Browse Items (11807 total)
Sort by:
-
A Review of Deep Learning Methods in Automatic Facial Micro-expression Recognition
Facial expression analysis to understand human emotion is the base for affective computing. Until the last decade, researchers mainly used facial macro-expressions for classification and detection problems. Micro-expressions are the tiny muscle moments in the face that occur as responses to feelings and emotions. They often reveal true emotions that a person attempts to suppress, hide, mask, or conceal. These expressions reflect a persons real emotional state. They can be used to achieve a range of goals, including public protection, criminal interrogation, clinical assessment, and diagnosis. It is still relatively new to utilize computer vision to assess facial micro-expressions in video sequences. Accurate machine analysis of facial micro-expression is now conceivable due to rapid progress in computational methodologies and video acquisition methods, as opposed to a decade ago when this had been a realm of therapists and assessment seemed to be manual. Even though the research of facial micro-expressions has become a longstanding topic in psychology, this is still a comparatively recent computational science with substantial obstacles. This paper a provides a comprehensive review of current databases and various deep learning methodologies to analyze micro-expressions. The automation of these procedures is broken down into individual steps, which are documented and debated. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Review of Deep Learning Methods in Cervical Cancer Detection
Cervical cancer is one of the most widespread and lethal malignancy that affects women aged 25 to 55 across the globe. Early detection of cervical cancer reduces burden of living and mortality drastically. Cervical cancer is caused through human papillomavirus transmitted sexually. Since the hereditary aspect is absent in cervical cancer, it can be cured completely if diagnosed early. Cervix cell image analysis is gold standard for classifying cervical cancer. Also known as pap smear, this histopathological test can provide dependable, and accurate diagnostic support. The current study examines the most recent research breakthroughs in deep learning models to classify cervical cancer. Three benchmark datasets are comprehensively described. Selective key classification models were implemented and comparative analysis was conducted on their performance. The findings of this study will allow researchers, publishers, and professionals to examine developing research patterns. 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
A review of hierarchical nanostructures of TiO2: Advances and applications
In the past few decades, extensive studies have been carried out on TiO2 nanostructures having hierarchical morphologies and their applications in diverse fields. By controlling the size and composition of the different TiO2 morphologies, new and improved properties have been realized, leading to significant advancements in materials chemistry, in the broad areas of energy and environment. The improved efficiency and wide applications of these materials are attributed to their physicochemical properties such as stability, efficient electronic and ionic charge transfer, higher specific surface area, etc. In this review, we discuss the different morphologies of hierarchical TiO2 nanoparticles and the properties that have been influenced by these morphologies, enabling their diverse applications. Several composites using the different TiO2 hierarchical forms have been synthesized which too find wide applications. The excellent physical properties of zero, one, two, and three-dimensional TiO2 nanostructures, the relationship between the morphologies of TiO2 nanostructures, and their activities in energy and environment applications have been discussed. 2021 The Author(s) -
A Review of Historical Context and Current Research on Cannabis Use in India
Background: The cultivation and use of cannabis is historically rooted in the Indian subcontinent and this rich heritage of cannabis use dates back to at least two thousand years. Cannabis remains an illicit substance in India despite its changing status globally with many countries legalizing cannabis use in recent years. Scientific research on cannabis use in India has also been sparse. Method: Extensive search of online databases resulted in the identification of 29 original research studies pertaining to one of three areas of cannabis research; a) prevalence of cannabis use b) psychological correlates of cannabis use, c) cannabis use in substance use treatment settings. Findings: We found that most Indian studies used very basic quantitative research designs and had poor scientific rigor. Samples were small, region specific and included only males. Data analyses were limited to descriptive methods. The criteria for cannabis use in most of the reviewed studies were not rigorous and prone to biases. Conclusion & Implications: With changing attitudes and loosening of restrictions on cannabis use, the prevalence of new users is rising dramatically particularly in the college going population. This presents a strong need for research on motivations and attitudes to cannabis use and how those can influence patterns of use, and also the short- and long-term effects of use. More studies with stronger research designs (both cross sectional and longitudinal) are required for the study of cannabis use and this knowledge will be critical for managing the growing substance epidemic, generating public health solutions as well as formulating effective policy frameworks. 2022 The Author(s). -
A review of innovative bond instruments for sustainable development in Asia
Purpose: Advancing the economies in Asia toward meeting sustainable development goals (SDGs) needs an unprecedented investment in people, processes and the planet. The participation of the private sector is necessary to bridge the financing gap to attain this objective. Engaging the private sector can contribute significantly to attaining the 2030 agenda for SD. However, the financial markets in Asian economies are yet to realize this potential. In this context, this paper aims to discuss the state of finance for SD in Asia and identifies innovative financial instruments for attracting private investments for SDs in these economies. Design/methodology/approach: This study relies on published articles, reports and policy documents on financing mechanisms for SD. The literature review covered journal data sources, reports from global institutions such as the UN, World Bank, International Monetary Fund and think-tanks operating in the field of climate change policies. Though the topic was specific to financial market instruments, a broader search was conducted to understand the different sources of sustainable finance available, particularly in Asia. Findings: The investments that are required for meeting the SDGs remain underfunded. Though interest in sustainability is growing in the Asian economies, the financial markets are yet to transition to tap the growing interest in sustainable investing among global investors. This paper concludes that to raise capital from private investors the Asian economies should ensure information availability, reduce distortions and unblock regulatory obstacles. It would also need designing policies and introducing blended financing instruments combining private and public funds. Research limitations/implications: Though the study has grouped Asian economies, the financing strategy for SDGs should be developed at the country-level considering the domestic financial markets, local developmental stage, fiscal capacity and nationally determined contributions. Further research can focus on developing country-specific strategies for using innovative financial instruments. Originality/value: Mobilizing funds for implementing the 2030 Agenda for SD is a major challenge for Asian economies. The paper is addressed to national policymakers in Asian economies for developing strategies to raise capital for SD through private participation. It provides opportunities for revisiting national approaches to sustainable finance in these economies. 2021, Emerald Publishing Limited. -
A Review of Optimization Algorithms Used in Proportional Integral Controllers (PID) for Automatic Voltage Regulators
The voltage in electrical grids is maintained at its nominal value by automatic voltage regulators (AVR). In AVR systems, proportional-integral-derivative (PID) is the most popular controllers due to their robust performance and simplicity. Controlling the parameters of proportional-integral-derivative (PID) controllers, which are used in AVR technology, is a nonlinear optimization problem. Optimization issues are of great importance to both the industrial and scientific worlds. A PID controller's objective function is designed to minimize the settling time, rise time, and overshoot of the step response of the resultant voltage. This paper presents the performance comparison of six optimization algorithms such as Enhanced Crow Search Algorithm (ECSA-PID), Slime Mould algorithm (SMA-PID), Future Search Algorithm (FSA-PID), Whale Optimization Algorithm (WOAPID), Equilibrium Optimizer (EO-PID) and Archimede's Optimization algorithm (AOA-PID) used in recent literatures. The Electrochemical Society -
A review of reinforcement learning approaches for autonomous systems in industry 4.0
[No abstract available] -
A Review of Smart Grid Management Systems Using Machine Learning Algorithms for Efficient Energy Distribution
The smart grid is an intelligent electricity network that uses digital technology to improve the efficiency, reliability, and sustainability of power delivery. Machine learning is a type of artificial intelligence that can be used to analyze data and learn from it. This makes it a valuable tool for the smart grid, as it can be used to solve a variety of problems, such asorecasting energy demand, detecting, and preventing outages, optimizing power flows, managing distributed energy resources, ensuring grid security.In this article, we will review the use of machine learning in the smart grid. We will discuss the different machine learning algorithms that are being used, the challenges that need to be addressed, and the future of machine learning in the smart grid.. The Authors, published by EDP Sciences, 2024. -
A Review of the Detection of Pulmonary Embolism from Computed Tomography Images Using Deep Learning Methods
Medical imaging has been evolving at a steady pace generating enormous amounts of health data, and the use of deep learning (DL) has helped a great deal in processing the detailed data. Deep learning-based methods are used in different medical imaging tasks to detect and diagnose diseases. For example, medical imaging is used to diagnose pulmonary embolism (PE), a commonly occurring cardiovascular disease with high mortality and prevalence and a low diagnosis rate. According to medical experts, PE has resulted in many deaths because of missed diagnoses for the medical condition. Another critical aspect of the disease is the possibility of permanent lung damage if left untreated. The use of deep learning methods in medical imaging is attributed to their ability to use learning-based methods to process enormous amounts of data. However, there are some unique challenges in the detection of PE. PE is not specific in its clinical presentation and is easily ignored, making it difficult to diagnose. Deep learning-based detection methods help a great deal in the disease detection in miniature sub-branches of the alveoli, and images with noisy artifacts easily compared to manual diagnosis. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Review of Various Line Segmentation Techniques Used in Handwritten Character Recognition
Segmentation is a very critical stage in the character recognition process as the performance of any character recognition system depends heavily on the accuracy of segmentation. Although segmentation is a well-researched area, segmentation of handwritten text is still difficult owing to several factors like skewed and overlapping lines, the presence of touching, broken and degraded characters, and variations in writing styles. Therefore, researchers in this area are working continuously to develop new techniques for the efficient segmentation and recognition of characters. In the character recognition process, segmentation can be implemented at the line, word, and character level. Text line segmentation is the first step in the text/character recognition process. The line segmentation methods used in the character recognition of handwritten documents are presented in this paper. The various levels of segmentation which include line, word, and character segmentation are discussed with a focus on line segmentation. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Review on Advanced Nanomaterials for Antibacterial Applications
The management of infectious diseases is one of the major public health challenges of the 21st century. Mutation of the microbes, biofilm formation, and other structural-morpholo-gical behaviors have resulted in pathogens acquiring multi-drug resistance. The development of advanced materials that can provide long-lasting and effective protection against harmful microbes is becoming a need of the hour. Biocompatibility, efficient microbial inactivation, thermal and chemical stability of nanomaterials help to reduce the excessive use of antibiotics and, thus, to overcome antimicrobial resistance. Metal and metal oxide nanostructures, graphene, carbon dots, and other two-dimensional materials exhibit excellent antimicrobial properties. This review provides a comprehensive overview of antibacterial mechanisms and factors that help to inactivate the bacteria by nanomaterials. It also points out the enhanced antibacterial behaviors of the modified nanomaterials for future research concerns. 2023 Bentham Science Publishers. -
A review on anti-cancer plants of India
India has a high level of endemism and a diverse range of floral species. Cancer is one of the most significant challenges facing global health today. The indigenous peoples and residents who live in India have, for a very long time, made use of specific medicinal plants to fight cancer. This practice is still prevalent today. Several different drugs may be utilized in the treatment of cancer. Because of the potential drawbacks associated with such treatments and the development of drug resistance, the quest for new therapies that are both safer and much more effective is still the most challenging field of study. Several cancer medicines used today come from natural sources. We're returning to our old ways because medicinal plants are a good, natural way to make medicines that prevent cancer without causing major side effects. Within the scope of this study, a few herbs traditionally used to treat cancer are looked at to see what they might be good for. The cytotoxicity of these plants, the processes that lead to them, and the different compounds they make were looked into. This study has tried to focus on how these plants fight cancer. The Author(s). -
A Review on Artificial Intelligence Techniques for Multilingual SMS Spam Detection
With social networks increased popularity and smartphone technology advancements, Facebook, Twitter, and short text messaging services (SMS) have gained popularity. The availability of these low cost text-based communication services has implicitly increased the intrusion of spam messages. These spam messages have started emerging as an important issue, especially to short-duration mobile users such as aged persons, children, and other less skilled users of mobile phones. Unknowingly or mistakenly clicking the hyperlinks in spam messages or subscribing to advertisements puts them under threat of debiting their money from either the bank account or the balance of the network subscriber. Different approaches have been attempted to detect spam messages in the last decade. Many mobile applications have also evolved for spam detection in English, but still, there is a lack of performance. As English has been completely covered under natural language processing, other regional languages, such as Urdu and Hindi variants, have specific issues detecting spam messages. Mobile users suffer greatly from these issues, especially in multilingual countries like India. Thus, this paper critically reviews the artificial intelligence-based spam detection system. The review lists out the existing systems that use machine and deep learning techniques with their limitations, merits, and demerits. In addition, this paper covers the scope for future enhancements in natural language processing to efficiently prevent spam messages rather than detect spam messages. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Review on Condition Monitoring of Wind Turbines Using Machine Learning Techniques
This document examines the most up-to-date research on the application of machine learning (ML) techniques in monitoring the conditions of wind turbines. The focus is on classification methods, which are used to identify different types of faults. The analysis revealed that the majority of the research utilizes Supervisory Control and Data Acquisition (SCADA) information, with neural networks, support vector machines, and decision trees being the most prevalent machine learning algorithms. The review also identifies several areas for future research, such as the development of more robust ML models that can handle noisy data and the use of ML methods for prognosis (predicting future faults). The Authors, published by EDP Sciences, 2024. -
A Review on DC-DC Converters with Photovoltaic System in DC Micro Grid
Photovoltaic system is the low-cost source of electrical power in high solar energy regions. The benefits of PV system are like nonpolluting and minimum maintenance. Solar energy changes as per irradiance and temperature and also one factor which reduces the power output is the partial shading in the cells. Hence f o r th, various algo rith ms a r e p u t fo rth to obta in t h e maximum power f r o m t h e PV arrangement and dc-dc converters intend to regulate the supply. The concept of micro grid is emerging as an excellent solution for inter connecting renewable energy sources and loads. DC micro grid is a necessity in today's world. There is wide increase in usage of DC systems in commercial, residential and industrial systems. DC micro grids are dominant in reliability, control and efficiency. Direct current architectures will be used in demand in the future electrical distribution systems. This paper reviews on all above concepts to be used in DC micro grid for future DC applications. Published under licence by IOP Publishing Ltd. -
A Review on Deep Learning Algorithms in the Detection of Autism Spectrum Disorder
Autism spectrum disorder (ASD) is a neurodisorder that has an impact on how people interact and communicate with each other for the rest of their lives. Most autistic symptoms appear throughout the first two years of a child's life. This is why autism is called a behavioral disease. If you have a child with ASD, the problem starts in childhood and keeps going through adolescence and adulthood. Deep learning techniques are becoming more common in research on medical diagnosis. In this paper, there is an effort to see if convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory network (LSTM), and a fusion technique known as convolutional recurrent neural network (CRNN) can be used to detect ASD problems in a child, adolescents, and adults. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Review on EMG-based Pattern Identification Methods for Effective Controlling of Hand Prostheses
The ability of amputees to do daily duties is significantly restricted by upper limb amputation. The myoelectric prosthesis uses impulses from the surviving muscles in the stump to gradually restore function to such severed limbs. Such myosignals are unfortunately tedious and challenging to gather and employ. The process of transforming it into a user control signal after it has been acquired often consumes a significant amount of processing resources. By modifying machine learning strategies for pattern recognition, the factors that influence the traditional electromyography (EMG)-pattern identification approaches may be significantly minimized. Although more recent developments in intelligent pattern recognition algorithms could discern between a variety of degrees of freedom with high levels of accuracy, their usefulness in practical (amputee) applications was less obvious. This review paper examined how well various pattern recognition algorithms for hand prostheses performed. Finally, we discussed the current difficulties and offered some suggestions for future research in our paper's conclusion. 2023 IEEE. -
A review on ensembles-based approach to overcome class imbalance problem
Predictive analytics incorporate various statistical techniques from predictive modelling, machine learning and data mining to analyse large database for future prediction. Data mining is a powerful technology to help organization to concentrate on most important data by extracting useful information from large database. With the improvement in technology day by day large amount of data are collected in raw form and as a result necessity of using data mining techniques in various domains are increasing. Class imbalance is an open challenge problem in data mining and machine learning. It occurs due to imbalanced data set. A data set is considered as imbalanced when a data set contains number of instance in one class vastly outnumber the number of instances in other class. When traditional data mining algorithms trained with imbalanced data sets, it gives suboptimal classification model. Recently class imbalance problem have gain significance attention from data mining and machine learning researcher community due to its presence in many real world problem such as remote-sensing, pollution detection, risk management, fraud detection and medical diagnosis. Several methods have been proposed to overcome the problem of class imbalance problem. In this paper, our goal is to review various methods which are proposed to overcome the effect of imbalance data on classification learning algorithms. Springer Nature Singapore Pte Ltd 2019. -
A review on ethanol tolerance mechanisms in yeast: Current knowledge in biotechnological applications and future directions
Saccharomyces cerevisiae is one of the prominent strains in the brewing and bioethanol industries and has been used for many industrial purposes for ages. Though the organism is an outstanding ethanol producer, the major limiting factor is the stress the organism undergoes during fermentation. One of the significant stresses is the ethanol stress, created by ethanol accumulation in the medium. The ethanol starts to interact with the yeast cell membrane; further, as ethanol concentration increases, it affects a lot of cell organelles. Thereby, cellular activities get disrupted, causing cell death and hence reducing ethanol production. The organism has developed many strategies to overcome this stress by activating the stress response pathway, which regulates many genes involved in modifying the cell membrane cell wall, renaturation of proteins, and altering the metabolism. However, with higher ethanol concentrations, the yeast cells will be unable to tolerate, leading to cell death. Hence, to minimize cell death at higher ethanol concentrations, there is a need to understand the effect of ethanol and its response by the organism; this helps improve the ethanol tolerance of the organism and, thereby, ethanol production. Although many research works are carried out to understand the vital aspect of the tolerance and are reported, very few review papers cover all these points. Hence, this review is designed to include information on all the elements of ethanol tolerance, i.e., ethanol tolerance of different strains of S. cerevisiae, the effect of ethanol on the yeast cells, the mechanism used to tolerate the ethanol, and various techniques developed to improve the ethanol tolerance of the yeast cells. 2024 Elsevier Ltd -
A review on extraction and separation of cellulose fibers from agro wastes
Over the past few decades, there was significant increase in research concerning resources that have certain desirable characteristics like renewability, ease of availability, economic value, excellent mechanicalthermal properties, biocompatibility and biodegradability. Cellulose is one such resource that possesses these characteristics and yet various sources that constitute ample quantities of lignocellulose are discarded, as their peculiarities and applications were not widely known to the population. Agro wastes, which are generated every year at a tremendous rate, are viewed as a promising substrate for the commercial extraction of cellulose. Hence in this review, an appropriate utilization of these agricultural by-products, with respect to extraction of cellulose is discussed, so as to ameliorate their applications in an aim to diminish the disposal rate of essential commodities. 2021 World Research Association. All rights reserved.