20 Kasım 2019 Çarşamba

Hologram Microscope to Facilitate Asthma Diagnosis in Children


A new hologram microscope has been developed which can be used to detect asthma, which is very common in children, before and faster.

Young children are more susceptible to disease than we are, and it is not always easy to diagnose a disease that occurs in them. Tests such as the standard lung function test used to detect asthma cannot be applied to children under certain age. A new blood analyzer can deliver results in less than 2 hours.

This device, a kind of holographic microscope, was developed by the Fraunhofer Marine Biotechnology and Cell Technologies Research Institute of Germany. Pattern imaging and visualization company Raytrix also supported the research. The research was sponsored by the partly state-funded KillAsthma project.


Users start the test by dropping a drop of the patient's blood into the microfluidic cartridge. White blood cells in this example are added to a substance that triggers shortness of breath. After loading, the cartridge is attached to the microscope and the image of 3000 cells is magnified and displayed in three dimensions thanks to the integrated LED and CMOS sensors.

The device was trained using blood samples from persons diagnosed by conventional methods. Thus, the diagnosis can be made with the help of a computer. Although both healthy and sick cells react to the substance that triggers the disease, the response rate drops considerably when it comes to the cells of asthmatics.

After about 90 minutes of monitoring and analysis, the software can accurately diagnose whether the person has asthma. The potential uses of the newly developed technology are not limited to this.

             Dr. Fraunhofer. Daniel Rapoport, methods can be used in the diagnosis of other diseases, he said. He said that immunity and chronic dyspnoea such as Crohn's disease and ulcerated tissues and rheumatism can also be discovered. Detection of these diseases by traditional methods requires a long and difficult test process.


1 Kasım 2019 Cuma

Google Engineers Developed Artificial Intelligence Which Determine Better Than Human, In Lung Disorders


Google, one of the leading companies in the healthcare field of artificial intelligence (AI) and machine learning technology, has collaborated with the Indian hospital chain Apollo Hospitals to develop an artificial intelligence algorithm that analyzes chest X-ray images.

Artificial intelligence (AI), which gives life to many sectors from smart phone to automotive, from military to health, has the potential to overcome many obstacles in front of humanity. One of the companies that are aware of this potential, Google has added a new one to its studies in artificial intelligence. The US technology giant has developed an artificial intelligence algorithm to detect four important findings in people's chest X-rays.

Designed by Google researchers, the model can detect four major lung disorders: pneumothorax, mass, fracture, and opacity. According to research published in the world-famous science journal Nature, the AI algorithm, which is trained using thousands of x-ray images, performs at the radiologist level.


More than 600,000 X-rays were obtained from the India-based hospital chain Apollo Hospitals, which was also supported by Google's umbrella company, Alphabet's artificial intelligence initiative DeepMind. Researchers developed a text-based system using radiology reports associated with each X-ray, and then analyzed more than 560,000 images from the data set provided by Apollo Hospitals.

Google researchers, the artificial intelligence algorithm they developed, doctors can easily see the x-ray images can be detected quickly, he says. Stating that the models determine the findings frequently missed by radiologists, the company said that in some cases, doctors made much better detection than artificial intelligence. Therefore, researchers expressed the need to develop models combining the skills of both AI systems and doctors, and stated that AI applications have tremendous potential in medical image interpretation.


16 Eylül 2019 Pazartesi

National Industry and Industry 4.0


It is possible to make many definitions for Industry 4.0. However, if we make a general definition, we can say that it describes the process of development in production and management. This process includes all developments in automation, interconnectivity, data exchange, information technologies, data processing and production. Therefore, industry 4.0 is a collective term that works, develops and relates with many different fields.

            In order to understand exactly what the fourth industrial revolution is and to discover their potential and to direct industry in the interests of the country for the future, and perhaps to form the basis of the fifth industrial revolution, it is necessary to examine the previous industrial revolutions and to know how they direct humanity.

            The first industrial revolution began in the late 1700s with the discovery of a steam engine, with the invention of machines that turned water and steam power into mechanical power for production. Thus, for the first time, the power of nature was used instead of arm strength in production.


            The second industrial revolution began in the late 19th century and early 20th century with the discovery of electricity, a more useful form of energy than steam. In this way, electric machines with more mass production potential were invented. In addition, the discovery of steel has led to the construction of durable automation machines, and the invention of telegraph and telephony has accelerated communication, thus becoming the dynamos of the second industrial revolution.

            It can be said that the third industrial revolution began in the late 1950s, when the first computers, which are the ancestors of today's computers, but can be regarded as the advanced technologies of the time, began to be used for production. In fact, the development of semiconductor technology and the invention of transistors in 1948 led to the emergence of computers and microprocessor-based devices. This stiation also heralded the transition from mechanical technology to digital technology.

            With digitalization, there are so many improvements that we can write for the fourth industrial revolution. But if we do not write the internet which is the pioneer of all these developments and technologies from the very beginning, we would be wrong. Interconnectivity, interoperability and communication have increased with the development and expansion of the Internet. This communication capability and increased processing power have enabled the development of many technologies including machine-machine interaction, internet of things, cloud computing, parallel and distributed system technologies, real-time data processing and autonomous robots and etc.

            Because of sociological and economic adversities that found in Turkey, unfortunately, industrial revolutions are not caught up in the time period of took places. However now with the acceleration of communication, Turkey has started to close the gap with the countries that have fully realized the industrial revolutions. As long as the necessary reforms in education are made and with the correct orientation of the dynamic manpower, Turkey will also catch these countries. For example, until ten years ago Turkey's own unmanned aerial vehicle (UAV) was not available. We can say that we are in the champions league in the UAV sector by taking the right and fast steps in ten years. We are even better than many members of this league.

            But how did we catch the countries that were 50 years ahead of us about the UAV ten years ago?

            As can be seen in this example, countries with advanced technology and industry, are no longer 50 years ahead of us. If the possibilities of technology and serial communication are used correctly, we may catch them a decade or a year.

            In order to increase our competitiveness in the international arena as a country and get more shares from the cake;
·         We have to invest in people. We need to be able to train our human resources in a quality and homogeneous way required by the age and to train qualified manpower that will lead us to industry 4.0.
·         We should be able to learn how to use developing technology in line with our goals as a society.
·         We should be able to turn our country into a center of attraction in this field in order to direct the investor to make technological investments in our country. Therefore, technological infrastructures should be realized by the government if necessary.
·         Turkish industrial companies should ensure digitalization and institutionalization. It should be able to produce faster and hassle-free production with artificial intelligence and automation.
·         We should raise awareness of our industrial companies and factories towards branding and support the branding efforts as a state.

If we can properly utilize the advantages of new age and technologies in our country as a society, we realize Industry 4.0 and open the doors of Industry 5.0.


Dr. Musa MİLLİ

22 Kasım 2018 Perşembe

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.


16 Kasım 2018 Cuma

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.

13 Şubat 2018 Salı

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/

7 Ocak 2018 Pazar

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/