A Multi-task Learning Framework for Grasping-Position Detection and Few-Shot Classification

Though both machine learning and deep learning have made great progress in developing intrusion detection systems (IDSs), two critical problems remain. The first is the ever-evolving nature of malicious activity. Data flows and packets can contain several types of attacks simultaneously, while machine learning and deep learning algorithms can only learn a single task at a time. Second, the publicly available datasets are created to evaluate only one type of attack. In order to address these issues, this paper proposes a Multi-Task Learning (MTL) model for an IDS based on deep neural networks (DNNs), which has the ability to detect several types of attacks simultaneously. To do this, we concatenated each corresponding sample in both the UNSW-NB15 and CICIDS2017 datasets into one feature vector. This guarantees that a portion of the data flows, in both the training and testing sets, contains two threats at one time. The experimental results demonstrate that the proposed system maximizes performance.

Sensitive information such as credit card information, username, password and social security number etc, can be stolen using a fake page that imitates trusted website is called phishing. The attacker designs a similar webpage either by copying or making small manipulation to the legitimate page so that the online user cannot distinguish the legitimate and fake websites. A Deep Neural Network (DNN) was introduced to detect the phishing Uniform Resource Locator (URL). Initially, a 30-dimension feature vector was constructed based on URL-based features, Hypertext Markup Language (HTML)-based features and domain-based features. These features were processed in DNN to detect the phishing URL. However, the irrelevant, redundant and noisy features in the dataset increase the complexity of DNN classifier. So the feature selection is required for efficient phishing attack detection. But feature selection is a time-consuming process since it is an independent process. So in this paper, a feature vector is generated by DNN itself using Stacked Denoise Auto Encoder (SDAE). Moreover, the noisy data such as missing features affect the efficiency of phishing detection so the SDAE is trained to reconstruct a clean input feature vector. The initial input feature vector is corrupted by setting some feature vectors as zero. Then the corrupted feature vector is then mapped with basic auto encoder, to a hidden representation from which the input feature vector is reconstructed. The reconstructed features are given as input to DNN which selects the most relevant features and predicts the phishing URL. Hence the sparse feature representation of SDAE increases the classification accuracy of DNN. The experiments are conducted in Ham, Phishing Corpus and Phishload datasets in terms of accuracy, precision, recall and F-measure to prove the effectiveness of DNN-SDAE.

In recent years, multitask learning has turned out to be of great success in various applications. Though single task model training has promised great results throughout these years, it ignores valuable information which might help in estimating better learning parameters. By virtue of learning-related tasks, multitask learning has been able to generalize the models even better. In this paper, we try to enhance the feature mapping of multitask deep learning models by sharing features among related tasks and inductive transfer learning. We have explored the learning of task relationship among various tasks for acquiring more benefits from multitask learning. The proposed enhanced model is compared with two state-of-the-art multitask deep learning models, namely Hyperface and FaceNet. The results show better performance of the proposed model in predicting age, gender and ethnicity on the UTK face dataset.KeywordsNeural networksMultitask deep learningDeep learningRecurrent neural networksConvolution neural networks

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

Computer assisted automatic smart pattern analysis of cancer affected pixel structure takes critical role in pre-interventional decision making for oral cancer treatment. Internet of Things (IoT) in healthcare systems is now emerging solution for modern e-healthcare system to provide high quality medical care. In this research work, we proposed a novel method which utilizes a modified vesselness measurement and a Deep Convolutional Neural Network (DCNN) to identify the oral cancer region structure in IoT based smart healthcare system. The robust vesselness filtering scheme handles noise while reserving small structures, while the CNN framework considerably improves classification accuracy by deblurring focused region of interest (ROI) through integrating with multi-dimensional information from feature vector selection step. The marked feature vector points are extracted from each connected component in the region and used as input for training the CNN. During classification, each connected part is individually analysed using the trained DCNN by considering the feature vector values that belong to its region. For a training of 1500 image dataset, an accuracy of 96.8% and sensitivity of 92% is obtained. Hence, the results of this work validate that the proposed algorithm is effective and accurate in terms of classification of oral cancer region in accurate decision making. The developed system can be used in IoT based diagnosis in health care systems, where accuracy and real time diagnosis are essential.

The optimal solution to an optimization problem depends on the problem’s objective function, constraints, and size. While deep neural networks (DNNs) have proven effective in solving optimization problems, changes in the problem’s size, objectives, or constraints often require adjustments to the DNN architecture to maintain effectiveness, or even retraining a new DNN from scratch. Given the nature of wireless networks, which involves multiple and diverse objectives that can have conflicting requirements and constraints, we propose a multi-task learning (MTL) framework to enable a single DNN to jointly solve a range of diverse optimization problems. In this framework, optimization problems with varying dimensionality values, objectives, and constraints are treated as distinct tasks. To jointly address these tasks, we propose a conditional computation-based MTL approach with routing. The multi-task DNN consists of two components, the base DNN (bDNN), which is the single DNN used to extract the solutions for all considered optimization problems, and the routing DNN (rDNN), which manages which nodes and layers of the bDNN to be used during the forward propagation of each task. The output of the rDNN is multiplied with all bDNN’s weights during the forward propagation, creating a unique computational path through the bDNN for each task. This setup allows the tasks to either share parameters or use independent ones, with the decision controlled by the rDNN. The proposed framework supports both supervised and unsupervised learning scenarios. Based on this framework, a soft modularization and a hard parameter sharing approach of lower complexity are proposed. The numerical results demonstrate the efficiency of the proposed MTL approaches compared to several multi-task benchmarks and the single-task DNN approach.

The excellent feature extraction ability of deep convolutional neural networks (DCNNs) has been demonstrated in many image processing tasks, by which image classification can achieve high accuracy with only raw input images. However, the specific image features that influence the classification results are not readily determinable and what lies behind the predictions is unclear. This study proposes a method combining the Sobel and Canny operators and an Inception module for ship classification. The Sobel and Canny operators obtain enhanced edge features from the input images. A convolutional layer is replaced with the Inception module, which can automatically select the proper convolution kernel for ship objects in different image regions. The principle is that the high-level features abstracted by the DCNN, and the features obtained by multi-convolution concatenation of the Inception module must ultimately derive from the edge information of the preprocessing input images. This indicates that the classification results are based on the input edge features, which indirectly interpret the classification results to some extent. Experimental results show that the combination of the edge features and the Inception module improves DCNN ship classification performance. The original model with the raw dataset has an average accuracy of 88.72%, while when using enhanced edge features as input, it achieves the best performance of 90.54% among all models. The model that replaces the fifth convolutional layer with the Inception module has the best performance of 89.50%. It performs close to VGG-16 on the raw dataset and is significantly better than other deep neural networks. The results validate the functionality and feasibility of the idea posited.

Survey on Deep Neural Networks in Speech and Vision Systems

Recent works show that knowledge transfer is an effective strategy to solve cross-domain diagnosis problems. The existing domain adaptation methods considering both global and local distribution between domains do not make the most of the knowledge learned by deep neural network, resulting in low diagnosis accuracy. To solve this problem, a deep multi feature dynamic adversarial diagnosis (DMDAD) method for transfer diagnosis of rotating machinery is presented in this paper. Firstly, the one-dimensional deep convolutional neural network is utilized as the feature encoder to learn the characteristics of vibration signals in different working conditions. The class prediction vector and feature vector are fused by the multilinear mapping. The fused features are conducted for the dynamic discrimination network for adversarial training. At the same time, considering the statistical alignment and adversarial alignment, the domain adaptation is finally realized. The experimental study demonstrates the effectiveness of the DMDAD.

Deep convolutional neural networks have achieved great success in recent years. They have been widely used in various applications such as optical and SAR image scene classification, object detection and recognition, semantic segmentation, and change detection. However, deep neural networks rely on large-scale high-quality training data, and can only guarantee good performance when the training and test data are independently sampled from the same distribution. Deep convolutional neural networks are found to be vulnerable to subtle adversarial perturbations. This adversarial vulnerability prevents the deployment of deep neural networks in security-sensitive applications such as medical, surveillance, autonomous driving and military scenarios. This paper first presents a holistic view of security issues for deep convolutional neural network-based image recognition systems. The entire information processing chain is analyzed regarding safety and security risks. In particular, poisoning attacks and evasion attacks on deep convolutional neural networks are analyzed in detail. The root causes of adversarial vulnerabilities of deep recognition models are also discussed. Then, we give a formal definition of adversarial robustness and present a comprehensive review of adversarial attacks, adversarial defense, and adversarial robustness evaluation. Rather than listing existing research, we focus on the threat models for the adversarial attack and defense arms race. We perform a detailed analysis of several representative adversarial attacks on SAR image recognition models and provide an example of adversarial robustness evaluation. Finally, several open questions are discussed regarding recent research progress from our workgroup. This paper can be further used as a reference to develop more robust deep neural network-based image recognition models in dynamic adversarial scenarios.

BackgroundAccurately predicting drug-target binding affinity (DTA) in silico plays an important role in drug discovery. Most of the computational methods developed for predicting DTA use machine learning models, especially deep neural networks, and depend on large-scale labelled data. However, it is difficult to learn enough feature representation from tens of millions of compounds and hundreds of thousands of proteins only based on relatively limited labelled drug-target data. There are a large number of unknown drugs, which never appear in the labelled drug-target data. This is a kind of out-of-distribution problems in bio-medicine. Some recent studies adopted self-supervised pre-training tasks to learn structural information of amino acid sequences for enhancing the feature representation of proteins. However, the task gap between pre-training and DTA prediction brings the catastrophic forgetting problem, which hinders the full application of feature representation in DTA prediction and seriously affects the generalization capability of models for unknown drug discovery.ResultsTo address these problems, we propose the GeneralizedDTA, which is a new DTA prediction model oriented to unknown drug discovery, by combining pre-training and multi-task learning. We introduce self-supervised protein and drug pre-training tasks to learn richer structural information from amino acid sequences of proteins and molecular graphs of drug compounds, in order to alleviate the problem of high variance caused by encoding based on deep neural networks and accelerate the convergence of prediction model on small-scale labelled data. We also develop a multi-task learning framework with a dual adaptation mechanism to narrow the task gap between pre-training and prediction for preventing overfitting and improving the generalization capability of DTA prediction model on unknown drug discovery. To validate the effectiveness of our model, we construct an unknown drug data set to simulate the scenario of unknown drug discovery. Compared with existing DTA prediction models, the experimental results show that our model has the higher generalization capability in the DTA prediction of unknown drugs.ConclusionsThe advantages of our model are mainly attributed to two kinds of pre-training tasks and the multi-task learning framework, which can learn richer structural information of proteins and drugs from large-scale unlabeled data, and then effectively integrate it into the downstream prediction task for obtaining a high-quality DTA prediction in unknown drug discovery.

Deep neural networks (DNNs) have made multi-task learning (MTL) a powerful way to learn multiple linked tasks at once, using shared models to improve generalization and speed. But successfully matching task goals is still one of the biggest problems in MTL, since giving all tasks the same level of value often results in poor performance. To solve this problem, we suggest a new way to improve MTL in DNNs: job priorities should be balanced automatically based on how important they are. Our framework includes a task priority balance system that changes how much each job contributes to the total loss function as training goes on. This system uses measures that are relevant to the job, like how hard it is and how much data is available, to automatically assign resources and set learning priorities. By managing task priorities well, our system lets DNNs focus more on important tasks while giving the right amount of resources to less important ones, which makes all tasks run better overall. We show that our method works by doing a lot of tests on a bunch of different standard datasets from different fields. The results show that our system regularly does better than other MTL methods by being more accurate and more general, especially when job difficulties are uneven. Overall, our framework offers an adaptable and effective way to enhance MTL in DNNs, boosting performance by constantly balancing job priorities.

Adversarial attacks are a big problem for deep neural networks (DNNs), especially when it comes to image classification tasks where even small changes can lead to big mistakes. This weakness makes deep convolutional neural networks (DCNNs), generative adversarial networks (GANs), and new architectures like Vision Transformers less reliable. In the last few years, there have been a lot of new ways to attack, from gradient-based methods like FGSM and PGD to optimization-based, patch, and backdoor attacks. As a result, defense mechanisms have developed in many areas, such as adversarial training, input transformations, detection frameworks, and generative purification methods. Even with these improvements, no one defense has been shown to be strong enough to work in all situations. Most methods have to choose between accuracy, scalability, and resistance to adaptive adversaries. To solve this problem, researchers are looking into optimization-driven methods to make systems more robust and improve training efficiency. These methods include biologically inspired metaheuristics like Sparrow Search and Cuckoo Optimization, as well as modern deep learning optimizers. Benchmark datasets like MNIST, Fashion-MNIST, and CIFAR-10 have become very important for testing both attacks and defenses. They give us a standard way to measure accuracy, precision, recall, and sensitivity when things go wrong. This review brings together changes from 2018 to 2023, with a focus on optimization-enhanced training and the different types of adversarial strategies and defense paradigms. Moreover, we suggest a hybrid defense framework that combines adversarial training, metaheuristic optimization, and lightweight input filtering to protect against both white-box and black-box attacks at multiple levels. The goal is to get a full picture of the adversarial landscape, find research gaps that keep coming up, and find ways to make deep learning models for image classification that are more resistant to attacks.

Traditional Image Processing Techniques (IPT), used for automating the detection and classification of weld defects from radiography images, have their own limitations, which can be overcome by Deep Neural Networks (DNN). DNN produces considerably good results in fields which offer big dataset for it to train. DNN trained with small datasets by conventional methods produces less accurate results. This limits the use of DNN in many fields. This study focuses to overcome this limitation, by adopting transfer learning using Pre-trained deep convolutional neural networks. By this method, a weld defect radiographic image classifier, which can classify 14 types of weld defects, was constructed. 940 Image patches of weld defects were manually collected and labelled from GDXray database. Subsequently the features of this weld defect dataset were extracted using VGG16 and ResNet50 CNNs, both pre-trained on the ImageNet database. Then machine learning models such as Logistic Regression, Support Vector Machine (SVM) and Random Forest were trained on these extracted features. The Classifier based on SVM trained on features extracted by ResNet50 outperforms the other counter parts with an accuracy of 98%. In all these cases, transfer learning improves performance and reduces the training time and computational system requirements.

Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks