Browse Items (11810 total)
Sort by:
-
Implementation Strategies for Green Computing
In this chapter, we look at how renewable energy sources can be integrated into the planning, design, and construction of long-term sustainability in green buildings. When it comes to establishing a framework for environmentally friendly building, there are two primary schools of thought. One is related to the use of conventional architecture and low-energy construction material. The fundamental focus of green building design is on using renewable energy solutions for the purpose of managing energy protection. When referring to a green building, either sustainable construction or green construction may be used instead. To guarantee a structure will last for its intended purpose and the environment will not be harmed in the process, sustainable construction practices should be included from the start. Additionally, the economics of renewable energy are presented in this chapter with eco-friendly construction practices that make use of renewable energy sources. 2024 selection and editorial matter, Vandana Sharma, Balamurugan Balusamy, Munish Sabharwal, and Mariya Ouaissa. -
Unobtrusive Engagement Detection through Semantic Pose Estimation and Lightweight ResNet for an Online Class Environment
Analysing student engagement in a class through unobtrusive methods enhances the learning and teaching experience. During these pandemic times, where the classes are conducted online, it is imperative to efficiently estimate the engagement levels of individual students. Helping teachers to annotate and understand the significant learning rate of the students is critical and vital. To facilitate the analysis of estimating the engagement levels among students, this paper proposes a dual channel model to precisely detect the attention level of individual students in a classroom. Considering the possible inaccuracy of emotion recognition, a dual channel is configured with a Lightweight ResNet model for macro-level attention estimation and a 3d pose estimation using Euler angles for Pitch, yaw and roll that is trained, validated and tested on the Daisee database. The Emotional detection extracts the context of Engaged, frustrated, confused and disgust as higher levels of classroom attention cognition while the facial pose coordinates provide the real-time movement of the faces in the video to provide a series of engaged and disengaged coordinates. The Lightweight ResNet Model achieves a 95.5% accuracy and the Pose estimation test is able to distinguish the test videos at 92% as Engaged and Bored on the Daisee Dataset. The Overall Accuracies using the Dual channel was curated to 87%. 2023 Scrivener Publishing LLC. -
Changing Structure of Consumer Buying Behaviour and Expectation in the Digital Era
The growing digital landscape has made a fundamental impact on consumer behaviour. The digital era has totally transformed the buyers and shifted them from the traditional approach to the digital technologies. Todays digitally literate consumers have grown out of the TV advertisement experience to a wide range of digital marketing communications on their smartphone, tabs and laptops and on various social media. Marketers are geared up to identify, reach and engage these latest species of consumers who are agile and active in this new digital ecosystem having multiple devices and multiple channels. This new digital savvy customers give the marketers biggest challenges and rewards over their traditional counterparts. Today customers have some indispensable hopes and demands while they are shopping. The customers expect their needs of products and services should be met at their own time and at their own place, and at reasonable price. Digital era has empowered todays customers by providing them with easy and quick access to voluminous information, compare and contrast between brands and their offerings, facility to purchase the brand offerings from diverse devices and gadgets and also giving them the opportunity to dispense their post-purchase knowledge and experiences. Customer shopping habits have evolved with technology, and companies continue to adapt to maintain relevance. This study examines the consumer behaviour during the digital era. This paper also attempts to understand consumer sentiments and new buying behaviours in this digital era. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023. -
IDS for Internet of things (IoT) and Industrial IoT Network
The Internet of Things (IoT) is a swiftly increasing domain of interconnected gadgets, technologies, and structures that may be achieved in a small, tightly associated environment or can travel across big geographic areas, including Smart Cities. IoT devices are increasingly deployed for numerous goals inclusive of records sensing, accumulating, and controlling. The IoT enhances user affairs by permitting a huge variety of smart gadgets to link and possible information. IoT gadgets are hastily evolving universally while IoT offerings have become pervasive. IoT devices include a big assortment of devices, along with small, embedded sensors, AI assistants, digital cameras, and so on, which can be found in various backgrounds, i.e., Smart Homes, Smart Communities, and Smart Cities. Smart Cities have developed into intriguing areas with technologies consisting of traffic-conscious streetlights which dynamically react to emergencies by editing site visitors styles. Moreover, with the adoption of 5G networks, technologies and techniques throughout towns have become blended. This persevered improvement of IoT advocated the expansion of sophisticated and complicated systems which appreciably adjust the community. However, these technologies have guided to a brand new threat to the security of grids. Many present-day malware assaults, targeted at classic computer systems linked to the Internet, will also be required for IoT gadgets. With those enhancements, malicious actors have found new methods to control their weaknesses. One of the biggest cyber-attacks in instances of terabits in step with 2d operated, infected IoT gadgets harmonized within a botnet provides a massive DDoS assault which disrupts the Internet range for large geographic regions. This attack underlines the increasing hazard posed via uncertain IoT devices. Moreover, attacks that include those are evolving as greater threats as a larger quantity of exposed gadgets is introduced to networks throughout the globe. Their actions are anomalous and higher are the numbers of hazards and assaults toward IoT devices. Cyber-attacks arent new to the IoT, however as the IoT may be deeply interwoven in our lives and societies, traditional protection resolutions are inadequate when managing these dangers. Oftentimes, safety answers are created to run locally on host appliances, i.e., antivirus software, or as standalone machines (i.e. community firewalls and intrusion detection structures (IDSs). However, the IoT has obtained a clean set of community protocols, together with Zigbee, Ant+, and 6LoWPAN, that traditional safety solutions, such as rule-primarily based firewalls and host-based total antivirus software programs, had been not equipped with or have no longer been revised to account for. Moreover, many IoT gadgets suffer from computational, storehouse, or network situations. Due to those constraints, IoT safety answers, especially an IoT IDS, must be lightweight enough, in phrases of the computational, garage, and networking resources, to be living on the devices but sturdy enough to accurately hit upon potential intrusions. Therefore, a holistic method needs to be regular while coming to IoT intrusion detection. IoT devices cant be considered in a vacuum as self-contained machines due to the fact a totally fledged, modern protection answer is just too aid-annoying for constructing on those gadgets. The normal safety of the network necessitates IoT gadgets to be included as associates within a security answer rather than as man or woman nodes. Therefore, green protection of IoT devices could keep millions of net customers away from malicious moves. However, present malware detection techniques are afflicted by excessive computational complexity. Hence, theres a real necessity to protect the IoT, which has therefore resulted in a requirement to completely recognize the threats and assaults in an IoT infrastructure. 2024 selection and editorial matter, Mayank Swarnkar and Shyam Singh Rajput; individual chapters, the contributors. -
ML Algorithms and Their Approach on COVID-19 Data Analysis
This chapter begins with characterizing Supervised Learning and Unsupervised learning and investigates Machine Learning algorithms in every one of the sub domains of Regression, Classification, Clustering, and so forth. It also talks about the engineering of calculations like Linear Regression, Logistic Regression, K-Means, K Nearest Neighbors, Hierarchical, DB Scan, Decision Tree, Random Forest Regression, and Random Forest classifier. Utilization of every algorithm to investigate the dataset will be displayed by carrying out it on renowned dataset model, and output of each piece of code is displayed with their preview. This section likewise takes care of the issue of predicting the future number of COVID-19 cases and the precision behind each model or algorithm is shown and investigated utilizing different measurements dependent on situation or issue articulation, for example, either issue is on forecast or order. This chapter does not focus on the solution of COVID-19 data analysis or expectation, rather it will be followed and will task different models dependent on need with conclusive target being clear comprehension of the Machine Learning algorithms and its execution in Python. 2023 Scrivener Publishing LLC. -
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. -
Comparative Analysis of Various Ensemble Approaches for Web Page Classification
The amount of data available on web pages is enormous, and extracting the relevant information and classifying them is an important task. Web page classification finds applications in web content filtering, maintaining and expanding web directories, building efficient crawlers, etc. Machine Learning methods known for their well-established classification approaches have proved to be effective in web page classification. The present work uses ensemble methods like Bagging Meta Estimator, Random Forest, Adaptive boosting, Gradient Tree boosting, Extreme Gradient boosting and stacking to improve single classifiers results. One dataset is manually created to classify web pages into IoT projects and non-IoT projects. Another publicly available dataset is used to classify publications- and conference-related web pages. The advantage of the Ensemble methods over single classifiers has been validated, and various parameters to tune the Ensemble classifiers have been presented and analysed, with accuracy being the metric for performance. Features like learning rate, number of estimators, and maximum number of features have been tuned besides other parameters, and a comparison has been presented. 2023 Scrivener Publishing LLC. -
Rational Designing of Ni-Ag/C Bimetallic Nanoparticles
Bimetallic nanoparticles have been found to show improved properties due to the synergistic effect between the incorporated metals as a result of electronic charge transfer between them. The importance of using bimetallic particles lies in the high selectivity that they offer. Ni being a reactive metal, was doped with Ag, a highly selective host. In this study, Ni-Ag bimetallic nanoparticles supported on carbon have been synthesized by co-impregnation by using nickel (II) nitrate and silver nitrate as precursors. The catalyst is characterized using XRD, FTIR, DLS, Zeta potential, EDX, SEM, and TEM. The scope of this synthesized catalyst can be extended to several reactions like CO2 reduction reaction, hydrogenation, and industrially important organic reactions. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Biomass Derived Fluorescent Nanocarbon Sensor for Effective Sensing of Toxic Cadmium Metal Ions
Cadmium ion (Cd2+) is common in our surroundings and may readily bioaccumulate into the organism following passage through the respiratory and digestive systems. Chronic exposure to Cd2+ can lead to considerable bioaccumulation in an organism because of its longer biological high life (1030 years), which permanently harms the health of humans and animals. Considering this hazardous effect of toxic Cd2+ metal ions, there is a need to develop a toxic-free and simple sensor synthesized from easily available and biocompatible biomass or natural precursor. Herein we report the effective synthesis and development of a fluorescence sensor from Indigofera tinctoria (L.), a well-known medicinal plant via one step green, hydrothermal synthesis method. The remarkable fluorescence and larger stokes shift make it ideal for fluorescence sensing strategy. This sensor detects potentially toxic Cd2+ assisting fluorescence sensing strategy in the metal ion concentration range from 1 nM to 1 M. The SternVolmer plot exhibits a remarkable linear detection range exhibiting limit of detection (LOD) as 14.74 nM. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Machine Learning- Based Driving Assistance System for Lane and Drowsiness Monitoring
Lane line detection is a vital component when driving heavy vehicles; this concept follows the path for driving a vehicle to prevent the risk of accidentally entering another lane without the drivers knowledge, which could result in an accident. To detect the lane, use frame masking and Hough line transformation with efficient machine learning algorithms, pre-processed and trained adequately for optimum accuracy as per the provided dataset to spot the white markings on both sides of the lane. Long-distance truck drivers suffer from sleep deprivation, making driving extremely dangerous while tired and they ignore the line markings and wander into the wrong lane. This chapter proposes a portable system that does not require any sensors or interference with the vehicles wiring system; instead, a system that fits on a windshield or any surface to monitor the actions of the driver, using computer vision and feature-extracted datasets within a trained neural network model using cameras. This driver-assisted system can detect drowsiness and give an alarm to wake up the driver by identifying the Region of Interest. These predictions are made based on eye movements, and the algorithm generates a score. The higher the score, the longer the time between alarms. 2024 Taylor & Francis Group, LLC. -
Special Military Application Antenna for Robotics Process Automation
A special military application antenna for robotics process automation is presented in the following chapter. An antenna is a device that uses wireless communication. Wireless communications main advantage is protecting our soldiers from undefined enemies. To keep this thing in mind, we have designed a special military application antenna. The presented antenna is useful for defense and satellite communication, including wi-fi and Wimax, which is useful for the robotics automation process. Most of the military robotics automation is based on wireless communication. Our proposed antenna is very useful and capable of receiving or transmitting high signals in terms of GHz. The presented geometry can radiate the large frequency band from 2.9 to 11.6 GHz, which covers the 5G-(I) Sub- 6GHz band and X-Band Communication, with high efficiency. The impedance bandwidth of the radiator is 120%, with an electrical size of .14?x.14?x0.014? in lambda. The antenna is simulated with an FR4 substrate using a CST Simulator. Simulations also investigate the 08-stages evolution process and corresponding S-parameter results are presented. The proposed structure also demonstrates stable radiation patterns across the operating bandwidth. The proposed radiator has a high gain of 6.78 dBi and an efficiency of 89%. Therefore, it is useful for 5G-(I) Sub-6GHz band and X-band military applications, including satellite mobile, Radar, and Satellite microwave communication. 2023 Scrivener Publishing LLC. -
Leveraging Employee Data to Optimize Overall Performance: Using Workforce Analytics
Consistent employee performance is necessary for timely achievement and business success. Many key performance indicators influence an employees organizational performance, such as employee satisfaction, employee work environment, relationship with managers and coworkers, work-life balance, and many more. It becomes critical to regularly understand how these factors are connected to employee performance. One such method that is commonly used in companies is workforce analytics. It is a process that uses data-based intelligence for improving and enhancing management decisions in hiring and constructing compensations in alignment with employee performance. This also helps the management make data-based decisions and predictions, which helps in cost reductions and increases the overall profit. This chapter aims to analyze and report the workforce-related data and visualize the performance of 1,470 employees using published IBM human resources (HR) data made available at https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9781003357070/bb25a486-c036-4524-ab00-446f8eda3fd1/content/www.Kaggle.com xmlns:xlink=https://www.w3.org/1999/xlink>Kaggle.com. The chapter considers the following factors - job involvement, job satisfaction, performance rating, relationship satisfaction, environmental satisfaction, employee tenure, work-life balance, and income level - for data analysis and visualization of employee performance. The chapter aims to adopt descriptive, diagnostic, and predictive analysis using various software like Python, the Konstanz Information Miner (KNIME), and Orange. The visualization will be made using Tableau, Power BI, and Google Data Studio. Thus, the chapter gives a comprehensive insight into the meaning and importance of workforce analytics, different technologies used in workforce analytics, workforce analytics trends and tools, challenges of workforce analytics, and the process of implementation of workforce analytics. 2024 selection and editorial matter, Alex Khang, Sita Rani, Rashmi Gujrati, Hayri Uygun, and Shashi Kant Gupta; individual chapters, the contributors. -
A Novel Auto Encoder- Network- Based Ensemble Technique for Sentiment Analysis Using Tweets on COVID- 19 Data
The advances in digitalization have resulted in social media sites like Twitter and Facebook becoming very popular. People are able to express their opinions on any subject matter freely across the social media networking sites. Sentiment analysis, also termed emotion artificial intelligence or opinion mining, can be considered a technique for analyzing the mood of the general public on any subject matter. Twitter sentiment analysis can be carried out by considering tweets on any subject matter. The objective of this research is to implement a novel algorithm to classify the tweets as positive or negative, based on machine learning, deep learning, the nature inspired algorithm and artificial neural networks. The proposed novel algorithm is an ensemble of the decision tree algorithm, gradient boosting, Logistic Regression and a genetic algorithm based on the auto-encoder technique. The dataset under consideration is tweets on COVID-19 in May 2021. 2024 Taylor & Francis Group, LLC. -
Data: An Anchor for Decision- Making to Build the Future Workforce Management System
In this digital era, the change in business environments and the nature of work lead to skill gaps. Training the workforce on desired skill sets must fill these skill gaps. Data play a crucial role in identifying the skills needed and helping organizations to plan the future workforce. Data is essential for any organizations growth and success in the dynamic market. Knowing the skill set in advance allows organizations and individuals to plan the business and skill requirements well. The way work is done may be impacted by these structural changes as the world is changing swiftly. Building the abilities necessary for the uncertain environments of the present and future environments is also crucial for training the employees. However, such skills must first be acknowledged and appreciated before being developed. Empirical data must support the methodology for valuing such abilities and skills. This chapter outlines the significance of data in skill identification for individuals to be future-ready. Finding the most relevant abilities in a given environment is the first step toward their formalization and acceptance at the systems level. It also presents the importance of creating skill matrices for students and organizations. The skill matrix objectively quantifies skill value for specific occupations and the possible trajectories to acquire those skill sets. This metric will allow policymakers to navigate this fast-changing workforce landscape and focus resources to ensure that skills are needed as students transition into the workforce and have skills that enable them to transition. 2024 selection and editorial matter, Alex Khang, Sita Rani, Rashmi Gujrati, Hayri Uygun, and Shashi Kant Gupta; individual chapters, the contributors. -
Diabetic Retinopathy Detection Using Various Machine Learning Algorithms
The advances in technologies have paved the way to generate huge amounts of data in a variety of forms. Machine learning techniques, accompanied by Artificial Intelligence with its challenging nature help in extracting meaningful information from such data. This will have a great impact on many sectors, such as social media analytics, construction and healthcare, etc. Computer-aided clinical decision-making plays a vital role in todays medical field. Hence, a high degree of accuracy with which machine learning algorithms can detect diabetic retinopathy is really in demand. Convolutional neural networks, a deep learning technique, have been used to recognize pathological lesions from images. Image processing and analytics methods are used and have been trained to recognize the significant complications of diabetes, which cause damage to the retina, diabetic retinopathy (DR). Though this condition does not show any symptoms in its early stages, it has to be screened, diagnosed and treated at the earliest or it may lead to blindness. Deep neural networks have proved successful in screening DR from retinal images and handling the risks that may arise due to the disease. This chapter focuses on detecting diabetic retinopathy in retinal images by using efficient image processing and deep learning techniques. It also attempts to investigate the requirements of image pre-processing techniques for diabetic retinopathy. Experiments are carried out by taking a set of retinal images and predicting the level of diabetic retinopathy on a scale of 0 to 4. Deep learning techniques like CNN and DenseNet are applied and tested. 2024 Taylor & Francis Group, LLC. -
Mining Heterogeneous Lung Cancer from Computer Tomography (CT) Scan with the Confusion Matrix
Early detection of any sort of cancer, particularly lung cancer, which is one of the worlds most lethal illnesses, can save many lives. Life expectancy can be improved and the degree of mortality reduced by adopting the early forecast. While there are different methods like X-ray and CT scans to detect lung cancer cells, CT images resulted as more favored. The 2D images are used for more accurate medical results, such as CT scans. The proposed approach here will address how to interpret the CT images for the Mining Heterogeneous Lung Cancer from Computer Tomography (CT) Scan with the Confusion Matrix. This research will explore how the image conversion can be achieved through different methods of image processing to obtain better results from CT images. The Confusion Matrix helps to estimate inequality in a picture pattern. After the evaluation of the processed images by Confusion Matrix, a final accuracy with a result of 93% is obtained. 2023 Scrivener Publishing LLC. -
Anti-caste Movement and Rise of Dalit Womens Voices from South Asia
There have been cohesive attempts at forging alliance through the sustained efforts of emergent Dalit Civil society network, Dalit academicians and the renaissance of Ambedkarite thought among the Dalit youth around the question of political representation and social justice. This has led to a renewed and greater visibility of caste-based social relations and interactions in the present millennium, which was otherwise, treated as a long-forgotten age-old tradition. The lived experiences of exclusion and atrocities faced by members of the Dalit community especially the violence against women and girls reflect the grim reality of the prevalent casteist and patriarchal society. In this background, the emergence of Dalit Womens collectives raising their voices not just on caste but also on the intersectionality of gender provides a new dimension of analysis based on the critical race theory. Thereby, the attempt has been on forging an alliance and building collective voices. The chapter seeks to highlight the numerous struggles and triumphs along the way made by Dalit Women (also with building alliances with Black Womanists and Feminists Movement) in challenging the way in which feminists discourses have been held leading to rethinking and reimagining womens collectives by way of building solidarities, recognizing the difference of experience and positioning in caste and gender ladder that have influenced access to resources, rights, political representation and decision-making power from the local governance to national level. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023. -
Unraveling the Interplay Between Indian Agricultural Sector, Food Security, and Farms Bill: Key to Sustainable Development Goals
Agriculture, along with its allied sectors, plays a significant role in the economic progress and expansion of any country; despite tremendous economic progress, Indias agriculture sector is in jeopardy for various reasons. Agriculture in rural areas has been the primary source of income for the poor. With the growing susceptibility, policymakers main problems are to design ways to promote sustain-able agriculture to achieve the Sustainable Development Goals (SDGs). The Sustain-able Development Goals emphasize the relevance of agriculture and the need to revi-talize agribusiness worldwide by aiding farmers, increasing investments in research, technology, and market infrastructure, and increasing knowledge sharing. It may lead to spur innovation and give farmers more power. One of the essential advantages of urban agriculture is its potential to boost social capital and civic participation in low-income neighborhoods. As a result, the most critical goal in agricultural develop-ment for food security should be to raise productivity and diversify food production. Diversification of crops should be encouraged among farmers. This would aid in the fight against starvation, but it would also assist in preventing biodiversity loss and strengthen farmer resilience. Hence, our Chapter attempts to analyze the poor food security and what strategies will contribute to the SDG goals to reduce hunger in India as well worldwide. It elucidates a variety of obstacles and opportunities for successful, sustainable, and resilient agriculture. It also covers topics such as the recent agricultural bill and its long-term implications for our growth and a few important takeaways that could help us get closer to our objectives, mainly through the application of technology. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023. -
Edge/Fog Computing: An Overview and Insight into Research Directions
The rapid proliferation of data from applications including IoT, and on-demand access to data have increased dependency on cloud computing, which helps to minimize the overhead related to data storage and maintenance. Applications such as IoT, industrial control, etc. generate data which are highly time-critical in most scenarios. The cloud platform offers permanent storage of this massive amount of data but with comparatively less focus on time-sensitivity. Edge/fog computing are extensions of the cloud computing paradigm and require less response time for time-sensitive data. The edge/fog brings processing and storage closer to the edge of the network, thereby reducing network traffic, delay, and latency. It acts as an intermediate layer between the end devices and the cloud platform, for data collection, offloading, processing, and data management. This chapter addresses the need for fog computing, presents the design model for edge/fog computing, and discusses applications and open issues of implementation. The three-layered network model, the services provided by the edge/fog computing, and a few research challenges of implementation will also be discussed. 2024 Taylor & Francis Group, LLC. -
Reduce Overfitting and Improve Deep Learning Models Performance in Medical Image Classification
A significant role in clinical treatment and educational tasks is played by clinical image classification. However, the traditional approach has reached its peak in terms of implementation. Additionally, using traditional approaches requires a lot of time and effort to remove and choose arrangement features. The deep learning (DL) model is a new machine learning (ML) technique that has proven effective for various classification problems. To alter image classification problems, the convolutional neural network performs well, with the best results. This chapter discusses the importance and challenges of deep learning models in medical image classification and explains some techniques for reducing overfitting and leveraging model performance during model training. 2024 Taylor & Francis Group, LLC.