به سمت لبه هوشمند: ارتباطات بی سیم به یادگیری ماشین میرسد
سال انتشار: 2020 - تعداد صفحات فایل pdf انگلیسی: 14 - تعداد صفحات فایل doc فارسی: 31
احیای هوش مصنوعی در اواخر (AI) تقریباً در هر شاخهای از علم و فناوری، انقلابی ایجاد کرده است. با توجه به گجتهای تلفن همراه هوشمند و همه جا حاضر و دستگاههای اینترنت اشیا (IoT)، انتظار میرود که اکثر برنامههای هوشمند را بتوان در لبهی شبکههای بی سیم استقرار داد. این روند باعث شده است، تمایل قوی برای تحقق «لبه هوشمند» ایجاد شود تا از برنامههای کاربردی مجهز به AI در دستگاههای لبه مختلف استفاده شود. بر این اساس، یک حوزهی پژوهشی جدید به نام یادگیری لبه به ظهور رسیده است که از دو رشته عبور میکند و انقلابی در آنها ایجاد میکند: ارتباطات بی سیم و یادگیری ماشین. یک موضوع اصلی در یادگیری لبه غلبه بر قدرت محاسباتی محدود و همچنین دادههای محدود در هر دستگاه لبه است. این امر با استفاده از پلت فرم محاسبات لبه تلفن همراه (MEC) و استخراج دادههای عظیم توزیع شده در تعداد زیادی دستگاه لبه محقق شده است. در چنین سیستمهایی، یادگیری از داده توزیع شده و برقراری ارتباط بین سرور لبه و دستگاهها دو جنبهی حیاتی و مهم است و همجوشی آنها، چالشهای پژوهشی جدید و زیادی را به همراه دارد. این مقاله از یک مجموعه جدید از اصول طراحی برای ارتباطات بی سیم در یادگیری لبه پشتیبانی میکند که در مجموع ارتباطات یادگیری محور نامیده میشوند. مثالهای گویایی ارائه شدند تا اثربخشی این اصول طراحی مشخص شوند و برای این منظور فرصتهای تحقیقاتی منحصر به فردی شناسایی شدند.
کلمات کلیدی: سرورها | مدل سازی جوی | هوش مصنوعی | پایگاه های داده توزیع شده | ارتباطات بی سیم | یادگیری ماشین | مدل سازی محاسباتی
|مقاله ترجمه شده|
Fast Authentication and Progressive Authorization in Large-Scale IoT: How to Leverage AI for Security Enhancement
احراز هویت سریع و مجوز پیشرو در اینترنت اشیا با مقیاس بزرگ: نحوه استفاده از هوش مصنوعی برای تقویت امنیت-2020
Security provisioning has become the most important design consideration for large-scale Internet of Things (IoT) systems due to their critical roles in supporting diverse vertical applications by connecting heterogenous devices, machines, and industry processes. Conventional authentication and authorization schemes are insufficient to overcome the emerging IoT security challenges due to their reliance on both static digital mechanisms and computational complexity for improving security levels. Furthermore, the isolated security designs for different layers and link segments while ignoring the overall protection leads to cascaded security risks as well as growing communication latency and overhead. In this article, we envision new artificial intelligence (AI)-enabled security provisioning approaches to overcome these issues while achieving fast authentication and progressive authorization. To be more specific, a lightweight intelligent authentication approach is developed by exploring machine learning at the base station to identify the prearranged access time sequences or frequency bands or codes used in IoT devices. Then we propose a holistic authentication and authorization approach, where online machine learning and trust management are adopted for achieving adaptive access control. These new AI-enabled approaches establish the connections between transceivers quickly and enhance security progressively so that communication latency can be reduced and security risks are well controlled in large-scale IoT systems. Finally, we outline several areas for AI-enabled security provisioning for future research.
Internet-of-things-based optimal smart city energy management considering shiftable loads and energy storage
مدیریت انرژی بهینه شهر هوشمند مبتنی بر اینترنت اشیا با توجه به بارهای قابل تغییر و ذخیره انرژی-2020
Formulating a novel mixed integer linear programing problem, this paper introduces an optimal Internet-of-Things-based Energy Management (EM) framework for general distribution networks in Smart Cities (SCs), in the presence of shiftable loads. The system’s decisions are optimally shared between its two main designed layers; a “core cloud” and the “edge clouds”. The EM of a Microgrid (MG), covered by an edge cloud, is directly done by its operator and the Distribution System Operator (DSO) is responsible for optimising the EM of the core cloud. Changing the load consumption pattern, based on market energy prices, for the edge clouds and their peak load hours, the framework results in decreasing the total operation cost of the edge clouds. Using the optimal trading power of the MGs aggregators as the input parameters of the core cloud optimisation problem, the DSO optimises the network’s total operation cost addressing the optimal scheduling of the energy storages. The energy storages are charged in low energy prices through the purchasing power from the market and discharged in high energy prices to meet the demand of the network and to satisfy the energy required by the edge clouds. As a result, the shiftable loads and the energy storages are used by the DSO and the MGs to meet the energy balance with the minimum cost.
Keywords: Energy management | Internet-of-Things | Microgrids | Optimal scheduling | Renewable energy sources
Challenges and recommended technologies for the industrial internet of things: A comprehensive review
چالش ها و فن آوری های پیشنهادی برای اینترنت اشیا صنعتی: مرور جامع-2020
Physical world integration with cyber world opens the opportunity of creating smart environments; this new paradigm is called the Internet of Things (IoT). Communication between humans and objects has been extended into those between objects and objects. Industrial IoT (IIoT) takes benefits of IoT communications in business applications focusing in interoperability between machines (i.e., IIoT is a subset from the IoT). Number of daily life things and objects connected to the Internet has been in increasing fashion, which makes the IoT be the dynamic network of networks. Challenges such as heterogeneity, dynamicity, velocity, and volume of data, make IoT services produce inconsistent, inaccurate, incomplete, and incorrect results, which are critical for many applications especially in IIoT (e.g., health-care, smart transportation, wearable, finance, industry, etc.). Discovering, searching, and sharing data and resources reveal 40% of IoT benefits to cover almost industrial applications. Enabling real-time data analysis, knowledge extraction, and search techniques based on Information Communication Technologies (ICT), such as data fusion, machine learning, big data, cloud computing, blockchain, etc., can reduce and control IoT and leverage its value. This research presents a comprehensive review to study state-of-the-art challenges and recommended technologies for enabling data analysis and search in the future IoT presenting a framework for ICT integration in IoT layers. This paper surveys current IoT search engines (IoTSEs) and presents two case studies to reflect promising enhancements on intelligence and smartness of IoT applications due to ICT integration.
Keywords: Industrial IoT (IIoT) | Searching and indexing | Blockchain | Big data | Data fusion Machine learning | Cloud and fog computing
AI Chips on Things for Sustainable Society: A 28-nm CMOS, Fully Spin-to-spin Connected 512-Spin, Multi- Spin-Thread, Folded Halved-Interaction Circuits Method, Annealing Processing Chip
تراشه های هوش مصنوعی درمورد چیزهایی برای جامعه پایدار: CMOS 28 نانومتری ، اتصال کاملاً چرخشی 512 چرخشی ، نخ چند چرخشی ، مدارهای برهم کنش خورده تاشو ، تراشه پردازش آنیل-2020
For sustainable society, next-generation Internet of Things (IoT) requires ultra-low-power information processing that is useful for both sensor area expansion and high-speed low-power feature extraction using a new signal processing artificial intelligence (AI) large-scale integration (LSI) chip developed for not only the cloud side but also the “things” side (edge) with an attached sensor. For this purpose, a fully spin-to-spin connected Ising model (annealing processing) AI LSI chip was successfully demonstrated for the first time. Its specifications are as follows: 521 spins, 262,144 interactions (with a halved-interaction circuit method), and 4-bit interaction accuracy. The chip was designed and fabricated using a 28-nm CMOS process. The new circuit technologies confirmed in actual operation of the chip are a block configuration realizing all spin-to-spin interactions, 8-spin-threads (core) method, and folded halved-interaction circuit method.
Keywords: IoT| artificial intelligence | Ising model | annealing processing | CMOS
A model for big spatial rural data infrastructure in Turkey: Sensor-driven and integrative approach
یک مدل برای زیرساخت های داده های بزرگ فضایی روستایی در ترکیه: رویکرد حسگر محور و یکپارچه-2020
A Spatial Data Infrastructure (SDI) enables the effective spatial data flow between providers and users for their prospective land use analyses. The need for an SDI providing soil and land use inventories is crucial in order to optimize sustainable management of agricultural, meadow and forest lands. In an SDI where datasets are static, it is not possible to make quick decisions about land use. Therefore, SDIs must be enhanced with online data flow and the capabilities to store big volumes of data. This necessity brings the concepts of the Internet of Things (IoT) and Big Data (BD) into the discussion. Turkey needs to establish an SDI to monitor and manage its rural lands. Even though Turkish decision-makers and scientists have constructed a solid national SDI standardization, a conceptual model for rural areas has not been developed yet. In accordance with the international agreements, this model should adopt the INSPIRE Directive and Land Parcel Identification System (LPIS) standards. In order to manage rural lands in Turkey, there are several legislations which characterize the land use planning, land classification and restrictions. Especially, the Soil Protection and Land Use Law (SPLUL) enforces to use a lot and a variety of land use parameters that should be available in a big rural SDI. Moreover, this model should be enhanced with IoT, which enables to use of smart sensors to collect data for monitoring natural occurrences and other parameters that may help to classify lands. This study focuses on a conceptual model of a Turkish big rural SDI design that combines the sensor usage and attribute datasets for all sorts of rural lands. The article initially reviews Turkish rural reforms, current enterprises to a national SDI and sensor-driven agricultural monitoring. The suggested model integrates rural land use types, such as agricultural lands, meadowlands and forest lands. During the design process, available data sets and current legislation for Turkish rural lands are taken into consideration. This schema is associated with food security databases (organic and good farming practices), non-agricultural land use applications and local/ European subsidies in order to monitor the agricultural parcels on which these practices are implemented. To provide a standard visualization of this conceptual schema, the Unified Modeling Language (UML) class diagrams are used and a supplementary data dictionary is prepared to make clear definitions of the attributes, data types and code lists used in the model. This conceptual model supports the LPIS, ISO 19156 International Standard (Geographic Information: Observations and Measurements) catalogue and INSPIRE data theme specifications due to the fact that Turkey is negotiating the accession to EU; however, it also provides a local understanding that enables to manage rural lands holistically for sustainable development goals. It suggests an expansion for the sensor variety of Turkish agricultural monitoring project (TARBIL) and it specifies a rural theme for Turkish National SDI (TUCBS).
Keywords: Spatial data infrastructures | Big data | Internet of things | Rural land use | INSPIRE | LPIS
Data mining of customer choice behavior in internet of things within relationship network
داده کاوی رفتار انتخاب مشتری در اینترنت اشیایی که در شبکه ارتباطی قرار دارند-2020
Internet of Things has changed the relationship between traditional customer networks, and traditional information dissemination has been affected. Smart environment accelerates the changes in customer behaviors. Apparently, the new customer relationship network, benefitted from the Internet of Things technology, will imperceptibly influence customer choice behaviors for the cyber intelligence. In this work, we selected 298 customers click browsing records as training data, and collected 50 customers who used the platform for the first time as research objects. and use the smart customer relationship network correspond to cyber intelligence to build the customer intelligence decision model in Internet of Things. The results showed that the MAE (Mean Absolute Deviation) of the customer trust evaluation model constructed in this study is 0.215, 45% improvement over the traditional equal assignment method. In addition, customers consumer experience can be enhanced with the support of data mining technology in cyber intelligence. Our work indicated the key to build eliminates confusion in customer choice behavior mechanism is to establish a consumer-centric, effective network of customers and service providers, and to be supported by the Internet of Things, big data analysis, and relational fusion technologies.
Keywords: Internet of things | Customer relationship network | Decision making | Recommendation | Fusion algorithm
Intelligent decision-making of online shopping behavior based on internet of things
تصمیم گیری هوشمندانه از رفتار خرید آنلاین مبتنی بر اینترنت اشیا-2020
The development of big data and Internet of things (IoT) have brought big changes to e-commerce. Different kinds of information sources have improved the consumers’ online shopping performance and make it possible to realize the business intelligence. Grip force and eye-tracking sensors are applied to consumers online reviews search behavior by relating them to the research approaches in IoT. To begin with, public cognition of human contact degrees of recycled water reuses with grip force test was measured. According to the human contact degrees, 9 recycled water reuses presented by the experiment are classified into 4 categories. Based on the conclusion drawn from grip force test, purified recycled water and fresh vegetable irrigated with recycled water are regarded as the drinking for high-level human contact degree and the irrigation of food crops for low-level human contact degree respectively. Several pictures are designed for eye-tracking test by simulating an on-line shopping web page on Taobao (the most popular online shopping platform in China). By comparing the fixation time participants spent on the areas of interest (AOIs), we justify that consumers online reviews search behavior is substantially affected by human contact degrees of recycled products. It was found that consumers rely on safety perception reviews when buying high contact goods.
Keywords: Online reviews search behavior | Recycled products | Grip force sensor | Eye-tracking sensor | Internet of Things (IoT)
AI and IoT Based Monitoring System for Increasing the Yield in Crop Production
سیستم مانیتورینگ مبتنی بر هوش مصنوعی و اینترنت اشیا برای افزایش عملکرد در محصولات زراعی-2020
Artificial Intelligence (AI) and Internet of things (IoT) based monitoring systems are in great demand and gives a precise extraction and analysis of data. In this paper, the research is performed on a marigold plant to detect the most suitable conditions for plant growth. The philosophy behinds this work is to reduce the risks in agriculture and to promote smart farming practices. The effect of physical conditions like humidity, temperature, soil temperature and moisture and light intensity on the plant growth, is monitored using IoT based monitoring system. The data responsible for the plant growth is obtained using different sensors units like DHT11, LDR, DS18B20, Soil Moisture sensors, Noir camera, singleboard microcontrollers and Application Programming Interfaces (APIs). The variation of plant growth rate w.r.t. the intensity of sunlight was observed within the range of 1000 lx- 1200 lx, category-2 (best). The further analysis of the extracted parameters is done using different Machine Learning (ML) algorithms. Logistic Regression, Gradient Boosting Classifier and Linear Support Vector Classifier (SVC) algorithms are found best for analysis of physical parameters responsible for the marigold plant growth.
Keywords: Machine Learning | Internet of Things | Smart farming | Agriculture | Artificial Intelligence | OpenCV | Python | Thingspeak
Bayesian networks + reinforcement learning: Controlling group emotion from sensory stimuli
شبکه های بیزی + یادگیری تقویتی : کنترل احساسات گروهی از محرک های حسی-2020
As communication technology develops, various sensory stimuli can be collected in service spaces. To enhance the service effectiveness, it is important to determine the optimal stimuli to induce group emo- tion in the service space to the target emotion. In this paper, we propose a stimuli control system to adjust the group emotion. It is a stand-alone system that can determine optimal stimuli by utility ta- ble and modular tree-structured Bayesian networks designed for emotion prediction model proposed in the previous study. To verify the proposed system, we collected data using several scenarios at a kinder- garten and a senior welfare center. Each space is equipped with sensors for collection and equipment for controlling stimuli. As a result, the system shows a performance of 78% in the kindergarten and 80% in the senior welfare center. The proposed method shows much better performance than other classifica- tion methods with lower complexity. Also, reinforcement learning is applied to improving the accuracy of stimuli decision for a positive effect on system performance.
Keywords: Adjusting emotion | Group emotion | Bayesian networks | Reinforcement Learning | IoT