Artificial Intelligence, Machine Learning and User Interface Design

Nowadays, an artificial perception of beverages is in high demand as working hours increase, and people depend on readymade food and beverages. An assurance of quality, safety, and edibility of food and drink products is essential both for food producers and consumers. Assurance of unique beverage taste and consistent taste uniformity creates a distinct identity in the market. India is the second largest tea producer country in the world. Based on geographic location, the tea has a specific flavor and aroma. Artificial Intelligence (AI) can contribute to the feature identification and grading of tea species. The taste, aroma, and color are the three main attributes that can be sensed with the help of E-tongue, E-nose and E-vision, and can be processed further for automatic tea grading. The various potentiometric, voltammetric, Metal Oxide Semiconductor (MOS) and acoustic sensors are available with Principal Component Analysis (PCA). For tea analysis, various reviews are mentioned, like User Experience (UX evaluation, literature review, bibliometric review, and patent review. An in-depth analysis of artificial taste perception using machine learning has been described in the chapter. The topic covered almost all possible approaches to the artificial perception of tea with various interesting facts. 

An evolutionary algorithm (EA) is known as a subset of evolutionary computation. It is inspired by natural evolution and applies natural phenomena to search for the optimal solution. Its parallel search capability and randomized nature enable it to be effective and unique in solving different real-world problems in comparison to existing classical optimization algorithms. The evolutionary algorithm applies biological techniques such as selection, reproduction, and mutation to solve complex problems. It starts with a random population of candidate solutions and applies biological techniques to every generation until feasible solutions are obtained. The only fit solutionis intelligence (AI) simulation human intelligence in machines. Machines are programmed enough to think like humans and imitate their actions. AI based models are developed to provide new solutions to real-world problems. As realworld problems are very complex, the desired solutions for such problems are required to be explored in complex, high-dimensional, and very large search spaces. In this context, nature inspired and population based evolutionary techniques are the most suitable approach to find the optimal solution. The nature-inspired evolutionary techniques follow the natural phenomenon and these phenomenon helps to search for the desired optimal solution when the direction of the search is allowed to survive and continue to move in further generations to determine the optimal solution. Artificial not known at the beginning. So, “Evolutionary Artificial Intelligence (EAI)” is the term that presents the combination of human intelligence and natural phenomenon-based solutions to real-world complex problems. This chapter covers an overview of optimization techniques, artificial intelligence, and evolutionary computation in detail. A detailed discussion on evolutionary artificial intelligence, followed by applications of evolutionary machine learning is also presented. After that, the significance of evolutionary artificial intelligence in decision making has been discussed. Finally, the conclusion has been given, which shows the summary of the chapter.

In the era of digitalization, electronic gadgets such as Google Translate, Siri, and Alexa have at least one characteristic: They are all the products of natural language processing (NLP). “Natural Language” refers to a human language used for daily communication, such as English, Hindi, Bengali, etc. Natural languages, as opposed to artificial languages such as computer languages and mathematical nomenclature, have evolved as they have been transmitted from generation to generation and are challenging to explain with clear limits in the first instance. In natural language processing, artificial intelligence (Singh et al., 2021), linguistics, information processing, and cognitive science are all related fields (NLP). NLP aims to use intelligent computer techniques to process human language. However, NLP technologies such as voice recognition, language comprehension, and machine translation exist. With such limited obvious exclusions, machine learning algorithms in NLP sometimes lacked sufficient capacity to consume massive amounts of training data. In addition, the algorithms, techniques, and infrastructural facilities lack enough strength.

 Humans design features in traditional machine learning, and feature engineering is a limitation that requires significant human expertise. Simultaneously, the accompanying superficial algorithms lack depiction capability and, as a result, the ability to generate layers of duplicatable concepts that would naturally separate intricate aspects in forming visible linguistic data. Deep learning overcomes the challenges mentioned earlier by using deep, layered modelling architectures, often using neural networks and the corresponding full-stack learning methods.

Deep learning has recently enhanced natural language processing by using artificial neural networks based on biological brain systems and Backpropagation. Deep learning approaches that use several processing layers to develop hierarchy data representations have produced cutting-edge results in various areas. This chapter introduces natural language processing (NLP) as an AI component. The history of NLP is next. Distributed language representations are the core of NLP's profound learning revolution. After the survey, the boundaries of deep learning for NLP are investigated. The paper proposes five NLP scientific fields.

In this paper, we have aimed to develop a system that will help waste collectors segregate different types of waste without needing much human intervention. We have experimented with various deep learning and transfer learning techniques to determine which model is more suited for this purpose. The dataset we used contained 8369 images that are classified into 9 classes: batteries, clothes, e-waste, glass, light bulbs, metal, organic, paper, and plastic. We used models like VGG16, Inceptionv3, ResNet50, MobileNET, NASNetMobile and Xception. We have also conducted a survey to know about the waste management habits of the respondents. Our experiments showed that models like MobileNET gave us the best accuracy of 93.17% and identified all the waste categories correctly and the Xception model predicted images correctly with the use of both Adam and Adadelta.

Many bird species are rare nowadays, and when they are found, they are difficult to classify. As an example, in various scenarios, birds include different sizes, forms, colors, and a person's viewpoint from different angles. Although domain specialists can classify birds manually, with increasing volumes of data, this becomes a tiresome and time-consuming procedure. Using our approach, we can reliably and quickly identify bird species. It is now feasible to track the number of birds as well as their activity using automated bird species recognition and machine learning algorithms. Convolutional neural networks (CNN) were chosen above standard classifiers such as SVM, Random Forest, and SMACPY. For this system, we used the “BirdCLEF 2021” dataset from Kaggle. The input dataset will be preprocessed, which will involve framing, silence removal, and reconstruction, which will be supplied as input to a convolutional neural network, followed by CNN modification, testing, and classification. To avoid overfitting, we add a dropout layer. Preprocessing includes importing the Librosa library. MFCC is a program that extracts distinct characteristics from audio files (Mel-Frequency-Cepstral-Coefficients). The MFCC summarizes the frequency distribution over the window size, allowing for sound frequency and temporal analysis. The result is then compared with respect to the pre-trained data, and output is shown, and birds are classified based on their classes. 

The term “User Experience” (UX) refers to all elements of a customer's relationship with a company, including its services, products, and overall customer experience. Meeting the specific consumer demands and knowing their behavioral patterns are the most important criteria for an efficient UX.

The backend that selects what to recommend and the frontend that gives the recommendation are the two essential components of recommendation systems (RS). An RS's user interface must deliver recommendations in a way that allows users to anticipate taking action on them. A user interface is required to provide the recommendations. When creating a recommender's user interface, the designers must make several decisions. Understandability, transparency, assessability, trust, and timeliness are five elements that the designer must address.

When it comes to organizing a trip, people are becoming increasingly accustomed to using modern technology. Users are provided with a large quantity of data, which they must evaluate in order to choose the offerings that are interesting or appropriate for them. A customized tourist attractions recommender system is thought to be the most efficient way for visitors to find tourist attractions. The recommender system compares the acquired data to comparable and dissimilar data from other sources to provide a list of recommended tourist sites.

 These systems, which assist people in finding what they need on the internet, have been a huge success, and they wouldn't be conceivable without an excellent user interface. Data can now be easily segmented based on demographics, habits, trends, and a variety of other factors, thanks to the application of machine learning and AI. The main concept is to provide each user with better strategic decisions to their preferences based on their prior travel data and behavior. In this way, every facet of human behavior that these systems supply and explore is then fed into algorithms, which develop meaningful patterns. These patterns are then expressed through an interface and then transformed into useful products and services that help businesses improve their user experience.

Both AI and machine learning are extremely compatible and friendly with UX; they all follow the same concepts and aims. However, there are many challenges to their implementation. AI/ML engineers and UX designers should collaborate on a shared platform to create a blueprint for a fantastic UX experience. The mix of qualitative and quantitative data is crucial if AI and machine learning connect with UX. There is no other technology that can improve UX as much as AI.

Complex Adaptive Systems (CAS) are gradually becoming the primary modelling framework in the industry where autonomously evolving and self-adaptive systems exist. There has been a quick escalation in the research results in the past few years as the concept of CAS is emerging in the working sectors due to its capabilities and vital properties to shape an organizational workflow. CAS exhibits selforganization, adaptability, modularity, and others beyond complex systems. Designing CAS models is a tedious task as the intra-system components are composed of subcomponents that interact with running operations across the system. Researchers in engineering, healthcare, defense and military automation are extensively progressing in adapting the CAS framework and conceptualizing the systems for increasing performance efficiency. This paper primarily argues for the relevance and value of the CAS approach and then presents a detailed discussion on the core concepts of CAS and Agent-based modelling, highlighting the difference between them. Furthermore, the paper provides a detailed review of the applications of CAS, such as Manufacturing (Assembly systems), Defense and Analysis, Internet of Things (IoT), Distributed Networks, Healthcare organizations and a few social-ecological systems (SES). Many pieces of software agent-based modelling, tools for CAS development and data visualizations are surveyed and discussed in the second half of the paper.

A source code clone is a type of bad smell caused by pieces of code that have the same functional semantics, but the syntactical representation varies. In the past few years, there have been several studies about code clone detection, steered by numerous machine learning models, software techniques and other mathematical measures. This paper aims to conduct an impartial comparative study of the existing literature on Deep Learning and Non-Deep Learning techniques. Due to the lack of work in studying the previous and the current state-of-the-art tools in code clone detection, there is no concrete evidence found to underpin the use of Deep Learning approaches in clone detection, except for a preference from the evolutionary point of view. We will address and investigate a few research questions related to the intentions of using DL techniques for code clone detection compared to those of non-DL approaches (Based on –token, text, AST, metrics, and others). Furthermore, we will discuss the challenges faced in the Deep Learning implementation for clone detection and their potential resolutions if feasible. This review would help the audience understand how different approaches aid the clone detection process along with their performance measures, limitations, issues, and challenges.

Nowadays, modern technologies are applied in many different areas of medical science. One such piece of technology that helps in the diagnosis of numerous illnesses and infections is the expert system. The Medical Expert System was created to assist doctors in making diagnoses and to make it easier for the public to recognize disorders. To diagnose the user, it treats facts and symptoms as queries or inputs. This suggests that a medical expert system makes a diagnosis based on information about the patient and knowledge of the diseases. Designing an Expert System for disease diagnosis in youngsters up to the age of 16 is the main goal of this project. Python, Java, and Flask are all used as computer programming languages. The selected symptoms supplied as the question will enable the expert system to correctly diagnose these diseases. With this discovery, we think the creation of an expert system will be advantageous for disease diagnosis in pediatric instances and will also become more affordable. Multiple tests are necessary for the diagnosis of disorders in children because the symptoms might occasionally be deceiving. In these situations, an expert system can aid in identifying and treating the true issue. In addition to a prescription, it can diagnose the illness and offer information.

The 2020s may see amazing advances in AI, however, as far as the foundation and proficient utilization of energy is concerned, we have not reached the optimized level. As AI research advances, we should demand the best platform, methodologies, and tools for building AI models. Organizations heavily rely on AI for various activities today, with only 7% of businesses trying to discover the facts related to the problem that a bigger carbon footprint is left by AI, with the training process for several large AI models emitting as much as 626,000 pounds of carbon dioxide equivalent to the lifetime carbon footprint of nearly 3640 iPhones. As we know, algorithmic training is an endless process for AI-powered tools, as a result, growing reliance on AI only speeds up the death of the immediate environment. The awareness among the people about how AI can impact the sustainability of the environment in the near future is not considered while developing the solution. Apart from big players in the market, the cognizant of sustainable and responsible AI is still a big question mark. The end user or the consumers should be aware of the services they use, whether they are only accurate or efficient as well. The balance between both factors should be maintained based on the context and requirement. The same is studied in the given paper concerning the concept of Red AI and Green AI and how they should be balanced considering the environmental sustainability factor.

In the realm of artificial intelligence, knowledge representation is a vital aspect that enables effective information sharing and processing. Humans excel at sharing trusted information, which is acquired through rigorous testing and validation, resulting in what we commonly refer to as knowledge. The representation of knowledge can take various forms, such as graphs, maps, or textual formats. With the continuous evolution of the IT sector, the introduction of AI has simplified many tasks, often surpassing human capabilities and effortlessly handling even the most basic activities. However, understanding the concept of knowledge representation remains a fundamental question. In this research paper, we delve into the basics of knowledge representation to directly address this question. The understanding of knowledge representation is best achieved by examining the role knowledge plays in specific case studies or systems, which includes scientific reasoning and comprehension of the world. By exploring the intricacies of knowledge representation, we aim to provide a practical approach to its implementation in the field of artificial intelligence. 

Malicious Software (MALWARE) is a serious threat to system security the moment any electronic gadget or ‘Thing’ is connected to the World Wide Web (WWW). The malware - stealthy software that is used to collect sensitive information gains access to private systems and can disrupt device operation. Thus, malware acts against the user requirement and is a threat to all operating systems (OS), but more to Windows and Android systems, as those are the most widely used OS. Malware developers try to invade the system by means of viruses, adware, spyware, ransomware, botware, Trojans, etc. Developers try different anti-forensic techniques so that malware cannot be detected or investigated. Malware developers typically play ‘peekaboo’ with the malware investigators. The result is that investigating such attacks becomes more complex, and many times it fails because of immature forensics methodology or a lack of appropriate tools. This chapter is the first step towards analysing malware. The process started with malware dataset collection and understanding the same. ML has two basic blocks, i.e., feature extraction and classification. In the case of supervised learning, this feature plays a significant role. This asks for understanding features and their effect on classification, which was a major task. Two separate experimental processes were explored. The first one involved extracting n-grams from the binary files using the kfNgram tool, and the second one used a shell script to parse the assembly files for method calls to external API libraries. Several supervised machine learning classifiers like Decision Trees, SVM, and Naive Bayes were used to classify the malware family based on extracted features. We proposed a method to classify malware into nine families as per the Kaggle dataset. It analyses the n-gram of the malware file to generate the feature vector. Here, the value of ’n’ in n-gram is selectable; presently, it is four. The objective was to extract highly probable n-grams from the binary files after pre-processing, i.e., calculating the IG parameter. The present threshold for selecting n-gram from the top-most lists is five hundred. It has been observed that SVM and Decision trees provide accuracy on the scale of 98%. Nevertheless, there are chances of improvement as there is a probability of selecting irrelevant n-grams due to the sequential selection of n-grams. This method is considered a starting point for malware classification.

Traditionally, image retrieval is done using a text-based approach. In the text-based approach, the user must query metadata or textual information, such as keywords, tags, or descriptions. The effectiveness and utility of this approach in the digital realm for solving image retrieval problems are limited. We introduce an innovative method that relies on visual content for image retrieval. Various visual aspects of the image, including color, texture, shape, and more, are employed to identify relevant images. The choice of the most suitable feature significantly influences the system's performance. Convolutional Neural Network (CNN) is an important machine learning model. Creating an efficient new CNN model requires considerable time and computational resources. There are many pre-trained CNN models that are already trained on large image datasets, such as ImageNet containing millions of images. We can use these pre-train CNN models by transferring the learned knowledge to solve our specific content-based image retrieval talk.

In this chapter, we propose an efficient pre-trained CNN model for content-based image retrieval (CBIR) named as ResNet model. The experiment was conducted by applying a pre-trained ResNet model on the Paris 6K and Oxford 5K datasets. The performance of similar image retrieval has been measured and compared with the stateof-the-art AlexNet model. It is found that the AlexNet architecture takes a longer time to get more accurate results. The ResNet architecture does not need to fire all neurons at every epoch. This significantly reduces training time and improves accuracy. In the ResNet architecture, once the feature is extracted, it will not extract the feature again. It will try to learn a new feature. To measure its performance, we used the average mean precision. We obtained the result for Paris6K 92.12% and Oxford5K 84.81%. The Mean Precision at different ranks, for example, at the first rank in Paris6k, we get 100% result, and for Oxford5k, we get 97.06%.

Rapid urbanisation and subsequent growth in population have brought about a worldwide spike in the production of municipal solid waste. Poor management skills in the collection of waste and the improper allocation of transporting vehicles due to lack of technology usage, also, insufficient funds and inappropriate management of human resources have contributed towards making Municipal Solid Waste Management (MSWM) which is a big challenge nowadays, especially in developing countries. Scientists and researchers have been working towards developing cuttingedge technology in order to address this issue. Modern Artificial Intelligence (AI) technologies are being studied for their potential usefulness in the Solid Waste Management (SWM) industry. Waste management as a whole, including collection, transportation, and sorting, may benefit substantially from the intelligent use of AI algorithms. This article provides a brief overview of the way in which Machine Learning (ML) algorithms are used in MSWM across the whole process, from the initial creation of waste through its collection, transportation, and ultimate disposal.