scholarly journals Performance Evaluation of Email Spam Text Classification Using Deep Neural Networks

2020 ◽  
Vol 7 (4) ◽  
pp. 91-95
Author(s):  
Venkata RamiReddy Chirra ◽  
Hoolda Daniel Maddiboyina ◽  
Yakobu Dasari ◽  
Ranganadhareddy Aluru
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Personal Information ◽  
Spam Filter ◽  
Huge Data ◽  
Junk Mail ◽  
Spam Filters ◽  
Benchmark Datasets ◽  
Domain Expertise ◽  
Traditional Approaches

Spam in email box is received because of advertising, collecting personal information, or to indulge malware through websites or scripts. Most often, spammers send junk mail with an intention of committing email fraud. Today spam mail accounts for 45% of all email and hence there is an ever-increasing need to build efficient spam filters to identify and block spam mail. However, notably today’s spam filters in use are built using traditional approaches such as statistical and content-based techniques. These techniques don’t improve their performance while handling huge data and they need a lot of domain expertise, human intervention and they neglect the relation between the words in context and consider the occurrence of the word. To address these limitations, we developed a spam filter using deep neural networks. In this work, various deep neural networks such as RNN, LSTM, GRU, Bidirectional RNN, Bidirectional LSTM, and Bidirectional GRU are used to a built spam filter. The experimentation was carried out on two datasets, one is a 20 newsgroup dataset, which contains multi-classes with 20,000 documents and the other is ENRON, a dataset contains 5,000 emails. The custom-designed models have performed well on both benchmark datasets and attained greater accuracy.

scholarly journals An efficient pruning scheme of deep neural networks for Internet of Things applications

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chen Qi ◽  
Shibo Shen ◽  
Rongpeng Li ◽  
Zhifeng Zhao ◽  
Qing Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Internet Of Things ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Compact Structure ◽  
Resource Limited ◽  
Benchmark Datasets ◽  
Iot Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

SPIT

2009 ◽  
pp. 1339-1344
Author(s):  
Kevin Curran
Keyword(s):  
Personal Information ◽  
Identity Theft ◽  
Internet Telephony ◽  
Urban Legends ◽  
The People ◽  
Junk Mail ◽  
Spam Filters ◽  
New Type ◽  
Monty Python ◽  
E Mail

Spam in the computer does not simply mean ads. Spam is any message, article, or ad that repeats itself an unacceptable number of times so that it causes annoyance. The content of the spam is of no importance. It could contain your simple “Make Money Fast” hyperlink or a beautiful piece of poetry, but if the message is continuously repeated it becomes spam. The term spam is thought to have been taken from a famous Monty Python sketch. In that sketch spam came with everything the people ordered and the waitress would be constantly saying the word spam. Therefore the meaning of spam is something that repeats itself causing much anger or annoyance. Spam can be categorized as follows: • Junk mail: Mass mailings from legitimate businesses that is unwanted. • Noncommercial spam: Mass mailings of unsolicited messages without an apparent commercial motive including chain letters, urban legends, and joke collections. • Offensive and pornographic spam: Mass mailings of “adult” advertisements or pornographic pictures. • Spam scams: Mass mailings of fraudulent messages or those designed to con people out of personal information for the purpose of identity theft and other criminal acts. • Virus spam: Mass mailings that contain viruses, Trojans, malicious scripts, and so forth. Spoofing (Schwartz & Garfinkel, 1998) is a technique often used by spammers to make them harder to trace. Trojan viruses embedded in e-mail messages also employ spoofing techniques to ensure the source of the message is more difficult to locate (Ishibashi, Yamai, Abe, & Matsuura, 2003). Spam filters and virus scanners can only eliminate a certain amount of spam and also risk catching legitimate e-mails. As the SoBig virus has demonstrated, virus scanners themselves actually add to the e-mail traffic through notification and bounceback messages. SMTP is flawed in that it allows these e-mail headers to be faked, and does not allow for the sender to be authenticated as the “real” sender of the message (Geer, 2004). This article looks at a new type of spam known as spam over Internet telephony (SPIT).

scholarly journals Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Mohammad Amin Nabian ◽  
Hadi Meidani
Keyword(s):  
Neural Networks ◽  
Engineering Design ◽  
Physical System ◽  
Deep Neural Networks ◽  
Complete Information ◽  
Training Data ◽  
Data Driven ◽  
Training Approach ◽  
Domain Expertise ◽  
Generalization Errors

Abstract In this paper, we introduce a physics-driven regularization method for training of deep neural networks (DNNs) for use in engineering design and analysis problems. In particular, we focus on the prediction of a physical system, for which in addition to training data, partial or complete information on a set of governing laws is also available. These laws often appear in the form of differential equations, derived from first principles, empirically validated laws, or domain expertise, and are usually neglected in a data-driven prediction of engineering systems. We propose a training approach that utilizes the known governing laws and regularizes data-driven DNN models by penalizing divergence from those laws. The first two numerical examples are synthetic examples, where we show that in constructing a DNN model that best fits the measurements from a physical system, the use of our proposed regularization results in DNNs that are more interpretable with smaller generalization errors, compared with other common regularization methods. The last two examples concern metamodeling for a random Burgers’ system and for aerodynamic analysis of passenger vehicles, where we demonstrate that the proposed regularization provides superior generalization accuracy compared with other common alternatives.

scholarly journals Sharing Residual Units Through Collective Tensor Factorization To Improve Deep Neural Networks

2018 ◽  
Author(s):  
Yunpeng Chen ◽  
Xiaojie Jin ◽  
Bingyi Kang ◽  
Jiashi Feng ◽  
Shuicheng Yan
Keyword(s):  
Neural Networks ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
Tensor Decomposition ◽  
Classification Performance ◽  
Model Parameters ◽  
Tensor Factorization ◽  
Unified Framework ◽  
Benchmark Datasets ◽  
Basic Network

The residual unit and its variations are wildly used in building very deep neural networks for alleviating optimization difficulty. In this work, we revisit the standard residual function as well as its several successful variants and propose a unified framework based on tensor Block Term Decomposition (BTD) to explain these apparently different residual functions from the tensor decomposition view. With the BTD framework, we further propose a novel basic network architecture, named the Collective Residual Unit (CRU). CRU further enhances parameter efficiency of deep residual neural networks by sharing core factors derived from collective tensor factorization over the involved residual units. It enables efficient knowledge sharing across multiple residual units, reduces the number of model parameters, lowers the risk of over-fitting, and provides better generalization ability. Extensive experimental results show that our proposed CRU network brings outstanding parameter efficiency -- it achieves comparable classification performance with ResNet-200 while using a model size as small as ResNet-50 on the ImageNet-1k and Places365-Standard benchmark datasets.

scholarly journals The FaceChannel: A Fast and Furious Deep Neural Network for Facial Expression Recognition

2020 ◽  
Vol 1 (6) ◽  
Author(s):  
Pablo Barros ◽  
Nikhil Churamani ◽  
Alessandra Sciutti
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Facial Expression ◽  
Facial Expression Recognition ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Facial Features ◽  
Expression Recognition ◽  
Current State ◽  
Benchmark Datasets

AbstractCurrent state-of-the-art models for automatic facial expression recognition (FER) are based on very deep neural networks that are effective but rather expensive to train. Given the dynamic conditions of FER, this characteristic hinders such models of been used as a general affect recognition. In this paper, we address this problem by formalizing the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks. We introduce an inhibitory layer that helps to shape the learning of facial features in the last layer of the network and, thus, improving performance while reducing the number of trainable parameters. To evaluate our model, we perform a series of experiments on different benchmark datasets and demonstrate how the FaceChannel achieves a comparable, if not better, performance to the current state-of-the-art in FER. Our experiments include cross-dataset analysis, to estimate how our model behaves on different affective recognition conditions. We conclude our paper with an analysis of how FaceChannel learns and adapts the learned facial features towards the different datasets.

scholarly journals Time-Effective Simulation Methodology for Broadband Achromatic Metalens Using Deep Neural Networks

Nanomaterials ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1966
Author(s):  
Chun-Yuan Fan ◽  
Guo-Dung J. Su
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Calculated Data ◽  
Visible Spectrum ◽  
Electromagnetic Simulation ◽  
Simulation Methodology ◽  
Electromagnetic Problems ◽  
Huge Data ◽  
Data Points ◽  
Data Library

Metasurface has demonstrated potential and novel optical properties in previous research. The prevailing method of designing a macroscale metasurface is based on the local periodic approximation. Such a method relies on the pre-calculated data library, including phase delay and transmittance of the nanostructure, which is rigorously calculated by the electromagnetic simulation. However, it is usually time-consuming to design a complex metasurface such as broadband achromatic metalens due the required huge data library. This paper combined different numbers of nanofins and used deep neural networks to train our data library, and the well-trained model predicted approximately ten times more data points, which show a higher transmission for designing a broadband achromatic metalens. The results showed that the focusing efficiency of designed metalens using the augmented library is up to 45%, which is higher than that using the original library over the visible spectrum. We demonstrated that the proposed method is time-effective and accurate enough to design complex electromagnetic problems.

scholarly journals Landmark-Guided Local Deep Neural Networks for Age and Gender Classification

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Yungang Zhang ◽  
Tianwei Xu
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Global Network ◽  
Gender Classification ◽  
Local Networks ◽  
Age And Gender ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Model Training ◽  
And Gender

Many types of deep neural networks have been proposed to address the problem of human biometric identification, especially in the areas of face detection and recognition. Local deep neural networks have been recently used in face-based age and gender classification, despite their improvement in performance, their costs on model training is rather expensive. In this paper, we propose to construct a local deep neural network for age and gender classification. In our proposed model, local image patches are selected based on the detected facial landmarks; the selected patches are then used for the network training. A holistical edge map for an entire image is also used for training a “global” network. The age and gender classification results are obtained by combining both the outputs from both the “global” and the local networks. Our proposed model is tested on two face image benchmark datasets; competitive performance is obtained compared to the state-of-the-art methods.

scholarly journals Phishing Website Detection using Supervised Deep Learning

2019 ◽  
Vol 8 (4) ◽  
pp. 4844-4846
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Personal Information ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Web Pages ◽  
Web Page ◽  
Algorithmic Approach ◽  
Learning Techniques

The website phishing is the tremendously growing problem over the internet which will lead to the loss of personal information. This process will run like, when ever user clicks a website link it will lead them to the web page that is created by the phisher to deceive the user. After this phishing has been started in order to stop it many techniques came into existence to detect the phished web site and help the user from being deceived by the attacker. Even though many techniques have adapted to stop the attackers, it is difficult because as many phished web pages are generated by the attackers within few hours. Most of the techniques to detect these phishing websites are not able to decide the fake website with legitimate one because the accuracy of getting results are much less. There are many supervised machine learning techniques which are supervised, where a primary set of data is given to the algorithm and depending on that set the algorithm will be trained and it will predict the results for the same. One of the most important techniques that is deep Learning classifiers is applied with significant features to detect phishing websites. By using this algorithm we can classify the phishing websites from genuine websites by using effective features. In this algorithmic approach to detect genuine websites a feature set is used so by analyzing these features using deep neural networks we can detect a website is phished or not. We can also increase the accuracy of our algorithm by adding certain more features and increasing the hidden layers in neural networks.

scholarly journals Leveraging the Bhattacharyya coefficient for uncertainty quantification in deep neural networks

2021 ◽  
Author(s):  
Pieter Van Molle ◽  
Tim Verbelen ◽  
Bert Vankeirsbilck ◽  
Jonas De Vylder ◽  
Bart Diricx ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Use Case ◽  
Bhattacharyya Coefficient ◽  
Output Uncertainty ◽  
Novel Approach ◽  
Benchmark Datasets ◽  
Network Approaches

AbstractModern deep learning models achieve state-of-the-art results for many tasks in computer vision, such as image classification and segmentation. However, its adoption into high-risk applications, e.g. automated medical diagnosis systems, happens at a slow pace. One of the main reasons for this is that regular neural networks do not capture uncertainty. To assess uncertainty in classification, several techniques have been proposed casting neural network approaches in a Bayesian setting. Amongst these techniques, Monte Carlo dropout is by far the most popular. This particular technique estimates the moments of the output distribution through sampling with different dropout masks. The output uncertainty of a neural network is then approximated as the sample variance. In this paper, we highlight the limitations of such a variance-based uncertainty metric and propose an novel approach. Our approach is based on the overlap between output distributions of different classes. We show that our technique leads to a better approximation of the inter-class output confusion. We illustrate the advantages of our method using benchmark datasets. In addition, we apply our metric to skin lesion classification—a real-world use case—and show that this yields promising results.

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT

2018 ◽  
Author(s):  
Alex Hernández-García ◽  
Johannes Mehrer ◽  
Nikolaus Kriegeskorte ◽  
Peter König ◽  
Tim C. Kietzmann
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation
Sign in / Sign up

Export Citation Format

Share Document