Search

The longitudinal tear of conveyor belts is the most common accident occurring at the workplace. Given the limitations on accuracy and stability of current single-modal approaches to detecting the longitudinal tear of conveyor belts, a solution is proposed in this paper through Audio-Visual Fusion. According to this method, a linear CCD camera is used to capture the images of the conveyor belt and a microphone array for the acquisition of sound signals from the operating belt conveyor. Then, the visual data is inputted into an improved Shufflenet_V2 network for classification, while the preprocessed sound signals are subjected to feature extraction and classification using a CNN-LSTM network. Finally, decision fusion is performed in line with Dempster-Shafer theory for image and sound classification. Experimental results show that the method proposed in this paper achieves an accuracy of 97% in tear detection, which is 1.2% and 2.8% higher compared to using images or sound alone, respectively. Apparently, the method proposed in this paper is effective in enhancing the performance of the existing detection methods. [ABSTRACT FROM AUTHOR]

In the wake of the development and advancement of signal processing technology for communication radiation source individual, Signal fingerprint feature extraction and analysis technology for communication radiation source individual has broad application prospects in many fields. To effectively extract the individual characteristics of different modulated signals under low SNR environment, and recognize the subtle features for communication radiation source individuals has been a hot spot. Aiming at the problem of signal feature extraction and classifier design under low SNR environment, in the paper, a multifractal dimension and improved gray relation theory based classifier design algorithm is proposed. Firstly, the multifractal dimension feature extraction of nine modulated communication signals is realized. Then multifractal dimension features of these modulated signals under different SNR are compared. An improved gray relation algorithm is used to recognize the extracted subtle characteristics. Meanwhile, FSK signal is used to simulate radio subtle features by adding different distribution of noise. Subtle feature extraction by means of multifractal dimension algorithm and pattern recognition by means of improved gray relation algorithm are used to test the effectiveness of the proposed method for identification of modulated signals and radio subtle features. The simulation results show that the recognition success rate of nine different communication modulated signals can reach 93% even under the SNR of 2 dB, and the recognition success rate of the subtle features of distributed noise can reach 100%. The proposed method provides an effective theoretical basis for identifying of radio modulated signals and communication radiation source individual subtle features. [ABSTRACT FROM AUTHOR]

Deep-learning-based automatic modulation recognition techniques have been extensively explored for wireless communication systems, because of their strong feature extraction and classification abilities of deep neural networks. Although the high recognition accuracy and low alarms, they also raise concerns about complexity and interpretability, which can affect the practical deployments. In this paper, we propose a randomly perturbation convolutional kernel activation mapping (RPCKAM) strategy to explain modulation recognition networks, and the RPCKAM-based filter pruning method to compress modulation recognition networks, combining the reasoning and interpretation of decisions made by modulation recognition networks with the compression of network models. The RPCKAM is used to evaluate the importance of convolutional kernels, and then the importance ranking is used to provide a basis for network pruning. Moreover, the effect of pruning is verified with VGG16 and ResNet34 as the baseline networks. The experimental results reflect that the RPCKAM-based convolutional kernel pruning can compress the model on a large scale while maintaining high accuracy, and can even improve the modulation recognition accuracy within a certain compression range. Specifically, the accuracy improvement is close to 1% at most in the VGG16, and it is also close to 0.5% at most in the ResNet34. Furthermore, by analyzing the performance changes before and after model compression, it is found that the compression effect of ResNet34 is better than that of VGG16, and the performance of the RPCKAM-based pruning method outperforms that of the Grad-CAM-based pruning method. [ABSTRACT FROM AUTHOR]

Middle-box based attacks create serious functional defects in the devices such as firewalls, address translators, load balancers, server units, and other data inspecting devices. Middle-box based attacks are more severe than terminal node-based attacks. These attacks are mainly initiated to malfunction the internal events of middle-level devices. Notably, Internet of Healthcare Things (IoHT) is a completely distributed and heterogeneous environment that leads into more vulnerable events. In the distributed medical system field, the middle-box devices manage secret medical data transactions, internal network communication, patient data protection principles and packet inspection procedures. The medical data collected from each patient needs secrecy and stability in various aspects in the IoHT environment. The middle-box based attacks injected into the IoHT nodes create inefficiency in maintaining patient data, Denial of Service (DoS) at middle-box nodes, excessive diagnosis time, and lack of data protection. For handling these issues, a new security architecture and a new attack detection model are proposed in this paper which has been developed using ranking subsets and Convolutional Neural Network (CNN) principles. The proposed CNN with ranking principles model is designed with binary class fuzzy fisher face optimization technique and flower pollination optimization method to initiate feature extraction. The extracted features of each data flow are analyzed using CNN and ranking subset methodologies. In this proposed model, the continuous involvement of middle-box events in respective devices are classified under various anomaly cases and legitimate cases. The proposed IoHT model attains maximum success rate than the existing models as indicated in implementation section. [ABSTRACT FROM AUTHOR]

Secure user authentication has grown importance in today’s modern culture. It is significant to authenticate the user identity in numerous consumer applications particularly financial transactions. Traditional authentication methods rely on easy-to-guess passwords, PIN numbers, or tokens with several security flaws, such as those printed on the back of credit cards for PIN numbers. As an alternative to current systems, biometric authentication techniques based on physical and behavioral characteristics have been proposed. Multibiometric systems, which combine several biometrics, are developed as a result of the difficulties that single-biometric authentication systems encountered in real-world applications including lack of precision and noisy data. The proposed system provides better performance and greater accuracy compared with other authentication techniques. The majority of them is inconvenient and demand complicated user interactions. This paper proposes Enhanced Elman Spike Neural Network along Glowworm Swarm Optimization (EESNN-GSO-AMT) for Multiple Transaction Authentication. The images are collected via SDUMLA-HMTalong CASIA V5 dataset. The pictures are provided to pre-processing to enhance the images quality utilizing Learnable Edge Collaborative Filter (LECF). The preprocessed images are fed to feature extraction using Adaptive and concise empirical wavelet transform (ACEWT) and the features are extracted such as entropy, homogeneity, energy and contrast. The extracting features are provided to EESNN classifier to categorize authorized or unauthorized persons. In general, the EESNN classifier does not express adapting optimization methods to determine ideal parameters to ensure accurately. Therefore, it is proposed to utilize the Glowworm Swarm Optimization to enhanceEESNN, which accurately categorizes the authorized and unauthorized person. The efficiency of the proposed approach is assessed usingsome metrics. The proposed EESNN-GSO-AMT method attains higher accuracy 20.54%, 21.76% and 23.89%; greater sensitivity 20.12% 20.34% and 21.43%; higher precision 23.34%, 22.68% and 24.34% are analyzed to the existing methods, like Optimal feature level fusion for safe human authentication in multimodal biometric scheme (OptGWO-AMT-FV), Joint attention network for finger vein authentication (JAnet-AMT-FV), Finger Vein Recognition Utilizing Deep Learning Technique (DCNN-AMT-FV) respectively. [ABSTRACT FROM AUTHOR]

Collaborative filtering (CF) is a prevailing technique utilized for recommendation systems and has been comprehensively explored to tackle the problem of information overload particularly in the Big Data context. The traditional CF algorithms are capable to perform adequately under various circumstances, nevertheless, there exist some shortcomings involving cold start and data sparsity. Moreover, a potential breakthrough rests in taking full advantage of any valuable semantic information contained in items. Therefore, for alleviating these defects, in this paper, we propose a two-stage collaborative filtering approach driven by Simhash-based semantic feature analysis, of which the first stage is Simhash-based semantic feature extraction for items and categories, and the second stage is reinforced CF rating prediction driven by intensely compressed category features. The rich semantic features of vast items and their categories can be rapidly extracted and compressed in the first stage by employing the Simhash, with being utilized to promote the traditional collaborative filtering processes. Besides, to solve the problems pertaining to the Big Data context, we design a parallel algorithm on Spark to accelerate the time-consuming process of semantic feature extraction for vast items. Finally, we conduct comprehensive experiments to validate the reinforced CF approach by adopting practical datasets, and the results reveal that compared with the traditional CF algorithms it can accomplish a promising performance. [ABSTRACT FROM AUTHOR]

Geolocation is important for many emerging applications such as disaster management and recommendation system. In this paper, we propose a multilayer recognition model (MRM) to predict the city-level location for social network users, solely based on the user's tweet content. Through a series of optimizations such as entity selection, spatial clustering and outlier filtering, suitable features are extracted to model the geographic coordinates of tweet users. Then, the Multinomial Naive Bayes is applied to classify the datasets into different groups. The model is evaluated by comparing with an existing algorithm on twitter datasets. The experimental results reveal that our method achieves a better prediction accuracy of 54.82% on the test set, and the average error is reduced to 400.97 miles at best. [ABSTRACT FROM AUTHOR]

Matrix-variate Restricted Boltzmann Machine (MVRBM), a variant of Restricted Boltzmann Machine, has demonstrated excellent capacity of modelling matrix variable. However, MVRBM is still an unsupervised generative model, and is usually used to feature extraction or initialization of deep neural network. When MVRBM is used to classify, additional classifiers must be added. In order to make the MVRBM itself be supervised, in this paper, we propose improved MVRBMs for classification, which can be used to classify 2D data directly and accurately. To this end, on one hand, classification constraint is added to MVRBM to get Matrix-variate Restricted Boltzmann Machine Classification Model (ClassMVRBM). On the other hand, fisher discriminant analysis criterion for matrix-style variable is proposed and applied to the hidden variable, therefore, the extracted feature is more discriminative so as to enhance the classification performance of ClassMVRBM. We call the novel model Matrix-variate Restricted Boltzmann Machine Classification Model with Fisher discriminant analysis (ClassMVRBM-MVFDA). Experimental results on some publicly available databases demonstrate the superiority of the proposed models. Of which, the image classification accuracy of ClassMVRBM is higher than conventional unsupervised RBM, its variants and supervised Restricted Boltzmann Machine Classification Model (ClassRBM) for vector variable. Especially, the image classification accuracy of the proposed ClassMVRBM-MVFDA performs better than supervised ClassMVRBM and vectorial RBM-FDA. [ABSTRACT FROM AUTHOR]

Sensor networks suffer from various sensor faults and false measurements in healthcare application and this vulnerability of the delay should handle efficiently and timely response in various application of WSN. For instance, in healthcare application, the false measurements generate false alarms which require to take unnecessary action from the healthcare department. The quality of the health care service can improve in remote healthcare monitoring system by introducing a new approach to identify the true medical condition and differentiate true and false alarms. In this paper, we proposed a novel approach to analysis past historical data collected from various medical sensors to identify the sensor anomaly. The main goal of this approach is to differentiate between true and false alarms effectively. The proposed system analysis the historical data to predicts the sensor value which compares with real sensed values at a time incident. The dynamically adjust the threshold value by comparing the difference between predicted value and historic value to determine the anomaly of sensor value. This system has been worked on huge real-time healthcare dataset and result shows that the new approach has been applied on real healthcare datasets and result of this system shows the detection rate is high and false positive rate is low which conclude that this approach is very useful in WSN application such as health monitoring system and it will be competitive with others. [ABSTRACT FROM AUTHOR]

Due to the rapid growth of the Internet and content development services, digital text has become the most extensively used type of media in digital communication. However, digital text is at risk of being illegally tampered with, copied or redistributed, which could lead to many security threats related to privacy and ownership protection. Over the last few years, digital watermarking has been used to authenticate and protect the ownership of digital media such as images, audio, and videos. Compared to other digital media, digital text faces greater challenges in regard to watermarking due to its low capacity for information hiding and its high sensitivity to modification. While limited research has been conducted on text watermarking, the preliminary results indicate that the available schemes do not achieve an acceptable trade-off between imperceptibility, robustness, capacity, and security. In this paper, we propose a novel text watermarking method called Bloom Filter and Text Similarity Watermarking (BFTSW). A Bloom filter is employed in our proposed BFTSW method to reduce the size of the watermark that is generated based on a vector space model (VSM) representation of a text document. To verify the watermark, the text similarity between the VSM representation of the original text (which is recovered from the Bloom filter) and the VSM representation of a suspect text is computed and compared against a predefined threshold value to determine whether the watermark is present in the suspect text. Experimental results obtained with a prototype implementation show that the proposed BFTSW method is effective in terms of its robustness against malicious attacks, information capacity, and text quality preservation. [ABSTRACT FROM AUTHOR]

Wi-Fi has become a successful technology since the publication of its first WLAN standard due to continuous advances and updates while remaining always backwards compatible. Backwards compatibility among subsequent standards is an important feature in order to take advantage of previous equipment when publishing a new amendment. At present, IEEE 802.11b support is still mandatory to obtain the Wi-Fi certification. However, there are several harmful effects of allowing old legacy IEEE 802.11b transmissions in modern WLAN deployments. Lower throughput per device is obtained at slow rates, but also the effect known as performance anomaly, which nearly leads to starvation of fast stations, has to be taken into account. Finally, backwards compatibility mechanisms pose an important penalty in throughput performance for newer specifications. This paper presents a thorough analysis of the current state of IEEE 802.11, comparing coverage range and throughput performance among subsequent amendments, and focusing on the drawbacks and benefits of including protection mechanisms. [ABSTRACT FROM AUTHOR]

The dynamic spectrum nature of cognitive radio challenges the connectivity and the stability of cognitive radio ad hoc networks (CRAHNs). Clustering is considered as an appropriate technique to overcome these issues. Various algorithms for clustering formation in CRAHN have been proposed, in which different system models and metrics are considered. This paper introduces an extensive survey of the most important published algorithms. This survey classifies the proposed algorithms based on their objectives. Moreover, it presents a detailed description of their techniques, evaluations of their performance, and discussion of the features and shortcomings of each algorithm. Furthermore, it provides and discusses the open issues for future research. [ABSTRACT FROM AUTHOR]

Smart manufacturing optimizes processes and marketing transactions, leading to more efficient manufacturing processes. Computational modeling is used to execute the improvement, which requires trustworthy and meaningful information as input. This paper uses a vision sensor for capturing accurate data. Hybrid techniques for vision-based classification and feature extraction methods were used. The ORB (Oriented FAST and Rotated BRIEF) and BRISK (Binary Robust Invariant Scalable Keypoints) feature recognition and characterization processes were chosen based on evaluating several feature recognition and characterization processes when applied to acoustic information recorded by an Apple dataset. After the feature extraction, a Deep CNN (DCNN) method is used for the classification process to achieve efficient accuracy. The vision-based algorithms classify the apple as damaged or not damaged, allowing for automated examination, classification, and analysis. To test the classifiers, 600 apple photos were obtained. There are 300 non-faulty apples and 300 damaged apples in the photographs. The faulty group encompasses a wide range of defective kinds and severities. The effectiveness of twofold, threefold, fourfold, fivefold, and tenfold detectors is evaluated. The Softmax classifiers were used in the study, achieving 98.84% classification accuracy for a tenfold dataset. [ABSTRACT FROM AUTHOR]

One important area of research in the field of remote sensing information processing is image object detection. Finding expected objects in an image and returning their category confidence and bounding boxes is the objective of the visual object detection task. Remote sensing images, in contrast to conventional images, contain many objects with large aspect ratios and are densely distributed, posing numerous challenging issues. In this paper, we propose Inception-Det, which makes use of a two-stage detection head design to solve these issues. The first stage is used to predict rotational anchors close to the GT-Box, and the second stage uses a higher positive IoU threshold and complete features calculated by FPN Inception to get better detection results. By effectively resolving the issue of objects with large aspect ratios being difficult to regress to high-precision bounding boxes, our proposed feature-complete transform (FCT) can effectively extend the detailed information contained in the feature map without introducing background noise. Extensive testing on two publicly available datasets, DOTA and HRSC2016, demonstrates that our proposed method outperforms the alternatives and further enhances detection performance at a rapid rate. [ABSTRACT FROM AUTHOR]

Aiming for the ResNet network structure used for feature extraction, there are still problems of overfitting, slow calculation speed and room for improvement of accuracy. A mixed depthwise separation residual network is proposed for image feature extraction. The residual and inverted residual blocks are used in the research, which makes the three kinds of residual units iteratively interact in the training process. This process promotes the feature representation of deep learning neural networks and alleviates the problem of feature dispersion caused by the deep network level in traditional expression recognition research. The experiment used CK+ and fer2013 datasets. The synthesis of multiple experimental results shows that the optimized deep learning model has an accuracy rate of about 2.8% higher than that of ResNet-50 on the Fer2013 test set. Compared with traditional residual network structure, it verifies that the network proposed in this paper has better effects in the field of facial expression recognition. [ABSTRACT FROM AUTHOR]