Browse Items (11807 total)
Sort by:
-
A proposed framework for crop yield prediction using hybrid feature selection approach and optimized machine learning
Accurately predicting crop yield is essential for optimizing agricultural practices and ensuring food security. However, existing approaches often struggle to capture the complex interactions between various environmental factors and crop growth, leading to suboptimal predictions. Consequently, identifying the most important feature is vital when leveraging Support Vector Regressor (SVR) for crop yield prediction. In addition, the manual tuning of SVR hyperparameters may not always offer high accuracy. In this paper, we introduce a novel framework for predicting crop yields that address these challenges. Our framework integrates a new hybrid feature selection approach with an optimized SVR model to enhance prediction accuracy efficiently. The proposed framework comprises three phases: preprocessing, hybrid feature selection, and prediction phases. In preprocessing phase, data normalization is conducted, followed by an application of K-means clustering in conjunction with the correlation-based filter (CFS) to generate a reduced dataset. Subsequently, in the hybrid feature selection phase, a novel hybrid FMIG-RFE feature selection approach is proposed. Finally, the prediction phase introduces an improved variant of Crayfish Optimization Algorithm (COA), named ICOA, which is utilized to optimize the hyperparameters of SVR model thereby achieving superior prediction accuracy along with the novel hybrid feature selection approach. Several experiments are conducted to assess and evaluate the performance of the proposed framework. The results demonstrated the superior performance of the proposed framework over state-of-art approaches. Furthermore, experimental findings regarding the ICOA optimization algorithm affirm its efficacy in optimizing the hyperparameters of SVR model, thereby enhancing both prediction accuracy and computational efficiency, surpassing existing algorithms. The Author(s) 2024. -
Mixed radiated magneto Casson fluid flow with Arrhenius activation energy and Newtonian heating effects: Flow and sensitivity analysis
The characteristics of Stefan blowing effects in a magneto-hydrodynamic flow of a Casson fluid past a stretching sheet are investigated. The effects of radiation, heat source/sink, Newtonian heating, Arrhenius activation energy and binary chemical reaction are considered for heat and mass transfer analysis. The homotopy analysis method (HAM) was utilised to solve the transformed non-dimensionalized equations analytically. The impact of various physical parameters affecting the flow are investigated. Further, the relationship of various parameters on the skin friction and rate of heat and mass transfer was explored using correlation and probable error. A sensitivity analysis was carried out based on the Response Surface Methodology to analyse the effect of Stefan blowing parameter, magnetic parameter and stretching/shrinking parameter on the reduced Nusselt number and reduced Sherwood number. A constant positive sensitivity for the reduced Nusselt number towards the Stefan blowing parameter for all levels of magnetic parameter and stretching/shrinking parameter was found. Further, the reduced Sherwood number indicated a negative sensitivity towards the Stefan blowing parameter. 2020 Faculty of Engineering, Alexandria University -
Wireless Sensor Data Acquisition and Control Monitoring Model for Internet of Things Applications
This article focuses on providing solutions for one important application termed as agriculture. In India, one major occupation for people living in urban and rural areas is agriculture where an economic rate depends only on the crops they yield. In such cases, if an intelligent monitoring device is not integrated then it becomes difficult for the farmers to grow their crops and to accomplish marginal income from what they have invested. Also existing methods have been analyzed in the same field where some devices have been installed and checked for increasing the productivity of horticulture crops. But existing methods fail to install an intelligent monitoring device that can provide periodic results within short span of time. Therefore, a sensor based technology with Internet of Things (IoT) has been implemented in the projected work for monitoring major parameters that support the growth and income of farmers. Also, an optimization algorithm for identifying the loss in different crops has been incorporated for maximizing the system boundary and to transmit data to farmers located in different areas. To prove the cogency of proposed method some existing methods have been compared and the results prove the projected technique produces improved results for about 58%. 2022 SulaimaLebbe Abdul Haleem et al. -
Stacked LSTM and Kernel-PCA-based Ensemble Learning for Cardiac Arrhythmia Classification
Cardiovascular diseases (CVD) are the most prevalent causes of death and disability worldwide. Cardiac arrhythmia is one of the chronic cardiovascular diseases that create panic in human life. Early diagnosis aids physicians in securing life. ECG is a non-stationary physiological signal representing the heart's electrical activity. Automated tools to detect arrhythmia from ECG signals are possible with Machine Learning (ML). The ensemble learning technique combines the power of two or more classifiers to solve a computational intelligence problem. It enhances the performance of the models by fusing two or more models, which extremely increases its strength. The proposed ensemble Machine learning amalgamates the potency of Long Short-Term Memory (LSTM) and ensemble learning, opening up a new direction for research. In this research work, two novel ensemble methods of Extreme Gradient Boosting-LSTM (EXGB-LSTM) are developed, which use LSTM as a base learner and are transformed into an ensemble learner by coalescing with Extreme Gradient Boosting. Kernel Principal Component Analysis (K-PCA) is a significant non-linear dimensionality reduction technique. It can manage highdimensional datasets with various features by lowering the dimensionality of the data while retaining the most crucial details. It has been applied as a preprocessing step for feature reduction in the dataset, and the performance of EXGB-LSTM is tested with and without K-PCA. Experimental results showed that the first method, fusion of EXG-LSTM, has reached an accuracy of 92.1%, Precision of 90.6%, F1-score of 94%, and Recall of 92.7%. The second proposed method, KPCA with EXGB-LSTM, attained the highest accuracy of 94.3%, with a precision of 92%, F1-score of 98%, and Recall of 94.9% for multi-class cardiac arrhythmia classification. (2023), (Science and Information Organization). All Rights Reserved. -
Effect of calcium sulfoaluminate additive on linear deformation at different humidity and strength of cement mortars
The effect of calcium Sulfoaluminate additives (CSA) on the compression and bending strength of mortar, as well as linear deformation of prism samples at different environmental humidity was studied. Test results indicate that bending strength of mortars with CSA and the referent at the age of 28 days are practically equal. Compressive strength of mortars with CSA reduced by 20... 23% for all dosages of CSA. Relative linear deformations depend on the humidity of the environment. At a humidity of 100%, the relative linear deformations are positive and the expansion increases with increasing dosage of the expanding additive. When hardening in dry air at a humidity of 55%, the greatest shrinkage deformations were observed for mortars with CSA. We can conclude that the expanding effect of CSA is fully manifested at high humidity, i.e. under construction conditions, this means very high-quality moisture care for concrete structures. The Authors 2020. -
Artificial Intelligence-Monitored Procedure for Personal Ethical Standard Development Framework in the E-Learning Environment
The changes in the lifestyle of human beings due to the pandemic COVID-19 have affected all walks of human life. As a pillar of human development, the arena of education has a vital role to play in this changing world. The humongous and disruptive technologies that had made inroads into the educational scene as E-learning paved the way for ethical concerns in an unimaginable manner. Artificial intelligence is prudently incorporated for developing an ethical lifestyle for students all over the world. The Personal Ethical Standard Framework would work as a vaccine for the pandemic of the cancerous growth of the unethical habits of learners. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A study exploring the effect of subliminally priming known human faces vs. unknown human faces on product selections by consumers: Unseen motivators
Unconscious thoughts more than often are seen to precede conscious contemplations of the surroundings. The Present chapter attempts to explore how subliminal priming of known and unknown human faces could impact product selection and decision-making time of consumers. 2 (Known face X Unknown face) X 2 (Product selection X Decision-making time) within-subject design was used for the study. A stimulus-priming experiment designed in E-prime software was used to subliminally expose the participants to both known and unknown human faces They were then asked to select a product that they were willing to buy from an option of four products, of which one of the products was primed along with Human face (Known Vs Unknown). The product selection rates as well as the time taken to select the product were recorded. A total of 100 Participants falling in the age category of young adults (18-39) took part in the study. The chapter discusses the results and dives deeper into the implications that they hold in the world of marketing. 2024, IGI Global. All rights reserved. -
Unseen motivators: A study exploring the effect of subliminally priming known human faces vs unknown human faces on consumers product selection decisions
The human mind is constantly being influenced by a vast number of external stimuli that are perceived consciously as well as unconsciously. The chapter attempts to explore how unconscious (subliminal) priming of known and unknown human faces could impact product selection and decision-making time of consumers. 2 (Known face X Unknown face) X 2 (Product selection X Decision-making time) within-subject design was used for the study. A pilot study was conducted to estimate the subliminal time threshold of the population. It was found to be 17ms. A stimulus-priming experiment designed in Opensesame software was used to subliminally expose the participants to both known and unknown human faces. They were then asked to select a product that they were willing to buy from an option of four products, of which one of the products was primed along with human face (known vs. unknown). The product selection rates as well as the time taken to select the product were recorded. A total of 100 participants falling in the age category of young adults (18-39) took part in the study. 2024, IGI Global. All rights reserved. -
Decolonizing the Home at Home in the Pandemic: Articulating Women's Experience
Feminism bears the promise of liberation of and equality for women. Reading and teaching feminist texts, within the academia and in activist spaces, has provided the opportunity to explore what it means to become and be a woman. This article explores the experience of teaching a course on women's writing at the undergraduate level during the COVID-19 pandemic. Normally, a course on feminist writings is an occasion for self-reflection, thereby providing an opportunity to establish a dialogue between the domestic and the public. Such dialogues took place in secure institutional spaces such as classrooms or conference halls, without the intrusion of the domestic. However, as the teacher-student interaction shifted to an online mode during the pandemic, all the participants in this dialogue, including the instructor and the students, found themselves in domestic spaces, with family members listening. The article chronicles the anxieties of a woman instructor, as she teaches feminist texts from home to learners who are sitting behind computer screen in their homes and the possible impact of feminist ideas on the domestic spaces of all participants. 2022 The Author(s). Published by Oxford University Press on behalf of the English Association. All rights reserved. -
God has signed: Nature, divinity and mysticism in the poetry of Kuvempu
Kuvempu wrote a large number of poems on the mysteries of nature. Kuvempu hails from the heart of Western Ghats and he spent his childhood and youth exploring the forests around his house. Untrammelled nature was both mysterious and beautiful; hence nature turned out to be a primary inspiration to write poetry. Kuvempu looks outward, seeking to comprehend the oneness of all in nature through his senses. But he is also struck by the inability to comprehend and explain nature through senses. Often he expresses his awe at natural sights such as dawn (which appears to him as a God's signature) or the greenery of Western Ghats (which seems to have painted everything in nature in green, including poet's soul and the blood in the stomach). This leads Kuvempu to resort to mysticism in order to relate, comprehend and sing about nature. He sees in nature the divine presence. The paper will analyze poems such as Devaru Rujumadidanu, Ba Phalguna Ravidarshanake, and Prakriti Upasane, and explore the poetic perception of nature as divine through mysticism. 2014 Journal of Dharma: Dharmaram Journal of Religions and Philosophies (Dharmaram Vidya Kshetram, Bangalore). -
-
Computational investigation into the structure, effect of band gap energies, charge transfer, reactivity, thermal energies and NADPH inhibitory activity of a benzimidazole derivative
This work contains computational investigations of a benzimidazole derivative consisting of density functional theory, electronic structure and biological evaluation of a benzimidazole derivative. Density functional theory evaluation were conducted, starting from geometry optimisation, followed by the molecular electrostatic potential, spectral analyses, polarizability studies and thermodynamic analyses via the frequency calculations. Solvent frontier molecular orbital analyses, impact on the properties of the molecule were modelled with the IEFPCM model of solvation. Topological analyses helped to ascertain the molecule's electronic structure. Biological assessment included pharmacokinetic property evaluation and molecular docking. Pharmacokinetic descriptors were generated using online tools and the molecule was assessed for its efficacy as a drug molecule by comparing with the rules concerning drug-likeness and analysing the descriptors relating to absorption, distribution, metabolism, excretion and toxicity of the molecule. Docking of the molecule with the two targets, 7D3E and 3A1F, yielded a good binding energy of ?7.39 and ?5.81 kcal/mol respectively. 2024 Elsevier B.V. -
Quantum computational, solvation and in-silico biological studies of a potential anti-cancer thiophene derivative
Heterocyclic molecules display a wide spectrum of properties that span both material and biological domains. Material properties stem from their interactions in the bulk, where a large number of molecules of the same type get together resulting in an enhancement of properties. However, biological properties emanate from the interaction of a single or a few molecules with a biologically functional macromolecule. Computational tools offer a particularly useful way of theoretically studying molecules to arrive at a conclusion regarding such properties, even though they may vary when experimentally evaluated. This study concerns itself with the theoretical investigation comprising density functional theory calculations, topological analyses and in-silico biological evaluation of a thiophene compound, i.e. the title compound. Density functional theory was used to compute properties of the title molecule and their variations in unsolvated and solvated phases using Gaussian 09. The molecule in solvent phases encompassing organic polar protic, organic polar aprotic and inorganic polar protic nature have been subjected to theoretical investigations. The suitability of the molecule for deployment as a modern optical material is examined with positive results. Topological characteristics of the molecule were evaluated using Multiwfn 3.8 to examine electron density distribution and the possible resulting covalent, non-covalent and weak interactions because of such distribution. The potency of the molecule towards brain cancer was evaluated by molecular docking with Auto Dock Tools against two brain cancer protein targets 6ETJ and 6YPE with a good docking score of ?6.63 and ?6.21 kcal mol?1 respectively and the resulting interactions visualized and its pharmacokinetic properties obtained using online tools. 2024 Elsevier B.V. -
Analytical Results of Heart Attack Prediction Using Data Mining Techniques
In the modern era of living a fast lifestyle, people are not more conscious of their food eating and lifestyle. Due to these reasons, the chances of having a cardiac-related disease have risen drastically. This paper has studied the various supervised and unsupervised machine learning algorithms in comparative methods with best accuracy. Models like classification algorithms, regression algorithms, and clustering algorithms have been used for this paper. This research paper majorly focuses on patients with certain medical attributes that indicate a higher risk of heart disease. The model almost gives a good accuracy for all the regression and classification models when compared to the clustering models. Among all the algorithms, random forest and decision tree gives better accuracy 2023 IEEE. -
Sentiment Analysis on Live Webscraped YouTube Comments Using VADER Sentiment Analyzer
After the covid disease came in the beginning of 2020s, the amount of people using social medias has increased dramatically. So as an effect of that, the viewers and engagement in one of the worlds largest platform by google called YouTube also increased. So many new content creators also born during these times. So this project is getting the sentiment from the audience or user to the content creators by which they can improve their content quality. This research holds promise in harnessing the power of sentiment analysis to enhance the overall YouTube experience and inform content creators and platform administrators in their decision-making processes. Understanding these trends is vital for content creators, as it can offer invaluable insights into viewer engagement and preferences. By gaining a deeper understanding of how viewers react to content, creators can refine their strategies, tailor their content to their audience, and enhance the overall quality of videos. By incorporating sentiment information into recommendations, the platform can suggest videos that resonate more effectively with users, thereby increasing engagement and satisfaction. The identification of negative sentiment and harmful comments enables YouTubes content moderation systems to proactively address issues such as hate speech, harassment, and toxicity. This, in turn, contributes to a safer and more welcoming space for users to share their thoughts and opinions. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Power Efficient e-Bike with Terrain Adaptive Intelligence
Electric bicycles or e-bikes are gaining momentum in the market as they are offering a smooth, noiseless and pollution free option for individual transportation in cities as well as in countryside. E-bikes are usually with a battery powered electric motor drive with an additional option for pedaling. In this work a low cost e-bike was designed and developed with a brushless DC hub motor with controllers. For smart control, smartphone was used a console and the e-bike can be controlled using a mobile application which was connected to the e-bike through Bluetooth. The controller will pick the gradient of the terrain and will control the power of the motor, which results in energy saving. Predicted range of the e-bike, speed, acceleration and total distance covered were displayed in the console along with the geographical position on the map and throttle control options. The bike with the proposed control tested and the results were giving a reduction in current drawn from the battery. 2019 IEEE. -
Assessing Land Use Transformation in Kanhangad Town: A Special Emphasis on Wetland Ecosystems
Kerala, renowned for its lush landscapes, is facing environmental challenges due to rapid urbanization, particularly in Kanhangad. This area, notable for its unique wetland ecosystem crucial for biodiversity and human livelihoods, is experiencing a conflict between residential development and wetland conservation. A comprehensive study in Kanhangad, employing diverse data sources such as open-source data, Google Earth Satellite Imagery, OpenStreetMap, and tools like ArcGIS, provides a detailed analysis of land use and its environmental impacts. The study combines digital data analysis with physical surveys to understand the ecological and developmental status comprehensively. The study reveals a dominant trend in Kanhangad's land use, with residential areas comprising 52% of the total land, mostly large, detached single-family homes. This reflects a societal shift towards viewing homes as status symbols, contributing to natural resource depletion. The research underscores the need for sustainable, low-cost housing, suggesting vertical housing as a potential solution to balance residential demands with environmental conservation. Kanhangad's wetlands, essential for local biodiversity and livelihoods, face threats from urban development and infrastructural expansion. The study shows a drastic reduction in wetland area, from 12.9 km in 2004-05 to just 1.66 km by 2020-21, indicating severe ecological degradation. Despite the Kerala Conservation of Paddy land and Wetland Act of 2008, which aims to protect these ecosystems, its limited effectiveness is evident from the ongoing depletion of wetlands. This situation calls for stricter enforcement of environmental regulations and greater public involvement in conservation efforts. Furthermore, the research examines the Kerala Paddy and Wetland Conservation Act-2008, analysing its role and effectiveness in local environmental governance. The Act, focusing on prohibiting wetland and paddy land conversion, is vital for regional conservation. However, gaps in its implementation are highlighted, especially considering the exacerbation of the 2018 and 2019 Kerala floods due to land conversion practices. The study emphasizes the urgent need for more robust environmental protection measures. 2024 by authors. All rights reserved. -
The effect of non-thermal argon plasma treatment on material properties and photo-catalytic behavior of TiO2 nanoparticles
In this paper, a brief study on the effect of non-thermal plasma generated with argon carrier on material properties and photo-catalytic reduction behavior of TiO2 is presented. Commercially available TiO2 nanoparticles (20 nm size) were subjected to Ar cold plasma at different time durations. Then the plasma treated materials were explored for chemical reduction of carbon dioxide (CO2) into methane (CH4) using sunlight as photo-irradiation source. The results show that the non-thermal plasma affects the material properties of TiO2 such as UV-visible absorption, XRD patterns and Raman scattering significantly and also the enhancement of CH4 yields in CO2photo-chemical reduction. 2020 American Institute of Physics Inc.. All rights reserved. -
Exploring The Multifaceted Benefits Of Strobilanthes Jomyi P. Biju, Josekutty, Rekha & J. R. I. Wood : A Comprehensive Pharmacognostic Investigation On Its Medicinal And Insecticidal Properties
Plant-based medication, is an established practice in Indian medicine, initially newlineinvolvedin the direct use of raw plant parts for treating various health conditions. Later, valuable components are identified, isolated, and utilized to treat diseases. The newlineStrobilanthes Blume genus has a rich therapeutic history around the globe, especially in countries such as India, China, Myanmar, and Thailand. Strobilanthes jomyi, a recently identified species found in Kerala, India is still in wide use by tribal communities in the Kasaragod district for wound healing. This study aimed to evaluate the microscopic, macroscopic, organoleptic, fluorescent, physicochemical, mineral composition, phytochemical, Gas Chromatography Mass Spectrometry, antioxidant, anthelmintic, insecticidal, antimicrobial, and cytotoxicity activities of S. jomyi leaves, stem, and root. The different vegetative parts were subjected to Soxhlet extraction using methanol as a newlinesolvent and analysed using standard Protocols. Macroscopic andmicroscopic examinations revealed non-glandular trichomes and paracytic stomata in the leaves, raphides in the stem and petiole, and tannin cells in the root. Cystoliths were observed only in the petiole. Powder analysis exhibited the presence of fibres, trichomes, palisade cells, spiral xylem vessels, bordered pit vessels, and raphides. The leaves contained higher phenolics, flavonoids, carbohydrate, protein, proline, and chlorophyll content compared to the root and stem. The methanolic extract of leaves showed higher antioxidant activities than the root and stem. GC-MS analysis identified bioactive compounds such as 2,4-di-tert-butyl phenol, phytol,squalene, phenol, neophytadiene, and lupeol in the root, stem, and leaves. All vegetative partsof S. jomyi exhibited excellent anthelmintic activity, with the highest newlineobserved in the leaves, followed by the root and stem. Insecticidal activity was only newlineobserved in the leaf extract. Anti-microbial and anti-cancerous activities were remarkable newlineacross all vegetative parts. -
An Approach for Detecting Frauds in E-Commerce Transactions using Machine Learning Techniques
This paper is primarily focused on E-commerce fraud detection using machine learning techniques. There are many different ways to detect E-commerce fraud using machine learning approach. In this work, comparison study is conducted between various available machine learning algorithms to detect the online frauds. During the comparative study, focus is underlined on comparison of all the algorithms to identify the fraud transactions. When compared to other algorithms, such as support vector machine, Decision Tree, K-nearest neighbour and Random Forest, it has been observed that Logistic regression gives better result among all machine learning algorithms. 2021 IEEE.