A Robust Plant Leaf Disease Recognition System Using Convolutional Neural Networks

Bala, Diponkor; Mynuddin, Mohammed; Hossain, Mohammad Ismail; Islam, Mohammad Anwarul; Hossain, Mohammad Alamgir; Abdullah, Md. Ibrahim

doi:10.1109/iceet56468.2022.10007185

Cited by 6 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, machine learning (ML) applications have witnessed unprecedented growth across various fields [5]- [7], revolutionizing the way tasks are performed and problems are addressed [8]- [10]. One notable domain where machine learning, particularly Deep Learning (DL), has made substantial contributions is in the realm of intrusion detection systems (IDS) [11].…”

Section: Introductionmentioning

confidence: 99%

Automatic Network Intrusion Detection System Using Machine learning and Deep learning

Mynuddin,

Khan,

Chowdhury

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Network Intrusion Detection System Using Machine learning and Deep learning

Mynuddin,

Khan,

Chowdhury

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Network Intrusion Detection System Using Machine learning and Deep learning

Mynuddin,

Khan,

Chowdhury

et al. 2024

Preprint

View full text Add to dashboard Cite

In recent years, the popularity of network intrusion detection systems (NIDS) has surged, driven by the widespread adoption of cloud technologies. Given the escalating network traffic and the continuous evolution of cyber threats, the need for a highly efficient NIDS has become paramount for ensuring robust network security. Typically, intrusion detection systems utilize either a pattern-matching system or leverage machine learning for anomaly detection. While pattern-matching approaches tend to suffer from a high false positive rate (FPR), machine learning-based systems, such as SVM and KNN, predict potential attacks by recognizing distinct features. However, these models often operate on a limited set of features, resulting in lower accuracy and higher FPR. In our research, we introduced a deep learning model that harnesses the strengths of a Convolutional Neural Network (CNN) combined with a Bidirectional LSTM (Bi-LSTM) to learn spatial and temporal data features. The model, evaluated using the NSL-KDD dataset, exhibited a high detection rate with a minimal false positive rate. To enhance accuracy, K-fold cross-validation was employed in training the model. This paper showcases the effectiveness of the CNN with Bi-LSTM algorithm in achieving superior performance across metrics like accuracy, F1-score, precision, and recall. The binary classification model trained on the NSLKDD dataset demonstrates outstanding performance, achieving a high accuracy of 99.5% after 10-fold cross-validation, with an average accuracy of 99.3%. The model exhibits remarkable detection rates (0.994) and a low false positive rate (0.13). In the multiclass setting, the model maintains exceptional precision (99.25%), reaching a peak accuracy of 99.59% for k-value=10. Notably, the Detection Rate for k-value=10 is 99.43%, and the mean False Positive Rate is calculated as 0.214925.

show abstract

“…[10] Advance modulations in OFDM systems are investigated recently in different studies on wired as well as wireless networks. [11] In binary phase-shift keying (BPSK), 64 quadrature amplitude modulation (QAM), 128-QAM, and 256-QAM are investigated in OFDM, and it was observed that BPSK surpassed all the other modulations in OFDM in terms of performance. PAPR reduction using the clipping technique and using BPSK, QPSK, and QAM in OFDM was reported in ref.…”

Section: Introductionmentioning

confidence: 99%

A 500 km Long Transmission with Coherent Optical OFDM Using Dual Polarization Quadrature Phase Shift Keying (QPSK) and Double Sideband Suppressed‐Enhanced Carrier (DSS‐EC)

Sachdeva

Sindhwani

Kaur

et al. 2023

Macromolecular Symposia

View full text Add to dashboard Cite

Coherent optical orthogonal frequency division multiplexing (CO-OFDM) systems are chosen for this task because of their high spectral efficiency, low inter-symbol interference (ISI), low intercarrier interference (ICI), robustness against chromatic dispersion (CD), and high nonlinearity interference tolerance (HNIT). The DSS-EC technique is utilized in this study to investigate a high-speed 100 Gbps CO-OFDM with a QPSK encoder over a 500 km uncompensated connection distance. The proposed system is compared to CO-OFDM-QPSK and CO-OFDM-16QAM systems in terms of log BER at various input optical signal to noise ratios (OSNRs). Results reveal that due to enhanced available bandwidth use of communication channels, the proposed CO-OFDM-DSS-EC-QPSK system provides minimum log BER at lower input OSNRs while the rest two systems show identical log BER performance at high input OSNRs. Therefore, proposed technique is a prominent solution for future generations high data demands and for a cost-effective solution due to an uncompensated transmission channel.

show abstract

A Robust Plant Leaf Disease Recognition System Using Convolutional Neural Networks

Cited by 6 publications

References 16 publications

Automatic Network Intrusion Detection System Using Machine learning and Deep learning

Automatic Network Intrusion Detection System Using Machine learning and Deep learning

Automatic Network Intrusion Detection System Using Machine learning and Deep learning

A 500 km Long Transmission with Coherent Optical OFDM Using Dual Polarization Quadrature Phase Shift Keying (QPSK) and Double Sideband Suppressed‐Enhanced Carrier (DSS‐EC)

Contact Info

Product

Resources

About