Browse Items (16488 total)
Sort by:
-
Identification of Predominant Genes that Causes Autism Using MLP
Autism or autism spectrum disorder (ASD) is a developmental disorder comprising a group of psychiatric conditions originating in childhood that involve serious impairment in different areas. This paper aims to detect the principal genes which cause autism. Those genes are identified using a multi-layer perceptron network with sigmoid as an activation function. The multi-layer perceptron model selected sixteen genes through different feature selection techniques and also identified a combination of genes that caused the disease. From the background study, it is observed that CAPS2 and ANKUB1 are the major disease-causing genes but the accuracy of the model is less. The selected 16 genes along with CAPS2 and ANKUB1 produce more accuracy than the existing model which proved 95% prediction rate. The analysis of the proposed model shows that the combination of the predicted genes along with CAPS2 and ANKUB1 will help to identify autism at an early stage. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Deep Learning Based Face Recognized Attendance Management System using Convolutional Neural Network
In today's digital age, manual attendance tracking is plagued by inefficiency and the potential for inaccuracies, often leading to proxy attendance. The main aim of this research work is to manage and monitor the student's attendance by using face recognition technology. This proposed model is mainly categorized four major modules. First module is database creation. Second module is face detection. Then third module is face recognition and final module is automatic attendance updating process. Student images are compiled to create a comprehensive database, ensuring inclusivity across the class roster. The system utilizes the face recognition library, which relies on deep learning based algorithms for face detection and recognition during testing. This face recognition part Convolutional Neural Network algorithm is used. The system matches detected faces with the known database and marks attendance, ensuring a streamlined and accurate attendance tracking process. This innovative approach has the potential to revolutionize attendance management in educational settings, offering a contactless and efficient solution while mitigating proxy attendance concerns. The proposed model is to compare the accuracy level of face recognition. 2023 IEEE. -
Influence of pulse reverse current parameters on electrodeposition of copper-graphene nanocomposite coating
This work focuses on the influence of pulse reverse current parameters such as duty cycle and frequency on the microstructure and properties of graphene reinforced copper nanocomposite (Cu-Gr) coating. Graphene nanosheets were prepared by a liquid phase exfoliation technique and characterized using FE-SEM and Raman spectroscopy. Cu-Gr nanocomposite coating on stainless steel was prepared by pulse reverse electrodeposition method. The influence of pulse reverse current parameters such as duty cycle and frequency on the coating structure and texture was analyzed. By reducing the duty cycle and increasing frequency, a high amount of graphene co-deposition was achieved. A duty cycle of 40%, frequency of 1000 Hz and stirring speed of 500 rpm produced Cu-Gr coatings with maximum graphene codeposition. XRD analysis showed that the change in duty cycle and pulse frequency influenced the crystal structure, preferred orientation, and crystallite size of the deposit. A high pulse frequency improved the compactness of the composite coating, while longer pulse off-time and application of reverse pulse resulted in highly oriented (220) texture of pure Cu and Cu-Gr nanocomposite coatings. Due to graphene co-deposition, the copper grains became more refined, and hence the microhardness of the composite coating showed a tremendous increase compared to pure Cu coating. The Tafel polarization and electrochemical impedance studies revealed that pulse reverse electrodeposited Cu-Gr coating has higher corrosion resistance than pure Cu coating due to strong (220) texture and barrier effect of graphene. 2021 The Authors -
The role of incentives in fostering green behaviour among the emerging workforce
Green behaviour refers to those behaviours that are pro-environmental in nature. Green behaviour is essential in an organization to ensure that the organization is meeting its organizational sustainability. Employees at all levels must support and participate in green behaviour. One way of encouraging employees to participate in green behaviour is by inducing them through incentives. This chapter dwells on why it is important to introduce green incentives in the workplace to encourage green behaviour. A short survey was conducted among employees in the Indian subcontinent to understand whether incentives can act as a catalyst in motivating green behaviour in the organization. It explores the advantages and disadvantages of bringing green incentives in the organization and the guidelines a company must keep in mind while designing an attractive green incentive system to motivate employees to engage in green behaviour 2024, IGI Global. All rights reserved. -
Workforce Forecasting Using Artificial Intelligence
Workforce forecasting predicts an organizations future demand and supply of the workforce. Each organization has its strategies to manage and track the appropriate workforce. The adequate forecasting technique for the workforce involves data analysis and pattern mining from various data points. Some of the critical attributes considered for the analysis and the forecasting of the workforce requirement include the data such as demographics, economic trends, and labor market conditions; these help in calculating informed predictions about future workforce requirements [1,2]. The primary aim of workforce forecasting is to ensure that an organization has suitable employees with the appropriate skills to meet its business needs by helping organizations make informed decisions about staffing levels, employee training, and other workforce management strategies. 2024 Sachi Nandan Mohanty, Preethi Nanjundan and Tejaswini Kar. -
Conversational Agents and Chatbots: Current Trends
Languages facilitate the communication and interaction process among people. Computers learn to communicate with humans intelligently with the help of conversational agents and chatbots based on Natural Language Processing (NLP). Conversational agents and chatbots are gaining popularity in various applications. The development of chatbots or conversational agents is tightly coupled with an organizations customer service requirement. However, the background procedures that power the bots brain are more or less dependent on Artificial Intelligence-based processes. NLP mechanisms powered by various Deep Learning techniques are often used in the training and development of such intelligent agents. These bots inevitably become more competent as they interact with more people. The interactions between a customer and the bot are usually used as data in further training iterations. Chatbots are likely to respond with faster and more precise suggestions leading to solutions for frequently asked questions. Therefore, the current trends indicate the need for a supplementary system rather than substituting human agents existing customer service. The customer experience and intelligence of the chatbots are improved with the help of data analysis and training with the use of Deep Learning techniques. The chapter covers the current trends of conversational agents and chatbots, how the various Artificial Intelligence techniques have transformed the development of multiple architectures of these intelligent systems, and it compares the different state-of-the-art NLP-based chatbot architectures. 2024 selection and editorial matter, Anitha S. Pillai and Roberto Tedesco. -
VERTEX INDUCED 2-EDGE COLORING AND VERTEX INCIDENT 2-EDGE COLORING OF SOME GRAPH PRODUCTS
Let G = (V, E) be a simple connected graph with vertex set V and edge set E. The vertex induced 2-edge coloring number ?vi2? (G) is the maximum number of colors used in coloring the edges of a graph G such that for each vertex v ? V, at most two edges in the induced subgraph ?N[v]?, generated by the closed neighborhood N[v], receive different colors. The vertex incident 2-edge coloring number ?vin2? (G) of graph G is the maximum number of colors required to color the edges of G such that at most two edges incident to a vertex v in G receive different colors. In this paper, the vertex induced 2-edge coloring number and vertex incident 2-edge coloring number of some graph products such as Cartesian product and strong product are discussed. The ?vi2?(G) and??vin2(G) number in the rooted product of a general connected graphs with some graph classes are also discussed in this paper. Palestine Polytechnic University-PPU 2022. -
VERTEX INDUCED k-EDGE COLORING AND VERTEX INCIDENT k-EDGE COLORING OF GRAPHS
Let k ? 2 be a natural number. Then the vertex induced k-edge coloring number ? vik(G) of a simple connected graph G = (V,E) is the highest number of colors needed to color the edges of a graph G such that the edges of the subgraph induced by the closed neighborhood N[v] of the vertex v ? V (G) receives not more than k colors. The vertex incident k-edge coloring number ? vink(G) of a simple connected graph G = (V,E) is the highest number of colors required to color the edges of a graph G such that the edges incident to a vertex v in graph G receives not more than k colors. In this paper, we initiate the study on ? vik(G) and ? vink(G). We also determine the exact values of ? vik(G) and ? vink(G) for k = 2 for some special graphs. 2023 Yarmouk University. All rights reserved. -
Vertex neighborhood restricted edge achromatic sums of graphs
The vertex induced 2-edge coloring number ?vi2?(G) of a graph G is the highest number of colors that can occur in an edge coloring of a graph G such that not more than two colors can be used to color the edges in the induced subgraph (N[v]) generated by the closed neighborhood N[v] of a vertex v in V (G). The vertex induced 2-edge coloring sum of a graph G denoted as vi2?(G), is the greatest sum among all the vertex induced 2-edge coloring of a graph G which concedes ?vi2?(G) colors. The vertex incident 2-edge coloring number of a graph G is the highest number of colors required to color the edges of a graph G such that not more than two colors can be ceded to the edges incident at the vertex v of G. The vertex incident 2-edge coloring sum of a graph G denoted as vi2?(G), is the maximum sum among all the vertex incident 2-edge coloring of graph G which receives maximum ?vin2?(G) colors. In this paper, we initiate a study on the vertex induced 2-edge coloring sum and vertex incident 2-edge coloring sum concepts and apply the same to some graph classes. Besides finding the exact values of these parameters, we also obtain some bounds and a few comparative results. 2023 World Scientific Publishing Company. -
Edge incident 2-edge coloring of graphs
The edge incident 2-edge coloring of a graph G is an edge coloring of the graph G such that not more than two colors are assigned to the edges incident to an edge e = uv in G. In other words, for every edge e in G, the edge e and all the edges that are incident to the edge e is in at most two different color classes. The edge incident 2-edge coloring number ?n2(G) is the maximum number of colors in any edge incident 2-edge coloring of G. The main objective of this paper is to study the edge incident 2-edge coloring concept and apply the same to some graph classes. Besides finding the exact values of these parameters, we also obtain some bounds. World Scientific Publishing Company. -
EDGE INCIDENT 2-EDGE COLORING SUM OF GRAPHS
The edge incident 2-edge coloring number, ?ein2(G), of a graph G is the highest coloring number used in an edge coloring of a graph G such that the edges incident to an edge e = uv in G is colored with at most two distinct colors. The edge incident 2-edge coloring sum of a graph G, denoted as (Formula presented.), is the greatest sum among all the edge incident 2-edge coloring of graph G which receives maximum ?ein2(G) colors. The main objective of this paper is to study the edge incident 2-edge coloring sum of graphs and find the exact values of this parameter for some known graphs. I??k University, Department of Mathematics, 2025; all rights reserved. -
Genome analysis for precision agriculture using artificial intelligence: a survey
Precision agriculture is a farm management technique which uses the help with the help of information technology to ensure that the crops and soil receive exactly what is required for optimum health and productivity. Genome analysis in plants helps to identify the plant structure and physiological traits. The identification of the right plant genome and the resulting traits help to optimize the cultivation of the plant for better productivity and adaptability. Genome analysis helps the biologist edit the plant genetic makeup structure to make the plant to adapt to the current conditions and thereby reducing the use of fertilizers. For precision agriculture, artificial intelligence techniques help to understand the relationships between plant genome and soil nutrient conditions that help in precision farming effectively reducing the usage of fertilizers by modifying the plants to adapt with the current soil characteristics. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021. -
Applications of Machine Learning and Deep Learning Models in Brain Imaging Analysis
Brain imaging is an umbrella term including many non-invasive techniques that objectively monitor brain function. Such monitoring leads to understanding how the brain works by presenting selected stimuli. More importantly, brain function monitoring allows physicians to diagnose and predict brain disorders. In the last decade, several machine learning and deep learning models have been developed by researchers to process and analyse brain imaging data for the diagnosis, detection, and prediction of brain disorders, such as stroke, schizophrenia, autism, psychosis, and Alzheimers. This chapter reviews the various applications and properties of machine learning and deep learning models for brain image analysis. The chapter also highlights the deep learning models that have either understood the test of time or shown the promise to solve challenging problems involving brain imaging data. The review also discusses various open issues yet to have practical solutions or methodologies with the help of machine learning and deep learning. The research covers a wide range of imaging modalities, disorders and models to expose researchers and practitioners in neurological disorders and machine learning and deep learning to each others field, hopefully leading to fruitful collaborations and practical solutions for processing brain images. 2024 selection and editorial matter, Anitha S. Pillai and Bindu Menon; individual chapters, the contributors. -
Efficient hydrogen evolution reaction performance of Ni substituted WS2 nanoflakes
We have investigated the structural, optical and electrocatalytic hydrogen evolution reaction (HER) performance of pristine, Co and Ni substituted WS2 nanoflakes synthesised by facile hydrothermal method. The XRD pattern confirms the formation of hexagonal WS2 for both pristine and substituted WS2 nanoflakes. The FESEM images validate the flake-like structure for both pristine and substituted WS2. In addition, we have also analysed the Raman and UV-Vis absorbance spectra of the samples. The electrocatalytic studies reveal that the nickel-substituted WS2 (Ni-WS2) nanoflakes show superior hydrogen evolution (HER) performance compared to cobalt-substituted WS2 (Co-WS2) nanoflakes. Hence, we have varied the Ni concentration and investigated the dependence of Ni content on the electrocatalytic performance. It is found that the electrocatalytic performance of the Ni-WS2 nanoflakes increases with an increase in Ni content owing to the modified edge structures. Thus, our studies suggest Ni substitution in WS2 nanostructures can boost electrocatalytic HER performance. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. -
Lora-WAN Powered by Renewable Energy, and Its Operation with Siri / Google Assistant
LoRa WAN is a newly emerged game changing communication technology for sending small data packets of size 50 bytes or less, wirelessly over an area of up to 10 Km without the need of an internet connection. LoRa WAN has its own frequency band and the band is different for every country. This technology is now starring to boost WSN technology better than ever before. This paper aims to, power up a LoRa Enabled Device or a LoRa Gateway by using a reliable dual mode non-conventional energy resource for storage and utilization, find peak performances altering the data rate that can be achieved in a LoRa WAN Communication (using Indoor RAK Gateway), make use data compression techniques, data packet encoding/decoding, Coding Apple Shortcuts, setting up Siri and Google Assistant for voice control and future scope. 2020, Asian Research Association. All rights reserved. -
Efficient Multilingual Language Detection Using Machine Learning Algorithms
Natural Language Processing (NLP) is one of the important technologies in recent days, because language detection this NLP is play a vital role. This research focuses on detecting languages using various machine learning algorithms. FastText, Recurrent Neural Networks (RNN), Support Vector Machines (SVM) algorithms are used for this experiment. The following datasets are used to take this result that is Europarl and Tatoeba. The proposed method is to preprocess, train, and test these models. Evaluation is done by measuring precision, recall, and F1 score of the three algorithms. Results show that RNN provides precision close perfect or near-perfect results in both bilingual and multilingual datasets. SVM performs with high precision and recall, but less than RNN. Its performance slightly decreases as the dataset increases. On the other hand, FastText, although fast and efficient, drops significantly in performance as the dataset grows, especially with the inclusion of a third language. It provides an all-inclusive methodology that has pinned the strengths and weaknesses of each algorithm, providing valuable insight into which one best fit real-world language detection task: RNN with their ability to handle complex sequences, SVM for large-scale high-dimensional sparse features, and FastText for simpler, smaller dataset. 2025 IEEE. -
Impact of anionic concentration on the structural, morphological, and optical characteristics of ZnS quantum dots
ZnS quantum dots exhibit remarkable versatility with novel properties and diverse applications. Highly crystalline ZnS quantum dots with cubic structure were prepared using a simple wet-chemical route by varying the sulphur concentration. This work offers an in-depth study of the influence of sulphur concentration on the optical, surface and structural characteristics of ZnS quantum dots. Structural analysis using XRD affirmed the cubic structure of ZnS. FESEM disclosed non-uniform nanosphere-like morphology, while TEM was utilized for particle size determination. Optical characteristics were assessed utilizing UVVis spectroscopy and photoluminescence spectroscopy. The ZnS quantum dots synthesized with sulphur concentration double that of the zinc concentration in the precursor solution exhibited the appropriate stoichiometry with minimum point defects. Owing to their high crystallinity, small crystallite size, excellent stability, and suitable optical properties, ZnS quantum dots are favourable candidates for optoelectronic applications. Indian Association for the Cultivation of Science 2025. -
Adoption of cashless payment systems among consumers
The primary goal of any national payment system is to ensure smooth circulation of money. It is recognized worldwide that an efficient and secure payment system triggers the economic activity. Efficiency in payment systems in general and electronic payment systems in particular, benefits both customer and country’s economic growth. There are diverse payment systems functioning in the country, ranging from the paper-based systems where the instruments are physically exchanged and settlements worked out manually to the most sophisticated electronic fund transfer systems which are fully secured and transactions settled on a gross, real time basis. Many researchers have used various technology adoption models to predict the adoption of a technology. The main purpose of the study is to investigate the key driving factors responsible for the consumers’ adoption of cashless payment system. A descriptive study method using the paradigm of post - positivism was employed in the study with a sample of 390 respondents from Bangalore who have already used cashless payments. These consumers were selected by purposive sampling using snowball sampling. The study is based on both primary and secondary sources of information collected from various sources. -
Adoption of cashless payment systems among consumers
The primary goal of any national payment system is to ensure smooth circulation of money. An efficient and secure payment system triggers economic activity and electronic payment systems in particular, benefit both the customer s and the country s economic growth. Diverse payment systems function ranging from paper-based ones where the instruments are physically exchanged and settlements worked out manually, to the sophisticated electronic fund transfer systems which are fully secured and transactions settled on a gross, real-time basis. Researchers have used various technology adoption models to predict their usage. The purpose of the study is to investigate the key driving factors responsible for the consumers adoption of cashless payment system. A descriptive study method using the paradigm of post - positivism was employed with a sample of 390 respondents from Bangalore who have used cashless payments. They were selected by purposive sampling using snowball sampling. The study is based on both primary and secondary sources of information. The current study extended the UTAUT with new constructs Habit, Hedonic Motivation, Price Value, Trust, Innovativeness, Perceived Risk, Attitude Towards Using Cashless Payment System and Anxiety. The findings of the study reveal that the factors namely Effort Expectancy, Performance Expectancy, Social Influence, Habit, Facilitating Conditions, Hedonic Motivation, Price Value, Trust, Innovativeness, Perceived Risk, Attitude Towards Using Cashless Payment System and Anxiety have significant influence on the consumers cashless payment usage. A close positive correlation of cashless payment systems usage with the independent variables was seen. The gender, age, income, occupation and educational qualification of the respondents has a significant role to play in their willingness to use cashless payments. The study gives an insight on what the considerations to look into while launching a new payment system are and the means to deal with consumers to adopt and use the same.