A Hybrid Approach for Feature Extraction and Classification Using Machine Learning Techniques

Artificial Intelligence (AI) and related technologies like Data Mining, Machine Learning or Neural Networks became very popular in recent years. Many IT companies today require graduated students to understand and be able to apply these technologies. Application potential of AI is not limited only to robotics, image processing or intelligent agents, but also in engineering areas like computer networking and communication. However, on most universities, networking courses focus mainly on transmission protocols, network services and hardware design only while AI, machine learning or neural networks are taught separately. This causes a gap that emerges between AI theory and engineering approach. Thus, teachers of engineering courses are challenged how to introduce their students to an application of AI in the engineering areas, e.g., electronics, communication, embedded systems, power grids, etc. This paper shows how selected AI techniques presently used in computer networks can be incorporated into networking curriculum and demonstrated to students which extends student competencies and prepares them better into future jobs. We also present two case studies where AI techniques are applied on networking data in order to solve typical engineering problems.

Artificial Intelligence (AI) techniques are becoming useful as alternate approaches to conventional techniques. They have been used to solve complicated practical problems and now a day is very popular. They can learn from examples, fault tolerant in the sense they are able to handle noisy and incomplete data and once trained can perform faster prediction and generalization. AI based systems are used mainly because of their symbolic reasoning, flexibility and explanation capabilities. This paper briefly presents the main AI techniques and outlines an application in boiler control. Master controller is required for a steam generating system having multiple boilers operating in parallel. AI technique of Fuzzy logic controller is proposed as master controller. The optimum performance of individual boilers is achieved by the master controller meeting the varying load demands of the steam system.

Artificial Intelligence (AI) and Software Engineering (SE) have traditionally been largely independent disciplines. A common interest in developing computer systems is an area of overlap but fundamental differences in goals and objectives has resulted in little actual interaction. Limited success with chronic problems in both disciplines has forced practitioners in both fields to look beyond their local horizons in the hope of discovering new sources of impetus for further progress within their individual areas of interest. Software engineers are looking towards AI for both potential increase in software ‘power’ that AI techniques seems to promise, and exploitation of complexity-reduction strategies that AI has, of necessity, pioneered. AI practitioners, struggling with fragile demonstrations, would dearly like to import from SE tools, techniques and ‘know-how’ for the production of robust, reliable, and maintainable software systems. In this paper, I shall survey the range and scope of this two-way interaction between AI and SE.

Artificial intelligence (AI) is already part of our everyday life. Nowadays, facial recognition and autonomous driving are common applications of AI. It has now gone on to invade the field of medicine, and many studies showed promising applications of AI in radiology, pathology, endoscopy, and so on. Artificial intelligence (AI) has been a disruptive innovation in all areas of medicine including surgery. Not only has it been applied for research purpose but also AI can already provide significant solutions in clinical settings. Attention is now turning to the potential of AI in the field of endoscopic surgery. It is essential to understand how machine learning (ML) and deep learning (DL) work, understand current applications in surgery, and prepare for the future of surgery in the era of AI.

Artificial intelligence (AI) and machine learning (ML) are opening up important avenues of value creation inside organisations. Value creation will be strengthened if AI and ML are conceptualised using theoretical anchors rooted in a strong understanding of employee psychology. Organisations need to address anxieties of employees and assure them that AI and ML are aids in improving their productivity. They need to communicate to employees that AI and ML are not meant to displace employees from their jobs. Organisations face another dilemma regarding how to use AI and ML to draw upon the tacit knowledge and judgement of human actors to make more effective business decisions.

Artificial intelligence (AI) has been transforming the practice of drug discovery in the past decade. Various AI techniques have been used in many drug discovery applications, such as virtual screening and drug design. In this survey, we first give an overview on drug discovery and discuss related applications, which can be reduced to two major tasks, i.e. molecular property prediction and molecule generation. We then present common data resources, molecule representations and benchmark platforms. As a major part of the survey, AI techniques are dissected into model architectures and learning paradigms. To reflect the technical development of AI in drug discovery over the years, the surveyed works are organized chronologically. We expect that this survey provides a comprehensive review on AI in drug discovery. We also provide a GitHub repository with a collection of papers (and codes, if applicable) as a learning resource, which is regularly updated.

Artificial intelligence (AI) based computer-aided diagnostic (CAD) systems can effectively diagnose critical disease. AI-based detection of breast cancer (BC) through images data is more efficient and accurate than professional radiologists. However, the existing AI-based BC diagnosis methods have complexity in low prediction accuracy and high computation time. Due to these reasons, medical professionals are not employing the current proposed techniques in E-Healthcare to effectively diagnose the BC. To diagnose the breast cancer effectively need to incorporate advanced AI techniques based methods in diagnosis process. In this work, we proposed a deep learning based diagnosis method (StackBC) to detect breast cancer in the early stage for effective treatment and recovery. In particular, we have incorporated deep learning models including Convolutional neural network (CNN), Long short term memory (LSTM), and Gated recurrent unit (GRU) for the classification of Invasive Ductal Carcinoma (IDC). Additionally, data augmentation and transfer learning techniques have been incorporated for data set balancing and for effective training the model. To further improve the predictive performance of model we used stacking technique. Among the three base classifiers (CNN, LSTM, GRU) the predictive performance of GRU are better as compared to individual model. The GRU is selected as a meta classifier to distinguish between Non-IDC and IDC breast images. The method Hold-Out has been incorporated and the data set is split into 90% and 10% for training and testing of the model, respectively. Model evaluation metrics have been computed for model performance evaluation. To analyze the efficacy of the model, we have used breast histology images data set. Our experimental results demonstrated that the proposed StackBC method achieved improved performance by gaining 99.02% accuracy and 100% area under the receiver operating characteristics curve (AUC-ROC) compared to state-of-the-art methods. Due to the high performance of the proposed method, we recommend it for early recognition of breast cancer in E-Healthcare.

Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent machines that work and react like humans. It is a growing discipline that has enabled computer to undertake activities like facial recognition and game playing in a manner that, to an outsider, looks intelligent. There are many different toolsets that are called AI including neural networks, machine learning, expert systems, fuzzy logics, swarm intelligence and many others. These tools are being used in a wide variety of situations to solve a wide variety of complex problems, problems which have been difficult to solve using traditional algorithmic processes. Human intelligence and AI are sufficiently similar that tools developed to understand human intelligence can be applied to computer-based AI systems as well. Blooms Taxonomy is used to provide a definition of what constitutes intelligent computer applications. The article then considers the relationships between applications and intelligent systems.

Artificial Intelligence (AI) is one of the essential parts of gaming industry. In this paper, we have examined how Artificial intelligence technology is effectively used to solve the problems that arise while developing a game and integrate new features to the game. In this research paper, two algorithms are examined they are, path finding of the bots and bots decision making. Few AI techniques are discussed in this paper and how these techniques are used to provide solution to the problems that occur in the games. These techniques are also taken into consideration to provide new features into the computer games. This paper aims to discuss on the Finite State Machine and A* methodologies, which helps in the decision making of a bot and also to find the path towards the goal.

Artificial Intelligence (AI) is gradually changing medical practice. With recent progress in digitized data acquisition, machine learning and computing infrastructure, AI applications are expanding into areas that were previously thought to be the exclusive domain of human experts. One such area is biobanking, which forms a natural extension for AI-driven activities, both because biobanking is a foundational activity for downstream precision medical research, as well as because biobanking can increasingly accommodate high-throughput sample-, image- and data-handling operational models. The increasing AI-driven appetite for higher volumes of data and images often necessitates the cross-border collaboration of biobanks; likely to develop to one of the major forces dictating the international biobanking collaboration in the near future. However there are significant challenges ahead at the same time: firstly key practical issues surrounding the implementation of AI into existing research and clinical workflows, including data standardization, data sharing and interoperability across multiple platforms. Secondly governance concerns such as privacy, transparency of algorithms, data interpretation and how the latter might impact patient safety. Here a high-level summary of these opportunities and challenges will be presented from the perspective of AI driving more and stronger international collaborations in biobanking.

Artificial intelligence (AI) is a set of technologies that allows robots to detect, understand, act, and learn at human-like levels. The vast bulk of the AI that surrounds us now is powered by ineffective AI. This sort of AI is demonstrated by IBM Watson, self-driving cars, and Apple's Siri. Machine learning includes deep learning as a subset which is commonly utilised in predictive modelling. It functions in the same manner that neurons do in our brains. Its structure and networking are also influenced by neural networks found in our brains. Since the 1950s, artificial intelligence (AI) has been applied in medicine. The use of artificial intelligence in ophthalmology is mostly focused on high-incidence illnesses such as diabetic retinopathy, glaucoma, age-related macular degeneration, and cataract. The chapter reviews research demonstrating AI enhancing medical diagnosis with a focus on diabetic retinopathy.

Artificial intelligence (AI), deep learning, machine learning and neural networks represent extremely exciting and powerful machine learning-based techniques wont to solve various real-world problems. For a primer on machine learning, you'll want to read this seven-part series that I wrote. While human-like deductive reasoning, presumption, and decision-making by a computer is still a long time away, there have been remarkable gains in the application of AI techniques and associated algorithms

Chemical heuristics have been fundamental to the advancement of chemistry and materials science. These heuristics are typically established by scientists using knowledge and creativity to extract patterns from limited datasets. Machine learning offers opportunities to perfect this approach using computers and larger datasets. Here, we discuss the relationships between traditional heuristics and machine learning approaches. We show how traditional rules can be challenged by large-scale statistical assessment and how traditional concepts commonly used as features are feeding the machine learning techniques. We stress the waste involved in relearning chemical rules and the challenges in terms of data size requirements for purely data-driven approaches. Our view is that heuristic and machine learning approaches are at their best when they work together.

Artificial intelligence (AI) arises from the desire of human beings to reproduce their intelligent behavior by means of computers. Recently, AI has been demonstrating remarkable success in medical image analysis owing to the rapid progress of deep learning algorithms, which have shown increasing power to solve complex real-world problems in computer vison and image analysis. The aim of this work is to introduce the main AI techniques for an interdisciplinary reader profile, specifically deep learning approaches applied nowadays in Radiology, for the intelligent diagnosis of lung cancer and respiratory diseases such as viral and bacterial pneumonia, tuberculosis and Covid-19. An overview of current techniques is presented, framed mainly in the area of deep learning and in particular convolutional neural networks. Reference to current reviews on techniques, applications, needs, software and databases is made. Then, the Deep Learning paradigm is introduced from its origins to then focus on CNNs, their main characteristics, aspects to be considered in training, representative architectures, implementation issues, including transfer learning. Finally, the software and hardware platforms widely used for the problem are described and then the concluding remarks are presented

Artificial intelligence (AI) technology–based intelligent robots are constructed using different technologies, such as Internet of Things (IoT), big data, deep learning, machine learning, neural network, and expert system. This particular type of robots can increase the work efficiency of humans and improve their quality of life. From the industry perspective, AI robots possess unlimited potential for development, and they are projected to be a 10-trillion-dollar industry. In this study, the critical technology of IoT is applied to develop a teaching module for an IoT smart home robot. Teaching and evaluation are performed through an embedded thematic-approach teaching strategy in the course named Automatic Measurement and Monitoring. This research aims to teach students how to integrate IoT technology into robot design and construction to build IoT smart home robots. This cross-disciplinary research incorporates emerging technology—integration of smart home, robot construction, and IoT technologies—into industrial education, teaching material and equipment development, and experimental teaching and evaluation. The participating students were juniors or seniors from the Department of Electrical Engineering or Electromechanical Engineering at the University of Technology.