Clustering Techniques

Various clustering techniques are used in the literature. These clustering techniques can be grouped under five groups:

Partitioning Clustering

At first all elements are considered as a single cluster, then iteratively grouped the respective elements together in smaller chambers. In other words, it is a clustering technique that divides a data set consisting of n elements into k pieces. Partition clustering is usually done with the help of a objective function. The most popular partitioning clustering techniques are k-Means (Lloyd, 1982), k-Median, k-Medoids, PAM (Rousseeuw and Kaufman, 1990), CLARA (Rousseeuw and Kaufman, 1990) ve CLARANS (Ng and Han, 2002).

Hierarchical Clustering

Data objects are grouped by creating tree-like structures in hierarchical clustering. There are two different approaches to hierarchical clustering: (i) agglomerative, (ii) divisive. In the agglomerative method, a single object is initially selected and the neighbors of these objects are combined with this object according to their distance from this object. In the divisive method, all data is initially a single set, then the set is divided into ideal small partitions iteratively. The most popular hierarchical clustering techniques are BIRCH (Zhang et al., 1996), CURE (Guha et al., 1998), ROCK (Guha et al., 2000), Chameleon (Karypis et al., 1999) ve CACTUS (Ganti et al., 1999).

Density Based Clustering

Data objects are categorized according to core points, boundary points and noise points. Based on the density, the elements around the core points are located in the same clusters. The most popular density based clustering techniques are DBSCAN (Ester et al., 1996), OPTICS (Ankerst et al., 1999), DBCLASD (Xu et al., 1998), DENCLUE (Hinneburg et al., 1998) ve SUBCLU (Kailing et al., 2004).

Grid Based Clustering

The data set is divided into a certain number of cells to form a grid structure and all clustering operations are performed over this grid structure. The most popular grid based clustering techniques are STING (Wang et al., 1997), CLIQUE (Agrawal et al., 1998), Wave Cluster (Sheikholeslami et al., 1998), BANG (Schikuta and Erhart, 1997) ve OptiGrid (Hinneburg and Keim, 1999).

Model Based Clustering

Data elements are combined by a series of statistical and conceptual methods. The harmony between data and some mathematical models is tried to be optimized. There are two different approaches in model-based clustering: statistical approach and artificial neural networks. The most popular grid based clustering techniques are EM (Dempster et al., 1977), COBWEB (Fisher, 1987), CLASSIST (Gennari et al., 1989), SOM (Kohonen, 1997) ve SLINK (Han et al., 2011).

All of the aforementioned clustering algorithms perform batch processing, so they access data on the disk. In this way, they have information about the whole data. They can process the data multiple times and randomly access the data at any point in the algorithm.

Clustering

Clustering in computer science, is an important issue that can be handled both in the field of data mining because it can obtain meaningful patterns from the data and in the field of machine learning because it is a learning method (unsupervised learning). For this reason, a lot of research has been done about clustering. In the field of machine learning, classification is known as supervised learning, clustering is also known as unsupervised learning technique. Because while group labels are known when classifying, group labels are not known in clustering, and finding class tags is the task of the clustering algorithm. Therefore, clustering is more difficult than classification. There are many definitions of cluster and clustering in the literature (Everitt, 1980).

·         A cluster is a collection of elements in which the elements in the same group are similar and in which the elements in different groups are not similar.

·         Clusters are groups in which the distance between two different elements in the same group is smaller than the distance between two elements in two different groups.

·         A cluster is a state of high-density points separated from lower-density points in a d-dimensional attribute space.

 

The purpose of clustering is to divide the finite, unlabeled data set into finite labeled natural groups (Baraldi and Alpaydin, 2002; Vladimir S et al., 2007).

Clustering, as mentioned earlier, is a learning method and nowadays is used in many areas ranges from manufacturing to artificial intelligent and from network security to surveillance system. Maybe you have a computer and work as a server on the internet. There are a lot of node to connect this server. The majority of these nodes also can be innocent so they have normal tcp or udp connection to the server. However there can be some malicious nodes that want to attack and corrupt the server in some ways like DDOS and man-in-the middle attack. So, clustering is a way to learn which node is innocent and which one is malicious node.

Microsoft Teaches Artificial Intelligence Goodness

Continuing its innovation efforts that focus on human beings, Microsoft teaches goodness to artificial intelligence systems within the scope of AI For Good initiative. Within the scope of the initiative that Microsoft has realized with an investment of 125 million dollars, it realizes projects to use artificial intelligence within the framework of social responsibility and for the benefit of humanity.

When Bill Gates and Paul Allen founded Microsoft 40 years ago, their goal was to make the computer’s facilities accessible to everyone. The computer that has entered all areas of life has changed many things in business life, industry and social life. Microsoft is now aiming to achieve a similar transformation with artificial intelligence, which provides fast and new solutions by adding experience and new knowledge of specified patterns.

Human and environmental problems are solved by artificial intelligence. Microsoft puts each individual and organization in a position where they can access and benefit from artificial intelligence technology. It is aimed to find solutions to the human and environmental problems that have been left unresolved until today with the artificial intelligence systems developed with a responsibility to empower everyone.

125 million dollar investment the services developed with artificial intelligence started to support people around the world on many issues in order to solve environmental, public and social problems that have been tried to be coped for a long time. Based on these benefits and potential, Microsoft launched the AI for Good initiative with an investment of $ 125 million.

Reference: http://www.hurriyet.com.tr/

Cloud Computing Benefits

We hear a lot about cloud computing, which can be accessed from anywhere with Internet access, where different information is stored. Many traditional desktop applications are disappearing; for example, most software vendors no longer offer desktop software. These companies are moving their products to the cloud and now offering cheap, online subscription-based services that seem ideal for small businesses. Cloud technology gives small businesses the opportunity to access technologies that were previously impossible to access, enabling them to compete with both small and large companies.

“Cloud computing is a model that allows access to a common pool of configurable computing resources, at any time, anywhere, under favorable conditions. Such resources (such as computer networks, servers, databases, applications, services, etc.) can be procured and disposed of in a manner that requires minimal managerial effort and client-provider interaction. This model supports accessibility and includes five key elements, three service delivery models, and four deployment models” (NIST, 2009).

Cloud computing enables you to access business-related data and applications anywhere, anytime at an affordable price. Instead of storing company data on hard drives in the office, you can upload information to the cloud and use it when needed.

Advantages Of Cloud Computing

·         The cloud computing simplifies things.

·         The company continuity is one of the priceless benefits of cloud computing.

·         The cloud computing helps ensure data security.

·         Using the cloud to store data makes collaboration easier and increases employee productivity.

·         The convenience of information on the move.

·         The cloud computing is cost effective.

·         The cloud computing works on cross-platforms.

·         The cloud computing is scalable.

·         The cloud computing usually comes with additional software.

·         The cloud computing application can facilitate integration.

·         You can reduce system hardware by using cloud computing.

·         The cloud computing is flexible.

Reference: https://www.isnet.net.tr/

Data Stream

Data stream is data that is continuously generated from thousands of data sources and arrives simultaneously as small data packets. The data stream can include data from various sources such as log files, e-commerce data, click flow data, social media data, financial transactions and location services data generated by customers.

The data stream consists of fast and infinite series of data. Due to these two characteristics of the data stream, it is seen that today's computers are insufficient to process the flowing data in terms of both their memory potential and processing capacity. In order to overcome this problem, either the old batch processing algorithms need to be modified and rewritten, or new methods, algorithms and platforms need to be developed for the data stream.

Real-time data stream mining is slightly different from conventional batch processing. Because the entire data cannot be accessed at any time t. Due to this nature of the data stream, there are some difficulties in processing the data:

·         The data stream is continuous and infinite. It is impossible to store and process such large data in memory. Therefore, mechanisms that can process large-scale data with less memory should be developed.

·         It is necessary to process the incoming data with high speeds and give real-time responses. For this reason, generally single pass strategy is used in the data processing. However, traditional methods can access data several times. That is, while conventional methods can make random access, it is not possible for data stream.

·         Data stream may evolve (drift) over time. Thus, there may be inconsistency between the first and subsequent data.

·         In many algorithms, parameters are determined by expert opinion. Setting these parameters is even more difficult for  data stream, due to the lack of whole data.

·         Algorithms that run on data stream have to relearn a repeating pattern.

·         Concept drifts need to be accurately detected. it is not only necessary to detect concept drifts, but also to manage them.

Security Of IoT

The Internet of Things (IoT) has entered our lives and has opened the doors for a new set of security threats. Have you ever thought about what could happen if your IoT-connected refrigerator was hacked? A kettle that you can turn on remotely using your phone. A refrigerator that tells you what food is on its shelves. The trainers who tell you the distance you jogging. We can easily give an examples of IoT in our lives.  But have you ever considered their safety?

For example, suppose you purchased an IoT-connected kettle with a standard default password and user name. You do not change the password and the manufacturer does not warn you; Suppose that the necessary security and data encryption measures are in place. What can a hacker do to detect this fundamental vulnerability and install malicious software on your kettle? Your attacked kettle can then be used to attack a targeted website, and what you perceive as a inanimate object can create a security nightmare.

The recent DDoS (distributed denial of service) Dyn attack also showed the need for an IoT security wake-up call. The October 21st attack included a cyber weapon called Mirai botnet, an IoT device used to bomb Dyn servers, such as digital cameras and DVR players. After the attack, a senior member of cyber security at the Council on Foreign Relations; David Fidler noted:

“We have a serious security issue with cyber security of IoT devices and we have no real strategy to combat it. Imagine what a well-sourced state actor can do with unsafe IoT devices.” Accordingly, security experts predicted the rise of the "Security of Objects" of the current year - new solutions, software and tools are needed to solve the security problems of smart devices.

What is really worrying is that IoT device owners are often not aware of the attacks. The reason for this is that once a device has been intercepted, it is impossible to say that they were attacked because they normally continue to function. When these devices, the targeted system, corporate servers, and even the same network with confidential government data are located, new scenes behind the problems continue to emerge. The point is that there is no way to develop an adequate security strategy without knowing which devices are exchanging data on a particular network or the Internet as a whole. In theory, each device added to a network needs to be evaluated for security.

What İs Internet Of Thıngs (IoT)?

Internet of things (IoT) technology is the interaction of smart devices and communication. Today, the Internet of things extends from small household appliances to smart cities. The data obtained from these systems called as big data. IOT refers to all systems capable of transmitting data over a network without the need for interconnected computing devices, mechanical and digital machines, objects, animals, or people provided with unique identifiers (UIDs).

Increasingly, organizations in various industries use IoT technology to work more efficiently, provide better customer service, improve decision making and increase business value, and better understand customers. For example; Suppose that you have a smart watch on your arm. This smart watch need sensors that detect the distance you take, the steps you take and how your heart beats while doing these activities. The data collected here is analyzed by a client (computer, mobile phone, etc.) and helps us to streamline our lives. The communication between these two devices is the most fundamental feature that makes up the internet of objects.

Industrial IoT system consists of:

• Intelligent beings that perceive, transmit and store information about themselves. So applications, controllers, sensors and security components.
• Data communication infrastructure such as cloud systems.
• Analytics and applications and people who produce business information from raw data.

IOT devices share the sensor data they collect by connecting it to an IOT gateway or to a terminal other than the cloud from which the data is sent to the cloud for local analysis or analyzed locally. Sometimes these devices communicate with other relevant devices and act on the information they receive from each other. Devices do most of the work without human intervention, but people can interact with the devices. For example, setting them up, giving instructions, or accessing data. The connectivity, network, and communication protocols used with these web-enabled devices depend largely on the specific IoT applications deployed.

Advantages Of IoT:

The Internet of Things provides organizations with a number of advantages that enable them to:

·         Monitor general business processes.

·         Improve customer experience.

·         To save time and money.

·         Improve employee productivity.

·         Integrate and adapt business models.

·         Make better business decisions.

·         To earn more income.