196 results
Search Results
2. Music Network Data Analysis Based on ISOMAP Algorithm Model
- Author
-
Shangqian Liu, Yue Li, Yanling Xu, and Kai Zhong
- Subjects
History ,business.industry ,Computer science ,Network data ,Isomap algorithm ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
The development of music is a tortuous process, and the network relationship between each genre and each artist is intricate. In order to have a better understanding of the history of music, this paper tells the stories hidden in the history of music by means of data processing. Firstly, this paper establishes a model to evaluate the similarity between music by using ISOMAP algorithm. At the same time, the forest evolution model was established to mark the most revolutionary musical characters. Finally, using the Page-Rank algorithm, we get the founders of several music genres. It turns out that the figures who led the development of music don’t coincide with the figures who revolutionized music. Through the analysis of this paper, we can more clearly understand the development of music and the evolution of genres.
- Published
- 2021
3. Offline Signature Verification System Using SVM Classifier with Image Pre-processing Steps and SURF Algorithm
- Author
-
Swee Kheng Eng and Li Wen Goon
- Subjects
History ,Svm classifier ,Computer science ,business.industry ,Image pre processing ,Verification system ,Pattern recognition ,Artificial intelligence ,business ,Signature (logic) ,Computer Science Applications ,Education - Abstract
A signature is a mark or name that represents the identity of the people and the Signature Verification System (SVS) is used to validate the identity of people. The signature verification system is mostly used for bank cheques, vouchers, intelligence agencies and others. There are two types of SVS which are online and offline signature verification systems. The paper deals with an offline signature verification system. The proposed system consists of four main stages, (i) image acquisition, (ii) image pre-processing, (iii) feature extraction and (iv) classification. The image pre-processing steps involved binarization, noise removal using Gaussian filter and image resizing and thinning. In the feature extraction stage, Bag-of-Features with the Speeded Up Robust Features (SURF) extractor was utilized. In the third stage, the Support Vector Machine (SVM) classifier is used. Lastly, the confusion matrix and the verification rate were used to evaluate the performance of the classifier. In this paper, we implement and compare the performance of the signature verification system without entering the user ID and the signature verification system entering the user ID. For the ratio of 75% and 25% of the training and testing, respectively, the average accuracy for the signature verification system without entering the user ID is 71.36%, whereas the average accuracy for the signature verification system entering the user ID is 79.55%.
- Published
- 2021
4. Application and Research of Convolution Neural Network in MRI Image Classification and Recognition
- Author
-
Fei Gao, Xuemei Hou, Jianping Wu, and Minghui Wu
- Subjects
History ,Mri image ,Computer science ,business.industry ,Pattern recognition ,Artificial intelligence ,business ,Convolutional neural network ,Computer Science Applications ,Education - Abstract
The traditional hepaticcell carcinoma (HCC) pathological grading depends on biopsy, which will cause damage to the patient's body and is not suitable for everyone's pathological grading diagnosis. The purpose of this paper is to study the pathological grading of liver tumors on MRI images by using deep learning algorithm, so as to further improve the accuracy of HCC pathological grading. An improved network model based on SE-DenseNet is proposed. The nonlinear mapping relationship between feature channels is modeled and recalibrated using attention mechanism, and rich deep-seated features are extracted, so as to improve the feature expression ability of the network. The method proposed in this paper is verified on the data set including 197 patients, including 130 training sets and 67 test sets. The experimental results are evaluated by receiver operating characteristic (ROC) and area under the ROC curve (AUC). The improved SE-Densenet network achieves good results, and AUC 0.802 is obtained on the test set. The experimental results show that the method proposed in this paper can well predict the pathological grade of HCC.
- Published
- 2021
5. High Camouflage Intrusion Detection Method for Structured Database Based on Multi Pattern Matching
- Author
-
Xun Zhu, Fengjuan Ma, and Dawei Song
- Subjects
History ,business.industry ,Computer science ,Camouflage ,Pattern recognition ,Pattern matching ,Artificial intelligence ,Intrusion detection system ,business ,Computer Science Applications ,Education - Abstract
with the rise and rapid development of mobile communication, intelligent terminal and data system, we are entering the era of mobile Internet. In recent years, more and more data need to be processed and transmitted in daily life, and structured data is becoming more and more important. Among them, multi-mode matching technology can search data in a wider range. Matching for multiple patterns at a time avoids unnecessary matching, accelerates the matching process, and helps to find longer matching information and obtain higher accuracy. This paper mainly introduces the high camouflage intrusion detection method of structured database based on multi-mode matching. This paper uses the high disguised intrusion detection method of structured database based on multi-mode matching, collects sensitive information of wireless access points and stations through the communication of WLAN in multimodal matching, then intercepts and forges data packets to initiate replay attack. Replay attack is characterized by abnormal traffic in the network, which can be detected by statistical analysis. The experimental results show that the high camouflage intrusion detection method based on multi-mode matching makes the camouflage intrusion detection rate increase by 23%. The limitations of the design and research of camouflage intrusion detection are analyzed, discussed and summarized, so as to enrich the academic research results.
- Published
- 2021
6. Low voltage abnormal user identification based on improved fish swarm algorithm
- Author
-
Zongyao Wang, Zhihao Xu, Jun Zhou, Bing Kang, Chuan Liu, Min Sun, and Tianqi Meng
- Subjects
History ,Identification (information) ,Computer science ,business.industry ,%22">Fish ,Swarm behaviour ,Pattern recognition ,Artificial intelligence ,business ,Low voltage ,Computer Science Applications ,Education - Abstract
The power consumption readings of sub meter and total meter of distribution transformer of low-voltage users follow the law of conservation of energy. The meter power loss rate of abnormal low-voltage users must also be abnormal. This paper studies the solution of the meter power loss rate under the four abnormal power consumption scenarios of single (multi) user and full (partial) period. The traditional linear solution method has accurate identification effect for the abnormal power consumption scenario of full period, but it cannot identify the abnormal power consumption scenario of partial period. In this paper, an improved artificial fish swarm algorithm is proposed. By adjusting the fixed step to the adaptive step, the power loss rate of each sub meter is obtained, and the abnormal power users are pinpointed. The research results are verified by simulation examples on IEEE European Low Voltage Test Feeder. The results show that the improved artificial fish swarm algorithm in this paper can identify abnormal power users for the above four abnormal electric field scenarios. The algorithm provides a new alternative for the identification of abnormal low voltage users.
- Published
- 2021
7. A Review on Edge Detection on Osteogenesis Imperfecta (OI) Image using Fuzzy Logic
- Author
-
Khairul Salleh Basaruddin, Muhammad Zainul Arif Ahmad Zaki, Mohd Hanafi Mat Som, H. Yazid, Shafriza Nisha Basah, and Megat Syahirul Amin Megat Ali
- Subjects
History ,business.industry ,Computer science ,Pattern recognition ,medicine.disease ,Fuzzy logic ,Edge detection ,Computer Science Applications ,Education ,Image (mathematics) ,Osteogenesis imperfecta ,medicine ,Artificial intelligence ,business - Abstract
Osteogenesis Imperfecta (OI) is a bone disorder that causes bone to be brittle and easy to fracture. The patient suffered from this disease will have poor quality of life. Simulation on the bone fracture risk would help medical doctors to make decision in their diagnosis. Detection of edges from the OI images is very important as it helps radiologist to segmentize cortical and cancellous bone to make a good 3D bone model for analysis. The purpose of this paper is to review the fundamentals of fuzzy logic in edge detection of OI bone as it is yet to be implemented. Several fuzzy logic concepts are reviewed by previous studies which include fuzziness, membership functions and fuzzy sets regarding digital images. The OI images were produced by modalities such as Magnetic Resonance Imaging (MRI), Ultrasound, or Computed Tomography (CT). In summary, researchers from the reviewed papers concluded that fuzzy logic can be implemented to detect edges in noisy clinical images.
- Published
- 2021
8. Research on Flower Image Classification Method Based on YOLOv5
- Author
-
Zhihao Liao and Ming Tian
- Subjects
History ,Contextual image classification ,Computer science ,business.industry ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
The rapid development of deep learning has accelerated the progress of related technologies in the computer vision field and it has broad application prospects. Due to flower inter-class similarity and intra-class differences, flower image classification has essential research value. To achieve flower image classification, this paper proposes a deep learning method using the current powerful object detection algorithm YOLOv5 to achieve fine-grained image classification of flowers. Overlap and occluded objects often appear in the images of the flowers, so the DIoU_NMS algorithm is used to select the target box to enhance the detection of the blocked objects. The experimental dataset comes from the Kaggle platform, and experimental results show that the proposed model in this paper can effectively identify five types of flowers contained in the dataset, Precision reaching 0.942, Recall reaching 0.933, and mAP reaching 0.959. Compared with YOLOv3 and Faster-RCNN, this model has high recognition accuracy, real-time performance, and good robustness. The mAP of this model is 0.051 higher than the mAP of YOLOv3 and 0.102 higher than the mAP of Raster-RCNN.
- Published
- 2021
9. Action recognition based on element-level fine-grained multi-modal fusion
- Author
-
Lixin Han, Guozheng Peng, and Jiaxue Yang
- Subjects
History ,Multi modal fusion ,business.industry ,Computer science ,Action recognition ,Pattern recognition ,Artificial intelligence ,Element (category theory) ,business ,Computer Science Applications ,Education - Abstract
Traditional action recognition algorithms often only pay attention to video RGB features or optical flow features. These methods do not make good use of the audio information in the video. Based on RGB and optical flow characteristics, this paper introduces the processing of audio information, and classifies videos based on element-level fine-grained multi-modal fusion. Through experimental comparison, the accuracy of the multi-modal fusion algorithm proposed in this paper is improved by 7.38% on the HMDB51 dataset and 3.18% on the UCF101 dataset compared to the simple modal splicing. At the same time, it is proved that the introduction of audio modes can effectively improve the performance of the model.
- Published
- 2021
10. A Classification Method for Network Traffic Based on Semi-supervised Approach
- Author
-
Zhu Zhiqiang, Zhong Pengfei, and Liu Yun
- Subjects
History ,Computer science ,business.industry ,Classification methods ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
Traffic data encryption has been a trend in most Internet applications, and traditional protocol filtering based on fixed port and traffic classification based on Deep Packet Inspection are unable to Identify encrypted traffic. Recently, the traffic classification method based on the statistical characteristics of network traffic, which can solve the problem of encrypting data or user privacy protection, has been widely discussed. However, the traditional supervised learning method requires manual marking of a large amount of network traffic data, which is tedious and time-consuming. In this paper, a improved semi-supervised traffic classification framework based on BIRCH clustering method is proposed, and through experiments, the proposed algorithm, supervised learning algorithm and classical semi-supervised traffic classification algorithm are analyzed and compared. The results show that the algorithm proposed in this paper has higher overall accuracy and classification accuracy, and the algorithm can increase the accuracy on traffic classification.
- Published
- 2021
11. Network Traffic Anomaly Detection Method Based on CAE and LSTM
- Author
-
Shuai Guo, Yang Su, and Yao Liu
- Subjects
History ,business.industry ,Computer science ,Anomaly detection ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
This paper constructs a deep learning method for detecting network traffic anomalies to enhance the secure transmission of data in networks due to the complex, diverse and numerous types of anomalous traffic in current networks. The method combines multiple convolutional auto-encoders (Multi-CAE) with a long short-term memory network. The convolutional auto-encoders are obtained by combining stacked auto-encoders with convolutional layers, which can not only reduce feature loss but also effectively extract the spatial structure of samples. The use of Multi-CAE greatly improves the feature extraction capability, and combined with the long short-term memory network to extract temporal features, the effective features extracted in this paper are more comprehensive and less losses compared to the models used in other researches. A comparison of the loss values in the training of CAE (Convolutional Auto-Encoders) and SAE (Stacked Auto-Encoders) in the experiments shows that the loss values of CAE are about one-tenth lower than those of SAE, and the method consisting of Multi-CAE and LSTM for the USTC- TFC2016 dataset was trained with accuracy values up to 99.98%, and the precision, recall and f1-score parameters were also above 99%, outperforming other studies.
- Published
- 2021
12. K-means clustering algorithm based on bee colony strategy
- Author
-
Zhenrong Zhang and Jiayi Lan
- Subjects
History ,business.industry ,Computer science ,k-means clustering ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
The traditional swarm intelligence optimization K-means algorithm has some problems, such as poor global search ability and blind area selection of initial center points, which leads to the reduction of clustering availability. In order to avoid the above limitations, this paper proposed IABC k-means algorithm. Firstly, the employed bees stage in the traditional artificial bee colony ABC algorithm uses the current colony optimal solution information to guide its optimization search. Secondly, this paper wanted to solve the search ability of the employed bees and expand the information sharing range between various individuals, a random guidance mechanism is proposed in the onlookers bees stage. Finally, chaotic sequence is introduced in the scout bee stage to accelerate the convergence speed of the algorithm. IABC algorithm is proposed and applied to K-means clustering algorithm to improve the poor global search ability of K-means algorithm and the random selection of initial center points. Experiments show that the IABC and IABCK-means proposed in this paper effectively improves the clustering availability.
- Published
- 2021
13. Network Anomaly Traffic Detection Method Based on Multi-SAE and LSTM
- Author
-
Bowei Chen, Shuai Guo, and Yang Su
- Subjects
History ,business.industry ,Computer science ,Pattern recognition ,Artificial intelligence ,Anomaly (physics) ,business ,Computer Science Applications ,Education - Abstract
For the purpose of faster and more accurate anomalous traffic detection with increasing classes of data traffic in the network, this paper proposes a new anomalous traffic detection method based on stacked auto-encoders and a long short-term memory network model. The method uses Multi-SAE to extract the effective features of sequential traffic, which is obtained by concatenating multiple stacked auto-encoders, and a long short-term memory network to extract the temporal structure of the effective features, with the Multi-SAE and the long short-term memory network in a back-and-forth tandem structure. To further improve the efficiency of the detection, redundant MAC addresses are also removed in the pre-processing. From the experimental results, this paper achieves effective detection of twenty types of data traffic with an accuracy rate of 98.25%, which is higher than that of the same category of research by nearly 2 percentage points, and the parameters of precision, recall and f1-score also reach over 96%, improving the detection results.
- Published
- 2021
14. EEG Motor-Imagery BCI System Based on Maximum Overlap Discrete Wavelet Transform (MODWT) and cubic SVM
- Author
-
Manal H. Jassim, Samaa S. Abdulwahab, and Hussain K. Khleaf
- Subjects
Discrete wavelet transform ,History ,medicine.diagnostic_test ,Computer science ,business.industry ,Pattern recognition ,Electroencephalography ,Computer Science Applications ,Education ,Support vector machine ,ComputingMethodologies_PATTERNRECOGNITION ,Motor imagery ,medicine ,Artificial intelligence ,business ,Brain–computer interface - Abstract
Communication of the human brain with the surroundings became reality by using Brain- Computer Interface (BCI) based mechanism. Electroencephalography (EEG) being the non-invasive method has become popular for interaction with the brain. Traditionally, the devices were used for clinical applications to detect various brain diseases but with the advancement in technologies, companies like Emotiv, NeuoSky are coming up with low cost, easily portable EEG based consumer graded devices that can be used in various application domains like gaming, education etc as these devices are comfortable to wear also. This paper reviews the fields where the EEG has shown its impact and the way it has proved useful for individuals with severe motor disorder, rehabilitation and has become a means of communication to the real world. This paper investigates the use of Cubic SVM algorithm In the EEG classification. EEG feature extraction is Implemented by maximum overlap discrete wavelet transform (MODWT) to reduce the dimensionality of data. The Sliding Window Technique is used to calculate the mean within each window samples. The feature vectors are loaded into the support vector machine (SVM) and optimize tree.
- Published
- 2021
15. Hybrid Approach for Identification of Manhole and Staircase Using Image Processing
- Author
-
Jadala Sravani, Ashwani Kumar, Adigiri Vaishnavi, and Peruri Sravani Durga
- Subjects
History ,Identification (information) ,business.industry ,Computer science ,Pattern recognition ,Image processing ,Artificial intelligence ,business ,Hybrid approach ,Computer Science Applications ,Education - Abstract
The main aim of this research paper is to provide multi security for the pedestrians/older using smart stick using IOT and GPS. This stick having IOT, voice module and attached with multiple sensors to provide high security to the blind peoples while walking. Now a day’s safety is main important cause to the peoples while walking or driving and many more places. This smart stick provides the high security and show way to walk, by using this system we can monitor the blind person position using web application/mobile application and also we can get emergency alert message along with exact location. This system has obstacle sensor, water sensor and MEMS sensors, so that it can detect obstacles sizes automatically and gives voice alert. By using water sensors, it can detect the floor condition is dry or wet and shows the way to walk. In case of any emergency person suddenly fall at floor/any place then this system immediately detects using MEMS tilt sensor and automatically send the message to respective numbers with location and also gives buzzer alarm continuously to alert the neighbours. So that this smart stick can be very useful to peoples to show correct path while walking on the floor or steps and many more places. In this paper, the system can be interconnected with the microcontroller and alert the respective persons when any emergency occurs. This tracking system is composed of a GPS receiver, Microcontroller. The Microcontroller processes this information and this processed information is sent to the respective numbers using web page.
- Published
- 2021
16. A Sympathetic Inrush Identification Method Using Substation-Area Currents
- Author
-
Fang Peng, Chong Li, Xiju Zong, and Yaotian Zhang
- Subjects
History ,Identification (information) ,Computer science ,business.industry ,Pattern recognition ,Artificial intelligence ,business ,Inrush current ,Computer Science Applications ,Education - Abstract
Transformers in power system usually take current differential protection as the main protection, but the protection is easy to be affected by inrush currents and then maloperates. Sympathetic inrush is one kind of inrush currents, which is caused by energization of an adjacent transformer. There were many transformer differential protection maloperation cases caused by sympathetic inrush in the field, while the conventional second harmonic restraint method did not work effectively. In this paper, a method based on substation-area currents and curve fitting is proposed to identify sympathetic inrush. The method is presented using the characteristic that sympathetic inrush and initial inrush alternatively appear in reverse polarities. The characteristic exists continuously during sympathetic inrush. In order to verify effectiveness of the proposed method, PSCAD/EMTDC software is used in this paper to build sympathetic inrush model and obtain simulation data. Simulation results prove that the proposed method can effectively identify sympathetic inrush.
- Published
- 2021
17. A Hyperspectral Image Classification Method with CNN Based on attention-enhanced Spectral and Spatial Features
- Author
-
Kun Yang, Lei Yuan, and Yangming Zhang
- Subjects
History ,Computer science ,business.industry ,Hyperspectral image classification ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
In recent years, the convolutional neural network (CNN) has had a wide application in hyperspectral image (HSI) classification. HSI has many spectral and spatial features, which is well known that different spectral bands and spatial positions in the cubes have different discriminative abilities. Therefore, this paper proposes a classification method with CNN, which uses attention-enhanced spectral and spatial features (CNN-ASS). First, we use spectral and spatial subnetworks to extract spectral and spatial features. At the same time, spectral attention and spatial attention are added to the two subnetworks, respectively. Then, we sum the weights of the classification results of the two subnetworks to get the final classification result. This paper conducts experiments on three typical hyperspectral image data sets, and the experiment results show the CNN-ASS has a competitive advantage compared with some advanced methods.
- Published
- 2021
18. Improved Chinese Short Text Classification Method Based on ERNIE_BiGRU Model
- Author
-
Chen Zhang, Xue Cheng, and Qingxu Li
- Subjects
History ,business.industry ,Computer science ,Classification methods ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
This paper is aimed at traditional word embedding models and Bidirectional Encoder Representations from Transformers (BERT) that cannot learn text semantic knowledge, as well as convolutional neural network (CNN) and Bidirectional long short-term memory (BiLSTM) unable to distinguish the importance of words, proposing an improved Chinese short text classification method based on ERNIE_BiGRU model. Firstly, learning text knowledge and information through the Enhanced Representation through Knowledge Integration (ERNIE) enhances the model’s semantic representation capabilities. Secondly, considering that CNN can only extract local features of the text while ignoring the semantic relevance between contextual information, and the Bidirectional Gating Recurrent Unit (BiGRU) is simpler, has fewer network parameters and faster calculation speed than the BiLSTM, the combination of CNN and BiGRU enables the model to capture both local phrase-level features and contextual structure information. Finally, according to the importance of features, the attention mechanism is used to assign different weights to improve the classification effect of the model. The experimental results show that the ERNIE_CNN_BiGRU_Attention (ECBA) model used in this paper has achieved good results in the task of Chinese short text classification.
- Published
- 2021
19. Research on Face Recognition Algorithm Based on Convolutional Nerve
- Author
-
Yunqian Fang
- Subjects
History ,Computer science ,business.industry ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Pattern recognition ,Artificial intelligence ,business ,Facial recognition system ,Computer Science Applications ,Education - Abstract
Facial expression can truly reflect people’s inner activities, human emotions can be fully reflected through the expression, facial expression recognition in the field of artificial intelligence has important research significance, in daily life also has its application value. At present, facial expression recognition technology has become a very promising frontier technology, but also the current research focus in the field of computer vision. In this paper, facial expression recognition based on convolution neural network is studied. The concrete work has the following several parts: For the part of face detection, this paper introduces the common methods of knowledge-based rules, feature-based, template-based matching, and statistical model-based, and V-J detector is used for face detection in this paper. In the part of expression recognition, we study the recognition of happiness, sadness, anger, depression, fear and surprise by convolution neural network. This paper uses keras to build a deep learning framework. The neural network consists of volume base layer, pool layer, activation layer and full connection layer. The classifier uses softmax. Using the image data in the standard database as input, after the processing of each layer in the neural network, and finally outputting the probability corresponding to six expressions through softmax, it is generally believed that the expression with the highest probability is the facial expression in the input image.
- Published
- 2021
20. Hyperspectral image classification based on composite kernel relevance vector machine
- Author
-
Jie Guo Han, Bei Yang, Donghao Liu, Cheng Sun, and Cheng Zhaoxiang
- Subjects
Relevance vector machine ,History ,Contextual image classification ,Computer science ,business.industry ,Hyperspectral image classification ,Hyperspectral imaging ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education ,Composite kernel - Abstract
This paper presents a composite kernel Relevance Vector Machine(RVM) algorithm, for enhanced classification accuracy of hyperspectral images. This paper constructs three forms of composite kernels based on properties of kernels. The spatial feature is extracted using multi-scale morphological method from the image after principal components transform. The final classification is achieved by composite kernel RVM classifier. The proposed approach is tested in experiments on AVIRIS data. Compared with spectral kernel RVM, the OA and Kappa coefficient of composite kernel RVM increased obviously. However, the training time dose not increased. Meanwhile, composite kernel RVM has ability to get high accuracy with relative small training set. The proposed method has practical use in hyperspectral imagery classification.
- Published
- 2021
21. A Novel Optimized Convolutional Neural Network Based On Attention Pooling for Text Classification
- Author
-
Chengjie Yao and Mengmeng Cai
- Subjects
History ,Computer science ,business.industry ,Pooling ,Pattern recognition ,Artificial intelligence ,business ,Convolutional neural network ,Computer Science Applications ,Education - Abstract
Convolutional neural network (CNN) is widely used in Natural Language Processing (NLP) and has achieved relatively good results. Since the convolutional layer of CNN can be initialized by encoding important semantic features, CNN can extract important semantic features in the convolutional layer. The pooling layer of CNN uses the feature of max-pooling to filter the features, but it does not consider the key information in the sentence and the context semantic information in the text. Therefore, a novel neural network algorithm combining with the attention mechanism and the pooling layer is proposed in this paper to make the model pay attention to the keywords in the sentence and automatically maintain the most meaningful text message, thereby improving the performance of text classification. Our paper uses important information features to initialize the convolution filter so that the model can notice the important semantic features. The resulting feature is enhanced by combining the attention mechanism in the pooling layer, so that the model can maintain the important information features of the text. Experiments show that the proposed model achieves excellent results for multiple text classification tasks, including sentiment classification and topic classification.
- Published
- 2021
22. Automatic keying algorithm for multi-category target recognition
- Author
-
Liping Mao
- Subjects
History ,Computer science ,business.industry ,Keying ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
In this paper, through an in-depth study of the automatic keying algorithm for target recognition and using multi-class algorithms for its analysis, a saliency detection model based on the hypercomplex Fourier transform is proposed, which can quickly search for information related to the current task requirements. The problem of sample imbalance in deep neural network training exists, the module is used many times to fuse multi-scale features, the loss function uses weighted cross-entropy loss, and the weights are determined according to the proportion of samples in the training sample, which can solve the problem of the model tends to fit the category with more samples. After analysis, the proposed hyperspectral image fast feature enhancement algorithm based on guided filtering can effectively solve the problem of “the same object, different spectrum”, and the classification accuracy of small sample high-dimensional data is improved greatly. At the same time, the complexity of processing high-dimensional data such as hyperspectral remote sensing images is greatly reduced. The experimental results show that the processing time of the proposed fast feature enhancement process for hyperspectral remote sensing images in this paper decreases than that of the direct use of guided filtering.
- Published
- 2021
23. Research on robot target recognition based on deep learning
- Author
-
Sun Zhenyu, Jiangxue Han, Xiaoyang Zhang, Jian Hou, and Guo Xiaoming
- Subjects
Structure (mathematical logic) ,History ,Computer science ,Machine vision ,business.industry ,Deep learning ,Pattern recognition ,Improved method ,Field (computer science) ,Computer Science Applications ,Education ,Feature (computer vision) ,Robot ,Artificial intelligence ,Semantic information ,business - Abstract
For the traditional machine vision recognition technology in the industrial field can not handle the problem of different classes of workpieces placed randomly and stacked on each other, this paper improves the SSD algorithm model based on the research of deep learning target detection algorithm. Firstly, a depth-separable convolutional structure is introduced to optimize the VGG backbone feature network. Then a multi-level feature fusion mechanism is introduced in the prediction part to increase the semantic information of features. Qualitative and quantitative experimental results show that the improved optimization method of the SSD model in this paper is validated well on the dataset, and the improved SSD model mAP value is increased by 4.3% compared with the original, and the detection speed is increased by nearly two times, thus proving the effectiveness of the improved method.
- Published
- 2021
24. An Improved Fully Convolutional Network for Semantic Segmentation
- Author
-
Gaihua Wang, Xu Zheng, Zhao Guo, and Xizhou Wan
- Subjects
History ,Computer science ,business.industry ,Computer Science::Computer Vision and Pattern Recognition ,Pattern recognition ,Segmentation ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
A novel loss function based on category distribution for semantic segmentation is proposed in this paper. The new loss function is composed of two parts: (1) Pixel-wise cross-entropy. (2) Category distribution loss proposed. Most of existing semantic segmentation networks adopt a single pixel-wise cross-entropy loss function, which guides the network to independently predict the class each pixel belongs to. The downside is that ignoring global information of the image -- the distribution of all kinds of objects in the image, resulting in an unsatisfactory segmentation result. Category distribution loss proposed in this paper obtins category distribution information of the whole image by calculating the percentage of pixels to each class of objets. Acquired category distribution information can be represented as a feature vector, the distance of two vectors between prediction and ground truth forms category distribution loss. The new loss function measures the difference between pixels as well as the difference between global information. We apply the new loss to several classical networks, its pixel accuracy and mIoU accuracy on two benchmark datasets CamVid and Pascal VOC2012 are improved compared to using only pixel-wise cross-entropy. In addition, we also introduced the attention mechanism, which proved to be able to improve segmentation accuracy of the networks as well.
- Published
- 2021
25. Survey of Target Detection Based on Neural Network
- Author
-
Hao Lv and Bao Deng
- Subjects
History ,Artificial neural network ,Computer science ,business.industry ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
Target detection is a hot topic in the field of artificial intelligence, which is widely used in robot, UAV, aerospace and other fields. In this paper, the research background and significance of target detection are summarized, and two categories of target detection algorithms based on deep learning, i.e., candidate region based and regression based, are described. For the first category, a series of region with convolutional neural network (r-cnn) algorithms are introduced, this paper introduces the researchers’ research on the basis of r-cnn algorithm: the improvement of feature extraction network, pooling layer of region of interest and non-maximum suppression algorithm. The second algorithm is divided into Yolo (you only look once) series, SSD (single shot multibox detector) algorithm and its improvement. According to the current target detection algorithm in the development of more efficient and reasonable development trend, the research hotspot of target detection algorithm in the future is prospected, including unsupervised and unknown class object detection.
- Published
- 2021
26. Image Compression and Reconstruction Based on PCA
- Author
-
Linglong Tan, Fengzhi Wu, and Weilong Li
- Subjects
History ,business.industry ,Computer science ,Dimensionality reduction ,Feature vector ,Feature extraction ,Data compression ratio ,Image processing ,Pattern recognition ,Computer Science Applications ,Education ,Feature (computer vision) ,Computer Science::Computer Vision and Pattern Recognition ,Principal component analysis ,Artificial intelligence ,business ,Image compression - Abstract
In view of the disadvantages of large image space, high dimension of feature representation and large storage, this paper uses principal component analysis to compress the data, which can effectively reduce the loss of information, reduce the dimension of data and extract features in all aspects of image compression. In this paper, based on the analysis of PCA algorithm dimension reduction, reconstruction, feature extraction principle, the PCA algorithm is applied to image compression and reconstruction. Through the principal component analysis of sample variables, the feature vector of sample variance is calculated, and its principal component is extracted, and the contribution rate is calculated to realize image PCA compression. By extracting different eigenvalues from the original image and calculating its compression ratio and contribution rate, we can see that the clarity of the image is positively correlated with the value of the eigenvalue, and the larger the value of the eigenvalue, the higher the contribution rate. PCA based image processing technology is simple to use, high compression rate and high quality of image reconstruction, which is unmatched by many other methods.
- Published
- 2021
27. Adhd Classification From FMRI Data Using Fine Tunining in SVM
- Author
-
S. Thomas Geroge and S. Anitha
- Subjects
Support vector machine ,History ,business.industry ,Computer science ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
ML (Machine learning) is a subset of AI and also improved learning technique has different performance in result over the conventional ML determining the complexity in structures of dimensional data. ADHD is one of the most important neurological disorders and it is represented by different symptoms and we can extract useful the information from FMRI time series. In this paper the ADHD identification and classification is obtained by machine learning techniques. This paper explores an artificial intelligence in unsupervised learning is appropriate to learn features from raw data. The proposed system presented with two stage approaches for ADHD diagnosis which associated SoftMax Regression and SVM fine tuning approach. In the implementation part used FMRI brain images are data sets. The two stage approach shows the high accuracy in performance by using the learning techniques.
- Published
- 2021
28. Cross-view geo-localization via Salient Feature Partition Network
- Author
-
Sijin He and Yuehuan Wang
- Subjects
History ,Salient ,Computer science ,business.industry ,Feature (computer vision) ,Pattern recognition ,Artificial intelligence ,business ,Partition (database) ,Computer Science Applications ,Education - Abstract
Cross-view geo-localization aims to find images containing the same geographic target from images obtained from different platforms. The extreme viewpoint variations bring challenges to this task. Existing methods usually focus on mining the fine-grained features of geographic targets in images, ignoring the potential contextual information around them. In this paper, we consider that the background regions can be used as auxiliary information, which can make the image representation for geo-localization more discriminative. Specifically, we designed a classification network that divides regional features based on saliency, called Salient Feature Partition Network (SFPN), which utilizes background information in an end-to-end manner. Without using additional part estimators, SFPN divides the features into foreground and background based on saliency. It simplifies part matching and realizes the region division learning. The method proposed in this paper has achieved competitive results on the university 1652 dataset.
- Published
- 2021
29. Support Vector Machine Tuning for Improving Four-Quadrant Emotion Prediction in Virtual Reality (VR) using Wearable Electrodermography (EDG)
- Author
-
James Mountstephens, Jason Teo, and Aaron Frederick Bulagang
- Subjects
History ,business.industry ,Computer science ,Headset ,Emotion classification ,Wearable computer ,Pattern recognition ,Virtual reality ,Python (programming language) ,Signal ,Field (computer science) ,Computer Science Applications ,Education ,Support vector machine ,Artificial intelligence ,business ,computer ,computer.programming_language - Abstract
Electrodermography (EDG) / Galvanic Skin Response (GSR) indicates the psychophysiological of emotion, EDG is an emerging signal used in the field of emotion classification aside from Electroencephalography (EEG) and Electrocardiography (ECG). The Empatica E4 wearable device was used in collecting EDG signals and employed as the method in capturing the test subject’s physiological signal of their skin activity. This experiment had 10 participants that use a Virtual Reality (VR) headset for viewing video stimuli in 360 degrees while collecting the EDG signals. Python with Support Vector Machine (SVM) was used in processing the 10 subjects’ data. This paper aims to compare the accuracy of the SVM experiments with different parameters, different settings based on the data retrieved from the wearable. The emotions were classified into four distinct quadrants with inter-subject classifications yielding an accuracy of 54.3%, and intra-subject classification yielded an accuracy of 57.1% to 99.2%. The presented results show that it is possible to achieve results with higher accuracy when parameter tuning. Hence, promising results were demonstrated for emotion prediction in four quadrants using wearable EDG technology in virtual reality environments. This paper provides two contributions, the use of EDG signals in emotion prediction, and the parameter setting to increase the accuracy for SVM classification.
- Published
- 2021
30. Exploring Standalone Electrodermography for Multiclass VR Emotion Prediction using KNN
- Author
-
Jason Teo, James Mountstephens, and Aaron Frederick Bulagang
- Subjects
History ,medicine.diagnostic_test ,business.industry ,Computer science ,Headset ,Emotion classification ,Pattern recognition ,Python (programming language) ,Virtual reality ,Electroencephalography ,Computer Science Applications ,Education ,Support vector machine ,Classifier (linguistics) ,medicine ,Artificial intelligence ,Skin conductance ,business ,computer ,computer.programming_language - Abstract
The use of Electrodermography (EDG) in emotion classification is emerging in recent studies, however, it is still limited when compared to the use of other physiological signals such as Electroencephalography (EEG) and Electrocardiography (ECG). Galvanic Skin Response (GSR) or EDG can be used in studies relating to the psychophysiological of emotion. This paper presents the result of an experiment conducted using EDG as the main signal for emotion classification with the use of K-Nearest Neighbor (KNN) as the classifier. In the experiment, the EDG data is acquired from 10 subjects while Virtual Reality (VR) headset is used to view 360 degrees video. Python is used as the programming language for the emotion classification with KNN as the classifier to classify intra-subject (individual) and inter-subject (overall) data. The main objective of this paper is to present the result of the experiment when using KNN as the classifier rather than using Support Vector Machine (SVM) which is synonymous with machine learning. The data were then classified into four classes of distinct emotion, inter-subject achieved an accuracy of 54%, while intra-subject classifications, two subjects achieved an accuracy of 96.9%. This result shows that KNN can provide good accuracy for emotion classification using machine learning as an alternative to SVM.
- Published
- 2021
31. Paired tenzotremorogramms structure similarity analysis based on time series distance functions: problem formulation
- Author
-
O.V. Zhvalevsky
- Subjects
Finger force ,History ,Series (mathematics) ,business.industry ,Computer science ,Dynamics (mechanics) ,Process (computing) ,Structure (category theory) ,Pattern recognition ,Computer Science Applications ,Education ,Similarity analysis ,Artificial intelligence ,business - Abstract
The paper is concerned with paired tenzotremorogramms that are a result of finger force registration (for both human arms) via sensitive platform with tenzosensor. The main hypothesis is: the dynamics of force hold process differs for different patient category (for healthy patients and for patients who have some pathology). In the paper some approaches to paired tenzotremorogramms structure similarity analysis are investigated. These approaches are based on application of time series distance functions.
- Published
- 2021
32. Research on Arrhythmia Classification Method Using Optimized Probabilistic Neural Network
- Author
-
Su Jinyu, Liu Junkong, Fang Yipin, and Li Lili
- Subjects
History ,Similarity (geometry) ,Computer science ,business.industry ,Feature extraction ,Bayesian optimization ,Pattern recognition ,Signal ,Standard deviation ,Computer Science Applications ,Education ,Probabilistic neural network ,Feature Dimension ,Feature (computer vision) ,Artificial intelligence ,business - Abstract
Aiming at the classification difficulty of complex and diverse ECG signals, this paper proposes a feature extraction method based on standard deviation. This method solves the problems of multi-dimensional, diverse, high similarity and the difficulty in extracting main features effectively of ECG(electrocardiogram, ECG) signal features. In addition, this method overcomes the difficulty of low classification accuracy because of large differences in ECG signals of the same type among different patients. This paper adopts optimized probabilistic neural network methods to achieve automatic classification of arrhythmia. First, the standard deviation of the dimensions of each sampling point of the ECG signal would be calculated and sorted by size. Second, the first m dimensions as the feature dimensions of arrhythmia would be extracted. After that, the probabilistic neural network would be used to train and classify feature dimension data. Finally Bayesian Optimization(BO) method would be used to optimize the parameters globally. In the experiment of the MIT-BIH arrhythmia database, the arrhythmia data was divided into 5 categories and verified, experimental results show that the correct rate of classification of the arrhythmia data of patients reached 99.67%, which proved the effectiveness of the method in this paper.
- Published
- 2021
33. Sound Event Detection Based on Convolutional Neural Networks with Overlapping Pooling Structure
- Author
-
Hongjie Wan and Hang Zhu
- Subjects
History ,Speedup ,business.industry ,Computer science ,Pooling ,Pattern recognition ,Convolutional neural network ,Computer Science Applications ,Education ,Feature (computer vision) ,Cepstrum ,Artificial intelligence ,Mel-frequency cepstrum ,Layer (object-oriented design) ,business ,Dropout (neural networks) - Abstract
In this paper, a sound event detection measure is proposed. This measure is based on convolutional neural networks with overlapping pooling structure Different from the traditional GMM-HMM model and DNN-HMM model, the CNN model uses the convolutional layer which can speed up training by reducing training parameters. In this paper, the extracted sound feature is the mel-frequency cepstrum coefficient (MFCC). The dropout layer is added to the convolutional layer. Over-fitting can decrease the accuracy of the detection, dropout layer can prevent the model from over-fitting. Moreover, the overlapping pooling structure is used in CNN, the stride size is smaller than the pooling kernel size. The output of pooling layer has overlapping parameters, which can increase the richness of features. The final experimental results show that the precision of the proposed CNN model more robust than the GMM-HMM model and baseline model.
- Published
- 2021
34. RETRACTED: Impact of Feature Selection for Data Classification Using Naive Bayes Classifier
- Author
-
Eman Hato
- Subjects
History ,Naive Bayes classifier ,ComputingMethodologies_PATTERNRECOGNITION ,Computer science ,business.industry ,Data classification ,Pattern recognition ,Feature selection ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
In the field of data processing and analysis, the dataset may be a large set of features that restrict data usability and applicability, and thus the dimensions of data sets need to be reduced. Feature selection is the process of removing as much of the redundant and irrelevant features as possible from the original dataset to improve the mining process efficiency. This paper presented a study to evaluate and compare the effect of filter and wrapper methods as feature selection approaches in terms of classification accuracy and time complexity. The Naive Bayes Classifier and three classification datasets from the UCI repository are utilizing in the classification procedure. To investigate the effect of feature selection methods, they are applied to the different characteristics datasets to obtain the selected feature vectors which are then classified according to each dataset category. The datasets used in this paper are the Iris, Ionosphere, and Ovarian Cancer dataset. Experimental results indicate that the filter and wrapper methods provide approximately equal classification accuracy where the average accuracy value of the Ionosphere and Ovarian Cancer dataset is 0.78 and 0.91 for the same selected feature vectors respectively. For Iris dataset, the filter method outperforms the wrapper method by achieving the same accuracy value using only half number of selected features. The results also show that the filter method surpasses when considering the execution time.
- Published
- 2021
35. EIoU: An Improved Vehicle Detection Algorithm Based on VehicleNet Neural Network
- Author
-
Zuomin Yang, Jianguang Li, and Xianlun Wang
- Subjects
History ,Artificial neural network ,Computer science ,business.industry ,Vehicle detection ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
The paper’s primary purpose is to optimize the performance (speed/accuracy) of vehicle detection. The vehicle dataset Vehicle2020 used in this paper is divided into ten different vehicle classes. Intersection over Union (IoU) is usually used as a standard to evaluate the accuracy of vehicle detection in a specific dataset. However, IoU as a performance of the object detection algorithm is still shortcomings. IoU is further improved and called a new algorithm EIoU. Finally, the neural network structure was redesigned, which was called VehicleNet. The experimental results show that EIoU as a performance evaluation algorithm used the vehicle detection framework can improve the performance of vehicle detection. Using the algorithm of this paper shows the performance superiority of vehicle detection.
- Published
- 2021
36. Detecting Spatial Autocorrelation for a Small Number of Areas: a practical example
- Author
-
Earl Duncan, Susanna M. Cramb, Aswi Aswi, and Kerrie Mengersen
- Subjects
History ,Geography ,business.industry ,Small number ,ComputingMethodologies_DOCUMENTANDTEXTPROCESSING ,Pattern recognition ,Artificial intelligence ,business ,Spatial analysis ,Computer Science Applications ,Education - Abstract
Moran’s I is commonly used to detect spatial autocorrelation in spatial data. However, Moran’s I may lead to underestimating spatial dependence when used for a small number of areas. This led to the development of Modified Moran’s I, which is designed to work when there are few areas. In this paper, both methods will be presented. Many R programs enable calculating Moran’s I, but to date, none have been available for calculating Modified Moran’s I. This paper aims to present both methods and provide the R code for calculating Modified Moran’s I, with an application to a case study of dengue fever across 14 regions in Makassar, Indonesia.
- Published
- 2021
37. Research on Condition Evaluation of Gearbox Based on PCA-FCM
- Author
-
Sixia Fan, Bin Wu, and Haitao Wang
- Subjects
History ,Computer science ,business.industry ,Condition evaluation ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
In order to evaluate the state of the gearbox, this paper proposes to use PCA-FCM algorithm to divide the state of the gearbox. By decomposing the vibration signal of the gearbox and taking the principal component, the state of the gearbox is divided. At the same time, this paper considers the fuzzy partition and geometric structure partition of the data set to determine the classification, which is verified by the wind turbine gearbox simulation experiment platform. The experimental results show that the gearbox state assessment based on PCA-FCM algorithm can effectively divide and identify the operation state of the gearbox, which makes the operation state division of the gearbox more scientific, and provides a theoretical basis for subsequent fault diagnosis and maintenance strategy.
- Published
- 2021
38. Normalized Cross Correlation Template Matching for Oil Palm Tree Counting from UAV image
- Author
-
S A A Shukor, Sharifah Nurul Husna Syed Hanapi, and Jalal Johari
- Subjects
History ,Tree (data structure) ,Cross-correlation ,business.industry ,Template matching ,Palm oil ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education ,Mathematics ,Image (mathematics) - Abstract
Tree crown detection and counting from remote sensing data such as images from Unmanned Aerial Vehicle (UAV) shows significant role in this modern era for vegetation monitoring. Since the data processing would depends on raw data available and for this case the RGB data, thus a suitable method such as template matching is presented. Normalized cross correlation is widely used as an effective measure in similarity between template image and the source or testing images. This paper focuses on six (6) steps involved in the overall process which are: (1) image acquisition, (2) template optimisation, (3) normalized cross correlation, (4) sliding window, (5) matched image and counting, and (6) accuracy assessment. Normalized cross correlation and sliding window techniques proposed for this work resulted in 80% to 89% F-measure values. This result indicates that UAV image data with appropriate image processing method/s have the potential to provide vital information for oil palm tree counting. This would be beneficial in plantation management to estimate yield and productivity. However, there are still rooms for improvement to achieve better results.
- Published
- 2021
39. Multi-operator feature enhancement methods for industrial defect detection
- Author
-
Bo Zhou, XuDong Yin, Yi Chao Fan, and YuXin Liu
- Subjects
History ,Multi operator ,business.industry ,Feature (computer vision) ,Computer science ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
Deep learning based object detection algorithms have been gradually applied to industrial defect detection, but the resulted accuracy does not fully meet the needs of industrial inspection. In order to enhance image features, this paper proposes a series of image preprocessing schemes based on edge detection operators, using a single-operator preprocessing scheme, a multi-operator serial preprocessing scheme and a multi-operator parallel preprocessing scheme for image preprocessing of data to enhance the edge features of images. The validation experiment of the SSD based object detection algorithm is performed on dataset used for industrial inspection, to verify the effectiveness of the processing schemes above. The result shows that the multi-operator based image preprocessing method is effective in improving the accuracy of surface defect detection in the field of industrial defect detection.
- Published
- 2021
40. An Improved Convolutional Neural Network for Text Classification
- Author
-
A Runa, Zhili Pei, Mingyang Jiang, and Xiaojing Fan
- Subjects
History ,Computer science ,business.industry ,Pattern recognition ,Artificial intelligence ,business ,Convolutional neural network ,Computer Science Applications ,Education - Abstract
This paper studies the text classification based on deep learning. Aiming at the problem of over fitting and training time consuming of CNN text classification model, a SDCNN model is constructed based on sparse dropout convolutional neural network. Experimental results show that, compared with CNN, SDCNN further improves the classification performance of the model, and its classification accuracy and precision can reach 98.96% and 85.61%, respectively, indicating that SDCNN has more advantages in text classification problems.
- Published
- 2021
41. A new data classification improvement approach based on kernel clustering
- Author
-
Bingsen Guo
- Subjects
History ,ComputingMethodologies_PATTERNRECOGNITION ,business.industry ,Computer science ,Data classification ,Pattern recognition ,Artificial intelligence ,business ,Kernel clustering ,Computer Science Applications ,Education - Abstract
Data classification is one of the most critical issues in data mining with a large number of real-life applications. In many practical classification issues, there are various forms of anomalies in the real dataset. For example, the training set contains outliers, often enough to confuse the classifier and reduce its ability to learn from the data. In this paper, we propose a new data classification improvement approach based on kernel clustering. The proposed method can improve the classification performance by optimizing the training set. We first use the existing kernel clustering method to cluster the training set and optimize it based on the similarity between the training samples in each class and the corresponding class center. Then, the optimized reliable training set is trained to the standard classifier in the kernel space to classify each query sample. Extensive performance analysis shows that the proposed method achieves high performance, thus improving the classifier’s effectiveness.
- Published
- 2021
42. Application of Convolutional Neural Network Method in Brain Computer Interface
- Author
-
Chunjin Ji, Lingzhi Chen, and Wei Deng
- Subjects
History ,business.industry ,Computer science ,Pattern recognition ,Artificial intelligence ,business ,Convolutional neural network ,Computer Science Applications ,Education ,Brain–computer interface - Abstract
Pattern Recognition is the most important part of the brain computer interface (BCI) system. More and more profound learning methods were applied in BCI to increase the overall quality of pattern recognition accuracy, especially in the BCI based on Electroencephalogram (EEG) signal. Convolutional Neural Networks (CNN) holds great promises, which has been extensively employed for feature classification in BCI. This paper will review the application of the CNN method in BCI based on various EEG signals.
- Published
- 2021
43. Modelling of Facial Images for Analysis of Recognition System
- Author
-
Shafriza Nisha B, Assyakirin M H, Haniza Y, Fathinul Syahir A S, and Muhammad Juhairi A S
- Subjects
History ,business.industry ,Computer science ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Recognition system ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
Face recognition is categorized as a biometric technology that employs the use of computer ability in image processing to detect and recognize human faces. Face recognition system has numerous applications for many purposes such as for access control, law enforcement and surveillance thus this system is dominant in present technology. Generally, face recognition system become more advance in term of the accuracy and implementation. However, there are a few parameters that effects the accuracy of recognition system for examples, the pose invariant, illumination effect, size of image and noise tolerance. Even though there are a number of systems were already available in the literature, the complete understanding of their performances are relatively limited. This is due to many systems focused on a narrow application band – therefore, a comprehensive analysis are needed in order to understand their performances leading to establishing the conditions for successful face recognition system. In this paper we developed a synthetic model to represent facial images to be used as a platform for performance analysis of facial recognition systems. The model includes 5 face types with the ability to vary all parameters that are affecting recognition performance – measurement noise, face size and face-background intensity differences. The model is important as it provide an avenue for performance analysis of facial recognition systems.
- Published
- 2021
44. Texture Feature Extraction of Lumbar Spine Trabecular Bone Radiograph Image using Laplacian of Gaussian Filter with KNN Classification to Diagnose Osteoporosis
- Author
-
K. V. Mahendra Prashanth, A Ramalingaiah, and Kavita Avinash Patil
- Subjects
History ,business.industry ,Radiography ,Osteoporosis ,Pattern recognition ,Filter (signal processing) ,medicine.disease ,Blob detection ,Computer Science Applications ,Education ,Image (mathematics) ,Trabecular bone ,medicine ,Lumbar spine ,Artificial intelligence ,business ,Texture feature - Abstract
The human bones are categorized based on elemental micro architecture and porosity. The porosity of the inner trabecular bone is high that is 40-95% and the nature of the bone is soft and spongy whereas the cortical bone is harder and is less porous that is 5 to 15%. Osteoporosis is a disease that normally affects women usually after their menopause. It largely causes mild bone fractures and further stages lead to the demise of an individual. The detection of Osteoporosis in Lumbar Spine has been widely recognized as a promising way to frequent fractures. Therefore, premature analysis of osteoporosis will estimate the risk of the bone fracture which prevents life threats. The paper is systematized in two different sections to classify normal (non-osteoporosis) and abnormal(osteoporosis)Lumbar spine trabecular bone. In this method, the first section is based on discriminating the lumbar spine trabecular bone micro-architecture predisposing by means of first and second order directional derivative of Laplacian of Gaussian filter with different standard deviation to acquire the minimum and maximum responses. The dimension reduction of texture features, quantization and adjacent scale coding with weighted multipliers are used to lessen the intensity variations of texture features. The second section is based on the reduction of histogram features as a training data set for classification of normal and osteoporotic images of lumbar spine (L1-L4) using K-Nearest Neighborhood (KNN) classifier. The tested dataset result gives effective classification accuracy of 97.22% with lesser texture feature dimension. The usage of weight multiplier as well as quantization technique plays a major role for the improvement of accuracy to diagnose osteoporosis for an input noisy and noiseless image.
- Published
- 2021
45. Facial Micro-expression Recognition Algorithm Based on Big Data
- Author
-
Xiaofeng Ding and Qun Xia
- Subjects
History ,Facial expression recognition ,business.industry ,Computer science ,Big data ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
The 21st century is the era of big data. All aspects of society, from facial expressions to national defense and military, will generate massive amounts of data. Facial expression recognition technology, as a new technology spawned in the era of big data, has broad applications The prospects are widely used in intelligent transportation, assisted medical care, distance education, interactive games and public safety. In recent years, it has attracted more scholars’ attention and has become another research hotspot in the field of computer vision and machine learning. The purpose of this article is to study the facial micro-expression recognition algorithm based on big data. This time, big data technology is used to analyze the algorithm. Big data can better solve the small changes in face recognition and complex data processing. This paper firstly summarizes the basic theory of big data, derives the core technology of big data, and analyzes its shortcomings and shortcomings based on the current research status of facial micro-expression in my country, and finally discusses the big data based on big data. Research on facial micro-expression recognition algorithm under the following. This article takes the research situation of the face micro-expression recognition by related companies as the survey object, and analyzes it through the literature data method, questionnaire survey method, mathematical statistics method and other research methods. Experimental results show that the lower the dimensionality reduction, the less classification time is used. When the dimensionality reduction is 45 dimensions, the recognition rate of facial expressions is the highest.
- Published
- 2021
46. Image Compression Algorithm Based On Variational Autoencoder
- Author
-
Ying Sun, Jiabao Bai, Lang Li, Yang Ding, and Xiangning Xin
- Subjects
History ,Computer science ,business.industry ,Image compression algorithm ,Pattern recognition ,Data_CODINGANDINFORMATIONTHEORY ,Artificial intelligence ,business ,Autoencoder ,Computer Science Applications ,Education - Abstract
Variational Autoencoder (VAE), as a kind of deep hidden space generation model, has achieved great success in performance in recent years, especially in image generation. This paper aims to study image compression algorithms based on variational autoencoders. This experiment uses the image quality evaluation measurement model, because the image super-resolution algorithm based on interpolation is the most direct and simple method to change the image resolution. In the experiment, the first step of the whole picture is transformed by the variational autoencoder, and then the actual coding is applied to the complete coefficient. Experimental data shows that after encoding using the improved encoding method of the variational autoencoder, the number of bits required for the encoding symbol stream required for transmission or storage in the traditional encoding method is greatly reduced, and symbol redundancy is effectively avoided. The experimental results show that the image research algorithm using variational autoencoder for image 1, image 2, and image 3 reduces the time by 3332, 2637, and 1470 bit respectively compared with the traditional image research algorithm of self-encoding. In the future, people will introduce deep convolutional neural networks to optimize the generative adversarial network, so that the generative adversarial network can obtain better convergence speed and model stability.
- Published
- 2021
47. Automated Classification of High-resolution Rock Image Based on Residual Neural Network
- Author
-
Weibo Cai, Juncan Deng, Qirong Lu, Kaiqing Luo, and Kengdong Lu
- Subjects
History ,Computer science ,business.industry ,High resolution ,Pattern recognition ,Artificial intelligence ,business ,Image based ,Residual neural network ,Computer Science Applications ,Education - Abstract
The identification and classification of high-resolution rock images are significant for oil and gas exploration. In recent years, deep learning has been applied in various fields and achieved satisfactory results. This paper presents a rock classification method based on deep learning. Firstly, the high-resolution rock images are randomly divided into several small images as a training set. According to the characteristics of the datasets, the ResNet (Residual Neural Network) is optimized and trained. The local images obtained by random segmentation are predicted by using the model obtained by training. Finally, all probability values corresponding to each category of the local image are combined for statistics and voting. The maximum probability value and the corresponding category are taken as the final classification result of the classified image. Experimental results show that the classification accuracy of this method is 99.6%, which proves the algorithm’s effectiveness in high-resolution rock images classification.
- Published
- 2021
48. Defects Detection Algorithm of Harumanis Mango for Quality Assessment Using Colour Features Extraction
- Author
-
M I Ahmad, W. M. F. Wan Nik, N.H.H. Abu Bakar, Abdul Halim Abdullah, S R Romle, M N Abu Bakar, Syed Hadzrullathfi Syed Omar, N M Maliki, N. Abdul Rahim, Khairel Rafezi Ahmad, Norzila Zakaria, Haniza Yazid, and S. Sulaiman
- Subjects
History ,Computer science ,Quality assessment ,business.industry ,Extraction (chemistry) ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
Visual defects detection is one of the main problems in the post-harvest processing caused a major production and economic losses in agricultural industry. Manual fruits detection become easy when it is done in small amount, but the result is not consistent which will generate issue in fruit grading. A new fruit quality assessment system is necessary in order to increase the accuracy of classification, more consistencies, efficient and cost effective that would enable the industry to grow accordingly. In this paper, a method based on colour feature extraction for the quality assessment of Harumanis mango is proposed and experimentally validated. This method, including image background removal, defects segmentation and recognition and finally quality classification using Support Vector Machine (SVM) was developed. The results show that the experimental hardware system is practical and feasible, and that the proposed algorithm of defects detection is effective.
- Published
- 2021
49. Stress Recognition Using Facial Landmarks and Cnn (Alexnet)
- Author
-
K Praveen, K Kiran, K Khalandar, P Ramesh Naidu, and S Pruthvi Sagar
- Subjects
History ,business.industry ,Computer science ,Stress recognition ,Pattern recognition ,Artificial intelligence ,business ,Computer Science Applications ,Education - Abstract
Stress is a psychological disorder that affects every aspect of life and diminishes the quality of sleep. The strategy presented in this paper for detecting cognitive stress levels using facial landmarks is successful. The major goal of this system was to employ visual technology to detect stress using a machine learning methodology. The novelty of this work lies in the fact that a stress detection system should be as non-invasive as possible for the user. The user tension and these evidences are modelled using machine learning. The computer vision techniques we utilized to extract visual evidences, the machine learning model we used to forecast stress and related parameters, and the active sensing strategy we used to collect the most valuable evidences for efficient stress inference are all discussed. Our findings show that the stress level identified by our method is accurate is consistent with what psychological theories predict. This presents a stress recognition approach based on facial photos and landmarks utilizing AlexNet architecture in this research. It is vital to have a gadget that can collect the appropriate data. The use of a biological signal or a thermal image to identify stress is currently being investigated. To address this limitation, we devised an algorithm that can detect stress in photos taken with a standard camera. We have created DNN that uses facial positions points as input to take advantage of the fact that when a person is worried their eye, mouth, and head movements differ from what they are used to. The suggested algorithm senses stress more efficiently, according to experimental data.
- Published
- 2021
50. Hyperspectral Data Clustering Using Hellinger Divergence
- Author
-
E Myasnikov
- Subjects
History ,ComputingMethodologies_PATTERNRECOGNITION ,business.industry ,Hyperspectral imaging ,Pattern recognition ,Artificial intelligence ,Divergence (statistics) ,business ,Cluster analysis ,Computer Science Applications ,Education ,Mathematics - Abstract
Clustering is an important task in hyperspectral image processing. Despite the existence of a large number of clustering algorithms, little attention has been paid to the use of non-Euclidean dissimilarity measures in the clustering of hyperspectral data. This paper proposes a clustering technique based on the Hellinger divergence as a dissimilarity measure. The proposed technique uses Lloyd’s ideas of the k-means algorithm and gradient descent-based procedure to update clusters centroids. The proposed technique is compared with an alternative fast k-medoid algorithm implemented using the same metric from the viewpoint of clustering error and runtime. Experiments carried out using an open hyperspectral scene have shown the advantages of the proposed technique.
- Published
- 2021
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.