In: ERCIM News, ISSN 0926-4981, E-ISSN 1564-0094, no 129, p. 41-42Article in journal (Other academic) Published
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:ri:diva-62439 (URN)
Available from: 2023-01-23 Created: 2023-01-23 Last updated: 2023-04-05Bibliographically approved
Mirsalari, S. A., Nazari, N., Sinaei, S., Salehi, M. E. & Daneshtalab, M. (2022). FaCT-LSTM: Fast and Compact Ternary Architecture for LSTM Recurrent Neural Networks. IEEE design & test, 39(3), 45-53
Open this publication in new window or tab >>FaCT-LSTM: Fast and Compact Ternary Architecture for LSTM Recurrent Neural Networks
Show others...
2022 (English)In: IEEE design & test, ISSN 2168-2356, E-ISSN 2168-2364, Vol. 39, no 3, p. 45-53Article in journal (Refereed) Published
Abstract [en]

This article proposes a Fast and Compact Ternary LSTM (FaCTLSTM), which bridges the accuracy gap between the full-precision and quantized neural networks.

Place, publisher, year, edition, pages
IEEE Computer Society, 2022
Keywords
ECG, EMG, Long Short -Term Memory (LSTM), Quantization, Wearable Devices, Convolutional neural networks, Digital arithmetic, Embedded systems, Memory architecture, Network architecture, Computation costs, Computation intensives, Computational costs, Floating point operations, Health care application, Precision signals, Proposed architectures, Long short-term memory
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:ri:diva-59770 (URN)10.1109/MDAT.2021.3070245 (DOI)2-s2.0-85103775592 (Scopus ID)
Available from: 2022-07-08 Created: 2022-07-08 Last updated: 2023-04-05Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-5951-9374

Search in DiVA

Show all publications