The traditional “one size fits all” education system has been largely criticized in recent years on the ground of its lacking the capacity to meet individual student needs. Global education systems are leaning towards a more personalized, student-centered approach. Innovations like Big Data, Machine Learning, and Artificial Intelligence (AI) have given the modern-day technology to accommodate the distinctive features of human beings - smart machines and computers have been built to understand individual-specific needs. This opens an avenue for “personalization” in the education sector. From, mushrooming of Education Technology (EdTech) start-ups to government funding in AI research, it is evident that the next generation educational reforms would take a quantum leap forward piloted by Big Data analysis and AI. The objective of this paper is to organize the vast literature on the use of AI for personalization of education and to shed light on the key themes by which an AI-driven approach makes structural modifications to the existing education system. To this effect, the paper employed a systematic review using a Human-In-The-Loop natural language processing model of past two years' literature (2019–2021) in English language from IEEE Xplore on countries China, India and the USA. This process yielded more than 2000 search results at first and these were eventually shortlisted to 353 relevant papers for in-depth analysis. Being the pioneers in EdTech innovations, insights from research done in these three countries provides valuable input for the development of global education systems and research. The findings bring forward AI's success in catering to specific learning requirements, learning habits, and learning abilities of students and guiding them into optimized learning paths across all three countries. Not just that, it is also evident from the literature that AI augments educational content, customizes it for any individual according to their needs, and raises the flag of caution for anticipated learning difficulties. This recalibrates the role of instructors as well as optimizes the teaching-learning environment for a better learning experience. The upward trajectory of educational development with AI opens a new horizon of personalized education for the future generation, but also comes with its challenges. Data privacy issues, availability of digital resources, and affordability constraints have been reported in the recent literature as impediments in the way of promoting such technologies for day-to-day practice. 

Personalized education and Artificial Intelligence in the United States, China, and India: A systematic review using a Human-In-The-Loop model

Separating household waste into categories such as organic and recyclable is a critical part of waste management systems to make sure that valuable materials are recycled and utilised. This is beneficial to human health and the environment because less risky treatments are used at landfill and/or incineration, ultimately leading to improved circular economy. Conventional waste separation relies heavily on manual separation of objects by humans, which is inefficient, expensive, time consuming, and prone to subjective errors caused by limited knowledge of waste classification. However, advances in artificial intelligence research has led to the adoption of machine learning algorithms to improve the accuracy of waste classification from images. In this paper, we used a waste classification dataset to evaluate the performance of a bespoke five-layer convolutional neural network when trained with two different image resolutions. The dataset is publicly available and contains 25,077 images categorised into 13,966 organic and 11,111 recyclable waste. Many researchers have used the same dataset to evaluate their proposed methods with varying accuracy results. However, these results are not directly comparable to our approach due to fundamental issues observed in their method and validation approach, including the lack of transparency in the experimental setup, which makes it impossible to replicate results. Another common issue associated with image classification is high computational cost which often results to high development time and prediction model size. Therefore, a lightweight model with high accuracy and a high level of methodology transparency is of particular importance in this domain. To investigate the computational cost issue, we used two image resolution sizes (i.e., 225×264 and 80×45) to explore the performance of our bespoke five-layer convolutional neural network in terms of development time, model size, predictive accuracy, and cross-entropy loss. Our intuition is that smaller image resolution will lead to a lightweight model with relatively high and/or comparable accuracy than the model trained with higher image resolution. In the absence of reliable baseline studies to compare our bespoke convolutional network in terms of accuracy and loss, we trained a random guess classifier to compare our results. The results show that small image resolution leads to a lighter model with less training time and the accuracy produced (80.88%) is better than the 76.19% yielded by the larger model. Both the small and large models performed better than the baseline which produced 50.05% accuracy. To encourage reproducibility of our results, all the experimental artifacts including preprocessed dataset and source code used in our experiments are made available in a public repository.

/pdf/solid-waste-image-classification-using-deep-convolutional-3n74psrb.pdf

Solid Waste Image Classification Using Deep Convolutional Neural Network

Introducing a new method of automatic cleaning of the PV array surface using a suction robot

: The nation and the world are challenging a massive issue of junking, separation and reusing of solid waste and unhappy operation of these wastes are dangerous to mortal well- being also natural frame to meetly deal with the waste it must be separated, conveyed and arranged to drop the troubles to the public life. The proposed strategy is simple and cost-effective. The separation of dry waste is proposed to classify the trash into metallic waste and plastic waste. Since it's dry waste isolation, the fashion uses a humidity seeing module to descry wet waste and if tasted therefore stops working. The essence is linked by using a essence sensor and the plastic by using a plastic seeing module after that they will be ditched into the allocated bins. However, plastic and humidity detectors also the object will be ditched in other accoutrements caddy, If any other dry waste is placed which isn't detected by essence. Whenever the lockers are filled the authorized persons will get notified and uploaded to pall.

Arduino based automatic waste segregation

Customer service plays a crucial role for a company. As an important aspect of e-commerce companies, they would be required to directly interact and try to solve customers’ problems that might occur anywhere and anytime. However, the limitation of human man hours became a barrier to overcome customers’ problems. On one hand, the rapid development of technology was predicted to replace the traditional human customer service with an Artificial Intelligence agent. On the other hand, this replacement affects the customer satisfaction. This paper performed a study literature review to discover the effect of chatbots and its impact towards customer satisfaction. In an e-commerce customer service use case, chatbots could be implemented in a number of methods. The methods implemented by chatbots are avatar-based, verbal-based, text-based, and menu-based. Research showed that text-based chatbot is the most commonly used methodology and has advanced the most, where some are implementing higher level machine learning methods, such as deep learning. The usage of such chatbot in e-commerce customer service systems will lower the cost but might also lower customer satisfaction, due to reasons such as unsatisfying answers and inhuman behavior. Research showed that even a more sophisticated chatbot doesn’t always mean higher customer satisfaction, even with high accuracy ratings. To look into customer satisfaction, this paper has identified 4 aspects of a chatbot that are relevant to customer satisfaction, which are privacy, reliability, personalization, and responsiveness. Chatbots currently excel in some of these quality measures, but require further research to effectively replace human customer service agents.

Study Literature Review: Discovering the Effect of Chatbot Implementation in E-commerce Customer Service System Towards Customer Satisfaction

In this paper, we have proposed a fully automated waste management system to implement waste segregation. The method adopted is computer vision and deep learning paired with an internet of thing (IOT) system that is capable of segregating municipal waste into Organic and Recyclable waste. Eliminating manual segregation in the process of waste management significantly reduces the risk to the health of municipal workers by preventing the contraction as well as the spread of transmissible diseases. Automation will also increase the speed while significantly reducing the cost of the waste segregation process. This study was conducted in order to ideate and bring to life innovative and sustainable ideas for effective waste management systems with little to no human intervention.

Waste Classification and Segregation: Machine Learning and IOT Approach

Nowadays, educators can show case the technology of chatbots in various fields such as teaching and learning. Earlier the resources are almost negligible, in the field of education with the learning design integrated in it. But now with the advancement of technology, chatbot can fill the gap in the teaching landscape too. Using chatbot in the education domain is reassuring, since these bots can point out some of the logistics and diversified issues that a normal class might face. Besides this, with the further advancement of Artificial Intelligence, tech-giants like Apple, Google, and Amazon are providing platforms where building conversation is more focused rather than technicalities of computer programming i.e., to be more specific in natural language processing. In this paper, we have built a rule based chatbot on a platform named Discord, also showcased that how a chatbot can be integrated into other online platforms to counter the challenges faced in teaching. Q/A features are used to get in-depth knowledge about various preinstalled data in chatbot.

Development of Information Technology Telecom Chatbot: An Artificial Intelligence and Machine Learning Approach

In this paper we have developed a combat robot which will assist our commandos to fight against terrorism. With additional weaponry system it can perform other tasks also. Our preliminary aim in this project is to design a combat robot which can be used to handle the unmanned situations like terror attack inside the building where the firing is heavy and the entry of commandos may be difficult. In such situations the combat robot with spy camera, which is controlled through the control room can be sent into the terrorist occupied area. The robot constantly sends the visuals captured through spy camera to the control room. Based on the visuals received from the robot the control room operator can give directions to the robot. This kind of spy robot can also be used in star hotels, shopping malls, jewelry show rooms.

http://ijres.iaescore.com/index.php/IJRES/article/download/20238/pdf

Design and development of combat robot for military applications

In this paper, the problem of object recognition faced by visually impaired people in their daily life is considered. This problem causes them to face problem while crossing road and sometimes land them in the scenario of accident. In the literature different assistive solutions have been proposed to assist the visually impaired people. Some of them are Assistance from stick, Robot Assistance and Assistance by the visually fit people. Assistance from stick helps them to sense the object and also helps them to carry out various activities such as walking, negotiating a crowd and so on, but at the same time they won't know the object that is in front of them. Robots help them to navigate from one place to another, but at the same time it is highly expensive. Assistance from visually fit people is not a viable solution since; nowadays in this busy world people do not find time to help others. Looking at the problems faced by the visually impaired people, an assistive technology solution is being proposed by leveraging Internet of Thing (IoT), Machine Learning and Embedded Technologies for the visually impaired that helps them to move from one place to another without depending on others. The solution employs Google Tensor Flow Machine Learning Framework for the classification of the real-world objects. Therefore, the proposed system can rise the cognizance of the explored environment, it interacts with its user by means of audio messages and at the same time it is a cost-effective solution.

Mallikarjuna Gowda C. P

Papers

Waste Classification and Segregation: Machine Learning and IOT Approach

Development of Information Technology Telecom Chatbot: An Artificial Intelligence and Machine Learning Approach

Design and development of combat robot for military applications

Design and Development of Cognitive IoT Assistance System for Visually Impaired