1,720,961 research outputs found
Novel Approach to Intrusion Detection: Introducing GAN-MSCNN-BILSTM with LIME Predictions
Full text linkThis paper introduces an innovative intrusion detection system that harnesses
Generative Adversarial Networks (GANs), Multi-Scale Convolutional Neural
Networks (MSCNNs), and Bidirectional Long Short-Term Memory (BiLSTM) networks,
supplemented by Local Interpretable Model-Agnostic Explanations (LIME) for
interpretability. Employing a GAN, the system generates realistic network
traffic data, encompassing both normal and attack patterns. This synthesized
data is then fed into an MSCNN-BiLSTM architecture for intrusion detection. The
MSCNN layer extracts features from the network traffic data at different
scales, while the BiLSTM layer captures temporal dependencies within the
traffic sequences. Integration of LIME allows for explaining the model's
decisions. Evaluation on the Hogzilla dataset, a standard benchmark, showcases
an impressive accuracy of 99.16\% for multi-class classification and 99.10\%
for binary classification, while ensuring interpretability through LIME. This
fusion of deep learning and interpretability presents a promising avenue for
enhancing intrusion detection systems by improving transparency and decision
support in network security
Stereo Vision-Based Road Obstacles Detection and Tracking
Full text linkThis paper presents a fast road obstacle detection system based on stereo vision. The algorithm contains three main components: road detection, obstacle detection and vehicle tracking. The road detection is achieved by using a small rectangular shape at bottom center of disparity image to extract the disparities of the road. The roadsides are located by using morphological processing and Hough transform. In the obstacle detection process, the objects can be easily located by the segmentation process. The vehicle tracking is achieved by the discrete Kalman filter. The proposed approach has been tested on different images. The provided results demonstrate the effectiveness of the proposed method
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Fine-Tuning CNN-BiGRU for Intrusion Detection with SMOTE Optimization Using Optuna
No full textNetwork security faces a significant challenge in developing effective models for intrusion detection within network systems. Network Intrusion Detection Systems (NIDS) are vital for protecting network traffic and preempting potential attacks by identifying signatures and rule violations.
This research aims to enhance intrusion detection using Deep learning techniques, particularly by employing the NSLKDD dataset to train and evaluate a hybrid CNN-BiGRU algorithm. Additionally, we utilize the Synthetic Minority Over-sampling Technique (SMOTE) to address imbalanced data and Optuna for fine-tuning the algorithm's parameters specific to NIDS requirements.
The hybrid CNN-BiGRU algorithm is trained and evaluated on the NSLKDD dataset, incorporating SMOTE to tackle imbalanced data issues. Optuna is utilized to optimize the algorithm's parameters for improved performance in intrusion detection.
Experimental results demonstrate that our approach surpasses classical intrusion detection models. Achieving an accuracy rate of 98,83 % on NSLKDD, the proposed model excels in identifying minority attacks while maintaining a low false positive rate.
The findings affirm the efficacy of our proposed approach in network intrusion detection, showcasing its ability to effectively discern patterns in network traffic and outperform traditional model
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Fine-Tuning CNN-BiGRU for Intrusion Detection with SMOTE Optimization Using Optuna
Full text linkNetwork security faces a significant challenge in developing effective models for intrusion detection within network systems. Network Intrusion Detection Systems (NIDS) are vital for protecting network traffic and preempting potential attacks by identifying signatures and rule violations.
This research aims to enhance intrusion detection using Deep learning techniques, particularly by employing the NSLKDD dataset to train and evaluate a hybrid CNN-BiGRU algorithm. Additionally, we utilize the Synthetic Minority Over-sampling Technique (SMOTE) to address imbalanced data and Optuna for fine-tuning the algorithm\u27s parameters specific to NIDS requirements.
The hybrid CNN-BiGRU algorithm is trained and evaluated on the NSLKDD dataset, incorporating SMOTE to tackle imbalanced data issues. Optuna is utilized to optimize the algorithm\u27s parameters for improved performance in intrusion detection.
Experimental results demonstrate that our approach surpasses classical intrusion detection models. Achieving an accuracy rate of 98,83 % on NSLKDD, the proposed model excels in identifying minority attacks while maintaining a low false positive rate.
The findings affirm the efficacy of our proposed approach in network intrusion detection, showcasing its ability to effectively discern patterns in network traffic and outperform traditional model
Optimizing cnn-Bigru performance: Mish activation and comparative analysis with Relu
Full text linkDeep learning is currently extensively employed across a range of research
domains. The continuous advancements in deep learning techniques contribute to
solving intricate challenges. Activation functions (AF) are fundamental
components within neural networks, enabling them to capture complex patterns
and relationships in the data. By introducing non-linearities, AF empowers
neural networks to model and adapt to the diverse and nuanced nature of
real-world data, enhancing their ability to make accurate predictions across
various tasks. In the context of intrusion detection, the Mish, a recent AF,
was implemented in the CNN-BiGRU model, using three datasets: ASNM-TUN,
ASNM-CDX, and HOGZILLA. The comparison with Rectified Linear Unit (ReLU), a
widely used AF, revealed that Mish outperforms ReLU, showcasing superior
performance across the evaluated datasets. This study illuminates the
effectiveness of AF in elevating the performance of intrusion detection
systems
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Robust ConvNet-Kalman Filter Integration for Mitigating GPS Jamming and Spoofing Attacks Basing on Inertial Navigation System Data
Full text linkGPS (Global Positioning System) is the most accurate system for various applications, especially in transportation. However, GPS is critically vulnerable due to its reliance on radio signals, which can be exploited by hackers through intentional attacks like spoofing and jamming, leading to potentially dangerous disruptions for both humans and services. Moreover, GPS systems can also experience accidental disruptions in urban environments, where signals from multiple satellites may be blocked by buildings, severely affecting the receiver\u27s accuracy. This paper presents a robust method designed to mitigate GPS outages caused by both jamming and spoofing by integrating inertial data. The proposed method leverages two key components: convolutional neural networks (ConvNet) and the Kalman filter (KF). A carefully optimized deep layer in the ConvNet is employed to correct errors in the inertial navigation system (INS). The findings indicate a considerable enhancement in accuracy, with the proposed method reducing the RMSE by 77.68% compared to standalone GPS and by 98.34% compared to standalone INS. This significant improvement underscores the proposed approach\u27s performance in maintaining reliable navigation in environments where GPS signals are compromise
- …
