scholarly journals A Two-Stage Cascaded Detection Scheme for Double HEVC Compression Based on Temporal Inconsistency

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Peisong He ◽  
Hongxia Wang ◽  
Ruimei Zhang ◽  
Yue Li
Keyword(s):  
Video Clip ◽  
Detection Methods ◽  
Support Vector ◽  
Detection Accuracy ◽  
Bit Rate ◽  
Two Stage ◽  
Detection Scheme ◽  
Double Compression ◽  
Leibler Divergence ◽  
Temporal Inconsistency

Nowadays, verifying the integrity of digital videos is significant especially for applications about multimedia communication. In video forensics, detection of double compression can be treated as the first step to analyze whether a suspicious video undergoes any tampering operations. In the last decade, numerous detection methods have been proposed to address this issue, but most existing methods design a universal detector which is hard to handle various recompression settings efficiently. In this work, we found that the statistics of different Coding Unit (CU) types have dissimilar properties when original videos are recompressed by the increased and decreased bit rates. It motivates us to propose a two-stage cascaded detection scheme for double HEVC compression based on temporal inconsistency to overcome limitations of existing methods. For a given video, CU information maps are extracted from each short-time video clip using our proposed value mapping strategy. In the first detection stage, a compact feature is extracted based on the distribution of different CU types and Kullback–Leibler divergence between temporally adjacent frames. This detection feature is fed into the Support Vector Machine classifier to identify abnormal frames with the increased bit rate. In the second stage, a shallow convolutional neural network equipped with dense connections is designed carefully to learn robust spatiotemporal representations, which can identify abnormal frames with the decreased bit rate whose forensic traces are less detectable. In experiments, the proposed method can achieve more promising detection accuracy compared with several state-of-the-art methods under various coding parameter settings, especially when the original video is recompressed with a low quality (e.g., more than 8%).

scholarly journals A Mass Spectrometric Analysis Method Based on PPCA and SVM for Early Detection of Ovarian Cancer

2016 ◽  
Vol 2016 ◽  
pp. 1-6 ◽  
Author(s):  
Jiang Wu ◽  
Yanju Ji ◽  
Ling Zhao ◽  
Mengying Ji ◽  
Zhuang Ye ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Cancer Detection ◽  
Detection Methods ◽  
Support Vector ◽  
Detection Accuracy ◽  
Analysis Method ◽  
Data Set ◽  
Specificity And Sensitivity ◽  
Svm Model ◽  
Tof Ms

Background. Surfaced-enhanced laser desorption-ionization-time of flight mass spectrometry (SELDI-TOF-MS) technology plays an important role in the early diagnosis of ovarian cancer. However, the raw MS data is highly dimensional and redundant. Therefore, it is necessary to study rapid and accurate detection methods from the massive MS data.Methods. The clinical data set used in the experiments for early cancer detection consisted of 216 SELDI-TOF-MS samples. An MS analysis method based on probabilistic principal components analysis (PPCA) and support vector machine (SVM) was proposed and applied to the ovarian cancer early classification in the data set. Additionally, by the same data set, we also established a traditional PCA-SVM model. Finally we compared the two models in detection accuracy, specificity, and sensitivity.Results. Using independent training and testing experiments 10 times to evaluate the ovarian cancer detection models, the average prediction accuracy, sensitivity, and specificity of the PCA-SVM model were 83.34%, 82.70%, and 83.88%, respectively. In contrast, those of the PPCA-SVM model were 90.80%, 92.98%, and 88.97%, respectively.Conclusions. The PPCA-SVM model had better detection performance. And the model combined with the SELDI-TOF-MS technology had a prospect in early clinical detection and diagnosis of ovarian cancer.

scholarly journals A supervised method for object-based 3D building change detection on aerial stereo images

2014 ◽  
Vol XL-3 ◽  
pp. 259-264 ◽  
Author(s):  
R. Qin ◽  
A. Gruen
Keyword(s):  
Change Detection ◽  
Current Trend ◽  
Detection Methods ◽  
Support Vector ◽  
Detection Accuracy ◽  
Status Change ◽  
Aerial Photos ◽  
Object Based ◽  
The Status

There is a great demand for studying the changes of buildings over time. The current trend for building change detection combines the orthophoto and DSM (Digital Surface Models). The pixel-based change detection methods are very sensitive to the quality of the images and DSMs, while the object-based methods are more robust towards these problems. In this paper, we propose a supervised method for building change detection. After a segment-based SVM (Support Vector Machine) classification with features extracted from the orthophoto and DSM, we focus on the detection of the building changes of different periods by measuring their height and texture differences, as well as their shapes. A decision tree analysis is used to assess the probability of change for each building segment and the traffic lighting system is used to indicate the status "change", "non-change" and "uncertain change" for building segments. The proposed method is applied to scanned aerial photos of the city of Zurich in 2002 and 2007, and the results have demonstrated that our method is able to achieve high detection accuracy.

scholarly journals Real-time Factory Smoke Detection Based on Two-stage Relation-guided Algorithm

2021 ◽  
Author(s):  
Zhenyu Wang ◽  
Senrong Ji ◽  
Duokun Yin
Keyword(s):  
Real Time ◽  
Contextual Information ◽  
Search Space ◽  
Detection Algorithm ◽  
Image Resolution ◽  
Single Stage ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Smoke Detection ◽  
Two Stage

Abstract Recently, using image sensing devices to analyze air quality has attracted much attention of researchers. To keep real-time factory smoke under universal social supervision, this paper proposes a mobile-platform-running efficient smoke detection algorithm based on image analysis techniques. Since most smoke images in real scenes have challenging variances, it’s difficult for existing object detection methods. To this end, we introduce the two-stage smoke detection (TSSD) algorithm based on the lightweight framework, in which the prior knowledge and contextual information are modeled into the relation-guided module to reduce the smoke search space, which can therefore significantly improve the shortcomings of the single-stage method. Experimental results show that the TSSD algorithm can robustly improve the detection accuracy of the single-stage method and has good compatibility for different image resolution inputs. Compared with various state-of-the-art detection methods, the accuracy AP mean of the TSSD model reaches 59.24%, even surpassing the current detection model Faster R-CNN. In addition, the detection speed of our proposed model can reach 50 ms (20 FPS), which meets the real-time requirements, and can be deployed in the mobile terminal carrier. This model can be widely used in some scenes with smoke detection requirements, providing great potential for practical environmental applications.

Abnormal Data Detection of Guidance Angle Based On SMP-SVDD For Seeker

2021 ◽  
Author(s):  
Chao Liang ◽  
Xiangrong Zhang ◽  
Dedong Cui ◽  
Zhengang Yan ◽  
Xiangyu Zhang ◽  
...  
Keyword(s):  
Pitch Angle ◽  
Detection Methods ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Data Detection ◽  
Detection Accuracy ◽  
Angle Data ◽  
Angle Deviation ◽  
Optimal Kernel ◽  
The One

Abstract The accuracy of the pitch angle deviation directly affects the guidance accuracy of the laser seeker. During the guidance process, the abnormal pitch angle deviation data will be produced when the seeker is affected by interference sources. In this paper, aiming to detect abnormal data in seeker pitch angle deviation data, a method based on Smooth Multi-Kernel Polarization Support Vector Data Description (SMP-SVDD) is proposed to detect abnormal data in guidance angle data. On the one hand, the polarization value is used to determine the weight of the multi-kernel combination coefficient to obtain the multi-kernel polarization function, and the particle swarm optimization is used to find the optimal kernel, which improves the detection accuracy. On the other hand, the constrained quadratic programming problem is smooth and differentiable, and the conjugate gradient method can be applied to reduce the complexity of problem solving. Through simulation experiments, it is verified that the SMP-SVDD method has higher detection accuracy and faster calculation speed compared with different detection methods in different guidance stages.

scholarly journals On the Detection of Low-Rate Denial of Service Attacks at Transport and Application Layers

Electronics ◽  
2021 ◽  
Vol 10 (17) ◽  
pp. 2105
Author(s):  
Vasudha Vedula ◽  
Palden Lama ◽  
Rajendra V. Boppana ◽  
Luis A. Trejo
Keyword(s):  
Network Traffic ◽  
Short Term Memory ◽  
Transmission Control Protocol ◽  
Denial Of Service ◽  
Detection Methods ◽  
Support Vector ◽  
Detection Accuracy ◽  
Ddos Attacks ◽  
Network Bandwidth ◽  
Low Rate

Distributed denial of service (DDoS) attacks aim to deplete the network bandwidth and computing resources of targeted victims. Low-rate DDoS attacks exploit protocol features such as the transmission control protocol (TCP) three-way handshake mechanism for connection establishment and the TCP congestion-control induced backoffs to attack at a much lower rate and still effectively bring down the targeted network and computer systems. Most of the statistical and machine/deep learning-based detection methods proposed in the literature require keeping track of packets by flows and have high processing overheads for feature extraction. This paper presents a novel two-stage model that uses Long Short-Term Memory (LSTM) and Random Forest (RF) to detect the presence of attack flows in a group of flows. This model has a very low data processing overhead; it uses only two features and does not require keeping track of packets by flows, making it suitable for continuous monitoring of network traffic and on-the-fly detection. The paper also presents an LSTM Autoencoder to detect individual attack flows with high detection accuracy using only two features. Additionally, the paper presents an analysis of a support vector machine (SVM) model that detects attack flows in slices of network traffic collected for short durations. The low-rate attack dataset used in this study is made available to the research community through GitHub.

scholarly journals DDoS Defense Method in Software-Defined Space-Air-Ground Network from Dynamic Bayesian Game Perspective

2022 ◽  
Vol 2022 ◽  
pp. 1-13
Author(s):  
Zhaobin Li ◽  
Bin Yang ◽  
Xinyu Zhang ◽  
Chao Guo
Keyword(s):  
Dynamic Balance ◽  
Denial Of Service ◽  
Detection Methods ◽  
Support Vector ◽  
Detection Accuracy ◽  
Real Time Control ◽  
Bayesian Game ◽  
Integrated Networks ◽  
Time Control ◽  
Attack And Defense

The centralized management of Software-Defined Network (SDN) brings convenience to Space-Air-Ground Integrated Networks (SAGIN), which also makes it vulnerable to Distributed Denial of Service (DDoS). At present, the popular detection methods are based on machine learning, but most of them are fixed detection strategies with high overhead and real-time control, so the efficiency is not high. This paper designs different defense methods for different DDoS attacks and constructs a multitype DDoS defense model based on a dynamic Bayesian game in the Software-Defined Space-Air-Ground Integrated Networks (SD-SAGIN). The proposed game model’s Nash equilibrium is solved based on the different costs and payoffs of each method. We simulated the attack and defense of DDoS in Ryu controller and Mininet. The results show that, under our model, the attacker and defender’s strategies are in a dynamic balance, and the controller can effectively reduce the defense cost while ensuring detection accuracy. Compared with the existing traditional Support Vector Machine (SVM) defense method, the performance of the proposed method is better, and it provides one of the references for DDoS defense in SD-SAGIN.

scholarly journals Robust Detection of Bearing Early Fault Based on Deep Transfer Learning

Electronics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 323 ◽  
Author(s):  
Wentao Mao ◽  
Di Zhang ◽  
Siyu Tian ◽  
Jiamei Tang
Keyword(s):  
Transfer Learning ◽  
Normal State ◽  
Low Rank ◽  
Detection Methods ◽  
Support Vector ◽  
Detection Accuracy ◽  
Robust Detection ◽  
Detection Model ◽  
Performance Reduction ◽  
The Common

In recent years, machine learning techniques have been proven to be a promising tool for early fault detection of rolling bearings. In many actual applications, however, bearing whole-life data are not easy to be historically accumulated, while insufficient data may result in training a detection model that is not good enough. If utilizing the available data under different working conditions to facilitate model training, the data distribution of different bearings are usually quite different, which does not meet the precondition of i n d e p e n d e n t a n d i d e n t i c a l d i s t r i b u t i o n ( i . i . d ) and tends to cause performance reduction. In addition, disturbed by the unstable noise under complex conditions, most of the current detection methods are inclined to raise false alarms, so that the reliability of detection results needs to be improved. To solve these problems, a robust detection method for bearings early fault is proposed based on deep transfer learning. The method includes offline stage and online stage. In the offline stage, by introducing a deep auto-encoder network with domain adaptation, the distribution inconsistency of normal state data among different bearings can be weakened, then the common feature representation of the normal state is obtained. With the extracted common features, a new state assessment method based on the robust deep auto-encoder network is proposed to evaluate the boundary between normal state and early fault state in the low-rank feature space. By training a support vector machine classifier, the detection model is established. In the online stage, along with the data batch arriving sequentially, the features of target bearing are extracted using the common representation learnt in the offline stage, and online detection is conducted by feeding them into the SVM model. Experimental results on IEEE PHM Challenge 2012 bearing dataset and XJTU-SY dataset show that the proposed approach outperforms several state-of-the-art detection methods in terms of detection accuracy and false alarm rate.

scholarly journals Cloud detection in all-sky images via multi-scale neighborhood features and multiple supervised learning techniques

2017 ◽  
Vol 10 (1) ◽  
pp. 199-208 ◽  
Author(s):  
Hsu-Yung Cheng ◽  
Chih-Lung Lin
Keyword(s):  
Supervised Learning ◽  
Detection Methods ◽  
Support Vector ◽  
Detection Accuracy ◽  
Cloud Detection ◽  
Multi Scale ◽  
Cloud Models ◽  
Learning Techniques ◽  
Image Patches ◽  
Local Image

Abstract. Cloud detection is important for providing necessary information such as cloud cover in many applications. Existing cloud detection methods include red-to-blue ratio thresholding and other classification-based techniques. In this paper, we propose to perform cloud detection using supervised learning techniques with multi-resolution features. One of the major contributions of this work is that the features are extracted from local image patches with different sizes to include local structure and multi-resolution information. The cloud models are learned through the training process. We consider classifiers including random forest, support vector machine, and Bayesian classifier. To take advantage of the clues provided by multiple classifiers and various levels of patch sizes, we employ a voting scheme to combine the results to further increase the detection accuracy. In the experiments, we have shown that the proposed method can distinguish cloud and non-cloud pixels more accurately compared with existing works.

scholarly journals When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time

2019 ◽  
Vol 31 (8) ◽  
pp. 1624-1670 ◽  
Author(s):  
David Miller ◽  
Yujia Wang ◽  
George Kesidis
Keyword(s):  
Confusion Matrix ◽  
Area Under The Curve ◽  
Detection Methods ◽  
Test Time ◽  
Detection Accuracy ◽  
Relative Paucity ◽  
Curve Detection ◽  
Leibler Divergence ◽  
True Detection ◽  
Characteristic Area

A significant threat to the recent, wide deployment of machine learning–based systems, including deep neural networks (DNNs), is adversarial learning attacks. The main focus here is on evasion attacks against DNN-based classifiers at test time. While much work has focused on devising attacks that make small perturbations to a test pattern (e.g., an image) that induce a change in the classifier's decision, until recently there has been a relative paucity of work defending against such attacks. Some works robustify the classifier to make correct decisions on perturbed patterns. This is an important objective for some applications and for natural adversary scenarios. However, we analyze the possible digital evasion attack mechanisms and show that in some important cases, when the pattern (image) has been attacked, correctly classifying it has no utility---when the image to be attacked is (even arbitrarily) selected from the attacker's cache and when the sole recipient of the classifier's decision is the attacker. Moreover, in some application domains and scenarios, it is highly actionable to detect the attack irrespective of correctly classifying in the face of it (with classification still performed if no attack is detected). We hypothesize that adversarial perturbations are machine detectable even if they are small. We propose a purely unsupervised anomaly detector (AD) that, unlike previous works, (1) models the joint density of a deep layer using highly suitable null hypothesis density models (matched in particular to the nonnegative support for rectified linear unit (ReLU) layers); (2) exploits multiple DNN layers; and (3) leverages a source and destination class concept, source class uncertainty, the class confusion matrix, and DNN weight information in constructing a novel decision statistic grounded in the Kullback-Leibler divergence. Tested on MNIST and CIFAR image databases under three prominent attack strategies, our approach outperforms previous detection methods, achieving strong receiver operating characteristic area under the curve detection accuracy on two attacks and better accuracy than recently reported for a variety of methods on the strongest (CW) attack. We also evaluate a fully white box attack on our system and demonstrate that our method can be leveraged to strong effect in detecting reverse engineering attacks. Finally, we evaluate other important performance measures such as classification accuracy versus true detection rate and multiple measures versus attack strength.

scholarly journals A Two-Stage Fall Recognition Algorithm Based on Human Posture Features

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6966
Author(s):  
Kun Han ◽  
Qiongqian Yang ◽  
Zefan Huang
Keyword(s):  
Human Body ◽  
Stable State ◽  
Recognition Algorithm ◽  
The Body ◽  
Support Vector ◽  
Unstable State ◽  
Detection Accuracy ◽  
Two Stage ◽  
Human Posture ◽  
Key Features

Falls are seriously threatening the health of elderly. In order to reduce the potential danger caused by falls, this paper proposes a two-stage fall recognition algorithm based on human posture features. For preprocessing, we construct the new key features: deflection angles and spine ratio to describe the changes of human posture based on the human skeleton extracted by OpenPose. In the first stage, based on the variables: tendency symbol and steady symbol integrated by the scattered key features, we divide the human body state into three states: stable state, fluctuating state, and disordered state. By analyzing whether the body is in a stable state, the ADL (activities of daily living) actions with high stability can be preliminarily excluded. In the second stage: to further identify the confusing ADL actions and the fall actions, we innovatively design a time-continuous recognition algorithm. When human body is constantly in an unstable state, the human posture features: compare value γ, energy value ε, state score τ are proposed to form a feature vector, and support vector machine (SVM), K nearest neighbors (KNN), decision tree (DT), random forest (RF) are utilized for classification. Experiment results demonstrate that SVM with linear kernel function can distinguish falling actions best and our approach achieved a detection accuracy of 97.34%, precision of 98.50%, and the recall, F1 score are 97.33%, 97.91% respectively. Compared with previous state-of-art algorithms, our algorithm can achieve the highest recognition accuracy. It proves that our fall detection method is effective.

Sign in / Sign up

Export Citation Format

Share Document