Search

Because of the limitations of current PCB detection methods, such as low detection accuracy and high rate of false and missed detection, a PCB defect detection algorithm based on improved RetinaNet is proposed, that is, RetinaNet-line. Firstly, the algorithm uses PVT v2B2-Hi as the backbone network of the whole model, which can not only solve the deep feature redundancy caused by the residual network in RetinaNet but also improve the feature extraction ability of the network. Then, the CARAFE up-sampling module is used to enrich the semantic features of defective targets and promote the discrimination ability of the algorithm to defective targets. Finally, HSV color space is used to process the input feature image, and the color distribution is expanded by random perturbation in H, S, and V channels, with the data enhancement completed. In this paper, experiments are conducted on the publicly shared PCB defect detection dataset from the Intelligent Open Laboratory of Peking University, and the results show that the improved algorithm achieves 94.2% in the mAP index, which is better than other networks. [ABSTRACT FROM AUTHOR]

Estimating the population in a given scene is a process known as crowd counting. The field has recently garnered significant attention, and many innovative methods have emerged. However, intense scale variations and background interference make crowd counting in realistic scenes always challenging. To address these in this paper, a multi-level attention network with multi-scale feature fusion named MLANet is proposed. The network consists of three sections: a multi-level base feature extraction front-end network, a centralized dilated multi-scale feature fusion mid-end network with a global attention module, and a back-end network for the generation of density maps. By incorporating a flexible attention module and multi-scale features, the method can accurately capture crowd information at different scales and achieve accurate counting results. We evaluated the method on four public datasets (UCF_CC_50, ShanghaiTech, WorldExpo'10, and Beijing BRT), and the experimental results demonstrate a significant reduction in counting error when compared with existing methods. [ABSTRACT FROM AUTHOR]

Internet of Things (IoTs) has been playing an important role in many sectors, such as smart cities, smart agriculture, smart healthcare, and smart manufacturing. However, IoT devices are highly vulnerable to cyber-attacks, which may result in security breaches and data leakages. To effectively prevent these attacks, a variety of machine learning-based network intrusion detection methods for IoT networks have been developed, which often rely on either feature extraction or feature selection techniques for reducing the dimension of input data before being fed into machine learning models. This aims to make the detection complexity low enough for real-time operations, which is particularly vital in any intrusion detection systems. This paper provides a comprehensive comparison between these two feature reduction methods of intrusion detection in terms of various performance metrics, namely, precision rate, recall rate, detection accuracy, as well as runtime complexity, in the presence of the modern UNSW-NB15 dataset as well as both binary and multiclass classification. For example, in general, the feature selection method not only provides better detection performance but also lower training and inference time compared to its feature extraction counterpart, especially when the number of reduced features K increases. However, the feature extraction method is much more reliable than its selection counterpart, particularly when K is very small, such as K = 4 . Additionally, feature extraction is less sensitive to changing the number of reduced features K than feature selection, and this holds true for both binary and multiclass classifications. Based on this comparison, we provide a useful guideline for selecting a suitable intrusion detection type for each specific scenario, as detailed in Table 14 at the end of Sect. 4. Note that such the comparison between feature selection and feature extraction over UNSW-NB15 as well as theoretical guideline have been overlooked in the literature. [ABSTRACT FROM AUTHOR]

Numerous data centers have adopted heterogeneous computing server to accelerate the processing speed with various applications. However, as the growth of efficiency, the issue of high power consumption is increasingly becoming crucial. Traditional researchers focus on the developing strategies for power efficiency that neglects the importance of power prediction that substantially impacts on energy planning on data center. Different to the previous work, this paper utilizes the advantage of Artificial Neural Network (ANN) to design and implement an improved algorithm of power consumption prediction on heterogeneous computing server with various types of jobs. First, the impact of multi-type of jobs has been taken into account, i.e., CPU-intensive, memory-intensive, I/O-intensive and GPU-intensive. We collect the data trace from these jobs by a set of benchmarks. Then, based on the collected data trace, power prediction algorithm has been established, so that developing an improved ANN-based power consumption prediction algorithm with CNN-BiLSTM neural network and attention mechanism. Specifically, one dimensional CNN is utilized to perform local feature extraction and dimension reduction on the input, the BiLSTM network is adopted to extract high-level features from the above results. The miscellaneous features extracted are filtered out by using attention mechanism. Last, the experiment has been conducted, and the peculiarity for four types of jobs has been discussed. Compared with the latest proposed ANN-based prediction power algorithms, our proposed algorithm has better performance in prediction accuracy on power consumption. [ABSTRACT FROM AUTHOR]

Nowadays, College English courses are rich, and college students are more willing to accept English knowledge. Among them, the English error correction grammar has become the main content of the College English course. The English error correction grammar has not achieved satisfactory results in the design of the language model. Therefore, in this paper, the English error correction grammar is used as the representative of the College English course algorithm, and the characteristics of the traditional English error correcting grammar are analyzed. A hierarchical language model, which can not only solve the problem of long distance between words, but also preserve the semantic information of the sentence, is put forward. The hierarchical model includes common grammatical error correction algorithm and verb phrase collocation error correction algorithm. The error correction effect of the two algorithms is tested and verified. Compared with the traditional English error correction algorithm, the English error correction algorithm based on hierarchical language model proposed in this paper has the advantages of high reliability and convenience, and at the same time, the description of sentences can also be more accurate. [ABSTRACT FROM AUTHOR]

The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely depend on tedious, time-consuming, and error-prone manual inspection of the EEG waveform. In this paper, a highly accurate K-complex detection system is developed. Based on multiple convolutional neural network (CNN) feature extraction backbones and EEG waveform images, you only look once v3 (YOLOv3) detector was designed, trained, and tested. Extensive performance evaluation was performed using five deep transfer learning feature extraction models; Darknet-53, MobileNets, ResNet-18, SqueezeNet, and Darknet-53-coco. The dataset was comprised of 10948 images of EEG waveforms, with the K-complex location automatically annotated with bounding boxes. The Darknet-53 model performed consistently high (i.e., 89.84–99.44% precision and 10.41–0.55% miss rate). Thus, it is possible to perform automatic K-complex detection in real-time with high accuracy that aid practitioners in speedy EEG inspection. [ABSTRACT FROM AUTHOR]

In order to realize the real-time progressive compression of massive data and ensure the quality of compressed data, a real-time progressive compression method of massive data based on improved clustering algorithm is proposed in this paper. Through the micro clustering stage of birch method based on K-Medoids clustering, Clustering Feature Tree hierarchy is constructed and numerical clustering features are extracted; Taking this feature as the input of macro clustering order, the Clustering Feature Tree leaf nodes are clustered based on the improved K-Medoids clustering method, and the clustering data cluster set is output; The set is used as the original data of real-time progressive compression, and the data is denoised and compressed by lifting format wavelet transform. On this basis, Huffman coding is used to compress the data losslessly. The test results show that this method has good clustering effect under the optimal number of clustering centers, can complete the real-time progressive compression of a large number of data, and the availability of compressed data is more than 92%. [ABSTRACT FROM AUTHOR]

Phishing is a fraudulent tactic for attackers to obtain victims personal information, such as passwords, account details, credit card details, and other sensitive information. Existing anti-phishing detection methods using at the application layer and cannot be applied at the transport layer. A novel machine learning (ML) based phishing detection technique from transport layer security (TLS) 1.2 and TLS 1.3 encrypted traffic without decryption is proposed in this paper. Our proposed model detects phishing URLs at the transport layer and classifies them as legitimate or phishing. The features are extracted from TLS 1.2 and TLS 1.3 traffic, and phishing detection is performed using ML algorithms based on the extracted features. The datasets for legitimate and phishing sites are created using features derived from TLS 1.2 and TLS 1.3 traffic. According to the experimental results, the proposed model effectively detects phishing URLs in encrypted traffic. The proposed model achieves an accuracy of 93.63% for Random Forest (RF), 95.07% for XGBoost (XGB), and the highest accuracy of 95.40% for Light GBM (LGBM). [ABSTRACT FROM AUTHOR]

This paper applies the slicing technique to extract the contour feature line. The sliced data are projected on the plane to obtain the feature line of the slice profile by grid computing, which can directly establish a three-dimensional model. Due to redundancy and the uneven distribution of the point cloud, it is difficult to determine the slice thickness, causing projection error and disconnection of the contour line. In this paper, the projection error and efficiency of calculation are improved with twice data layer compression to extract the point cloud data generated by the contour. In the contour feature extraction, the line segment code is established using its structure to calculate the contour boundary by connectivity judgment. Through experimental comparison, the algorithm using the line segment to determine the boundary is more effective and robust than the eight neighborhood algorithm. [ABSTRACT FROM AUTHOR]

Security threaten is the primary issue in mobile ad hoc networks (MANET). The efficiency of the MANET system is affected by presence of malicious nodes. It is very difficult task to identify the malicious nodes from the trusty nodes in MANET system due to similar characteristics between malicious and trusty node. This paper proposes an efficient feature extraction based malicious node detection system using adaptive neuro fuzzy inference system (ANFIS) classification approach. In this paper, trust function features and service trust features are extracted from trusty and malicious nodes. These extracted features are trained and classified using ANFIS classifier. The performance of the proposed malicious node detection in MANET system is analyzed in terms of throughput, average packet loss ratio, energy consumption and detection ratio. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low accuracy and slow detection rate of existing target detection algorithms for PCB defect detection, and too many parameters of algorithm model leading to the inability to deploy on mobile terminals, a PCB defect detection algorithm based on MSD-YOLOv5 is proposed. Firstly, to ensure both detection accuracy and speed while reducing the model's size,we combine the lightweight MobileNet-v3 network with the CSPDarknet53 network. Further,the attention mechanism is introduced to highlight the important feature channels and weaken the less useful ones, so as to improve the feature extraction ability of the network. Finally, the coupling detection head is replaced with a decoupling detection head, and the defect location information and category information on the PCB are extracted and learned respectively, which solves the problem of highly coupling of different information feature distributions and enhances the generalization ability of the model. We conduct experiments on a publicly available PCB defect dataset from Peking University using this algorithm. The results show that the proposed method reduces the parameters of YOLOv5 model by 46% and improves the detection accuracy by 3.34%. [ABSTRACT FROM AUTHOR]

In recent years, the exponential growth of malware has posed a significant security threat to intelligent systems. Earlier static and dynamic analysis methods fail to achieve effective recognition rate and incurs high computational complexity. The recently developed machine learning (ML) and deep learning (DL) models can be employed to detect and classify cyberattacks and Malware efficiently. This paper presents a fusion of deep learning based cyberattack detection and classification model for intelligent systems named FDL-CADIS technique. The proposed FDL-CADIS technique transforms the Malware binary files into two-dimensional images, which are then classified by the fusion model. The FDL-CADIS technique employs the binary input images into the MobileNetv2 model for the extraction of features and the hyper parameter tuning process takes place utilizing the black widow optimization technique. The MobileNetv2 model derives all features from the Malware dataset and trains the model using the derived features. Finally, an ensemble of voting based classifiers, including gated recurrent unit and long short-term memory techniques, for Malware cyberattack detection and classification was developed. A comprehensive range of experimental analysis is performed against the benchmark dataset to demonstrate the FDL-CADIS technique's promising performance. According to the comparative analysis of the results, the FDL-CADIS technique outperformed current approaches. [ABSTRACT FROM AUTHOR]

It is important to recognize the rice image captured by unmanned aerial vehicle (UAV) for monitoring the growth of rice and preventing the diseases and pests. Aiming at the image recognition, we use rice images captured by UAV as our data source, the structure of capsule network (CapsNet) is built to recognize rice images in this paper. The images are preprocessed through histogram equalization method into grayscale images and through superpixel algorithm into the superpixel segmentation results. The both results are output into the CapsNet. The function of CapsNet is to perform the reverse analysis of rice images. The CapsNet consists of five layers: an input layer, a convolution layer, a primary capsules layer, a digital capsules layer and an output layer. The CapsNet trains classification and predicts the output vector based on routing-by-agreement protocol. Therefore, the features of rice image by UAV can be precisely and efficiently extracted. The method is more convenient than the traditional artificial recognition. It provides the scientific support and reference for decision-making process of precision agriculture. [ABSTRACT FROM AUTHOR]

In order to improve the intelligent traffic management and dispatching capabilities, it is required to optimize the design of intelligent acquisition of dynamic traffic data and optimize the processing of traffic data information by dynamically mining traffic data. Therefore, an intelligent acquisition algorithm of dynamic traffic data based on Internet of Things is proposed in this paper. In this algorithm, the distributed wireless sensor networking is used to construct an Internet of Things model of traffic data acquisition and optimize deployment and design of Internet of Things nodes for data acquisition; the adaptive weighted algorithm is used to process the fusion of dynamic traffic data to extract spectral characteristic quantity of dynamic traffic data, and the spectrum analysis method is used to perform anomaly detection to dynamic traffic data; then the detection results are conducted with fuzzy clustering, so as to realize intelligent acquisition of dynamic traffic data in Internet of Things environment. The simulation results show that in acquisition of dynamic traffic data, this method has high acquisition accuracy under different SNR. In this paper, when the SNR is 4 dB, the acquisition accuracy is 100, while the traditional method is up to 16 dB, the acquisition accuracy is 100. The proposed method has the advantages of high accuracy, good data recall, strong anti-interference ability during acquisition and good self-adaptability. [ABSTRACT FROM AUTHOR]

To solve the problem that massive intrusion data in hybrid networks greatly interfere network intrusion detection and cause relatively great difficulty to detection due to their frequency discontinuity, a mining algorithm of massive intrusion cluster computing data in hybrid networks based on spectral feature extraction under fixed constraints of time–frequency window is proposed in this paper. The multi-component cross-detection method is used to collect massive intrusion information in hybrid networks and construct a model of massive intrusion signal in hybrid networks. Cascading notch method is used to suppress intrusion interference under constraints of fixed time–frequency window, and extract fundamental quantity and primary function with locality in massive interference information, and obtain a complete energy distribution spectrum on the time–frequency plane. The energy distribution spectrum is used as guidance function to realize cluster calculating data mining with massive intrusion interference constraints. Simulation results show that, in the intrusion detection process of signal-to-noise ratio from − 15 to − 5 dB, the detection accuracy of the method proposed in this paper is always better than that of others. When the signal-to-noise ratio is − 9 dB, the detection accuracy of this method is over 90%. When the signal-to-noise ratio is −9 dB, the detection accuracy of this method can reach 100%. About the detection time, especially after the Number of intrusion date is 2000, the detection time difference between the three methods is increased, and the detection time of other methods is 2–3 times of paper method. The method proposed can accurately locate mass intrusion distribution sources in hybrid networks under the large frequency oscillation of intrusion data in the hybrid networks, realize network intrusion detection and interference suppression and can filter interference information well, so this method improves intrusion detection probability in hybrid networks. [ABSTRACT FROM AUTHOR]

Since deep learning is introduced into the field of super-resolution (SR), many deep learning-based SR methods have been proposed and achieved good results. At present, most neural networks use ordinary convolution and deeper neural layer in image super-resolution reconstruction in order to achieve better results. Therefore, most existing models have a massive amount of parameters and calculation, which limits the practical application. To solve this problem, in this paper, we propose an efficient feature cheap convolution SR (FCCSR) model, which consists of several multi-level information fusion Blocks (MIFB). In the MIFB, the features are extracted by combining normal convolution and cheap convolution, and the features obtained from each layer of convolution are fused. Under limited parameters and reconstruction speed, it enables the whole model to obtain the features from shallow to deep layers in the low-resolution (LR) images. Secondly, a novel lightweight channel attention module is designed to obtain fewer parameters and better performance. Finally, we add a gradient loss function to the original L1 loss function, making the model pay more attention to the high-frequency part of the LR image and making the reconstructed image's texture details more straightforward. The experimental results show that the proposed model has reached the most advanced level regarding image quality, memory consumption, parameter number, and calculation amount. The operation speed of FCCSR is roughly the same as that of the current STOA models, and the number of parameters is only 0.63 M. On some data sets, the best performance of FCCSR can be improved by 7%. [ABSTRACT FROM AUTHOR]

In this paper, a discrete differential algorithm is proposed to extract data features. The strategy of regional tourism development, features extraction and the technology of retaining the subject information of industry characteristic data are analyzed to reduce the feature space dimension and achieve data dimension reduction through the key factors in the development of tourism industry in the region. In this paper, a kind of distributed feature selection system is obtained based on local fisher discriminant according to the feature selection method based on data structure and the feature of modal distribution in industrial characteristic data. The experimental results show that this feature can make the space describe the data distribution structure accurately after dimension reduction. [ABSTRACT FROM AUTHOR]

Nowadays, the economy of countries highly depends on the agriculture productivity which has a great effect on the development of human civilization. Sometimes, plant diseases cause a major reduction in agricultural products. This paper proposes a new approach for the automatic detection and classification of plant leaf diseases based on using the ELM deep learning algorithm on a real dataset of plant leaf images. The proposed approach uses the k-means clustering algorithm for image segmentation and applies the GLCM for feature extraction. The BDA optimization algorithm is employed for feature selection, and lastly the ELM algorithm is used for plant leaf diseases classification. The presented approach optimizes the input weights and hidden biases for ELM. The dataset used in this study includes 73 plant leaf images, such that we tested our approach on four diseases that usually affect plants, including: Alternaria alternata, Anthracnose, Bacterial blight, and Cercospora leaf spot. The experimental results show that the proposed approach has achieved encouraging results in terms of these classification measures: accuracy, error rate, recall, F score, and AUC which are 94%, 6%, 92%, 95%, and 96% respectively. Babu [ABSTRACT FROM AUTHOR]

A method of leaf species identification based on principal component and linear discriminant analysis is proposed in this paper. The method consists of four phases. Leaf images obtained by cameras or other devices typically have petioles and wormholes that affect the recognition rate. Hence, it is necessary to first preprocess the images before feature extraction. After preprocessing of the leaf samples, the binary image, grayscale image, and texture image of the leaves are output for feature extraction. Then, shape features and texture features are extracted to describe the leaves. The shape features can be divided into three groups: geometric characteristics, Hu moment invariants features, and structural characteristics. The texture features consists of gray level co-occurrence matrix features, fractal dimension features, Local Binary Patterns features, and Gabor features. Next, principal component analysis and linear discriminant analysis are combined to reduce the dimension of the features. Finally, Back Propagation Neural Network is used to classify the feature data. The proposed method was tested on two leaf image datasets: Flavia and ICL; the average accuracy of leaf species identification was 94.22 and 87.82%, respectively. The experiment demonstrated the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

As we know that the nearest neighbor search is a good and effective method for large-scaled image search. This paper mainly focuses on the design and implementation of parallel image retrieval system based on Hadoop architecture and hashing binary code. Firstly, the whole architecture design of the system and the whole flow of image Hash retrieval are introduced. Then, the image feature extraction based on MAPREDUCE parallel data processing framework, as well as the next feature quantization and the construction method of the Hash index table are introduced in details. Finally, through the comparison of retrieval performances on the INRIA data set, it has been proved that the proposed system has better performance than the single node system on both the retrieval speed and the capability of dealing with massive data. [ABSTRACT FROM AUTHOR]

Instance selection and feature extraction is one of the most important task in data mining, due to the huge amount of data is constantly being produced in many fields. If the dataset is very large means most of the existing machine learning algorithms are inapplicable to handle such huge amount of data and computational cost is high. Two of the approaches have been used for solving this problem. One is scaling up algorithms and another one is data reduction. Scaling up data mining algorithm is not always feasible, but data reduction is possible. In this paper we take both, instance selection and feature extraction for data reduction. Instance selection is a technique that will reduce the size of the original training data. Feature extraction is input data having m dimension space that should be mapped into lower dimension space i.e., eliminate those components which are contributing less information. In this paper Cuttlefish optimization algorithm is used for instance selection, while principal component analysis is used for feature extraction. The combination of feature extraction and instance selection will reduce the large amount of computational time of training the classifiers. The optimal extracted subset of data points and reduced feature space are providing almost similar detection rate, accuracy rate, false positive rate and takes less amount of computational time for training the classifiers what we obtained from using original dataset. [ABSTRACT FROM AUTHOR]

Splicing Image Forgery Identification controls and picture tampering with no proof being left behind has turned out to be exceptionally moderate and exceedingly utilized, because of presence of to a great degree intense altering apparatuses, for example, Adobe Photoshop. Along these lines, there has been a quick expansion of the digitally adjusted pictures on the Internet and prevailing press. The genuineness of a digital image experiences extreme dangers because of the ascent of capable digital image altering devices that effectively adjust the image substance without leaving any obvious hints of such changes. The splicing forgery should be possible by replicated a one/more area from source image and pasted into an objective picture to create a composite image called spliced image. In this manner, this sort of forgery is viewed as challenge issue difficult from tamper identification perspective. To influence the issue most exceedingly awful some to post preparing impacts, for example, blurring, JPEG compression, rotation and scaling perhaps presented in the spliced image. This study aims to perform quantification and data analysis following feature extraction using computational techniques to detect interesting textural and anatomical changes, these extracted features then can be used as a key to distinguish between different classes (Splicing Image and non-Splicing image). This paper presents a new framework to identify the spliced image by exploiting the image texture features, and to automatically identification of spliced images. To accurately identify the spliced image, the proposed solution uses different texture features to capture deferent texture related to the edge of the object and the colour features. We have combine these features to produce a good vector to describe the splice object. Two models have been proposed in this paper first combine the vectors of the three features and feed them to the ANN classifier. Second, use the majority voting of the result of three features to take the decision. This is followed by a ANN classifier; in this model we have trained the system with 30 training 20% validation 50% testing. We evaluated the effectiveness of the classification framework for identifying spliced images by compare the result with the manual label which is done by the people who have created the data sets. In this approach we have combine different features to capture different information and feed them to the neural network to identify the splicing image. The findings outcome from this study have shown an improved approach that automatically splicing image forgery identification. We have evaluated the splicing image forgery identification using the texture features. The identification accuracy in the technique used is about 98.06%., with 99.03% sensitivity and 96.07% specificity. [ABSTRACT FROM AUTHOR]

Denial of service (DoS) attack is the menace to private cloud computing environment that denies services provided by cloud servers leading to huge business losses. Efficient DoS attack detection mechanisms are demanded which necessitates the extraction of features for its best performance. The lacuna in the existing feature extraction based detection systems is the sensitiveness of initial cluster center which leads to high false alarm rate and low accuracy. In this paper, this issue is addressed by proposing a class center based triangle area vector (CCTAV) method which computes the mean of target classes individually and extracts the correlation between features. Mahalanobis distance measure is used for profile construction and DoS attacks detection. The proposed CCTAV method is tested with five publicly available datasets and compared with existing methods. It is noticed that the proposed statistical method reduces the complexity of feature extraction and enhances the attack detection process. The proposed approach is evaluated by conducting tenfold cross validation to compute 95% confidence interval. It is evident that the accuracy obtained for all the datasets are within the confidence interval. Further, the proposed CCTAV method provides significant results compared to the state-of-the-art attack detection methods. [ABSTRACT FROM AUTHOR]

Presently, the fruit industry requires a fast and efficient method for classification and recognition of the quality of fruits in bulk processing. Fruit recognition based on computer vision is quite challenging as it is based on the intensity, size, contour, and texture features extraction from fruits along with their suitable classifier selection. In this paper, the pixels containing the defected regions are segmented and their features are extracted. Further, a support vector machine (SVM) classifier is used to identify the defects and recognizes the cause with its stage. During the process of classification, fruits are categorized into two groups, defected and no-defect. The sample image observed defected further classified into three categories as the first, second and final stage of fruit defect. The sample testing at an early stage helps one to further proceed with the production or halt based on the outcome of a computer vision-based recognition system. [ABSTRACT FROM AUTHOR]

Image fusion plays a significant role in various computer vision applications. However, designing an efficient image fusion technique is still a challenging task. In this paper, a novel deep belief networks based image fusion framework is proposed to improve the performance of the image fusion process further. We have initially, evaluated the fusion dataset by applying various feature extraction techniques. Thereafter, features selection techniques are applied to select potential features. Finally, the image fusion machine learning model is built by using a deep belief network model. Extensive experiments reveal that the proposed technique outperforms existing image fusion techniques. [ABSTRACT FROM AUTHOR]

With the advent of powerful, low-cost IoT systems, processing data closer to where the data originates, known as edge computing, has become an increasingly viable option. In addition to lowering the cost of networking infrastructures, edge computing reduces edge-cloud delay, which is essential for mission-critical applications. In this paper, we show the feasibility and study the performance of image classification using IoT devices. Specifically, we explore the relationships between various factors of image classification algorithms that may affect energy consumption, such as dataset size, image resolution, algorithm type, algorithm phase, and device hardware. In order to provide a means of predicting the energy consumption of an edge device performing image classification, we investigate the usage of three machine learning algorithms using the data generated from our experiments. The performance as well as the trade-offs for using linear regression, Gaussian process, and random forests are discussed and validated. Our results indicate that the random forest model outperforms the two former algorithms, with an R-squared value of 0.95 and 0.79 for two different validation datasets. The random forest also served as a feature extraction mechanism which enabled us to identify which predictor variables influenced our model the most. [ABSTRACT FROM AUTHOR]

Twitter, a social blogging site which became the tremendous topic in today's environment, which made several organizations and public to develop their identity and overwhelming through this social website. But unfortunately, twitter facing great challenges due to spammers who break the reputation of the website from deliberate users to stop using it. Researchers have proposed many techniques to overcome the issues faced by the spammers. As far researchers find a new path so as the spammers develop new techniques to travel in that path. So far, many algorithms were proposed to detect the spammers and some extraction techniques have developed to increase the potential of detection rate. In this paper, the main focus is about feature extraction of our data with a hybrid approach of combining logistic regression with dimensional reduction technique using principal component analysis. Our dataset contains 17 million users' tweets with 159 features included in it. Then we are going to extract particular features from it which would be helpful for the further process of increasing the classification accuracy. For the classification process, our work extended for the process of classification of data using some machine learning techniques. From the proposed work the detection rate could be increased by using particular features for the classification process. [ABSTRACT FROM AUTHOR]

Recently computer aided diagnosis is largely used in many clinical processes to detect, predict and analyze many abnormalities. It is clear that in medical image processing, brain tumor classification and detection plays a significant task. MRI gives anatomical structure's information, and the potential abnormal tissues' information. Hence in this paper a new system is proposed for detection and classification of brain tumors. The proposed system consists of feature extraction and tumor classification. In feature extraction, Rough set theory (RST) is used and for classification task particle swam optimization neural network (PSONN) is trained and tested in order to classify the MRI brain images into normal and abnormal. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) is the most important monitoring methodology for the detection of epileptic seizure diseases. In this paper, EEG based epileptic seizure detection is assessed by employing Bern-Barcelona EEG and Bonn University EEG database. The proposed technique contains three major steps: decomposition, feature extraction and classification. Initially, decomposition using variational mode decomposition delivers an effective frequency localization. After decomposition, semantic feature extraction is carried-out by employing differential entropy and peak-magnitude of root mean square ratio for achieving optimal feature subsets and also for the rejection of irrelevant and redundant features. After finding the feature information, a superior classifier named as random forest is employed for classifying the normality and abnormality of seizure. The experimental result shows that the proposed approach distinguishes the normality and abnormality of seizure EEG signals in terms of sensitivity, specificity, accuracy, positive predictive value and negative predictive value with a superior recognition accuracy. [ABSTRACT FROM AUTHOR]

Developing technologies over digitalization have become more popular and become a threat to society and cybersecurity. Generally, the phishing method is used by hackers to access the data without the influence of users whose data was stolen. Several techniques are used to detect whether the data is phished or non-phished. Some anti-phishing software is used to identify the phishing data. However, few of these techniques did not provide efficient performance. Hence, the proposed model is introduced to overcome the issues obtained and improve the efficiency of detecting whether the data is phished or non-phished. The data is gathered from the Phishstorm dataset, which is pre-processed using the Z score normalization method and data cleaning. Data balancing is done by the Advanced synthetic sampling approach (Adv-SyN) to balance the dataset, and the features are extracted using a Double self-sparse autoencoder (DSelSa). The Opposition Gazelle optimization algorithm (OpGoA) model is used for optimal feature selection, and finally, the data is classified using Multi Head Depth wise Tern integrated long short term memory (MDepthNet). The sooty tern optimization is used to evaluate the loss function of the network model. The performance of the proposed model is analyzed based on some evaluation metrics and compared with other models, which describes the efficiency of the proposed model. The main objective of proposed technique used to detect the phishing attack and phishing or non-phishing. An automated DL methodology introduced for effective detection of phishing attacks for enhancing the cyber security. The accuracy of the proposed model is obtained as 99.45%, and Precision is 99.45%. RMSE and MSE rate of the proposed model is reduced to 0.73 and 0.05 for better performance. [ABSTRACT FROM AUTHOR]

Medical image registration is vital for precise healthcare diagnosis, treatment planning, and disease progression tracking, but traditional methods fail to capture complex spatial transformations and anatomical variations. A Kernel Principal Component Analysis (KPCA) driven Teaching Learning based optimization (TLBO) approach is proposed to overcome these limitations. The proposed approach is categorized into three phases, i.e., pre-processed phase, contour extraction phase with feature extraction using KPCA, and evaluating robust affine transformation parameters leveraging TLBO for accurate alignment. In the pre-processing phase, gaussian filter is applied to remove noise from source and target images, followed by normalization process. Afterwards, contour extraction is carried out to create a feature image that represents the boundaries of an image. Centroid localization is then utilized to compute translation parameters, which determine the spatial alignment between the images. By utilizing KPCA, this method captures non-linear relationships in the data to enhance the representation of image features. TLBO is employed to optimize the rigid transformation parameters to improve the accurate alignment of source and target images. Extensive experiments are carried out on monomodal and multimodal medical images such as CT and MRI taken from the Harvard Brain ATLAS, Kaggle as well as in-house clinical dataset to demonstrate the effectiveness of the proposed approach. The proposed approach significantly outperforms state-of-the-art methods, with improvements of 44.37% in Root Mean Square Error (RMSE), 19.93% in Structural Similarity Index Measure (SSIM), 20.01% in Peak Signal-to-Noise Ratio (PSNR), and 16.21% in Cross Correlation (CC) quality assessment metrics. [ABSTRACT FROM AUTHOR]

Accurate resource utilization estimation is crucial for efficient resource allocation, capacity planning, and cost optimization in cloud systems. In the past, several artificial intelligence, machine learning, and deep learning-based techniques have been evolved to forecast cloud cluster workload. Despite the abundance of available techniques, most existing techniques fail to achieve the desired prediction efficiency and generalization capability. They are computationally inefficient in accurately determining resource utilization at a machine-level granularity. The current research proposes a computationally less-expensive hybrid approach combining cluster analysis and deep neural learning with transfer learning to estimate the machine-level workload. The method implements clustering to identify the similarity patterns among the non-linear usage profiles of machines present in the input dataset. Subsequently, the generalized deep neural learning models are developed considering only a sample dataset belonging to each identified cluster. Lastly, the concept of transfer learning is deployed using pre-trained generalized models to estimate the workload for all remaining machines relating to the clusters. The performance validation of the proposed approach is carried out on the real-world traces dataset of the google cluster. The comparative evaluation of the proposed approach with benchmark approaches verifies the achieved performance benefits and accuracy. [ABSTRACT FROM AUTHOR]

With the fast growing demands in authentication biometric-based authentication system has been widely utilized in many applications which require secured personal identification/verification. In the existing computer systems, there is a possibility of an imposter gaining access when a user session is active and the user moves away from the system. To solve this problem, proposes a continuous user authentication scheme. Continuous authentication (CA) system verifies the user continuously once a person is logged in. CA system prevents the intruders from invoking the system. It passively verifies the system without interrupting the users work progress. In this paper, score level fusion is carried out using optimization that is genetic particle swarm optimization and classifiers lazy classifier—Naïve Bayes held for recognition process. The main objective of the proposed method is to fuse the user biometric traits and to accomplish the optimal result in the continuous user authentication. The proposed technique consists of four modules, namely processing module, feature extraction module, fusion module and recognition module. Finally, the proposed fusion method is applied to remote biometric authentication. The implementation is carried out using MATLAB and the evaluation metrics employed are false acceptance rate, false rejection rate and accuracy, sensitivity and specificity. From the results, we can observe that the proposed technique has achieved better performance metrics values for continuous authentication process. [ABSTRACT FROM AUTHOR]

Clustering the images is generally based on the image's visual features. Selection of relevant features is the most essential task. A clustering approach based on the bundled features is presented in this paper. Bundling of affine scale invariant feature transform (ASIFT) feature helps to cluster the near duplicates. When the local features are combined with the ASIFT features, the clustering efficiency is increased. Clustering the results from the web image search engines is very essential to help users narrow their search. We applied our idea of clustering with bundled features over Google Image search results. The results obtained show that the presented approach outperforms compared to the clustering done only with local features. [ABSTRACT FROM AUTHOR]

The major challenge of feature based blind steganalysers lies in designing effective image features which give true evidence of the stego noise rather than the natural noise present in the images. Hence they report low detection accuracy in real time implementation in spite of employing 100s of features in the process. In this paper, we coin a new paradigm for detecting steganography by examining the task as a three-steps process with the following repercussions: (a) employing curvelet transform denoising as a pre-processing step that produces better stego noise residuals suppressing the natural noise residual rather than a general denoising step before feature extraction, (b) extracting various steganalytic features, both in spatial domain as well transform domain and (c) implementing the system based on an efficient classifier, multi-surface proximal support vector machine ensemble oblique random rotation forest, that provides detection rate superior to other existing classifiers. Extensive experimentation with huge database of clean and steganogram images produced from seven steganographic schemes with varying embedding rates, and using five steganalysers, shows that the proposed paradigm improves the detection accuracy substantially and proves to be a high performance strategy even at low embedding rates. This model can be employed as a preprocessing component for any image steganalyser and high performance accuracy can be obtained. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a novel classification method for face recognition which adopts the functionalities of linear discriminant and regression. Linear discriminant and regression analysis methods have benefits regarding minimising time, memory usage and better feature extraction. Linear regression and discriminant classification (LRDC) makes use of the principle that a sample class lie in a linear subspace, proposed method represents a predicted image as a linear combination of class-specific galleries. LRDC belongs to the category of nearest subspace classification and finds the set of optimal discriminant projection vectors by adopting singular value decomposition (SVD) and null space, and the decision made for a class with the minimum distance. LRDC is extensively evaluated by applying it to different classified datasets and compared with the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

In order to fully utilize potential feature information of RGB-D images, current popular algorithms mainly use convolutional neural network (CNN) to execute both feature extraction and classification. Such methods could achieve impressive results but usually on the basis of an extremely huge and complex network. What's more, since the fully connected layers in CNN form a classical neural network classifier, which is trained by gradient descent-based implementations, the generalization ability is limited and sub-optimal. To address these problems, this paper introduce a multi-view CNN-SPMP-RNN-ELM (MCSPMPR-ELM) model for RGB-D object recognition, which combines the power of MCSPMPR and fast training of ELM. It uses the MCSPMPR algorithm to extract discriminative features from raw RGB images and depth images separately. Then the abstracted features are fed to a nonlinear ELM classifier, which leads to better generalization performance with faster learning speed. At last, co-training is employed to learn from the unlabeled data using the two distinct feature sets by semi-supervised learning method. Experimental results on widely used RGB-D object datasets show that our method achieves competitive performance compared with other state-of-the-art algorithms specifically designed for RGB-D data. [ABSTRACT FROM AUTHOR]

According to the problem that the elevation data does not reflect the slope and surface roughness of target topography, the preprocessing of topographic elevation data and extraction algorithm of topographic feature are proposed, and the corresponding extraction of topographic feature is done. A terrain risk assessment method is presented based on terrain roughness and slope information fusion, aiming at the problem that terrain roughness and gradient cannot be directly reflected from the terrain elevation data, in this paper. The innovation is that it is the first time that the bilinear interpolation algorithm is applied in preprocess of elevation data and extraction of topographic feature, as well as the terrain roughness and gradient information fusion algorithm are applied to terrain feature extraction and risk assessment for the first time. By simulation and checking calculation of a certain digital topography example, it is proved that the extraction method of topographic information based on elevation data is feasible and reliable. It will provide a new research approach for target information recognition and topography risk assessment accurately. [ABSTRACT FROM AUTHOR]

Most of the advancements are now carried out by interconnecting physical devices with computers; this is what known as Internet of Things (IoT). The major problems facing by blind people fall in the category of navigating through indoor and outdoor environments consisting of various obstacles and recognition of person in front of them. Identification of objects or person only with perceptive and audio information is difficult. An intelligent, portable, less expensive, self-contained navigation and face recognition system is highly demanded for blind people. This helps blind people to navigate with the help of a Smartphone, global positioning system (GPS) and a system equipped with ultrasonic sensors. Face recognition can be done using neural learning techniques with feature extraction and training modules. The images of friends, relatives are stored in the database of user Smartphone. Whenever a person comes in front of the blind user, the application with the help of neural network gives the voice aid to the user. Thus this system can replace the regular imprecise use of guide dogs as well as white sticks to help the navigation and face recognition process for people with impaired vision.In this paper, we have proposed a novel image recognition and navigation system which provides precise and quick messages in the form of audio to visually challenged people so that they can navigate easily. The performance of the proposed method is comparatively analyzed with the help of ROC analysis. [ABSTRACT FROM AUTHOR]

Distinguishing subsequence patterns mining aims to discover the differences between different categories of sequence databases and to express characteristics of classes. It plays an important role in biomedicine, feature information selection, time-series classification, and other areas. The existing distinguishing subsequence patterns mining only focuses on whether a pattern appears in a sequence, regardless of the number of occurrences of the pattern in the sequence and the proportion of the pattern in the entire sequence database, which affects the discovery of the distinguishing patterns when there are a large number of irrelevant occurrences. Therefore, the nonoverlapping conditional distinguishing subsequence patterns mining algorithm is proposed. In this paper, we focus on the number of nonoverlapping occurrences that effectively reduce the number of irrelevant or redundant occurrences, and in this way, the number of occurrences can be better grasped. At the same time, we use a specially designed data structure, namely, a Nettree, to avoid backtracking. In addition, we use the distinguishing patterns as classification features, and carry out classification experiments on DNA sequences and time-series data with two classes. Extensive experimental results and comparisons demonstrate the efficiency of the proposed algorithm and the correctness of the feature extraction. [ABSTRACT FROM AUTHOR]

Knowledge bases (such as Wikipedia) are valuable resources of human knowledge which have contributed to various of applications. However, their manual maintenance makes a big lag between their contents and the up-to-date information of entities. Cumulative citation recommendation (CCR) concentrates on identifying worthy-citation documents from a large volume of stream data for a given target entity in knowledge bases. Most previous approaches first carefully extract human-designed features from entities and documents, and then leverage machine learning methods such as SVM and Random Forests to filter worthy-citation documents for target entities. There are some problems in handcraft features for entities and documents: (1) It is an empirical process that requires expert knowledge, thus cannot be easily generalized; (2) The effectiveness of humanly designed features has great effect on the performance; (3) The implementation of the feature extraction process is resource dependent and time-consuming. In this paper, we present a Joint Deep Neural Network Model of Entities and Documents for CCR, termed as DeepJoED, to identify highly related documents for given entities with several layers of neurons, by automatically learn feature extraction of the entities and documents, and train the networks in an end-to-end fashion.An extensive set of experiments have been conducted on the benchmark dataset provided in the Text REtrieval Conference (TREC) Knowledge base acceleration (KBA) task in 2012. The results show the model can bring a significant improvement relative to the state-of-the-art results on this dataset in CCR. [ABSTRACT FROM AUTHOR]

Unstructured online reviews are undergoing a rather rapid expansion with the development of E-commerce, and they contain sentiment information in which consumers and businesses are very interested. Therefore, effective sentiment classification has become one of the important research topics. Many studies have shown that ensemble learning methods may have great hopeful applicability in sentiment classification tasks. In this paper, we propose a new ensemble learning framework for sentiment classification of Chinese online reviews. First of all, according to the complicated characteristics of Chinese online reviews, we extract Part of Speech Combination Pattern, Frequent Word Sequence Pattern and Order Preserved Submatrix Pattern as the input features. Furthermore, we use the algorithm of Random Subspace based on Information Gain by considering the problem of massive features in the reviews, which can improve the base classifiers simultaneously. Finally, we adopt the algorithm of Constructing Base Classifiers based on Product Attributes to combine the sentiment information of each attribute in a review so as to obtain better performance on sentiment classification. The experimental results show that the proposed ensemble learning framework has significant improvement in sentiment classification of Chinese online reviews. [ABSTRACT FROM AUTHOR]

A new speech feature extraction technique called moving average multi directional local features (MA-MDLF) is presented in this paper. This method is based on linear regression (LR) and moving average (MA) in the time–frequency plane. Three-point LR is taken along time axis and frequency axis, and 3 points MA is taken along 45° and 135° in the time–frequency plane. The LR captures the voice onset\offset, formant contour, while the moving average captures the dynamics on time–frequency axes which can be seen as voiceprints. The MA-MDLF performance is compared to commonly used speech features in speaker recognition. The comparison is performed in a speaker recognition system (SRS) for three different conditions, namely clean speech, mobile speech, and cross channel. MA-MDLF has shown better performance than the baseline MFCC, RASTA-PLP and LPCC. In clean and mobile speech, MA-MDLF feature performs the best and also in the cross channel task MA-MDLF performed excellent. We also evaluated the MA-MDLF using three speech databases, namely KSU, LDC Babylon and TIMITdatabases, and found that MA-MDLF outperformed the other commonly used features with speech from all the three databases. The first and second databases are for Arabic speech while third is for English speech. [ABSTRACT FROM AUTHOR]

Big data is centered upon the technique of expanding volume of high velocity, intricate along with different kind of data. Organizations that hold vast sum of data deals with new creation of systematic tools intended for large data. The conventional data-intensive business application starts to go down behind the times, on account of the deficient abilities to manage large data volumes, unstructured information, low rate of information retrieval along with complex algorithms. Big data relies upon the data complexity, relatively than the data size only. For resolving this kind of trouble, this paper establishes a mutual refinement technique for big data retrieval to augment the performance. The intended system comprises the system of training and retrieval which is performed consecutively. In training process, initially input data is preprocessed by splitting the data. Then frequency and entropy features are extracted from the preprocessed data. After the feature extraction data is exhibited to the mutual refinement process. In mutual refinement step hash tag graph is generated to train the data and this removes the uncertainty from the data. In retrieval process, the input query data is used for the similarity assessment. Features like frequency and entropy are extracted from the query data. Then the feature value is compared with the hash tag graph. If the feature value is matched then the data is retrieved as of the hash tag graph and the retrieved data is visualized. The proposed technique's performance is assessed by relating our intended work with the other conventional works. The experimental output exhibits that our intended mutual refinement process augments the system performance process by confiscating the uncertainty comprised in the system. This work offered a unique mutual refinement approach which yields better outcomes for retrieving the big data in a proficient manner. The proposed process retrieving process in big data gives the better performance but in future, experiments can be done on large datasets and some real-time applications to calculate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Various types of three-dimensional (3D) cameras have been used to analyze real-world objects or environments effectively. However, because most existing 3D cameras capture scenes by statically using one type of camera, there may be a limit to the quality of the captured images. Therefore, in this paper, we build a hybrid camera system that combines passive triangulation (PT)- and active triangulation (AT)-based cameras and suggest a new mechanism of estimating accurate 3D depth by adaptively switching between the two types of cameras depending on the complexity of the environment. The suggested method initially uses initial input images to extract brightness and texture, which are major features representing the current state of the surrounding environment. The method subsequently generates a set of rules that dynamically select the PT- or AT-based camera, whichever can operate more suitably in the current environment, by analyzing the two extracted features. In experimental results, we demonstrate that the proposed adaptive camera-selection approach can be applied to extract 3D depth reliably with reasonable performance in terms of accuracy and time. [ABSTRACT FROM AUTHOR]

In recent years, the incorporation of sensing technology into residential buildings has given rise to the concept of ”smart buildings”, aimed at enhancing resident comfort. These buildings are typically part of interconnected neighborhoods sharing common energy sources, which makes the energy consumption a critical consideration in decision-making processes. Consequently, optimizing energy usage in smart buildings has posed significant challenges for both enterprises and governments, prompting numerous studies to address this issue. One such challenge is organizing energy usage within neighborhood networks while ensuring the user comfort and without exceeding the total energy capacity. In this paper, we present a novel mechanism that predicts the future behavior of each house based on its historical consumption data, generating a weekly schedule annotated with hourly energy usage levels (high, normal, or low) tailored to individual user needs. Additionally, we introduce an incentive-based program that rewards users with bill discounts for adhering to high energy consumption periods. The scheduling process involves extracting features from data and utilizing a genetic algorithm for construction, coupled with dynamic programming to enhance efficiency by storing house features and schedules. This enables rapid provision of suitable schedules for similar houses. Evaluation results demonstrate that the proposed technique achieves an accuracy of 92%\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$92\%$$\end{document} and improves the execution time of the optimization algorithm by 26%\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$26\%$$\end{document}. [ABSTRACT FROM AUTHOR]

In the backdrop of an ever-expanding urban transportation road network, the dramatic changes in traffic flow make traffic flow forecasting become a challenge. Which encompass intricate spatial correlations and intricate non-linear temporal relationships. Given a complex time series of traffic flow, accurately predicting traffic flow under such circumstances becomes an arduous task, particularly for long-term sequences. To tackle this conundrum, we put together a traffic prediction framework called the multi-scale attention-based graph convolutional recurrent network (MAGRN). Based on GCN and RNN, this framework skilfully extracts dynamic spatial and temporal features from node attributes. By incorporating multi-scale feature extraction and two attention mechanisms within the attention structure, MAGRN adeptly captures features at varying granularities. This enables MAGRN to diligently capture both the temporal interdependencies and spatial correlations inherent in traffic sequences, thereby minimizing errors. Experimental validation on three real-world traffic datasets unequivocally attests to the superior performance of the MAGRN model. [ABSTRACT FROM AUTHOR]

In the present scenario, the product recommendation system is important to boost sales on many e-commerce websites. The majority of the existing product recommendation systems completely rely on the customer's website browsing history or historical transaction records to precisely predict the user's preferences for online product recommendations that are constrained by the limited information available on the e-commerce websites. Usually, processing the customer's feedback is a difficult procedure, where it is tough in interpreting and analyzing the text information. Therefore, an effective deep learning-based recommendation framework is implemented in this research manuscript. After acquiring text information from the amazon product reviews database, the data pre-processing is carried-out by using stemming, lemmatization, and stop word removal techniques. The undertaken pre-processing techniques remove both inconsistent and duplicate data that eases the process of data interpretation and use. Further, the computational time of the model is decreased by removing inconsistent and duplicate data from the original dataset. Then, the feature values are extracted from the pre-processed text data using the term frequency-inverse document frequency (TF-IDF) technique. The extracted feature values are fed to the enhanced convolutional-neural-networks (CNNs) for sentiment analysis. The enhanced CNN model uses Glove as a pre-trained model with a skip-gram in the word-embedding layer for identifying the relevant product ratings based on the user's experience to further enhance product sentiment analysis. The embedding layer in the enhanced CNN-model effectively converts every word into fixed feature vectors that helps in better word representation along with reduced dimensions. The enhanced CNN model obtained a mean recall of 94.80%, the precision of 93.64%, and accuracy of 96.92% on the amazon product reviews database and it is superior to the traditional CNN. [ABSTRACT FROM AUTHOR]

Even though video technologies have continuously advanced, playing a video still requires full length of the videos playtime, high volume of data traffic, and appropriate sound play devices. To overcome these limitations, this paper proposes a method to serve a video in an image carousel format. By providing multiple key frame images in carousel form with full script of the video, the proposed image carousel system transforms any playable video content into a readable form so that users can read the content rather than watch. Reading a video make consumers be freed from sound restrictions, and increase the potential and efficiency in the video linkage and usage in other services. In addition, this approach saves both playtime and data traffic. When a video encoded in H.264 codec with 720p resolution is transformed into the proposed image carousel form, in average 90-95 % of the data traffic were saved. [ABSTRACT FROM AUTHOR]

In the last several decades, application of affine transformation and optimization approaches have received enough attention in the domain of monomodal/multimodal image registration. A novel and robust image registration method is proposed which leverages teaching learning-based optimization (TLBO) to obtain the optimal value of rigid transformation parameters. Further, speeded up robust features (SURF) framework is employed to extract features along with Random sample consensus (RANSAC) algorithm. Afterwards, projective transformation is used to obtain more accurate registered image. To remove noise, gaussian filter is used during pre-processing and then normalization is carried out. TLBO is used to identify the optimal geometric transformation parameters by considering the mutual information (MI) as an objective function. This method detects keypoints (features) using SURF then K-nearest neighbour (KNN) is employed to match the detected features. Furthermore, RANSAC eliminates false matches. The registered image with optimal value of rigid transformation parameters is obtained and then enhanced by using SURF-RANSAC followed by projective transformation. Experiments are conducted on Whole Brain ATLAS and KAGGLE datasets. Robustness of proposed approach is verified by the improvement in evaluation metric, such as structure similarity index measure (SSIM) by 8%, MI by 12.71% on monomodal and root mean square error (RMSE) by 41.44% on multimodal images as compared to recent state-of-the-art methods. [ABSTRACT FROM AUTHOR]