International Journal for Modern Trends in Science and Technology
EISSN : 2455-3778
Published by: International Journal for Modern Trends in Science and Technology (IJMTST) (10.46501)
Total articles ≅ 579
Latest articles in this journal
Published: 1 August 2022
Journal: August 2022
August 2022, Volume 8, pp 92-99; https://doi.org/10.46501/ijmtst08s0817
Image recognition includes the categories of object localization, object identification, and image categorization. Despite the fact that these terms are sometimes used interchangeably, object detection and object localization are not the same. Similar to this, categorizing photographs and pinpointing their locations are two separate processes that shouldn't be mixed up. It's important to evaluate how well these models work with data points that haven't been seen before while creating machine learning models for use in the real world. To assess how well different models perform when applied to actual data points, we use an assessment metric. The most popular way for gauging the success of an image localization operation is IoU. "Intersection over Union" is referred to as IoU. In this work, object localization was carried out utilizing a Fast Recurrent Reginal Based Network (OL-FR-RPN). The accuracy and recall of each of the best-matching bounding boxes for the recognised objects in the image are used to measure how good an proposedOL-FR-RPN object recognition model is
Published: 20 July 2022
September 2021, Volume 8, pp 98-101; https://doi.org/10.46501/ijmtst0807016
In today’s life all the organization over the globe are facing a major issue with security’s most common challenging issue of intrusion into their network. This intrusion in the network may lead to security concerns hampering the organizations integrity, confidentiality and availability. To solve this issue there are multiple tools in the market which detects the intrusion in a networkby surveillance of network activities and block the unusual activity detected. These tools and technologies monitor the network for sudden change in activity or behavior and processing them further for analyzing if unusual activity is noticed and inform the administrator about the change in behavior of network.Most of these tool uses the traditional machine learning method for intrusion classification into ‘good’ or ‘bad’ network. In this paper we propose a deep learning model whose architecture compromises of Multi-Layer Perceptron used for intrusion classification and uses GridSearchCV to automate the best model selection for the problem. Using deep learning to solve the problem of intrusion detection in an organization by classification of network has numerous advantages as deep learning performs well on large datasets, unstructured data, better self-learning capabilities, cost effective and scalable. In the implementation of the proposed architecture, we have achieved an accuracy of 98.10% for binary classification and 97.62% for multi-class classification.For hyperparameter tuning as we have used GridSearchCV and used five k-fold cross validation for evaluating the best performing model.
Published: 30 June 2022
September 2021, Volume 8, pp 503-510; https://doi.org/10.46501/ijmtst0806087
Different types of social media sites exist, wherein some of them are LinkedIn, Twitter, Facebook, Instagram, WhatsApp, etc. As the number of social media users increases, the opportunity for the user to express their feelings also increases. Twitter is a choice of many users as it not only allows the users to express their thoughts but to interact with official accounts (PMO, Defense Ministry) which can be seen with a verified tick on the website. In this thesis titled ‘Sentiment Analysis of COVID data extracted via Twitter’, multiple machine learning and deep learning techniques have been researched and implemented to perform sentiment analysis. Moreover, a novel approach using deep learning architecture has been proposed. It is based on a combination of Bidirectional Long Short Term (BiLSTM) neural networks and Convolution Neural Networks (CNN). Prior to implementing the algorithms, the data is acquired by using web-scraping techniques and/or public APIs pertaining to Twitter. A comparative analysis of the efficiency and performance of the proposed technique along with other existing approaches discovered during the literature review phase is also presented. KEYWORDS: Sentiment analysis, machine learning, deep learning, Natural Language Processing
Published: 10 April 2022
September 2021, Volume 8, pp 210-218; https://doi.org/10.46501/ijmtst0802035
The World Wide Web has taken a serious look at new ways for individuals to express their viewpoints and conclusions on a variety of topics, models, and concerns. Clients provide material for a variety of media, such as web gatherings, discussion groups, and weblogs, and provide a robust and open foundation for gaining clout in areas such as promoting and research. Strategy, justification research, market estimations, and a business perspective are all important considerations. Theory study eliminates derivations from publicly available data and organizes the sentiments that the author associates with a given object into one of two specified categories (positive and negative). Make a distinction between the two problems. This follows a Twitter speculation audit cycle for quickly seeking unstructured news. Furthermore, we're looking at several ways to present an itemized positive assessment on Twitter News. It also shows a parametric relationship between operations that are influenced by perceived boundaries. The qualities conveyed in them address the tweets: positive, negative, or fair. This work will in general present the defense appreciate exploring on Twitter; the qualities conveyed in them address the tweets: positive, negative, or fair. Twitter is a web-based application that integrates with a blog and a wide range of contacts, allowing users to send brief 140-character messages. It's a rapidly growing partnership with over 200 million endorsers, 100 million of whom are active clients, and a large portion of them follow Twitter on a regular basis, sending out over 250 million tweets. This study aims to perform Sentimental analysis using deep learning with bigrams and trigrams to classify the tweets accurately.
Published: 11 January 2022
September 2021, Volume 7, pp 14-19; https://doi.org/10.46501/ijmtst0712003
A system named ‘Our Indian Shop’ has been developed and presented in this paper. This system involves an android application, a website and an IVR system for online selling and delivery of agricultural products from farmers to the consumers directly at the market price without the involvement of any middleman. It provides facilities of online shopping of essentials from consumers’ nearby shops as the delivery options will be localized according to pin code to lower the risks of spreading of Covid-19. It also supports selling of groceries, vegetables, and medicines by relevant shop owners directly to the consumers. It enhances the employment as delivery personnel for economically backward people or daily wagers who have lost their livelihood due to the pandemic. The IVR system is to be provided to make all the above facilities available in the offline mode for technologically backward classes, for efficient working of the system in a digital divide environment. The prime objective of this development is to promote social distancing and provide efficient technical solutions for sustainability in the post pandemic world. Our Indian Shop is an all in one platform which provides the online facilities of shopping and selling as well as it will help to enhance the employment and prevent the brokerage charges.
Published: 31 October 2021
Journal: August 2022
August 2022, Volume 7, pp 79-83; https://doi.org/10.46501/ijmtst0710012
We can recognize the emotion of a human by seeing their facial expression and it is an efficient way of human communication. It is the easiest way and essential technology for realizing the human and machine interaction. Facial expression recognition task can be able to classify the face images into various categories of emotions such as happy, sad, angry, fear, surprise, disgust and neutral. In this paper, we are analysing and efficiently classifying each facial image into one of the emotion category. There are numerous approaches to address and solve this problem, out of them convolutional neural network (CNN) is the best approach. Here, we are proposing a novel technique called facial emotion recognition using convolutional neural networks. It is based on the feature extractor to extract the feature and the classifier to produce the label based on the feature. The extraction of feature may be imprecise by variance of location of object and lighting condition on the image. The feature of image can be extracted without user defined feature engineering, and classifier model is integrated with feature extractor to produce the result when input is given. In this way, the CNN approach can produces a feature location invariant image classifier that achieves higher accuracy than conventional linear classifier and our model classified the emotions with 66.62 accuracy.
Published: 31 October 2021
September 2021, Volume 7, pp 159-164; https://doi.org/10.46501//ijmtst0710026
The world is facing significant environmental challenges like improving the standard of air, soil, and water. Currently, industry is that specialize in detecting pollutants (from chemical spills, fertilizer and pesticide run-off), improving industrial and mining sites, treating contaminants and stopping further pollution. A potential solution to those problems is to use nanomaterials. Nanomaterials are often wont to assist with cleaning the environment and even provide efficient energy solutions, like nanomaterial based solar cells additionally to the present, nanomaterials help to enhance the standard and performance of the many consumer products. As results of this, the exposure to made nanomaterials is increasing day-by-day. However, there are both positive and negative impacts on the environment thanks to nanotechnology.Recent advances in nanotechnology have shown numerous societal benefits through the event or improvement of smart materials. Several engineered nanomaterials (ENMs) are produced during the last years which will be found in related sectors like health, food, home, automotive, electronics, and computers (Hansen et al., 2016). The estimated output of ENMs produced was up to 270,000 metric tons/year and during this case considering only SiO2, TiO2, FeOx, AlOx, ZnO, and CeO2 nanoparticles.
Published: 31 October 2021
September 2021, Volume 7, pp 8-16; https://doi.org/10.46501/ijmtst0710002
For welfare of environment, world needs to use more and more renewable energy system not only at the level of industrial but also for domestic load system. Due to much installation cost involving in a solar PV cell/panel based system there is a need of better mechanisms to get maximum utilization and benefits from the system with reliable operation, especially in the case of microgeneration power plant to full fill the minimum desired requirements of domestic appliances to achieved reliable operation. Mostly available PV based inverter system having problem of low output voltage generation and THD producing issue, which needs to a requirements of extra circuit to the control THD and boost up the level of output voltage. In this paper, solar PV based closed loop SEPIC converter by PWM technique to maintain a step up constant dc output voltage with no polarity reversal, low ripple in output and minimizing the requirement of additional filter circuit and fed to single phase inverter. This paper has been focused for the overall single phase PV based SEPIC inverter system implementation, performances and simulated on MATLAB/SPS software to provide low losses, 2% minimum THD and reliable operation in compare with single phase PV based Cuk inverter is used for DC-AC conversion system to compatible with domestic load appliances.
Published: 31 October 2021
September 2021, Volume 7, pp 48-51; https://doi.org/10.46501/ijmtst0710007
Yogurt, often known as yoghurt, is one of the most popular fermented dairy products in the world, with a wide range of health advantages in addition to basic nutrition. In general, yogurt is a nutrient-dense food because of its nutritional profile, and it is a high-calcium source that supplies considerable amounts of calcium in bio-available form. Furthermore, it contains milk proteins with a higher biological value as well as nearly all of the essential amino acids required for optimal health. Yogurt is a probiotic carrier food that may transfer large numbers of probiotic bacteria into the body, providing unique health benefits if consumed. These are commonly referred to as "bio-yogurts." Yogurt is also said to help with lactose tolerance, immunological boosting, and the prevention of gastrointestinal problems. Consumer demand for yogurt and yogurt-related products has surged as a result of these well-known health benefits, and it has become the fastest-growing dairy category in the world. Yogurts are currently available in a variety of styles and variations, each with its own fat content, flavor profile, and texture, making them suited for a variety of meal settings and plates as a snack, dessert, sweet or savory dish.
Published: 31 October 2021
September 2021, Volume 7, pp 61-67; https://doi.org/10.46501/ijmtst0710010
COVID-19 is a global pandemic infecting human life. There are many patients who have recovered from this deadly virus and need to be monitored constantly even when they are at home. IoT plays a vital role in health systems that help to monitor patient’s health conditions. These healthcare frameworks consist of smart sensors to keep a track of patient’s vitals on a real-time basis. These systems will help bridge gaps between the patients and doctors during the pandemic situation. In order to make our system competitive against the already existing devices, we prepared a comprehensive review where we extensively studied other products and compared them to find what's best for the patients.