Browse Items (2150 total)
Sort by:
-
An efficient cloud based architecture for integrating content management systems
The use of digital content is increasing day after day and now it is an essential element of our day today life. The amount of stored information is so huge that it is highly difficult to manage the content especially in a distributed cloud environment. There are many open source software solutions available in cloud to handle huge amount of digital data. However none of these solutions addresses all the requirements needed to manage the content spread out in multiple systems effectively. The user has to relay on multiple content management systems to do the work. This turns into ever more unwieldy, time consuming and leads to loss of data. Using robust and integrated content management systems, these issues could be solved effectively. In this paper we have identified various challenges of using the content management system in the cloud after surveying many Content Management System related article and proposed an integrated solution named Cloud based Architecture integrating Content Management System which is capable of interfacing with various unique features available at different content management system installations in the cloud. This maximizes the functionality and performance of any Content management systems. The Representational State Transfer (REST) protocol is used to integrate the best features of various open source content management systems. REST provides higher level of security compared to existing systems as it does not store the user sessions. The users can interact with the system with the help of an interface which abstracts the complexities of multiple content management systems running in the cloud. 2017 IEEE. -
An Efficient Compressive Data Collection Scheme for Wireless Sensor Networks
The Compressive Data Collection (CDC) scheme is an efficient data-acquiring method that uses compressive sensing to decrease the bulk of data transmitted. Most existing schemes are modeled as Non-Uniform Sparse Random Projection (NSRP), and an NSRP-based estimator is used. These models cannot deal with anomaly readings that deviate from their standards and norms. Therefore, we provide a new CDC strategy in this study that uses an opportunistic estimator and routing. Initially, neighbor nodes are identified using the covariance function following the Gaussian process regression, and the data transfer to the neighbor node is done using the compressive sensing technique. Compressed data are then projected by using conventional random projection. Finally, the sample required to retrieve data is estimated using margin-free and maximum likelihood estimators. Results show that the sample needed to retrieve the data is less in the proposed scheme. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
An Efficient Deep Learning Framework FPR Detecting and Classifying Depression Using Electroencephalogram Signals
Depression is a common and real clinical disease that has a negative impact on how you feel, how you think, and how you behave. It is a significant burdensome problem. Fortunately, it can also be treated. Feelings of self-pity and a lack of interest in activities you once enjoyed are symptoms of depression. It can cause a variety of serious problems that are real, and it can make it harder for you to work both at home and at work. The main causes include family history, illness, medications, and personality, all of which are linked to electroencephalogram (EEG) signals, which are thought of as the most reliable tools for diagnosing depression because they reflect the state of the human cerebrum's functioning. Deep learning (DL), which has been extensively used in this field, is one of the new emerging technologies that is revolutionizing it. In order to classify depression using EEG signals, this paper presents an efficient deep learning model that allows for the following steps: (a) acquisition of data from the psychiatry department at the Government Medical College in Kozhikode, Kerala, India, totaling 4200 files; (b) preprocessing of these raw EEG signals to avoid line noise without committing filtering; (c) feature extraction using Stacked Denoising Autoevolution; and (d) reference of the signal to estimate true and all. According to experimental findings, The proposed model outperforms other cutting-edge models in a number of ways (accuracy: 0.96, sensitivity: 0.97, specificity: 0.97, detection rate: 0.94). 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
An Efficient Deep Learning-Based Hybrid Architecture for Hate Speech Detection in Social Media
Social media has become an integral part of life as users are spending a significant amount of time networking online. Two primary reasons for its increasing popularity are ease of access and freedom of speech. People can express themselves without worrying about consequences. Due to lack of restriction, however, cases of cyberbullying and hate speeches are increasing on social media. Twitter and Facebook receive over a million posts daily, and manual filtration of this enormous number is a tedious task. This paper proposes a deep learning-based hybrid architecture (CNN + LSTM) to identify hate speeches by using Stanfords GloVe, which is a pre-trained word embedding. The model has been tested under different parameters and compared with several state-of-the-art models. The proposed framework has outperformed existing models and has also achieved the best accuracy. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
An Efficient Detection and Prediction of Intrusion in Smart Grids Using Artificial Neural Networks
In recent years, fraud identification on Internet of Things (IoT) devices has been essential to obtaining better results in all fields, such as smart cities, smart grids, etc. As a result, there are more IoT devices in the smart grid's power management sectors, and apart from these identifications, intrusion into the smart grid is very difficult. Hence, to overcome this, a proposed intrusion detection system in a smart grid using an artificial neural network (ANN) has been used to detect the intrusion and improve the prediction rate, and it has been very effective on various faults injected into the smart grids in ranges and seasons. As per the simulation result, the proposed method shows better results as compared to a conventional neural network (CNN) with respect to the root mean square error in terms of weekly, monthly, and seasonal terms of 0.25%, 0.15%, and 0.26%, respectively. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
An Efficient Face Recognition System using Deep Transfer Learning
Face recognition is an AI-based innovation used to find and recognize human appearances in videos and images. Organizations can apply face recognition to many different kinds of fields which may include biometrics, regulation of law, security and individual wellbeing; so as to take observation of individuals in any scenario. Face recognition has advanced from simple vision methods to progress in ML; and further to progressively refined neural networks (ANN) and related advances. It currently assumes an indispensable part as the initial phase in numerous basic applications, including the task of tracking a face. Face recognition is utilized to focus cameras or count the number of individuals present in a particular region. The innovation likewise has showcasing applications, for instance, showing recommended promotions when a specific user is detected. 2022 IEEE. -
An Efficient Fuzzy Logic Cluster Formation Protocol for Data Aggregation and Data Reporting in Cluster-Based Mobile Crowdsourcing
Crowdsourcing is a procedure of outsourcing the data to an abundant range of individual workers rather than considering an exclusive entity or a company. It has made various types of chances for some difficult issues by utilizing human knowledge. To acquire a worldwide optimal task assignment scheme, the platform usually needs to collect location information of all workers. During this procedure, there is a major security concern; i.e., the platform may not be trustworthy, and so, it brings about a threat to workers location privacy. Recently, many distinguished research papers are published to address the security and privacy issues in mobile crowdsourcing. According to our knowledge, the security issues that occur in terms of data reporting were not addressed. Secure and efficient data aggregation and data reporting are the critical issue in Mobile Crowdsourcing (MCS). Cluster-based mobile crowdsourcing (CMCS) is the efficient way for data aggregation and data reporting. In this paper, we propose a novel procedure, the efficient fuzzy logic cluster formation protocol (EFLCFP) for cluster formation, and use cluster cranium (CC) for data aggregation and data reporting. We recommend a couple of secure and efficient data transmission (SET) protocols for CMCS, (i) SET-IBE uses additively homomorphic identity-based encryption system and (ii) SET-IBOOS uses the identity-based online/offline digital signature system, respectively. Then, we have widen the features of cluster cranium by increasing the propensity to achieve aggregation and reporting on the data yielded by the requesters without scarifying their privacy. Also, considering query optimization using cost and latency. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
An Efficient HOG-Centroid Descriptor for Human Gait Recognition
Automatic recognition of human gait have gained much attention nowadays. Histogram of Oriented Gradient (HOG) is a widely adopted descriptor for object's shape analysis. In this paper, combination of HOG descriptor with silhouette centroid for human gait recognition is proposed. The resultant descriptor, namely HOG-Centroid, achieves better recognition performance on comparison with HOG descriptor individually as well as other existing gait recognition methods. Experiments are carried out with CASIA gait dataset B and cumulative matching scores of 95.3%, 98.1% and 99.2% are obtained for rank 1, rank 5 and rank 10 respectively. 2019 IEEE. -
An Efficient Localized Route Recommendation Scheme using Fusion Algorithm for VANET based Applications
The evolution of vehicles has led to the need for improved and advanced techniques to solve traffic related problems. The improvement related to cooperative vehicles has been a recent focus in dealing with such difficulties. The most popular application of co-operative vehicles is the route planning for travelers. In this paper, an innovative module namely Localized Route Recommendation with Fusion Algorithm (LR2FA) is proposed to enumerate a localized route recommendation system to communicate to co-operative vehicles. Traffic parameters such as vehicle speed and density information collected from the centralized location and used as decision factor to provide suggestions of routes using a novel Fusion Algorithm (FA). To evaluate the factors for route suggestion, FA uses a combination of genetic and heuristic-based approaches. The performance of the proposed localized route references is analyzed using simulated values of vehicle speed and density. It is seen from the results that the proposed LR2FA provides top fitting routes compared to greedy based route suggestion. 2022 IEEE. -
An Efficient Machine Learning Approach: Analysis of Supervised Machine Learning Methods to Forecast the Diamond Price
Diamond, a found natural process compound of carbon, is one of the hardest and most immensely expensive material known to men, especially more to women. Investments in expensive gems like diamonds are in significant demand. The rate of a diamond, nevertheless, is not as easily calculated as the value of either gold or platinum since so many factors must be taken into account. Because there is such a broad range of diamond dimensions and qualities; as a result, being able to make reliable price predictions is crucial for the diamond industry. Although, making accurate predictions is challenging. In this study, we implemented multiple machine learning techniques employed to the challenge of diamond price forecasting's such as Linear Regression, Random Forest, Decision Tree Random Forest, Cat-Boost Regressor and XGB Regressor. This article's goal is to develop an accurate model for estimating diamond prices based on its characteristics such as weighting factor, cut grade, and dimensions. We compared the sum of estimated values and test values of predicted values with overestimated, underestimated and exact estimations. We applied cross-validation to calculate how much the model deviates from the actual when faced with a difference between the training set and the test set. We predicted values side by side. We performed a comparative analysis of supervised machine learning models with other models to evaluate the model accuracy and performance metrics. The Study's experimental findings show that out of all the supervised machine learning models, Random Forest performs well with R2score and Low RMSE and MAE values and CV Score. 2023 IEEE. -
An Efficient Machine Learning Classification model for Credit Approval
Credit authorization is a critical step for banks as well as every bank's main source of revenue is its line of credit. Thus, banks can profit from the loan interest they approve. Profitability or lost opportunity of a bank is highly dependent on loans that are whether consumers repay the debt or refuse. Loan collection is a significant factor in a bank's economic results. Forecasting the customer's ability to repay the loan in order to determine whether it should authorize or deny loan documents is a significant undertaking and a critical method in data analytics is being utilized to investigate the problem of loan default prediction: On the premise of assessment, the Logistic-Regression Classification Model, Random-Forest Classifier and Decision Tree Classification Models are compared. The mentioned classification algorithms were created as well as subsequently various evaluation metrics were obtained. By utilizing a suitable strategy, the appropriate clients for loan providing may be simply identified by assessing their probability of non-performing loans. This indicates that a bank really shouldn't simply prioritize wealthy consumers when giving loans, but it should also consider a client's other characteristics. This approach is critical in making credit judgments and forecasting default risk. 2023 IEEE. -
An Efficient Multi-Modal Classification Approach for Disaster-related Tweets
Owing to the unanticipated and thereby treacherous nature of disasters, it is essential to gather necessary information and data regarding the same on an urgent basis; this helps to get a detailed overview of the situation and helps humanitarian organizations prioritize their tasks. In this paper, "An Efficient Multi-Modal Classification Approach for Disaster-related Tweets,"the proposed framework based on Deep Learning to classify disaster-related tweets by analyzing text and image contents. The approach is based on Gated Recurrent Unit (GRU) and GloVe Embedding for text classification and VGG-16 network for image classification. Finally, a combined model is proposed using both text and image modules by the Late Fusion Technique. This portrays that the proposed multi-modal system performs significantly well in classifying disaster-related content. 2022 IEEE. -
An Efficient Preprocessing Step for Retinal Vessel Segmentation via Optic Nerve Head Exclusion
Retinal vessel segmentation plays a significant role for accurate diagnostics of ophthalmic diseases. In this paper, a novel preprocessing step for retinal vessel segmentation via optic nerve head exclusion is proposed. The idea relies in the fact that the exclusion of brighter optic nerve head prior to contrast enhancement process can better enhance the blood vessels for accurate segmentation. A histogram based intensity thresholding scheme is introduced in order to extract the optic nerve head which is then replaced by its surrounding background pixels. The efficacy of the proposed preprocessing step is established by segmenting the retinal vessels from the optic nerve head excluded image enhanced using CLAHE algorithm. Experimental works are carried out with fundus images from DRIVE database. It shows that 1%3% of improvement in terms of TPR measure is achieved. 2019, Springer Nature Singapore Pte Ltd. -
An Efficient Quantum Transfer Learning for Cancer Prediction Using Tumour Markers: New Era of Computer in Medical
Ovarian cancer prediction models or algorithms estimate a person's risk of getting the disease based on different variables, such as their medical history, genetics, and biomarkers. Early identification and intervention will enhance patient successive diagnosis outcomes. Tumour markers are chemicals frequently detected in higher concentrations than usual in cancer patient's blood, urine, or tissues. They could be certain chemicals or proteins linked to the presence of tumours or cancer kinds. Tumour markers are employed for diagnosis, prognosis, and treatment response monitoring. Applying information or models from one quantum job to enhance the performance of another requires quantum transfer learning. Transferring knowledge from one domain to another seeks to increase learning effectiveness in novel quantum contexts. The main goal of efficient Quantum Transfer Learning (QTL) is to minimize the resources (computer power, data, or time) necessary to transfer between tasks successfully. In this research work, QTL is used to predict Ovarian Cancer (OC) with the assistance of biomarkers. The Quantum Transfer Learning- Ovarian Cancer (QTL-OC) achieves 93.78% accuracy and outperforms the existing techniques. 2023 IEEE. -
An Efficient Underwater Image Restoration Model for Digital Image Processing
Digital image processing (DIP) is showing a massive growth intodays trending world particularly, in the field of biological research. Underwater image analysis plays a vital role, where the images are easily prone to attenuation and haziness. Capturing underwater images has always been a challenging job due to dispersion and scattering of light inside water on a high scale. Several image enhancement and restoration methodologies are currently available to address these issues, where hazing and color diffusion are viewed as a common phenomenon in it. Such procedures normally includes two basic methodologies in it, namely dehazing and contrast or color enhancement, which improves the overall output of the degraded image. However, the quality and processing time of the images can still be enhanced with additional techniques incorporated to it. This work is intended toward proposing one such channel called improvised bright channel prior for dehazing the underwater images. The technique further improves on the existing methodologies by estimating the atmospheric light and refining the transmittance of the image along with image restoration. The experimental results show that the improvised bright channel prior methodology is found to perform better in dehazing underwater images with a balanced intensity in terms of dark and white patches obtained from it. When comparing and contrasting the processing time of the proposed methodology with the existing techniques, it is found that improvised bright channel prior performs better. Also, the quality of the dehazed underwater image obtained from the proposed channel is found to be effective when compared with the existing channels. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
An Efficient Wireless Sensor Network based Intrusion Detection System
Wireless Sensor Networks (WSNs) are widely used in diverse applications due to their cost-effectiveness and versatility. However, they face substantial difficulties because of their innate resource constraints and susceptibility to security attacks. A possible method to improve the security of WSNs is clustering-based intrusion detection and responding mechanisms. An in-depth analysis of the clustering-based intrusion detection and response method for WSNs is presented in this study. The suggested method efficiently uses data mining and machine learning techniques to identify unusual behaviour and probable intrusions. The system effectively analyses data inside clusters by grouping Sensor Nodes (SN) into clusters, allowing it to differentiate between legitimate patterns and insecure activity. The network may respond promptly to identified breaches and react to the responsive mechanism, which reduces their impact and protects network integrity. The proposed Mathematically Modified Gene Populated Spectral Clustering Based Intrusion Detection System and Responsive Mechanism (MMMMGPSC-IDS-RM) is compared with existing state-of-art techniques, and MMMMGPSC-IDS-RM outperforms with the highest detection rate of 96%. 2023 IEEE. -
An Empirical and Statistical Analysis of Classification Algorithms Used in Heart Attack Forecasting
The risk of dying from a heart attack is high everywhere in the world. This is based on the fact that every forty seconds, someone dies from a myocardial infarction. In this paper, heart attack is predicted with the help of dataset sourced from UCI Machine Learning Repository. The dataset analyses 13 attributes of 303 patients. The categorization method of Data Mining helps predict if a person will have a heart attack based on how they live their lives. An empirical and statistical analysis of different classification methods like the Support Vector Machine (SVM) Algorithm, Random Forest (RF) Algorithm, K-Nearest Neighbour (KNN) Algorithm, Logistic Regression (LR) Algorithm, and Decision Tree (DT) Algorithm is used as classifiers for effective prediction of the disease. The research study showed classification accuracy of 90% using KNN Algorithm. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
An Empirical and Statistical Analysis of Fetal Health Classification Using Different Machine Learning Algorithm
The health of both the mother and the baby is affected by how well the fetus is doing during pregnancy, making it a matter of utmost importance. To achieve the best results possible, it is essential to regularly monitor and intervene when needed. While there are many ways to observe the wellbeing of the fetus in the mother's womb, using artificial intelligence (AI) has the potential to enhance accuracy, efficiency, and speed when it comes to diagnosing any issues. This study focuses on developing a machine learning-driven system for accurate fetal health classification. The dataset comprises detailed information on the signs and symptoms of pregnant individuals, particularly those at risk or with emerging fetal health issues. Employing a set of ten machine learning models namely Nae Bayes, Logistic Regression, Decision Tree, Random Forest, KNN, SVM, Gradient Boosting, Linear Discriminant Analysis, Quadratic Discriminant Analysis Light Gradient Boosting Machine (LGBM) along with ensemble-based processes, the Light Gradient Boosting Machine (LGBM) has been identified as a standout performer, accomplishing an accuracy of 96.9%. Furthermore, our exploration demonstrates overall performance like character fashions, signaling promising prospects for sturdy and correct fetal fitness class systems. This study highlights the power of machine learning that could revolutionize prenatal care by identifying fetal health problems early. 2024 IEEE. -
An Empirical and Statistical Analysis of Regression Algorithms Used for Mental Fitness Prediction
In today's focus on mental well-being, technology's capability to predict and comprehend mental fitness holds substantial significance. This study delves into the relationship between mental health indicators and mental fitness levels through diverse machine learning algorithms. Drawing from a vast dataset spanning countries and years, the research unveils concealed patterns shaping mental well-being. Precise analysis of key mental health conditions reveals their prevalence and interactions across demographics. Enriched by insights into Disability-Adjusted Life Years (DALYs), the dataset offers a comprehensive view of mental health's broader impact. Through rigorous comparative analysis, algorithms like Linear Regression, Random Forest, Support Vector Regression, Gradient Boosting, K-nearest neighbors and Theil Sen Regression are assessed for predictive accuracy. Mean squared error (MSE), root mean squared error (RMSE), and Rsquared (R2) scores are used to assess the predictive accuracy of each algorithm. Results show that Mean Squared Error (MSE) ranged from 0.030 to 1.277, Root Mean Squared Error (RMSE) from 0.236 to 1.130, and R-squared (R2) scores ranged between 0.734 and 0.993, with Random Forest Regressor achieving the highest accuracy. This study offers precise prognostications regarding mental fitness and establishes the underpinnings for the creation of effective tracking tools. Amidst society's endeavor to tackle intricate issues surrounding mental health, our research facilitates well-informed interventions and individualized strategies. This underscores the noteworthy contribution of technology in shaping a more Invigorating trajectory for the future. 2023 IEEE. -
An Empirical Examination of the Factors of Big Data Analytics Implementation in Supply Chain Management and Logistics
Numerous companies have effectively exploited Big Data Analytics (BDA) potential to enhance their effectiveness in the Big Data period. Given that big data application in logistics and supply chain management (SCM) is nevertheless in its early stages, assessments of BDA could differ from various viewpoints, producing certain difficulties in comprehending the significance and potential of big data. Based on past research on BDA and SCM, this work examines the factors that influence organizations' willingness to implement BDA in their everyday activities. This research divides potential elements into 4 groups: technical, firm, ecological, and supply chain issues. A framework consisting of direct factors like technical, firm, and mediators was presented based on the technology diffusion hypothesis. The experimental findings demonstrated that anticipated advantages and high-level management assistance might have a considerable impact on intended adoption. Furthermore, ecological variables like competitive adoption, administration legislation, and supply chain connection can greatly alter the direct connections between influencing causes and intended adoption. 2023 IEEE.