classification models
Recently Published Documents


TOTAL DOCUMENTS

1457
(FIVE YEARS 756)

H-INDEX

43
(FIVE YEARS 11)

2022 ◽  
Author(s):  
Amogh Palasamudram

<p>This research introduces and evaluates the Neural Layer Bypassing Network (NLBN), a new neural network architecture to improve the speed and effectiveness of forward propagation in deep learning. This architecture utilizes 1 additional (fully connected) neural network layer after every layer in the main network. This new layer determines whether finishing the rest of the forward propagation is required to predict the output of the given input. To test the effectiveness of the NLBN, I programmed coding examples for this architecture with 3 different image classification models trained on 3 different datasets: MNIST Handwritten Digits Dataset, Horses or Humans Dataset, and Colorectal Histology Dataset. After training 1 standard convolutional neural network (CNN) and 1 NLBN per dataset (both of equivalent architectures), I performed 5 trials per dataset to analyze the performance of these two architectures. For the NLBN, I also collected data regarding the accuracy, time period, and speed of the network with respect to the percentage of the model the inputs are passed through. It was found that this architecture increases the speed of forward propagation by 6% - 25% while the accuracy tended to decrease by 0% - 4%; the results vary based on the dataset and structure of the model, but the increase in speed was normally at least twice the decrease in accuracy. In addition to the NLBN’s performance during predictions, it takes roughly 40% longer to train and requires more memory due to its complexity. However, the architecture can be made more efficient if integrated into TensorFlow libraries. Overall, by being able to autonomously skip neural network layers, this architecture can potentially be a foundation for neural networks to teach themselves to become more efficient for applications that require fast, accurate, and less computationally intensive predictions.<br></p>


2022 ◽  
Vol 11 (1) ◽  
pp. 6
Author(s):  
Dheeraj Basavaraj ◽  
Shahab Tayeb

With the emergence of networked devices, from the Internet of Things (IoT) nodes and cellular phones to vehicles connected to the Internet, there has been an ever-growing expansion of attack surfaces in the Internet of Vehicles (IoV). In the past decade, there has been a rapid growth in the automotive industry as network-enabled and electronic devices are now integral parts of vehicular ecosystems. These include the development of automobile technologies, namely, Connected and Autonomous Vehicles (CAV) and electric vehicles. Attacks on IoV may lead to malfunctioning of Electronic Control Unit (ECU), brakes, control steering issues, and door lock issues that can be fatal in CAV. To mitigate these risks, there is need for a lightweight model to identify attacks on vehicular systems. In this article, an efficient model of an Intrusion Detection System (IDS) is developed to detect anomalies in the vehicular system. The dataset used in this study is an In-Vehicle Network (IVN) communication protocol, i.e., Control Area Network (CAN) dataset generated in a real-time environment. The model classifies different types of attacks on vehicles into reconnaissance, Denial of Service (DoS), and fuzzing attacks. Experimentation with performance metrics of accuracy, precision, recall, and F-1 score are compared across a variety of classification models. The results demonstrate that the proposed model outperforms other classification models.


2022 ◽  
Vol 8 ◽  
pp. e820
Author(s):  
Hafiza Anisa Ahmed ◽  
Anum Hameed ◽  
Narmeen Zakaria Bawany

The expeditious growth of the World Wide Web and the rampant flow of network traffic have resulted in a continuous increase of network security threats. Cyber attackers seek to exploit vulnerabilities in network architecture to steal valuable information or disrupt computer resources. Network Intrusion Detection System (NIDS) is used to effectively detect various attacks, thus providing timely protection to network resources from these attacks. To implement NIDS, a stream of supervised and unsupervised machine learning approaches is applied to detect irregularities in network traffic and to address network security issues. Such NIDSs are trained using various datasets that include attack traces. However, due to the advancement in modern-day attacks, these systems are unable to detect the emerging threats. Therefore, NIDS needs to be trained and developed with a modern comprehensive dataset which contains contemporary common and attack activities. This paper presents a framework in which different machine learning classification schemes are employed to detect various types of network attack categories. Five machine learning algorithms: Random Forest, Decision Tree, Logistic Regression, K-Nearest Neighbors and Artificial Neural Networks, are used for attack detection. This study uses a dataset published by the University of New South Wales (UNSW-NB15), a relatively new dataset that contains a large amount of network traffic data with nine categories of network attacks. The results show that the classification models achieved the highest accuracy of 89.29% by applying the Random Forest algorithm. Further improvement in the accuracy of classification models is observed when Synthetic Minority Oversampling Technique (SMOTE) is applied to address the class imbalance problem. After applying the SMOTE, the Random Forest classifier showed an accuracy of 95.1% with 24 selected features from the Principal Component Analysis method.


2022 ◽  
Author(s):  
Arunabha Mohan Roy

Electroencephalogram (EEG) based motor imagery (MI) classification is an important aspect in brain-machine interfaces (BMIs) which bridges between neural system and computer devices decoding brain signals into recognizable machine commands. However, the MI classification task is challenging due to inherent complex properties, inter-subject variability, and low signal-to-noise ratio (SNR) of EEG signals. To overcome the above-mentioned issues, the current work proposes an efficient multi-scale convolutional neural network (MS-CNN) which can extract the distinguishable features of several non-overlapping canonical frequency bands of EEG signals from multiple scales for MI-BCI classification. In the framework, discriminant user-specific features have been extracted and integrated to improve the accuracy and performance of the CNN classifier. Additionally, different data augmentation methods have been implemented to further improve the accuracy and robustness of the model. The model achieves an average classification accuracy of 93.74% and Cohen's kappa-coefficient of 0.92 on the BCI competition IV2b dataset outperforming several baseline and current state-of-the-art EEG-based MI classification models. The proposed algorithm effectively addresses the shortcoming of existing CNN-based EEG-MI classification models and significantly improves the classification accuracy. The current framework can provide a stimulus for designing efficient and robust real-time human-robot interaction.


2022 ◽  
Vol 12 (1) ◽  
pp. 499
Author(s):  
Ying Zhou ◽  
Xiaokang Hu ◽  
Vera Chung

Paraphrase detection and generation are important natural language processing (NLP) tasks. Yet the term paraphrase is broad enough to include many fine-grained relations. This leads to different tolerance levels of semantic divergence in the positive paraphrase class among publicly available paraphrase datasets. Such variation can affect the generalisability of paraphrase classification models. It may also impact the predictability of paraphrase generation models. This paper presents a new model which can use few corpora of fine-grained paraphrase relations to construct automatically using language inference models. The fine-grained sentence level paraphrase relations are defined based on word and phrase level counterparts. We demonstrate that the fine-grained labels from our proposed system can make it possible to generate paraphrases at desirable semantic level. The new labels could also contribute to general sentence embedding techniques.


2022 ◽  
pp. 209-232
Author(s):  
Xiang Li ◽  
Jingxi Liao ◽  
Tianchuan Gao

Machine learning is a broad field that contains multiple fields of discipline including mathematics, computer science, and data science. Some of the concepts, like deep neural networks, can be complicated and difficult to explain in several words. This chapter focuses on essential methods like classification from supervised learning, clustering, and dimensionality reduction that can be easily interpreted and explained in an acceptable way for beginners. In this chapter, data for Airbnb (Air Bed and Breakfast) listings in London are used as the source data to study the effect of each machine learning technique. By using the K-means clustering, principal component analysis (PCA), random forest, and other methods to help build classification models from the features, it is able to predict the classification results and provide some performance measurements to test the model.


Author(s):  
Enrique Luna-Ramírez ◽  
Jorge Soria-Cruz ◽  
Ramón Fabio Ramírez-Báez ◽  
Gloria Yaneth Cordova-Delgado

The State of Guanajuato, located in the center of Mexico, is one of the regions of the country with a high rate of infections of the SARS-CoV-2 virus in relation to its population size, according to official data provided by the federal government. Motivated by this fact, we undertook to further analyze such data in order to identify correlations between a possible complication of the COVID-19 disease, caused by the SARS-CoV-2 virus, and some non-transmissible chronic diseases and other comorbidities. To carry out our study, we rely on the KDD methodology and specialized machine-learning tools, that allow to extract hidden knowledge in the data, which cannot usually be obtained using traditional information analysis techniques. In this way, initially, the cases infected by the SARS-CoV-2 virus were characterized in a general way and, later, classification models were built to identify some rules among the comorbidity variables.


Sign in / Sign up

Export Citation Format

Share Document