CC BY
35Disadvantages of method: more complex than other methods, organizational support; influence of specialists-experts competence level; presence of subjective factor.
Positive properties of extrapolation method include: availability of statistical and other information on transportations volume of required detail, developed mathematical apparatus and software for forecasting operations.
Main disadvantages: transfer to the future of past trends that may not be sufficiently confirmed and lack of connection with passenger-forming factors.
Advantages of methods based on correlation and regression analysis are accounting in forecast models of passenger-forming factors, sufficient methodological support (mathematical), reliability of results with correctly selected factors, ability to use at any time forecasting.
Main disadvantage of method is difficulty of obtaining information about numerical values of passenger-forming factors and reducing reliability of results with formal approach to passenger-forming factors choice.
For air transportations planning, it is advisable to use different methods of forecasting. Preference should be given to regression models and methods of heuristic forecasting, as they take into account influence of real factors on passenger flows formation processes.
References
1. Yaschenko L.A., Shapoval N.S., Merzhvin-skaya A.N. Feasibility studies and forecasting industry development. Tutorial - K.: Center for educational literature, 2006 - 240 p.
2. Kulaev Y.F. Economic evaluation of investment projects of technical and for the air transport. Brief Guidelines - K.: KMUHA, 1996 - 16 p.
INTERNET OF THINGS (IoT) AND NEURAL NETWORKS INTERACTION DURING VIDEO
OPERATION SURVEILLANCE SYSTEMS
Krutko D.
Siberian State University of Science and Technology named after Academician M.F. Reshetnev (Krasnoyarsk), student Khodenkova E.
Siberian State University of Science and Technology named after Academician M.F. Reshetnev (Krasnoyarsk), Candidate of Philosophy
Abstract
Our future is progressing more and more rapidly under the influence of such trends as the Internet of Things, neural networks and hardware accelerated video analysis, which provides new opportunities for participants in the IP industry. In this regard, the most important task for security and video surveillance service providers is to follow the speed of change and focus on efforts to achieve highly effective results.
Keywords: Internet of Things, neural networks, video surveillance, machine learning, video analytics.
Cloud and local information services have become fundamental components of modern life, and a new class of services, the Internet of Things (IoT), has emerged, increasing our dependence on network technologies in various areas of human life. IoT services enable communication between everyday devices, such as home appliances, consumer devices, industrial controls, sensors, and virtually anything that transmits information.
Before we begin to study the interaction of the Internet of Things and machine learning environment, we will consider these areas sequentially. The Internet of Things (IoT) is a network of networks where people communicate with their devices, and these devices interact and communicate with each other, respond to environmental changes, and even make decisions without human intervention [5]. IoT devices function independently; however, people can configure them and provide access to data. Internet of Things (IoT) systems operate in real time and consist of a network of smart devices and a cloud platform to which they are connected using WiFi, Bluetooth or other forms of communication. First, the devices collect information, for example, a burglar is found in the house. Then the software processes this information, notifies the user about
it, or performs further actions itself - calls the police. The IoT platform is secure. It has tools similar to those used in Internet banking, namely secure SSL and HTTPS encryption protocols, a network antivirus, and a cyber-threat protection centre. Thus, the platform anticipates equipment wear and possible failures before critical situations occur.
Delving into the future of the Internet of Things (IoT), you can predict that cybercriminals will continue to attack devices, because the IoT system is one of the most reliable and fast ways to spread malware [6]. Users, companies, entire cities and countries are increasingly using smart technologies to save time and money. For example, already now traffic lights with built-in video sensors regulate traffic depending on traffic or, for example, that refrigerators will begin to warn people about the imminent deterioration of certain products. Today, the main problem of IoT implementation is the lack of uniform standards. That is why existing solutions are difficult to integrate with each other, and new ones appear much slower than they could. Also, one of the most important features of the Internet of Things should be autonomy, so that devices can receive the energy of the environment, without human intervention.
Let's move on to the study of artificial intelligence, which already makes decisions for us in many areas. So, for example, navigators that analyse traffic flows at the expense of Internet-connected devices, and we, the people, completely trust them.
It is widely believed that artificial intelligence is dangerous for people, but it can carry much more opportunities. If we consider the cognitive abilities of artificial intelligence, we will notice that they are not yet very developed and have serious limitations. And this is true, because several cognitive processes can occur simultaneously in a person's head, and in artificial intelligence, one model processes one cognitive function. Not to mention, every person has common sense. Attacks on artificial intelligence also exist, it is easy to mislead, so, for example, it does not understand that a person is smaller than a mountain.
Speaking about the future of video analytics, it is already safe to say that it will depend on a combination of machine and human intelligence, where most of the work is done by machines in an automated mode, and a person connects to the process only if the machine doubts something. This will help make decisions faster and more efficiently, further accelerate technology development, and virtually end patent wars.
The analysis of Big Data flows allows us to make forecasts with an accuracy that we could never have dreamed of before, and to make important decisions based on them - in every area [2]. So, for example, data streams need to be collected by sensors connected to the Internet in real time - this is the Internet of Things (IoT). The data we collect needs to be stored - this is cloud technology - and processed - this is artificial intelligence. Companies that see the prospects of such communication and the prospects of the Internet of Things (IoT) in particular are actively investing in the development of the IoT.
At the moment, there are two types of video analytics [3]:
- Classic, or traditional. It is based on a fixed set of certain predefined rules. In traditional video analytics, there are many patented algorithms, that periodically leads to patent wars, courts, etc.;
- Video Analytics of the future. It works on the basis of neural networks and independently evaluates a person's behaviour or an event, and the operator can only decide whether he agrees with her assessment or not. This leads to a combination of artificial machine intelligence with human intelligence, which gives the most effective result.
Today, it is the second type of analytics that will really change the world and the old rules. Moreover, by spreading more and more, neural network-based video analytics will make patent wars a thing of the past. At the same time, robots will not replace humans - they will work together, and this will become a key factor in the development of video analytics as a whole: machines will perform part of the work, and human intelligence will connect in difficult situations and make the final decision.
In Video Surveillance System (VSS), built on the principles of the Internet of Things (IoT), video cam-
eras are transformed from devices that only capture images, into intelligent sensors that can collect a variety of information intended not only for security systems [4]. In addition, they can be integrated into systems with broader functionality than security, for example, in "smart cities" - for complex monitoring of lighting, traffic flows, traffic lights, and urban transport. In the eastern countries, these integrated solutions (where they are called "Safe City") are already used in the largest megacities: Singapore, Yangon and Hangzhou are fully equipped with tracking systems. They help to record crowds and other street processes. The advantage of smart cameras is the ability to reprogram and adapt to dynamically changing conditions.
Under the influence of the Internet of Things (IoT), VSS functions will expand, they can become an organic part of a wide range of business systems [3]. Using the Internet of Things (IoT), it will be possible to combine cameras with other types of sensors, which will create a single system for tracking complex or dangerous objects. Such potentially dangerous objects usually include mines and other underground workings. If you integrate gas analysers, seismic and other sensors with cameras, you can not only increase labour safety, but also reduce operating costs.
Smart VSS systems will help improve the work of healthcare, banks, retail, and many others. The current provision of physical security will remain one of the functions.
VSS become "smart" if their operation is supported by smart functions. VSS works with the elements of the intelligent system based on machine vision. Machine vision is usually understood as hardware and software solutions that allow you to automatically extract information from an image, that is, filter out the part of the data that is of interest from the stream - this, for example, can be people's faces, characteristic poses or gestures. Machine vision should not be confused with image processing, in the latter case; the result of processing is a different image, for example, the selection of a car number. The idea of machine vision is to compare the characteristics of the image under study with a given model. In the view of the model can be represented by the appearance of a person or car, behavioural patterns, etc. The more accurately the model is constructed, the better the results of machine vision.
Most of the VSSs with elements of intelligent technologies used today belong to the "rule-based" category, that is, they are based on relatively simple rules formulated and embedded in these systems by developers. The rules contain, for example, signs that an image element is considered as causing an alarm. A program that implements machine vision algorithms can be located on the camera itself or on a server that supports it.
A more promising approach to the implementation of intelligent technologies based on deep learning algorithms, takes into account more complex, non-easy to assess behavioural analytics. The scheme of solving any problem through machine learning consists of two stages-the actual training of the model and the practical use of this model, it is called inference. Learning and output differ significantly from a methodological and
technical point of view. Training requires very large volumes of "normal or training data" (normal behaviour of people, cars, etc.), and the model is trained on specialized computers. At the moment, servers based on universal GPGPU GPUs are usually used in this capacity. During the training process, the data is normalized, classified, and prepared in such a way that anomalies can be detected at the inference stage. During the operation of the trained model (at the output stage), such high performance is not required as in the training process. The model can be loaded into a computer with a regular processor (CPU).
Thus, we can say that the introduction of the Internet of Things contributes to improving the collection and increasing the range and volume of accumulated data, and the use of machine intelligence allows you to cope with large flows of information and ensure higher efficiency of analytics. Every day, the pace of development is becoming faster, and it is already difficult for individual companies to cope with the upcoming volumes of work. In this regard, market players should unite, cooperate with different industries and experts, and act as a single entity to create solutions and products of new quality that meet modern customer requirements.
References
1. "Internet of Things" (IoT) in Russia [Electronic resource] URL: https://www.pwc.ru/ru/publica-tions/iot/iot-in-russia-research-rus.pdf
2. How the Internet of Things changes business and life around-says MTS [Electronic resource] URL: https://ryazan.mts.ru/business/novosti-korp/2019-01-28/kak-internet-veshhej-menyaet-biznes-i-zhizn-vokrug-rasskazyvaet-mts
3. How will the Internet of Things, neural networks, and hardware acceleration of video analysis change video surveillance? [Electronic resource] URL: http://secuteck.ru/articles2/all-over-ip/kak-internet-veschey-neyroseti-i-apparatnoe-uskorenie-videoana-liza-izmenyat-videonablyudenie
4. Neural networks and the Internet of Things caused a breakthrough in video surveillance [Electronic resource] URL: http://www.tadviser.ru/plus/hik-vision/pub/article1 .php
5. What is the Internet of Things? [Electronic resource] URL: https://trends.rbc.ru/trends/indus-try/5db96f769a7947561444f118
6. What is the Internet of Things? [Electronic resource] URL: https://ain.ua/special/what-is-iot/
БЕЗОПАСНОСТЬ ЕДИНОЙ СИСТЕМЫ ГАЗОСНАБЖЕНИЯ МОБИЛЬНЫЕ КОМПРЕССОРНЫЕ СТАНЦИИ
Мацук З.Н.
Государственное высшее учебное заведение «Приднепровская государственная академия строительства и архитектуры», кафедра безопасности жизнедеятельности (аспирант)
SAFETY OF A UNIFIED GAS SUPPLY SYSTEM MOBILE COMPRESSOR STATIONS
Matsuk Z.
State Higher Education Establishment «Pridneprovsk State Academy of Civil Engineering and Architecture», Department of Life Safety (Doctoral Student)
Аннотация
Газотранспортная система - совокупность взаимосвязанных газопроводов и сопутствующих им сооружений, предназначенных для обеспечения газом потребителей. Магистральные газопроводы -технологический комплекс машин и оборудования, который функционирует как единая система. Объекты газотранспортной системы отнесены к перечню объектов повышенной опасности, для которых характерно наличие большинства существующих производственных рисков. Газотранспортная система поддерживается в исправном, надёжном и безопасном состоянии путём выполнения ремонтных (регламентных) работ, связанных с заменой или ремонтом дефектных участков трубопроводов (другого оборудования, агрегатов). Многие способы, применяемые операторами газотранспортных систем для обеспечения производственной безопасности ремонтных (регламентных) работ, либо экологически вредны («стравливание газа»), либо не лишены рисков с точки зрения производственной безопасности, энерго- и ресурсо- не эффективны («стравливание газа», «срабатывание газа на потребителя», усиление несущей способности трубопроводов, ремонт дефектов под давлением газа без остановки процесса транспортировки...). При таком подходе к производственному процессу сложно повысить общий уровень безопасности и энергоресур-соэффективности газотранспортных предприятий. Во втором десятилетии двухтысячных годов, благодаря стремительному развитию компрессорной техники и изобретению достаточного количества способов подключения компрессорных агрегатов к магистральным газопроводам без остановки процесса транспортировки газа, у газотранспортных предприятий появилась возможность эвакуировать газ из участков трубопроводов, подлежащих ремонту (техническому обслуживанию) и/или отключению путём перекачивания его в действующие магистральные газопроводы или следующий/предыдущий по ходу/против хода газа, за
