Browse Items (2150 total)
Sort by:
-
Modeling a Logistic Regression based Sustained Approach for Cancer Detection
This assessment and treatment of cancer may be done using logistic regression. To properly forecast whether a tumour is malignant or benign, the likelihood of binary outcomes may be simulated based on input variables and taken into account for factors like volume, topology and texture. It aids in risk assessment by estimating an individual's likelihood of developing cancer using factors like age-group, relatives past data, life choices and gene based markers. Logistic regression plays an important role in early cancer detection and creating screening tools that identify high-risk individuals through patent characteristics, biomarkers, and medical imaging data. Prediction of the probability of survival based on age, tumor characteristics, treatment options and comorbidities is useful for survival analysis. In a comparative study, logistic regression achieved a high accuracy of 97.4%, along with random forest, in cancer detection and diagnosis. 2023 IEEE. -
Sustainable Climatic Metrics Determination with Ensemble Predictive Analytics
Sustainable features are dependent on vital climatic elements that has a prominent impact on the retention of sustainability provided its metrics are in desired domain. Regression analysis and ensemble learning models are some of the predictive analytics methods which were used to detect the association of every feature on sustainable criteria. Weather samples from Delhi during 1970-2020 is used in the research which considers features like humidity, pollutant level, temperature etc which are gathered from several authenticated sites like pollution management unit of India. After analyzing several elements affecting weather endurability, it is noticed that pollutant level and temperature exhibit the highest significance recording 30% and 44% respectively. Also the R-square metric of 86% and 82% was observed with implementation of analytics models. The major conclusion recorded that random forest outperformed regression model and it established the importance of predictive analytics in predicting sustainability results. The research validated the relevance of climatic tracking for regulating sustainability. 2023 IEEE. -
Mental Health Data Analysis Using Cloud
In health care related research studies, there exists a need for retrieving patient's health record from multiple sites. So here comes the digitization of health records, which leads to a wide range of access to various users such as doctors, patients, psychiatrists and pharmacists. The sensitive nature of individual health care data pose a threat to security. Moreover, the increased access of health information by the users threatens the privacy and confidentiality of the stored data. Notwithstanding the existing privacy protection approaches used for mental health records, we suggest a privacy preserving data analysis methodology enabling protection of health records, once user access to records are granted. This paper mainly focuses on utilizing the data analysis approach in preserving privacy of personal health records to overcome the drawbacks of existing approaches. 2020 IEEE. -
Energy sector in India: Challenges and solutions
Energy plays a vital role in the socio-economic development and human welfare of a country. It is indeed a difficult task to meet the ever increasing demand with minimum environmental risks. Population explosion and economic growth are the two major facts that drives the energy demands. The economic growth rate of India has hit the decade low of 5% in 2012-13, which shows the challenges yet to come. India being a fast developing nation with second largest population in the world, faces a significant challenge to meet the desired economic growth rate and to provide adequate access to affordable and clean energy for a large population. With the growing concern about India's population, energy demands and climatic issues, it is difficult to formulate a sustainable energy plan for the country. At the same time energy plan should have minimal effects on the health of nature by reducing CO2 emissions. To cut down CO2 emissions, to reduce fossil fuel import bills and to reduce the dependence on a third country energy supplies, India has to increase the share of renewable energy sources in the country's final energy consumption to at least 18% by 2020. This paper provides a comprehensive overview of India's energy sector, discusses the current scenario, identifies the energy utilization, challenges and puts forward some effective solutions in meeting the increasing energy demands. 2013 IEEE. -
Photometric and spectroscopic study of candidate be stars in the magellanic clouds
[No abstract available] -
Hybrid Approach for Predicting Heart Disease Using Optimization Clustering and Image Processing
Heart disease (cardiovascular disease) is one of the core issues prevalent in this generation. Every year, millions of people die due to various heart diseases. The problem occurs due to hereditary or changes in life styles. Various data mining techniques are used in order to predict heart diseases. Data mining increases the accuracy, precision, and sensitivity of the model being used. In the proposed hybrid approach for predicting heart disease using optimization clustering and image processing (Hy-OCIP) model, a hybrid approach is used to predict heart diseases with the help of optimization, clustering, and image processing. After the heart image is being processed, centroid clustering is used for clustering the processed imaged into a set of chromosomes for optimization. The optimization method used for our model is genetic algorithm. The same methods are performed for both, a healthy and a heart patient. As a result, the model used in this research is able to distinguish between a normal patient and a heart patient by a hybrid combination of image processing, clustering, and optimization. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Prevention and Mitigation of Intrusion Using an Efficient Ensemble Classification in Fog Computing
Cloud services in fog network is a platform that inherits software services to a network to handle cloud-specific problems. A significant component of the security paradigm that supports service quality is represented by intrusion detection systems (IDSs). This work develops an optimization environment to mitigate intrusion using RSLO classifier on a cloud-based fog networks. Here, a three-layer approach namely the cloud, end point, and fog layers is used as a trio to carry out all of the processing. In the cloud layer, three layers of processing are required for handling the dataset metrics which are data transformation metrics, feature selection metrics, and classification processes. With log transformation, data is transformed using KS correlation-based filter which is used to choose a feature. The classification using an ensemble methodology of RideNN classifiers which is a Rider Sea Lion Optimization (RSLO), a created classifier, is used to tune the ensemble classifier. Physical work is carried out at another layer called an end point layer. A trained ensemble classifier is used for intrusion detection in the fog layer. A greater precision, recall, and F-measure were obtained with an accuracy approximately 95%, with all benefits of the suggested RSLO-based ensemble strategy. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
AI-Driven Home Climate Optimization: The Role of ChatGPT in Enhancing AC Efficiency
The convergence of Internet of Things (IoT) and Artificial Intelligence (AI) has revolutionized home automation, yet traditional air-conditioning (AC) systems still struggle with energy inefficiency. Our research presents a novel solution, integrating AI, IoT, and user-centric design with ChatGPT, to optimize AC systems responsively to occupants' needs. Our methodology employs ChatGPT's capability to analyze historical data, discern patterns, and provide intelligent recommendations for AC operation. This transcends the functions of standard smart thermostats through AI-driven decision-making, optimizing every AC operational moment for both comfort and energy conservation. The system's foundation in data-driven decisions ensures alignment with external and internal conditions, enhancing energy efficiency and user comfort. 2024 IEEE. -
Removal of Artifacts from Electroenchaphalography Signal using Multiwavelet Transform
The signal from the brain can be recorded using Electroenchaphalography (EEG). The proposed work summarizes a unique method which is used for the removal of mixed artifacts presented in the electroencephalography signal during the acquisition process. Artifacts comprises of various bio-potential unit such as electrooculogram, electrocardiogram, and electromyogram. These artifacts are referred as a noise sources which is responsible for the complexity of the EEG signal. The artifacts obtained from the EEG signal leads towards improper diagnosis of pathological conditions. The EEG signal which is obtained from the brain is the multi-dimensional signal with the various statistical properties. Time consumption of the EEG signal is not reproducible due to the biological properties of the signal. The information of the EEG signal consists of the data of the neuron levels which is collected for every millisecond with the temporal resolution scale. In account of special cases, EEG signal contains noise and artifacts where information is collected using the extraction of signals. To obtain the information of the artifacts the proposed technique is used to maintain higher accuracy in the extraction process. The proposed technique consists of multiwavelet transform to remove the artifacts from the input EEG signal. In the proposed multiwavelet transform, the signal which consists of noisy features can be decomposed using GHM and thresholding technique. This experimental analysis shows the removal of artifacts from the EEG signals. The pathological conditions are removed which leads to the increase in the accuracy of the system. Also, this research findings shows that the proposed multiwavelet transform based approach outperforms significantly with respect to conventional approaches. The reconstructed EEG signal has the lesser reliability range which is measured in-terms of signal to noise ratio and power spectral density. Published under licence by IOP Publishing Ltd. -
Proficient technique for satellite image enhancement using hybrid transformation with FPGA
Visual quality of images is improved by digital techniques for the improvement of photographs. The main purpose of image improvements is to process an image to make the output more desirable for a particular use than the original image. This paper proposes a new approach, which improves the picture of the satellite by the use of the SVD DWT concept, the Gaussian transformation DWT and multiwavelet transformation. This suggested approach would convert and approximate the single-colour value matrix of the low-flowing sub-band into one low-frequency and 15 high-frequency sub-bands, and then recreate the improved picture using the inverse transformation. In terms of technical criteria as PSNR, RMSE and CC, this approach can have higher quality and quantitative performance. This paper introduces strategies for improving hardware images using a programmable door array in real-time (FPGA). The suggested algorithm is implemented successfully with Xilinx ISE, MATLAB and ModelSim on different scale satellite images in Verilog HDL. In this article, these algorithms should be simulated and implemented using Verilog HDL. The Spartan-3E from Xilinx is the unit chosen here. 2021 IEEE -
Diagnosis of Retinal Disease Using Retinal Blood Vessel Extraction
The eye is one of the important organs of the human body. In recent times, major parts of the eye are damaged due to various retinal diseases. Major diseases related to the retina are glaucoma, papilledema, retinoblastoma, diabetic retinopathy, and macular degeneration. These diseases can be detected using image processing techniques. These diseases can cause damage to the eye; hence the early diagnosis can prevent the loss of vision. Thus the early stage of rectification may lead to smaller damage than the risky ones. By extracting the blood vessels, various retinal diseases can be identified, and the severity of the disease can also be identified. Some of these diseases in the retina will occur due to hypertension, blood pressure, and diabetics. Thus, the tear in the blood vessels leads to the loss of visuality in human beings. The proposed work consists of image processing techniques such as segmentation, feature extraction, and boundary extraction which lead to the identification of various retinal diseases with a certain level of accuracy, sensitivity, and specificity by using image processing techniques. The training and testing of retinal images are carried out by using the artificial neural network (ANN) classifier for glaucoma detection and support vector machine (SVM) classifier for detecting diabetic retinopathy. 2021, Springer Nature Switzerland AG. -
Equalization of Finite-Alphabet MMSE for All-Digital Massive MU-MIMO mm-Wave Communication
For more than twenty years, growing the performance and efficiency of wireless communications systems using antenna arrays has been an active field of study. Wireless networks with multiple-input multiple-output are also part of the current norms and are implemented around the world. Access points or BSs with comparatively few antennas are used for standard MIMO systems, and the resulting increase in spectral efficiency was relatively modest. A Multiple-Input Multiple-Output platform's capacity is researched where the transmitter outputs are processed and quantified by a set of limit quantizes through an analogue linear combining network. The linear mixing weights and cutoff levels are chosen from with a collection of possible combinations as a function of the transmitted signal. Millimetre-wave networking requires optimum data transmission to various computers on same moment network in combination with large multi-user actually massive. In order to guarantee efficient data transmission, the heavy insertion loss of wave propagation at su ch a faster speed needs proper channel estimation. A new channel estimation algorithm called Beam space Channel Estimation is suggested. From a set of possible configurations, the capacity of a massive stream from which antennas signals are handled by an analog channel as a part of the channel matrix, linear mixture weights and frequency modulation levels are selected. Probable implementations of specific analogue receiver designs for the combined network model, such as smart antenna selection, sign antennas output thresholding or linear output processing. To demonstrate the effectiveness of BEACHES in service and have FPGA implementation results, we are developing VLSI architecture. Our results show that for large MU-MIMOs, mm-wave communications with hundreds of antennas, specially made denoising can be done at maximum bandwidth and in an equipment format. Published under licence by IOP Publishing Ltd. -
A Relative Analysis on the Spotting of Cardiovascular Disease Employing Machine Learning Techniques
Heart is one of the significant segments in the human body since it powers blood to the all the pieces of the body. Blood courses through the vein. Cardiovascular sickness is corresponded with the blockage of vein. The sign of heart sickness depends whereupon condition is impacting an individual. The term coronary illness is ordinarily utilized instead of cardiovascular infection. Dilated cardiomyopathy, Heart failure, Arrhythmia, Pulmonary stenosis, Mitral regurgitation, Coronary artery disease, Myocardial infraction, Mitral valve prolapse, Hypertrophic cardiomyopathy are the sorts of coronary illness. The several machine learning techniques are analyzed to spot heart disease. This paper gives relative investigation of coronary illness expectation utilizing machine learning. 2021 IEEE. -
Growth Of ZnSnN2 Semiconductor Films For Gas Sensor Applications
ZnSnN2 is a member of class of nitride semiconductors which have the additional benefits of earth abundance and non-toxicity. For device applications, NH3 gas detecting senor, which finds use in chemical, pharmaceutical, and food process industries, are fabricated with zinc-tin-nitride (ZnSnN2) thin-films on glass substrate by making use of metal as contacts. The ZnSnN2 sensor is found extremely selective to ammonia (NH3) amongst other gases like ethanol, NO2, H2S and exhibited good detecting responses at room temperature. There are many ways to develop thin films of ZnSnN2, and hence in this work we are trying to find a cost effective, feasible and easier method of synthesis, i.e., chemical vapor deposition method. The first step was the optimization of process parameters to grow Zinc-Tin (ZnSn) thin-films. Later, optimization of the process parameters for the growth of compound ZnSnN2 was completed. The grown films are characterized by material quality using X-Ray Diffraction and UV- Vis spectroscopy. 2022 American Institute of Physics Inc.. All rights reserved. -
Machine Learning Methods to Identify Aggressive Behavior in Social Media
With the more usage of Internet and online social media, platforms creep with lot of cybercrimes. Texts in the online platforms and chat rooms are aggressive. In few instances, people target and humiliate them with the text. It affects victim mental health. Therefore, there is a need of detecting the abuse words in the text. In this paper, a study of machine learning methods is done to identify the aggressive behavior. Accuracy can be improved by incorporating additional features. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Evidence Acquisition in Social Media for Cyber Crime
Social Media forensics a branch of forensics involves in collecting the evidences for the cyber crime. Investigating social media is a complex process which involves the privacy issues for accessing the users, suspects and victims information on social media. Manual processing of social media data is not feasible as it contains large volumes of data. An automated process is needed to incident specification, evidence extraction and for provenance. The need for handling heterogeneity of data as users have accounts with multiple social websites is also explained. This study briefs the existing models and the challenges faced in analyzing with those models. The research goals in this field are also addressed. A pool of tools which can contribute in guarding the solution for cyber crime is also presented. 2022 IEEE. -
An AI-Based Forensic Model for Online Social Networks
With the growth of social media usage, social media crimes are also creeping sprightly. Investigation of such crimes involves the thorough examination of data like user, activity, network, and content. Although investigating social media looks quite straight forward process, it is always challenging for the investigators due to the complex process involved in it. Due to the immense growth of social media content, manual processing of data for investigation is not possible. Most of the works from this area provide an automatic model or semi-automated, and much of the contributions lacks the logical reasoning and explainability of the evidence extracted. Searching techniques like entity-based search and explainable AI add value to the quick retrieval within appropriate scope and explain the results to the court of law. This paper provides a model by adding these new techniques to the basic forensic process. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Explainable AI Method for Cyber bullying Detection
People of all ages and genders are using social media platforms to engage themselves in all sorts of activities. People create profiles on online social networks in order to communicate with one another in this virtual environment. Hundreds or thousands of friends and followers are split across many profiles. Along with the virtual communication in this social media life, cyber-crimes also creep in many distinguished forms to grab user's information and emotionally degrade them with harassment and arrogant behavior. A set of machine learning methods are proposed and used to detect such a bullying behavior. Along with the detection of such an act, the model should also provide the logical reasoning of the evidence extracted. The explain ability of the models classification will give us a view of the way towards portraying a suspect as a bullier. This paper illustrates a machine learning model that works on a twitter data set to suggest the tweets as category bullying or non-bullying. LIME a tool to predict the interpretability of the model is used to depict the performance of model and provides explainability. 2022 IEEE. -
Miniaturized Band Stop Frequency Selective Surface for Stable Resonance Characteristics
In this paper, miniaturized 7.45 GHz resonant frequency band stop frequency selective surface (FSS) is designed. The unit cell dimensions of designed FSS is only about 0.1?0 at the 7.45 GHz. Proposed design involves a crossed dipole metallic element together with meander shape on the substrate. Simulation results provide about 800 MHz bandwidth (7.1 GHz-7.9 GHz) with-20 dB insertion loss. The FSS properties are studied on a unit cell using electromagnetic (EM) solver to observe the characteristics. Proposed FSS demonstrates a stable resonance frequency behavior for the arbitrary angle of incidences in both the polarizations such as TM and TE modes. Thus, the design holds a polarization independent characteristic for all incident angles and polarizations. Finally, the FSS properties are validated by a fabricated array of 311 mm2. 2018 IEEE. -
A Space Vector Modulated Direct Torque Control of Induction Motor with Improved Transient Performance and Reduced Parameters Dependency
Direct torque control (DTC) of induction motors is hampered by high torque and current ripple. Integrating DTC with space vector pulse width modulation (DTC-SVPWM) is one of the frequently used approaches to solve this problem. However, it adds to the computational complexity, increases the number of necessary motor parameters needed for control scheme implementation, and also affects the transient performance of the induction motor; this approach compromises the robustness and simplicity of DTC scheme. To get around these restrictions, a novel control strategy is put forth in this paper. The suggested scheme enhances the steady-state performance and transient response of the motor while preserving the simplicity and robustness of the DTC scheme. To accomplish this, the proposed control scheme operates at varying switching frequencies during transient conditions and constant switching frequencies during steady-state. The suggested speed control method does not employ any rotating reference frame transformations or usage of many rotor parameters for computation, nor does it call for sector identification and operates with a single PI controller. The suggested topology also uses a bus-clamped PWM modulation technique, which lowers the average switching frequency to 2/3 times the actual switching frequency. Thus, switching losses are also decreased. Simulation results show the effectiveness of the proposed topology in enhancing the transient and steady-state performance of the induction motor. The results are compared with the traditional DTC and DTC-SVPWM scheme. 2023 IEEE.