Volume 9 | Issue 6 |

 Abstract

Covid even though has created havoc but has presented many business sectors a great opportunity for who were able to acclimatize to work from home (WFH) practices. Such crisis mandates not only the business but employees doing WFH also need to fine-tune this model with learning how to carry it out appropriately. This WFH model has both opportunities and threats on both the ends i.e., business and employees. While business can draw a lot of benefits in terms of widening talent pool, saving costs etc. Also, when employees are working from home, they are working with the same business having same responsibilities, deliverables and need to meet the targets with no change in timelines. Employees working from home have the opportunity to work in a stress free environment with good health and wellbeing. However, the challenges are also faced by both the ends and these challenges need to be mitigated in order to make the WFH truly successful.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Remote work, work from home, WFH

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Python, Machine Learning, Convolutional Neural Network

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Word affiliation, uncovering mental portrayals and associations of humans, has been generally concentrated in brain science. However, the size of accessible acquainted signal reaction words is harshly limited because of the customary physically gathering approach. In the meantime, with the huge accomplishment in (NLP) technique tasks, an extremely huge measure of plain messages can be effectively obtained. This proposes a knowledge about discovering affiliation words from the content corpus rather than physically assortment. This paper moves toward proposing a profound learning-based structure for programmed affiliation word extraction as a unique endeavor. The Framework comprises two phases of affiliation word identification and machine affiliation network development. Specifically, consideration instrument-based Reading Comprehension (RC) calculation is investigated to discover important affiliation words consequently. To approve the worth of the extricated affiliation words, the connection coefficient between semantic similitudes of a machine and human affiliation words is presented as a viable estimation for assessing affiliation consistency. The investigation further confirms that the machine affiliation words are for the most part steady with human affiliation words as for semantic likeness, which features the promising usage of the machine affiliation words, later on, explores both brain science and NLP.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Text Extraction, NLP Technique, Deep Learning, Transcript, Word Affiliation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Over the years, an explosive growth in the number of items in the catalogue of e-commerce businesses, such as Amazon, Netflix, Pandora, etc., have warranted the development of recommender systems to guide consumers towards their desired products based on their preferences and tastes. Some of the popular approaches for building recommender systems, for mining user derived input datasets, are: content-based systems, collaborative filtering, latent-factor systems using Singular Value Decomposition (SVD), and Restricted Boltzmann Machines (RBM). In this project, user-user collaborative filtering, item-item collaborative filtering, content based recommendation, SVD, and neural networks were chosen for implementation in Python to predict the user ratings of unwatched movies for each user, and their performances were evaluated and compared.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Recommender systems, collaborative filtering, neural network, machine learning, RMSE

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In 2019, Corona virus Disease (COVID-19) spread seriously in more than 180 countries, causing a global crisis. The lack of immunity to COVID-19 in the absence of aggressive treatment increases the vulnerability of the population. Due to the lack of vaccines, social distance (suspicious activity against COVID-19) is the only way to combat this pandemic. Motivated by this concept, this article describes a deep learning-based framework for automating social distance tasks with surveillance videos. The generated boundary box helps identify clusters or groups of people that meet the neighborhood properties calculated using the pair wise vectorization method.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

suspicious activity, deep learning

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

With the widespread use of credit cards, fraud has become a major problem in the credit card industry. As a result of theft, businesses and banks are reluctant to disclose the amount of money lost. Another issue with calculating credit card fraud losses is that it can only estimate the number of frauds that have been detected. It becomes harder to monitor the behavior and pattern of such transactions. Therefore, the assessment of fraud is necessary on a regular basis. The technologies like machine-learning, data-mining, and other artificial technologies are used to resolve this. In this regard, enhancing effective fraud detection using machine-learning methods is critical for empowering fraud investigators with these losses. This research paper explores how several Machine Learning models are being used to diagnose suspicious transactions. Machine learning contributes to the critical function of detecting credit card fraud during transactions. The dataset sampling methodology, selection of variables, and methods used for identification always have a massive influence on fraud detection efficiency. This system provides the necessary characteristics for monitoring both illegal and legal transactions. Classification Techniques like Decision Tree, K-nearest Neighbors algorithm, Logistic Regression, Gaussian Naive Bayes, and Artificial Neural Networks are demonstrated to identify fraudulent transactions. By training these techniques and evaluating them on various factors such as precision, accuracy, recall, and visualized the ROC curve. Based on the criteria of different methods, the best approach for detecting credit card fraud is chosen. As opposed to other algorithms, this paper shows that Decision Tree is the best optimal approach and can be used to detect further frauds

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Neural Networks; Decision Tree; K-Nearest Neighbors; Logistic regression, Gaussian Naive Bayes.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Forensic Investigation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Theme of Love and Revenge in the Novel Wuthering Heights

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

With the advent of Information Technology (IT) and Data Sciences, businesses now have the opportunity to better understand and forecast consumer demands using quantitative methods. The use of Big Data to better understand business processes and results is an evolving IT trend that has piqued the interest of researchers and practitioners. Big Data systems have the potential to assist businesses in better understanding complicated business relationships by delivering knowledge that was previously unavailable. Previous research has shown that providing an effective supply chain gives a producer a competitive advantage over its competitors, how data from online marketplaces or e-commerce allows manufacturers to better understand product demands is a field that has not been thoroughly researched by previous researchers. This paper provides a comprehensive survey about the ongoing researches done in this field by reviewing the articles of the other computer scientists. This paper paves a better way for the upcoming researchers in this field.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Web scraping, Neural Network, Locating files in websites, online sale promotion strategies.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The most important part of a city is the people who live in it. Therefore, wellness and health are indispensable for the Smart Cities concept. In this paper, we introduce an approach that combines genetic research with environmental monitoring in real time by using an integrated system of IT and IOT that helps to understand better and prevent diseases, improving the quality of life of the citizens. We are working to develop a virtual platform that creates and establishes correlations between the genetic information of the user and their environment. The principal advantages of this project are to allow health care providers, governments and citizens to make smarter decisions oriented to health care, implementing Health Information Technologies (HIT) and improving the concept of Mobile Health (mHealth), all of these based on the Quadruple Helix Innovation model.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

genetics, HIT, smart health, predictive modelling, smart cities

  License

Creative Commons Attribution 4.0 and The Open Definition