Abstract
Today’s life is going to be easy with the use of various devices. Mostly, devices are based on various Machine Learning (ML) techniques, which is one of the most thrilling technologies of Artificial Intelligence (AI). If such devices are operated by internet, then this will increase the efficiency and effectiveness of the working and such type of technology is based on Internet of Thing (IoT). Every web search like Bing or Google is used to search on the internet using these techniques and retrieved results, efficient and accurate in short span of time as they used such learning algorithms to rank the web pages. Like every time, Facebook is used to identify the friends’ photo that is also ML. Product recommendation, online fraud detection, online customer support, videos surveillance, healthcare industries, face recognition, email spam, and malware are also based on various learning algorithms. The objective of this article is to give the brief introduction of various AI, ML, and IoT-based techniques with their applications in real life. Article also included the various aspect of Green IoT (G-IoT) which is based on utilization of IoT with environment friendly.
Keywords: Artificial intelligence, IoT, G-IoT, machine learning, deep learning, supervised learning, unsupervised learning
1.1 Introduction
Artificial Intelligence (AI) refers to the system where machines are given AI and such machines are called intelligent agents. These days AI is growing to be popular due to their features. It is simulating the natural intelligence in machines that are performing the mimic and learn actions of humans. These agents are able to learn with knowledge and carry out human-like work. As AI is continued to grow, they are having a big impact on our worth of life [1].
AI is also defined as follows:
- • An intelligent agent shaped by humans.
- • Capable to perform tasks intelligently without human interventions.
- • Able to think and act sensibly as human.
1.2 Machine Learning
When a machine gains the capability to learn from practices and experience rather than just by preset instructions is called Machine Learning (ML). It is the subset of AI. ML algorithms produce results and improve their own results on the basis of past experiences. It produces the desired output by modifying its own produced output according to available datasets and implicitly comparing the current outcome to the final output [2].
1.2.1 Difference Between Artificial Intelligence and Machine Learning
In a general sense, AI and ML are much the same, but the fact is ML is the subset of AI as depicted in Table 1.1 [3].
1.2.2 Types of Machine Learning
- • Supervised learning
- • Unsupervised learning
- • Semi-supervised learning
- • Reinforcement learning
Figure 1.1 depicts the various types of machine learning techniques.
Table 1.1 Difference between AI and machine learning.
| Artificial Intelligence | Machine learning |
| AI enables the machines to behave or simulate like humans. | ML permits a machine to learn from available past data without giving instructions to it explicitly. |
| AI is used to make such systems which can solve complex problems like humans. | ML goal is to make a machine to be trained itself from historical data without any human intervention. |
| AI has ML and DL as subset. | ML has DL as subset. |
| Following three types of AI: general AI, strong AI, and weak AI. | Following four types of ML: semi-supervised, unsupervised, reinforcement, and Supervised learning. |
| AI focuses to maximize the chance of success. | Machine learning focuses on accuracy and patterns. |
| AI uses structured, unstructured data, and semi-structured. | ML uses structured and semistructured data only. |
1.2.2.1 Supervised Learning
In the supervised ML, a machine learns from past data and then produces the desired output [4]. A machine gets its training from already available dataset using appropriate algorithms and inferred function. This inferred function predicts the output and gives an approximate desired result. The used labeled data set helps the algorithm to understand the data and produce the labeled output for more accurate results [5]. Figure 1.2 shows the complete process of supervised learning.
The following are some algorithms which are based on supervised learning:
- • Linear Regression
- • Naive Bayes
- • Nearest Neighbor
- • Neural Networks
- • Decision Trees
- • Support Vector Machines (SVM)
Figure 1.1 Classification of machine learning.
Figure 1.2 Process of supervised learning.
1.2.2.2 Unsupervised Learning
When a machine learns from unlabeled data or it discovers the input pattern itself, it is known as unsupervised learning. It divides the learning data into diverse clusters. Therefore, this learning is known as clustering algorithm. In this learning, the training data will not be labeled and inferences functions create its own inferences by exploring the unlabeled dataset in order to find suitable patterns [6]. Figure 1.3 shows the complete process of unsupervised learning.
Name of common unsupervised algorithms:
- • Anomaly detection
- • K-means clustering
- • Neural networks
- • Hierarchal clustering
- • Independent component analysis
- • Principle component analysis
1.2.2.3 Semi-Supervised Learning
When the machine learns from both labeled and unlabeled data, it is known as semi-supervised learning. When it is not feasible to label the data due to lack of resource to label it or due to the large size of the data, semi-supervised learning is used [7]. It lies among the supervised and unsupervised learning. For the model building, semi-supervised learning is best. Semi-supervised learning makes use of small amount of labeled data but large amount of unlabeled data [8].
Figure 1.3 Process of unsupervised learning.
Figure 1.4 Process of reinforcement learning.
1.2.2.4 Reinforcement Learning
Reinforcement learning does not need training examples. In the reinforcement learning, models are given an environment, group of some actions, a goal and a reward. This algorithm learns by rewards and penalties. For every correct output, a reward is given and a penalty for every wrong output. To produce the desired output, the algorithm has to maximize these rewards. It is named reinforcement learning because for every reward the model gets a reinforcement that it is on right path. The reward feedback system helps the model to predict future behavior [9]. Figure 1.4 shows the complete process of reinforcement learning.
The following are algorithms which are based reinforcement learning:
- • State Action Reward State action (SARSA)
- • Q-Learning
- • Deep Q Neural Network (DQN)
1.3 Deep Learning
Deep Learning (DL) is the concept AI that acts like the human brain to process and creating the patterns which helps to take the decisions. It is a subset of ML in AI that has ability to learning from unsupervised, unlabeled or unstructured. DL is becoming more popular as it achieves high accuracy and helps us in making decisions, translating languages, detecting objects, and recognizing speech [10].
Figure 1.5 Correlation between AI, ML, and DL.
1.4 Correlation Between AI, ML, and DL
Figure 1.5 [9] depicts the correlation among ML, DL, and AI. Here, as we can see that DL is the subset of ML, and ML is the subset of AI. Hence, initially, AI came into the existence first, and later, ML erupted from it. To be more specific and denser, DL is derived from ML further.
1.5 Machine Learning–Based Smart Applications
1.5.1 Supervised Learning–Based Applications
1.5.1.1 Email Spam Filtering
It helps in filtering junk e-mail or unwanted commercial e-mail and bulk e-mail from the true e-mails. With the usage of these learning algorithms, spam filter helps the user not to be flooded with the bulk or junk e-mails. The spam filter learns by watching the pattern of genuine e-mails and junk e-mails [11].
1.5.1.2 Face Recognition
Human face is not unique. Various factors cause to vary the face. With the help of these learning algorithms, face recognition has become easier. Face recognition is used in various situations such as security measure at an ATM, criminal justice system, image tagging in social networking sites like Facebook, an image database investigation, and areas of surveillance [11].
1.5.1.3 Speech Recognition
To recognize the speech, the ML methods can be used. It involves two different learning phases: The first phase is speaker dependent where, after purchasing, the software user has to train the model by his/her voice to achieve accuracy, and in the second phase, before the software is shipped, the model is trained by default. It is speaker independent fashion [12].
1.5.1.4 Handwriting Recognition
Automated handwriting recognition through supervised ML really solves a complex problem of humans and cut down a large amount of time. Therefore, it is being utilized in various applications [12].
1.5.1.5 Intrusion Detection
Intrusion is the biggest problem of today’s era. When a person or a process wants to enter unauthorizedly into another network, it is known as Intrusion. Therefore, this intrusion detection is important to scrutinize and to identify the threats or violations to the computer security. Learning algorithms helps in finding the intrusion.
1.5.1.6 Data Center Optimization
Huge energy requirement and environmental responsibility are rising a pressure day by day to Data Center (DC) companies to keep a DC operating efficiently. The ML algorithms help the DC to monitor the energy consumptions and pollution levels relentlessly to improve the operating efficiency [13].
1.5.2 Unsupervised Learning–Based Applications
1.5.2.1 Social Network Analysis
Identification of a person with in a large or small circle on social media platforms such as Facebook and Instagram has become easier with the help of unsupervised learning. It assists in maintain the similar posts in the proper way [14].
1.5.2.2 Medical Records
Automation helped the medical industry to manage the records in better way. Now, e-medical records have turn out to be ubiquitous [15]. Therefore, medical data is getting shape of medical facts and surprisingly helping to understand the disease in better way.
1.5.2.3 Speech Activity Detection
Speech activity detection (SAD) helps to detect the presence or absence of human speech for speech processing. ML assists to reduce the unwanted noisy and long non-speech intervals from the speech. SAD helps in making human-computer interfaces. It helps the hearing-impaired people to use the machine or computer using the voice commands [16]. It is language independent program. SAD is having two types: supervised SAD and unsupervised SAD. Supervised SAD uses the available training data and models a system accordingly, while unsupervised SAD is a feature-based technique.
1.5.2.4 Analysis of Cancer Diagnosis
Nowadays, human life is being saved with the help of medical science and technology. Therefore, the contribution of technology to fight against the cancer is not surprising anymore. It is first step to find the type of cancer in order to cure it. Now, it is possible with the help of classification process by collecting patient samples. Some ML techniques like radial basis function (RBF), Bayesian networks, and neural networks trees are used to detect the cancer and its type [17].
1.5.3 Semi-Supervised Learning–Based Applications
1.5.3.1 Mobile Learning Environments
Mobile learning means with the help of mobile device and internet facility, we can learn anywhere any time. To learn from mobile, various mobile apps are available which are based on various ML algorithms. Such type of learning is similar to where network bandwidth is consumed to operate [17].
1.5.3.2 Computational Advertisement
Online computational advertisement is the new concept in this scientific era. It is different from classical or traditional advertisement process. Computational advertisement is based on best match of the users. It is reached to the relevant user in digital format or online mode by using various ML techniques, and those are based on recommendation system, text analysis, information retrieval, classification, modeling, and optimization techniques. Within short span and in cost-effective way, it targets the number of relevant person [18].
1.5.3.3 Sentiment Analysis
Sentiment analysis is different from the text analysis. Text analysis is focused to retrieve the facts and information but not be able to find the customer’s sentiments which lead to misunderstand the customers need. This misunderstanding may be loss of the valuable information. Hence, sentiment analysis is important to find the product’s review either a positive or negative. Sentiment categorization used in movie reviews, recommendation systems, and business intelligence applications [18].
1.5.4 Reinforcement Learning–Based Applications
1.5.4.1 Traffic Forecasting Service
Traffic forecasting system is the real-time prediction of the traffic on the road. Day by day, numbers of vehicles are increasing on the road, which leads to increase the road accident. So, it is very necessary for traffic management. Using ML method, we can predict the real-time traffic and easily solve this problem. Such types of the systems find the digital traffic flow using satellite map and routing-based information [19].
1.5.4.2 Computer Games
The gaming industry has grown-up extremely in the recent time. AI-driven applications are widely used to create interactive gaming experience for the users. Such agents can take a multiple roles such as teammates, player’s opponents, or other non-player characters [19]. Different fields of ML help the programmers to develop games that are well suited to the present market demands.
1.5.4.3 Machinery Applications
Current era is the digital and robotic era. There will be requirement of such machine which can be work without human intervention. This is leading the automation of machine. Some works are very difficult and lives threaten, like to learn to fly the helicopter or any vehicles. Such types of situation can be handling by implementing such types of simulators, which gives the similar types of environment for training purpose. Such simulators are implemented by using AI algorithms.
1.5.4.4 Stock Market Analysis
To make profit in financial market, it is necessary to analyze and predict the stock market trends. For this proper understanding and prediction, skills are required. This is possible by using ML algorithms. Reinforcement learning and SVM [19] are used to predict such types of market trends, which help us to maximize the stock profit with low risk.
1.6 IoT
Due to cheap and high speed internet connection, the internet is growing very rapidly with various internet devices, and these internet devices are connected with the help of IoT (Internet of Things). IoT includes some physical devices with internet connection to provide smart or intelligence applications in real world. Such types of physical devices are capable to analyze, process, and store the sensor data. These devices are some types of embedded machines which can be controlled from around the world using some processing elements and software.
“Internet of Things” is a combination of various software and hardware that support connectivity among the globe. IoT devices can sense the situation, processed data, and interact with others. It becomes a great and prominent technology which reduces the irregularities present in the real world. As it provided many solutions using advanced technology like radiofrequency identification (RFID) [20], QR codes, biometrics, sensor networks, and nanotechnologies will be the main pillar of the upcoming IoT, which helps in communication, embedding, real problem addressing like smart grid computing, e-health, manage e-transportation, etc. IoT maintains the required privacy during communication within the devices. In a simple way, we can say that IoT is everything that is around us and we can sense, connect, and communicate on the internet, e.g., smart rooms with fully equipped with sensors and embedded systems [20]. Table 1.2 gives various works in RFID field time to time.
Table 1.2 Time line of investigation in RFID.
| Year | Summary of the research | Reference |
| 2008 | Discussed decomposable RFID devices for healthcare | [21] |
| 2010 | Discussed various protocols to increase energy savings at the reader by decreasing collisions between tag responses | [22] |
| 2011 | Discussed RFID inventory technique called automatic power stepping (APS) based on tag response and variable slot sizes | [23] |
| 2012 | Discussed energy-efficient probabilistic estimation techniques to minimize the energy disbursed by active devices | [24] |
| 2013 | Discussed a cost-effective RFID devices with printing facilities in order to attain ecofriendly tag antennas | [25] |
| 2014 | Discussed Reservation Aloha for No Overhearing (RANO) for effective communication intervals to removing problem in active RFID | [26] |
| 2017 | Discussed RFID size reduction of non-decomposable substantial in their industrial | [27] |
In IoT, all devices having their own unique IP address and sensors are the brains of this. These sensors can be microelectromechanical systems (MEMS) which respond results in the form of weight, temperature, time, sound, light, humidity, motion, pressure, etc., and take further action which is decided through programming [28]. The Internet is everything which is connected to all living thing and nonliving thing to exchange the information. Nonliving things like any machines or objects could be received and send information to each other, without human intervention.
1.7 Green IoT
Environmental problems are obtaining more consideration as the broad public develops more alert of the terrible significances of the environmental ruin causes. Current technological lead to spreads and increases in the carbon imprint. The development in this arena is concrete on green IoT (G-IoT). Latest few years there will be green support for managing various tasks. The G-IoT is projected to introduce substantial changes in daily life and would help to grasp the visualization of green ambient which joins our real world through these green systems (grid). G-IoT helps to decrease discharges and smog to make it environmentally convenient and surveillance and reduces the power consumption and functioning costs [28]. The aim of G-IoT is to become energy efficient in terms of the design and development of IoT. To become the energy-efficient procedures, IoT focused on decreasing the green house conclusion of current applications and amenities or to decrease the effect of greenhouse influence of IoT them self. G-IoT life cycle consists of G-design, G-production, G-utilization, and, finally, G-disposal/recycling to have no or very small effect on the atmosphere. As per global consultants Gartner, Inc. (GCG), ICT currently produces carbon discharges of approximately 0.86 MGT annually (about 2% of universal carbon discharges) and, if ICT including IoT, its decreasing effect of carbon dioxide (CO2) emissions [29].
G-IoT not only designates green atmosphere but also protects energy and time. It provides an efficient resolution that permits green and ecological development of the culture. It includes revolutions and applications for addressing community challenges like smart ecological city, smart transport, and proficient depletion of energy, to create a G-IoT atmosphere. IoT results can be examined online, and user can trace those data online.
1.8 Green IoT–Based Technologies
IoT comprises of six components that are identification, communication technologies, sensing, services, computation, and semantic.
1.8.1 Identification
Identification is the process which comprises of labeling, coding, identifying, resolution, transmission, and application of the objects or things in IoT. For orderly management, things identification is a primary requirement. This may be information given by a wearable device, an appliance, or a group of devices.
1.8.2 Sensing
Sensing is the name of activity where data is collected from various objects and it is sent to a data center, database, data warehouse, etc. According to the required services, this stored data is analyzed further and specific operations are performed. There can be various sensors such as temperature sensors, humidity sensors, mobile phones, and wearable sensing devices. Specific sensors are used as per the required service. Hence, sensing is categorized into environmental, biometric, biological, audible or visual, or all the above.
1.8.3 Communication Technologies
Communication technologies are used to connect various components to provide specific services. It uses either wide area network (WAN) communications or Wi-Fi (wireless LAN-based communications), Bluetooth, Z-wave, Near Field Communication (NFC), LTE Advanced, Wi-Fi, ultra wide bandwidth (UWB), IEEE 802.15.4, etc., which are the protocols used by IoT for communication [29].
1.8.4 Computation
Computation is the stage which is performed by the various hardware processing units such as microprocessors, microcontrollers, field programmable gate arrays (FPGAs), system on chips (SoCs), and software applications. To perform the computation, various hardware platforms such as Raspberry PI, Arduino, Intel Galileo, UDOO, Friendly ARM, and Gadgeteer are available, and many software platforms like LiteOS, TinyOS, and Riot OS are used. The important computational component of IoT is the Cloud platform. Since cloud platform has the high capability of computation in order to extract the valuable information from the stored data. Now, the transmission of this stored data takes place to a cloud-based service where other information that arrives from the IoT device is collected along with the cloud-based data in order to yield vital information to the end-user [30]. The data is gathered from the internet and other similar devices connected to the IoT. A process called “Data Processing” is required to extract vital information from the data.
1.8.5 Services
Services of IoT are broadly divided into below classes:
- • Identity-related services
- • Information aggregation services
- • Collaborative-aware services
- • Global services
Identity-related services are the foundation for all other services because identification of the object is the primary step for translating the real-world objects to the virtual world.
As the name describes, information aggregation service is used to accumulate the data from various sources. This data is then summarized and processed in order to gain fruitful results. This analyzed information is nowadays helping in making decisions and predictions. Global services denote the services provided to anyone on the demand, anywhere and anytime.
1.8.6 Semantic
Semantic is the name of task where knowledge is extracted intelligently from the mass of data to yield the demanded services. This is done by discovering resources, utilization of resources, modeling information, recognition, and analyzing data. Web ontology language (OWL), efficient XML interchange (EXI), resource description framework (RDF), etc., are the most common semantic technologies.
Figure 1.6 Life cycle of Green IoT.
1.9 Life Cycle of Green IoT
There is huge growth in IoT and its components in upcoming time. Therefore, it is needed to mitigate the number of resources to implement the logic and the reduction of energy as well to keep the things working for longer time. G-IoT relies on the optimum energy consumption.
For the smooth functioning of smart world, IoT should consume less energy and should reduce the green house effects at the same time. It has to focus on to mitigate the emission of CO2 from the devices and sensors [31].
Figure 1.6 represents the life cycle of G-IoT. It has four phases; they are green design, green production, green utilization, and green disposal/ recycle. Here, green disposal means the disposal should be in such a way that there should be no adverse effect on environment. Figure 1.6 depicts the life cycle of G-IoT.
1.10 Applications
In this section, we will discuss the various application based on G-IoT. Figure 1.7 depicts some applications, those that are based on G-IoT.
1.10.1 Industrial Automation
1.10.1.1 Machine to Machine Communications
Automation can be achieved through RFID tags. Without any sort of human intervention, direct communication is made by RFID to the robot [32].
1.10.1.2 Plant Monitoring
IoT helped to the industry for monitoring the various parameters of any plant like temperature, machine faults, and air pollution.
1.10.2 Healthcare
1.10.2.1 Real-Time Tracking
It helps in the monitoring of the patients and tracking of medical equipment.
It also helps in the tracking of the medical instruments in order not to be left in the body of the patient during surgery.
Figure 1.7 Green IoT–based applications.
1.10.2.2 Identification
IoT helps is the identification by coherent tracking methods. RFID-based identification is the easiest way to do it. It provides quick retrieval of patient information and finding the current location of the patient in the hospital. This also helps to reduce the blunder rate of patient incidents like overdose, wrong drug, infant identification (to prevent mismatching), etc., to a great extent by the constant monitoring of the patient information [33].
1.10.2.3 Smart Data Collection
It aids to reduce the processing time in every section either it is related to auditing, searching, or analysis. It also helps in reducing the cost. It provides automated care.
1.10.2.4 Smart Sensing
Various sensors can be used to access the real-time health of patient within seconds.
1.10.3 Environment Monitoring
It helps in monitoring the various changes happening in the environment whether it is temporal, organism, physical, or spatial made by human or nature itself.
1.10.3.1 Agriculture
It measures the water level, this way it helps in suggesting the suitable crop to be grown. It helps in saving of the water by sensing the humidity of the soil. Only required amount of water is supplied then. It prevents forest fires also.
1.10.3.2 Smog Control
IoT Academy (IoTA) worked to improve the air quality in UK. It is employing sensors and other gadgets for improving the air quality in London. IoTA proposed a solution named “BuggyAir project”. According to this, to measure the street level smog various sensors are to be installed in strollers (buggies) and the data will be recorded for analysis. The exact location of the pollution will be given the GPS installed in the stroller. This way, with the usage of IoT it will be easier to understand the complexity of the pollution and to control the air quality also to the great extent [34].
1.10.3.3 Waste Management
It has become a serious problem due to the rapid rise in the volume of solid and hazardous waste. It causes a serious impact on the environment. It is challenging because the costs for waste disposal are significant especially in densely populated countries. There are many types of waste such as biomedical waste, municipal waste, electronic waste, industrial waste, and biomedical waste. Various corporate and municipal bodies are working day and night to lessen the impact of waste dumping. RFID technology can be helpful in the handling of waste management. RFID-enabled trash is thrown into the bin, as it receives the trash the antenna and reader communicate through RFID tags, and automatic bin identifies the junk and helps in reprocessing accordingly. This leads to better health management [34].
1.10.3.4 Smart Water
Various sensors can be used to monitor the emissions of factories, the quality of tap water, toxic gages generated by cars, etc.
1.10.4 Suburban Sector
1.10.4.1 Smart Buildings
A homeowner can monitor all their instruments and devices easily and can track which device is wasting unnecessary energy in order to save energy. Solar panels are one of them to save energy and to promote green energy. Various IoT solutions suggest how to allocate energy properly without wasting money. The better the analysis of data provided by IoT; the more energy can be saved. It is directly proportional. Now, we have heat and motion sensors, with this energy can be saved. When a person comes into the room, the light automatically turns on and when he/she goes out, the light automatically turns off [35].
1.10.4.2 Garbage Collection
These days, some cities are using smart dust bins that tell automatically once they get full. This saves a large amount of time for dust bin collectors and helps in keeping the environment clean.
1.10.4.3 Water Sensors
These sensors help in finding where the taps are open unnecessarily and which restaurant and hotels are blocking the sewers.
1.10.4.4 Smart Metering
Smart meter provide the reading of consume electricity to the electricity board which helps for better billing and monitoring purposes. Traditional meters only provide information such as total consumption only while Smart meters provides information about how the energy is being disbursed. By using smart meters, a householder can manage their energy consumption in proper way, can save his/her money by cutting the bills, and can help to mitigate the carbon emissions [36].
1.10.5 People and Goods Transportation
With the passage of time, the world population has been grown also. Therefore, to manage the traffic in a sustainable way these days, trains, cars, bicycles, buses, and roads are equipped with tags, actuators, and sensors to provide accurate and real-time information to traffic controllers. This advanced transportation system is the backbone of on-time delivery and keeping the information up to date for better services. It provides the tourists with appropriate information on the go.
1.10.5.1 Smart Parking
IoT helps to ascertain the vacant space for packing in densely populated cities.
1.10.5.2 Smart Traffic Congestion Detection
Now, the world’s population has become the biggest problem and it is rising by leaps and bounds. Therefore, in this scenario, managing the traffic is a tough job. Here, vehicular ad hoc network (VANET) provides a way to escape traffic jamming. This enables the vehicles to connect nearer one for gaining traffic information in a better way. It helps to build a green environment by cutting carbon emissions to a larger level [37].
1.10.6 Marketing and Shipment Management
1.10.6.1 Smart Logistics/Shipment
Supply chain management provides real-time monitoring information by RFID, NFC, and sensors. With the help of these technologies, companies are now able to handle responses to the demands of the market within a short span. Enterprises such as Metro and Walmart are using the technology to meet the demands of customer within days.
1.10.6.2 Managing Quality
Product quality and quantity can be monitored by using such technology which helps to the customer to getting quality product from company. Many products like meat and fruits dairy products need to be monitored regularly to ensure quality standards. It is possible due to IoT to maintain the transparency in marketing. IoT also helps in limiting the carbon footprint [38].
1.10.7 Recycling
Public is now more aware and serious about the new paradigm of energy resources. Now, all are focusing on several renewable resources rather than traditional nuclear energy or fossil resources. IoT is emphasizing the more flexible design of the electrical grids which can handle power fluctuations efficiently according to the consumption behaviors of the consumers. IoT has changed our lives dramatically [39]. Day by day, all the IoT-based companies are making our life easier and greener. Moreover, IoT is leading us to a better and greener environment and making this planet safer for future generations.
1.11 Challenges and Opportunities for Green IoT
There is an important role of Green technologies in empowering the energy competent IoT [40]. Various constraints are to be measured. Some issues for further consideration are as follows.
1.11.1 Architecture of Green IoT
For any type of network communication has to follow either TCP/IP model or ISO OSI model. In the network, when IoT devices will be used, they must be compatible according to the network. It is also important that used IoT devices can be energy efficient, environment friendly, and compatible according to network architecture [41].
1.11.2 Green Infrastructure
Using the redesign approach, energy-efficient infrastructure for IoT can be attained.
1.11.3 Green Spectrum Management
Green mobile services are the current restriction of RF system which can be eliminated through the cognitive radio approach [42].
1.11.4 Green Communication
Constant energy supply to the component is really a big challenge in the way of energy-efficient communication. It supports energy-efficient communication protocols to communicate reliably with peers. IoT seems promising in the efficient implementation of new sources like solar, thermal, and wind.
1.11.5 Green Security and Servicing Provisioning
Privacy and security is the crucial factor of IoT deployment. Really, a significant amount of processing is required from devices to implement the security algorithms [43].
1.12 Future of G-IoT
IoT has changed our lives in a big manner. We can feel it everywhere. It has brought a digital revolution around the globe. It collects the real-time data with the help of smart sensors then this data is analyzed to extract valuable information from it which indeed helps in the decision making. In this way, it has improved transparency and reduced the processing time. It has created a wide and new market for sensors, and day by day, it is booming. IoT is improving our lives every day whether it is home, workplace, or playground. Soon, we will see automated door locks, intelligent street lights, industrial robots, smart cars, artificial hearts, etc. The upcoming generation is the world of IoT.
1.13 Conclusion
Ecological issues are obtaining more devotion as the universal public come to be more aware of the significances that atmosphere deprivation causes. We need to focus on the field of authority, safety, and standardization for the smooth operation of IoT which can help the people entirely. This research highlights several related tools, technologies, and worries about G-IoT for a smarter sphere. IoT characterizes an important pattern change in ICT which gives smooth growth of smart cities around the globe. The G-IoT is likely to take in remarkable revolutions in daily routine and would assist the dream of a green ambient world. This research also focused on ML and its various applications which give the ability to the machines to think logically, using training data. A remarkable contribution to the various areas has been made by the AI techniques from the last some decades. This article is focused on various applications based on AI and ML with IoT, that lead to providing various facilities to human lives. Some areas where AI algorithm used to detect intrusion in the network to defend our private network from invaders, AI also focused on the field of medicine, where medical image classification helps to predict disease in advance. AI algorithms are also involved to design the various level of computer gaming where people enjoyed a loT. It is also used to control the traffic with smart devices and dropped misshaping on the road, etc. Such latest technologies are offered more easiness, reliability, effectiveness, and efficiency in human life.
References
1. Tzanis, G. et al., Modern Applications of Machine Learning. Proceedings of the 1st Annual SEERC Doctoral Student Conference–DSC, 2006.
2. Horvitz, E., Machine learning, reasoning, and intelligence in daily life: Directions and challenges. IEEE Proceedings, vol. 360, 2006.
3. Mitchell, T.M., The discipline of machine learning, Carnegie Mellon University, School of Computer Science, Machine Learning Department, Pittsburgh, July 2006.
4. Ball, G.R. and Srihari, S.N., Semi-supervised learning for handwriting recognition. Document Analysis and Recognition, ICDAR’09. 10th International Conference on IEEE, 2009.
5. Valenti, R. et al., Machine learning techniques for face analysis. Mach. Learn. Techniques Int. J. Comput. Appl. (0975 – 8887), 115, 9, Springer Berlin Heidelberg, 159–187, 2008.
6. Al-Hmouz, A., An adaptive framework to provide personalisation for mobile learners, Doctor of Philosophy thesis, School of Information Systems & Technology, University of Wollongong, Australia.
7. Al-Hmouz, A., Shen, J., Yan, J., A machine learning based framework for adaptive mobile learning. Advances in Web Based Learning–ICWL 2009, Springer Berlin Heidelberg, pp. 34–43, 2009.
8. Graepel, T., Machine Learning Applications in Computer Games. ICML 2008 Tutorial, Helsinki, Finland, 5 July 2008.
9. Gabrilovich, E., Josifovski, V., Pang, B., Introduction to Computational Advertising. Association for Computational Linguistics Columbus, Ohio, USA, June 2008.
10. Cunningham, S.J., Littin, J., Witten, I.H., Applications of machine learning in information retrieval. University of Waikato, Department of Computer Science, Hamilton, New Zealand, 1997.
11. Bratko, A. et al., Spam filtering using statistical data compression models. J. Mach. Learn. Res., 7, 2673–2698, 2006.
12. Kaur, H., Singh, G., Minhas, J., A Review of Machine Learning based Anomaly Detection Techniques., Int. J. Comput. App. Technol. Res., 2, 2, 2(2), 185–187, 2013.
13. Gao, J. and Jamidar, R., Machine Learning Applications for Data Center Optimization, Google, 2014. Retrieve: https://docs.google.com/a/google.com/viewer?rl=www.google.com/about/datacenters/efficiency/internal/assets/machine-learning-applicationsfor-datacenter-optimization-finalv2.pdf
14. Haider, P., Chiarandini, L., Brefeld, U., Discriminative clustering for market segmentation. Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2012.
15. Kononenko, I., Machine learning for medical diagnosis: history, state of the art and perspective. Artif. Intell. Med., 23, 1, 23(1), 89–109, 2001.
16. Sadjadi, S.O. and Hansen, J.H.L., Unsupervised Speech Activity Detection Using Voicing Measures and Perceptual Spectral Flux. IEEE Signal Proc. Let., 20, 3, March 2013.
17. Hwang, K.E., Cho, D. Y., Park, S.W., Kim, S.D., Zhan, B. T., Applying machine learning techniques to analysis of gene expression data: cancer diagnosis, Methods of Microarray Data Analysis, Kluwer Academic Publishers, Springer US, pp. 167–182, 2002.
18. Pang, B., Lee, L., Vaithyanathan, S., Thumbs up?: sentiment classification using machine learning techniques. Proceedings of the ACL-02 conference on Empirical methods in natural language processing, vol. 10, Association for Computational Linguistics, 2002.
19. Horvitz, E.J., Apacible, J., Sarin, R., Liao, L., Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service. Microsoft Research, 2012. Retrieve: https://www.microsoft.com/en-us/research/wp-content/uploads/2014/06/horvitz_traffic_uai2005.pdf
20. Clarke, B., Fokoue, E., Zhang, H.H., Principles and theory for data mining and machine learning, Springer Series in Statistics, Springer Verlag New York, 2009.
21. Mowry, M., A Survey of RFID in the medical industry with emphasis on applications to surgery and surgical devices. MAE188, Introduction to RFID, Dr. Rajit Gadh, UCLA, p. 22, Jun. 9, 2008. Retrieve: https://silo.tips/download/a-survey-of-rfid-in-the-medical-industry-contents#
22. Namboodiri, V. and Gao, L., Energy-aware tag anti-collision protocols for RFID systems. IEEE Trans. Mob. Comput., 9, 1, 44–59, 2010.
23. Xu, X., Gu, L., Wang, J., Xing, G., Cheung, S., Read more with less: An adaptive approach to energy-efficient RFID systems. IEEE J. Sel. Areas Commun., 29, 8, 1684–1697, 2011.
24. Li, T., Wu, S., Chen, S., Yang, M., Generalized energy-efficient algorithms for the RFID estimation problem. IEEE ACM Trans. Netw., 20, 6, 1978–1990, 2012.
25. Amin, Y., Printable green RFID antennas for embedded sensors. PhD dissertation, KTH School of Information and Communication Technology, Kista, Sweden, 2013.
26. Lee, C., Kim, D., Kim, J., An energy efficient active RFID protocol to avoid over heading problem. IEEE Sens. J., 14, 1, 15–24, 2014.
27. Shaikh, F., Zeadally, S., Exposito, E., Enabling Technologies for GreenInternet of Things. IEEE Syst. J., 11, 2, 983–994, 2017.
28. Minerva, R., Biru, A., Rotondi, D., Towards a definitionof the Internet of Things (IoT), IEEE Internet initiative, Telecom Italia S.P.A., May 2015.
29. Atzori, L., Iera, A., Morabito, G., The Internet of Things: A survey. Comput. Network, Elsevier, 54, 15, 2787–2805, Oct. 2010.
30. López, T.S. et al., Adding sense to the IOT-An architecture framework for smart object systems. Pers. Ubiquit. Comput., 16, 3, 291–308, Mar. 2012.
31. Gershenfeld, N., Krikorian, R., Cohen, D., The Internet of Things. Sci. Am., 291, 4, 76–81, 2004.
32. Murugesan, S., Harnessing green IT: Principles and practices. IEEE IT Prof., 10, 1, 24–33, Jan.-Feb. 2008.
33. Xu, L.D., He, W., Li, S., Internet of Things in industries: A survey. IEEE Trans. Ind. Inf., 10, 4, 2233–2243, Nov. 2014.
34. Perera, C., Liu, C.H., Jayawardena, S., The Emerging Internet of Things Marketplace From an Industrial Perspective: A Survey. IEEE Trans. Emerg. Topics Comput., 3, 4, 2015.
35. Zhu, C., Leung, V.C.M., Shu, L., Ngai, E.C.-H., Green Internet of Things for Smart World. IEEE Access, 3, 2151–2162, 2015.
36. Rose, K., Eldridge, S., Chapin, L., The Internet of Things (IoT): An Overview, Understanding the issues of more connected world, Karen Rose, Scott Eldridge, Lyman Chapin, Internet Society, 2015.
37. Gershenfeld, N., Krikorian, R., Cohen, D., The Internet of Things. Sci. Am., 291, 4, 76–81, 2004.
38. Rawashdeh, S., Eyadat, W., Magableh, A., Mardini, W., Yasin, M.B., Sustainable Smart World. 10th International Conference on Information and Communication Systems (ICICS), 2019.
39. Albreem, M.A.M., El-Saleh, A.A., Isa, M., Salah, W., Jusoh, M., Azizan, M.M., Ali, A., Green internet of things (IoT): An overview. IEEE 4th International Conference on Smart Instrumentation, Measurement and Application (ICSIMA), 2017.
40. Poongodi, T., Ramya, S.R., Suresh, P., Balusamy, B., Application of IoT in Green Computing, Advances in Greener Energy Technologies, Springer Singapore, 2020.
41. Lohan, V. and Singh, R.P., Research challenges for Internet of Things: A review. International Conference on Computing and Communication Technologies for Smart Nation (IC3TSN), 2017.
42. Haldorai, A., Ramu, A., Murugan, S., Computing and Communication Systems in Urban Development, Urban Computing, Springer Nature Switzerland AG, 2019.
43. Mohana Sundaram, K., Hussain, A., Sanjeevikumar, P., Holm-Nielsen, J.B., Kaliappan, V.K., Kavya Santhoshi, B., Deep Learning for Fault Diagnostics in Bearings, Insulators, PV Panels, Power Lines, and Electric Vehicle Applications—The State-of-the-Art Approaches. IEEE Access, 9, 4124641260, 2021.
