Mobile Data Center Research Articles

Sequentialized Virtual File System: A Virtual File System Enabling Address Sequentialization for Flash-Based Solid State Drives

Solid-state drives (SSDs) are widely adopted in mobile devices, desktop PCs, and data centers since they offer higher throughput, lower latency, and lower power consumption to modern computing systems and applications compared with hard disk drives (HDDs). However, the performance of the SSDs can be degraded depending on the I/O access pattern due to the unique characteristics of SSDs. For example, random I/O operation degrades the SSD performance since it reduces the spatial locality and induces garbage collection (GC) overhead. In this paper, we present an address reshaping scheme in a virtual file system (VFS) called sVFS for improving performance and easy deployment. To do this, it first sequentializes a random access pattern in the VFS layer which is an abstract layer on top of a more concrete file system. Thus, our scheme is independent and easily deployed on any concrete file systems, block layer configuration (e.g., RAID), and devices. Second, we adopt a mapping table for managing sequentialized addresses, which guarantees correct read operations. Third, we support transaction processing for updating the mapping table to avoid sacrificing the consistency. We implement our scheme at the VFS layer in Linux kernel 5.15.34. The evaluation results show that our scheme improve the random write throughput by up to 27%, 36%, 34%, and 2.35× using the microbenchmark and 25%, 22%, 20%, and 3.51× using the macrobenchmark compared with the existing scheme in the case of EXT4, F2FS, XFS, and BTRFS, respectively.

Artwork Traceability and Anti-Counterfeiting Model Based on Block Chain Technology

The Chinese art market fostered the advancement of culture and spirituality. Nevertheless, false and counterfeit artwork is not uncommon. The art technology and security introduce the innovative method to determine Artwork Traceability and Anti-Counterfeiting. The aim of the work is to prevent the creation and circulation of fake or unauthorized copies of artworks. Because of the cryptographic security and immutability of block chains, it would be challenging to falsify artwork records or make accurate duplicates. This would foster confidence in the art market and shield collectors and artists from monetary losses and harm to their reputations. The data on mobile Application Data Center (ADC) platform and the cleansing the data using sub-aperture keystone transform matched filtering (SAKTMF) and the preprocessed data is fed into the Hierarchically Gated Recurrent Neural Network (HGRNN) classify the art work and Anti-Counterfeiting. The Bald Eagle Search Optimization (BES) Algorithm is used to optimize the weight parameter of HGRNN. The proposed model is implemented in MATLAB/ Simulink platform and the accuracy is compared to various existing approaches such as Dual-Branch Multi-Scale Feature Fusion network (DMF-Net), Region Convolutional Neural Network (R-CNN) and practical Byzantine fault tolerance (PBFT) algorithm. The gained results of the proposed HGRNN-BES method attains higher accuracy 97%, 96%, and 99%, higher precision 98%, 99%, and 97%.

A Study on Secure Wireless Mobile Data Exchange System in Healthcare Using RFID (Radio-Frequency Identification)

IoT provides a unified framework for coordinating the use of diverse real-world and digitally- enhanced healthcare assets. Telemedicine is appealing in poor countries because of a lack of access to healthcare services, an aging population with chronic diseases, rising healthcare expenditures, and a need to monitor patients remotely. The Internet of Things can provide individualized health services that enhance people’s quality of life while also reducing the burden on public health infrastructure. Therefore, the purpose of this work is to catalog, compare, and categorize previous research into Healthcare IoT (HIoT) systems. In order to better understand the backdrop, we looked at research articles on RFID-based Secure Wireless mobile data exchange systems in healthcare. There was also discussion of other crucial issues including security and interoperability. At the conclusion of this report, we briefly discuss the main advantages and disadvantages of each study. Lastly, there is a dearth of research into the security and interoperability concerns of IoT design in healthcare. Important outcomes of IoT in healthcare include improved information sharing, shorter hospital stays, and lower overall healthcare expenses. IoT in healthcare faced major obstacles due to concerns over patient privacy and data security.

Study of permutation decoding algorithms in UAV control systems

Relevance. This paper presents relevant topic of the use of unmanned aerial vehicles (UAV) in the agroindustrial complex (AIC) to obtain timely reliable information about the state of agricultural land for the entire period. In modern infocommunication technologies and communication systems, high requirements are placed on the reliability of information transmission. In mobile data exchange systems, compositions of noise-resistant codes are used in the form of cascade designs or turbo codes, and in order to increase their efficiency, it is necessary to make the fullest use of the redundancy introduced at each stage of data processing. To solve such a problem, it is advisable to apply a decoding method based on the ordering of the character confidence indices (CCI) of the code combination.Methods. When determining the encoding-decoding systems, the Mathcad application software was used. Mathematical studies have shown that binary block codes for reaching the specified boundary can be decoded not only on the basis of ordered statistics, but also using the method of dividing the space of allowed code combinations into clusters. Based on this method, a block diagram of the algorithm of the simulation model of the operation of the block code decoder based on cluster calculation is compiled.Results. The application of the proposed method of soft decoding of systematic block codes reduces the processing time of code combinations in the decoder by reducing the dimension of the square matrix to determine the nonlinearity property of the rows of the rearranged generating matrix after ordering the columns of the original generating matrix.

A Comparative Analysis of Dynamic Scheduling Algorithms for Enhanced Resource Management in Homogeneous and Heterogeneous Fog Computing Environments

Fog computing, an emerging paradigm, extends cloud capabilities to the network's edge, enhancing real-time data processing and analysis. This study focuses on optimizing fog computing systems using an adaptive scheduling algorithm. It efficiently categorizes incoming tasks based on their security requirements into private, semi-private, and public groups, distributing them among Mobile Data Centers (MDCs) and Cloud Data Centers (CDCs). By considering various parameters like job quantities, MDCs, CDCs, their capacities, and communication delays, the algorithm ensures tasks are allocated optimally. The performance of three scheduling algorithms (FCFS, SJF, EDF) is analyzed in both homogeneous and heterogeneous fog environments, shedding light on system efficiency, workload distribution, and resource management. This study provides valuable guidance for the design and operation of efficient fog computing infrastructures tailored to the diverse requirements of IoT applications while optimizing resource utilization.

Differential Evolution Algorithm With Asymmetric Coding for Solving the Reliability Problem of 3D-TLC CT Flash-Memory Storage Systems

In recent years, NAND flash memory has been widely used in mobile devices, laptops, desktops, and data center storage systems due to its low-power consumption, high performance, high density, lightweight, shock resistance, and high-reliability natures. However, as the stacked layers and the storage density increase, flash memory also suffers from a higher raw bit error rate (RBER) and shorter lifetime. Observing that reliable cell states suffer from less data retention errors and program disturbance, we propose a differential evolution coding scheme to increase the probability of storing data in more reliable cell states, thereby reducing the RBER. We conducted the experiments over a development platform of SSD storage device with 3D-TLC charge trap (CT) NAND flash memory. The experimental results showed that the proposed differential evolution algorithm with asymmetric coding scheme could averagely reduce RBER by 48.88%, 65.45%, 52.61%, 61.99%, 80.19%, and 33.18% compared with baseline, asymmetric coding algorithm, asymmetric coding scheme with stripe-pattern elimination algorithm, UAC- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> LC, word-line batch score modulation programming, and SCB schemes.

Optimizing the placement of cloud data center in virtualized environment

&lt;p&gt;&lt;span&gt;In cloud mobile networks, precise assessment for the position of the virtualization powered cloud center would improve the capacity limit, latency and energy efficiency (EEf). This paper utilized the Monte Carlo oriented particle swarm optimization (PSO) and genetic algorithm (GA) to first, obtain the optimal number of virtual machines (VMs) that maximize the EEf of the mobile cloud center, second, optimize the position of the mobile data center. To fulfil such examination, a power evaluation framework is proposed to shape the power utilization of a virtualized server while hosting an amount of VMs. In addition, the total power consumption of the network is examined, including data center and radio units (RUs). This evaluation is based on linear modelling of the network parameters, such as resource blocks, number of VMs, transmitted and received powers, and overhead power consumption. Finally, the EEf is constrained to many quality of service (QoS) metrics, including number of resource blocks, total latency and minimum user's data rate.&lt;/span&gt;&lt;/p&gt;

The technique of point visualization of the electric field in space and time

Testing of electronic devices is an integral part of the technological process of any manufacturer of such equipment. In this case, an electronic device is understood as an energy-intensive unit such as a mobile phone, data center or spacecraft. One of the key stages of testing is to identify the effect of electric fields on various electronic components of the device. This stage often requires making a mock-up of some part of an unfinished device in order to fix interference with special equipment. This requires time, financial and human resource costs. In order to reduce these costs in the modern world, the use of mathematical modeling tools for testing noise immunity and electromagnetic compatibility is becoming popular. In this paper, it is proposed to use an algorithm for visualizing electric fields in three-dimensional space and time. The algorithm is easily embedded into applications as a component of a mathematical modeling system. The work considered three ways of visualizing the electric field strength: starting from a simple setting of points in space, on the basis of which the electric field will be built, around the source of electric field radiation, to the use of algorithms that make it possible to arrange points equidistantly based on a given number of points in space for the formation of an electric field. The performance and visual implications of these methods were analyzed. The proposed methodology will be useful to the developer community as an embedded solution for point visualization of the electric field in any project in any algorithmic language with the ability to animate in time.

A Survey of Software-Defined Networks-on-Chip: Motivations, Challenges and Opportunities.

Current computing platforms encourage the integration of thousands of processing cores, and their interconnections, into a single chip. Mobile smartphones, IoT, embedded devices, desktops, and data centers use Many-Core Systems-on-Chip (SoCs) to exploit their compute power and parallelism to meet the dynamic workload requirements. Networks-on-Chip (NoCs) lead to scalable connectivity for diverse applications with distinct traffic patterns and data dependencies. However, when the system executes various applications in traditional NoCs—optimized and fixed at synthesis time—the interconnection nonconformity with the different applications’ requirements generates limitations in the performance. In the literature, NoC designs embraced the Software-Defined Networking (SDN) strategy to evolve into an adaptable interconnection solution for future chips. However, the works surveyed implement a partial Software-Defined Network-on-Chip (SDNoC) approach, leaving aside the SDN layered architecture that brings interoperability in conventional networking. This paper explores the SDNoC literature and classifies it regarding the desired SDN features that each work presents. Then, we described the challenges and opportunities detected from the literature survey. Moreover, we explain the motivation for an SDNoC approach, and we expose both SDN and SDNoC concepts and architectures. We observe that works in the literature employed an uncomplete layered SDNoC approach. This fact creates various fertile areas in the SDNoC architecture where researchers may contribute to Many-Core SoCs designs.

ВОПРОСЫ ОЦЕНКИ НАДЕЖНОСТИ СОВРЕМЕННЫХ СИСТЕМ ХРАНЕНИЯ ДАННЫХ ДЛЯ МОБИЛЬНЫХ ДАТА-ЦЕНТРОВ

Introduction: the review is conducted in the field of modern approaches to the creation and improvement of methods for assessing the reliability of data storage systems of mobile data centers designed for the continuous provision of a high-quality set of basic and additional information services. At the same time, services are provided to consumers in any place of their location, where typical data centers solve not only the tasks of building the information infrastructure of organizations, departments and individual large enterprises, but also tasks focused on ensuring the information security of these infrastructures. The goals and objectives of data storage systems as the technological basis of mobile data centers, the features of architectures, technologies and conditions for their construction and operation are summarized and systematized. The reliability indicators of data storage systems are studied and formulated, the role and place of reliability assessment tasks are investigated. The relevance of ensuring the accuracy and multi-criteria reliability assessment in the interests of decision making support for the design and construction of data storage systems is justified. The subject of the study is the reliability of data storage systems as a set of interconnected components (channels, switches, blade servers, disks, disk arrays, and libraries), as well as the conditions for designing and building systems of this class that affect their reliability. Purpose: analysis of existing and development of new scientific and methodological tools and software for assessing the reliability of mobile data center data storage systems to ensure reliable and multi-criteria (taking into account the variety of components and interaction schemes) analysis of the reliability of both storage systems themselves and mobile data centers as a whole. Results: a method for analyzing the reliability of data storage systems for mobile data centers, consisting of a number of sequential steps, is proposed. The method and algorithm of its implementation are based on the logical-probabilistic approach to reliability assessment, are simple in software implementation and rational in terms of efficiency and computational complexity. Practical relevance: the presented approach allows us to formulate reliability indicators and evaluate the reliability of complex structures of data storage systems. A practical software implementation in C++ in the Visual Studio development environment has been implemented. The results of a computational experiment are obtained, which can serve as input data when making a decision on the choice of storage systems at the stages of design, project approval, replacement or update of data storage systems for mobile data centers.

Cooperative Offloading in D2D‐Enabled Three‐Tier MEC Networks for IoT

Mobile/multi‐access edge computing (MEC) takes advantage of its proximity to end‐users, which greatly reduces the transmission delay of task offloading compared to mobile cloud computing (MCC). Offloading computing tasks to edge servers with a certain amount of computing ability can also reduce the computing delay. Meanwhile, device‐to‐device (D2D) cooperation can help to process small‐scale delay‐sensitive tasks to further decrease the delay of tasks. But where to offload the computing tasks is a critical issue. In this article, we integrate MEC and D2D cooperation techniques to optimize the offloading decisions and resource allocation problem in D2D‐enabled three‐tier MEC networks for Internet of Things (IoT). Mobile devices (MDs), edge clouds, and central cloud data center (DC) make up these three‐tier MEC networks. They cooperate with each other to finish the offloading tasks. Each task can be processed by MD itself or its neighboring MDs at device tier, by edge servers at edge tier, or by remote cloud servers at cloud tier. Under the maximum energy cost constraints, we formulate the cooperative offloading problem into a mixed‐integer nonlinear problem aiming to minimize the total delay of tasks. We utilize the alternating direction method of multipliers (ADMM) to speed up the computing process. The proposed scheme decomposes the complicated problem into 3 smaller subproblems, which are solved in a parallel fashion. Finally, we compare our proposal with D2D and MEC networks in simulations. Numerical results validate that the proposed D2D‐enabled MEC networks for IoT can significantly enhance the computing abilities and reduce the total delay of tasks.

An intelligent big data collection technology based on micro mobile data centers for crowdsensing vehicular sensor network

The fast development of Internet of Things (IoT) has greatly driven the development of mobile crowdsensing vehicular sensor network (CVSN). A lot of fascinating big data–based applications have been developed such as traffic management, health monitoring, and smart city. How to effectively collect enough data while not increasing too much redundancy is still a challenging problem in the big data application for CVSN. In this paper, a data relay mule–based collection scheme (DRMCS) is proposed to improve the quality of service (QoS). Comparing with the previous researches, the innovation of DRMCS is as follows: First, a data collection framework which considers the sensing task completion rate, redundancy rate and delay is proposed. Second, the micro mobile data center (MMDC) is proposed to solve the problem of connecting the huge number of intelligent sensing devices with data centre. Third, a MMDC selection strategy based on simulated annealing algorithm is proposed by DRMCS to improve the data collection performance. Compared with traditional vehicular network opportunistic communication without data relay mule (OCDRM), the sensing task completion rate of DRMCS has been improved by 78.6%.

Electro-optically tunable laser with ultra-low tuning power dissipation and nanosecond-order wavelength switching for coherent networks

The huge amount of data traffic behind the rapid growth of cloud computing is putting pressure on the operation of mobile fronthauls and data center networks so there is a need to improve their power consumption and latency. We developed an electro-optically tunable laser diode employing a tunable filter that is practically tuned even with small refractive index change of the electro-optic effect. The laser shows a small tuning power dissipation of less than 10 mW for a practical tuning range of over 35 nm with a linewidth of about 350 kHz. We also achieved high-speed optical switching of less than 50 ns for 100 Gb/s coherent signals. In addition to its application in optical communications, the electro-optically tunable laser diode is also beneficial to laser sensing applications because its higher tuning speed increases the time resolution of the sensing system. Furthermore, a narrow linewidth, conventionally difficult to reconcile with high-speed tuning, can also enable a longer sensing distance and/or a higher signal-to-noise ratio when using coherent detection. Our result shows that we can use the electro-optic effect to overcome the limitations of conventional tunable laser diodes and drastically change optical communications and laser sensing systems.

DATA PROCESSING CENTER AS THE BASIS OF INFORMATION SECURITY OF THE DEFENSE MINISTRY OF UKRAINE

Nowadays, the development of information technologies determines the successful functioning of the political system, since they allow to control political processes, prevent social and political conflicts. Increasing the level of reliability of the information, the most effective use of information resources, external and internal information ropes increase the stability of the political system, stability of the socio-political development of the country. The combination of different telecommunication technologies that create the preconditions for building flexible and high-performance service-oriented systems can be used to solve problems in different industries. However, nowadays, one of the constraints on the implementation and further development of such networks is the theoretical under-development of service delivery models, due to the lack of comprehensive information on the structure of data center networks. During the research conducted by the authors, it was found that the data processing center is the basis for informing the defense ministry of Ukraine. During the research, the authors used general scientific methods of analysis and synthesis, as well as the basic provisions of the theory of informatics, the theory of complex technical systems, the theory of information, etc. During the research, the authors substantiated the main tasks that will be performed by the data processing center of the defense ministry of Ukraine, identified the main information and calculation tasks that will be performed by them. The authors also substantiated the requirements for building a data center of the Defense Ministry of Ukraine. The authors evaluated modern technological solutions and software and hardware for the creation of the information infrastructure of the defense ministry of Ukraine. Possible technical and software for building a reliable and secure data processing center of the defense ministry of Ukraine are proposed. Therefore, the prospective direction of further scientific research of the authors should be considered the justification of ways of improvement of informatization of the armed forces of Ukraine and the creation of information infrastructure of the defense ministry of Ukraine are mobile data centers. This will allow the deployment of information infrastructure in various conditions, including in the open space, which is very relevant for the specifics of actions in the east of Ukraine.

Load balancing aware scheduling algorithms for fog networks

SummaryFog networks have attracted the attention of researchers recently. The idea is that a part of the computation of a job/application can be performed by fog devices that are located at the network edge, close to the users. Executing latency sensitive applications on the cloud may not be feasible, owing to the significant communication delay involved between the user and the cloud data center (cdc). By the time the application traverses the network and reaches the cloud data center, it might already be too late. However, fog devices, also known as mobile data centers (mdcs), are capable of executing such latency sensitive applications. In this paper, we study the problem of balancing the application load while taking account of security constraints of jobs, across various mdcs in a fog network. In case a particular mdc does not have sufficient capacity to execute a job, the job needs to be migrated to some other mdc. To this end, we propose three heuristic algorithms: minimum distance, minimum load, and minimum hop distance and load (MHDL). In addition, we also propose an ILP‐based algorithm called load balancing aware scheduling ILP (LASILP) for solving the task mapping and scheduling problem. The performance of the proposed algorithms have been compared with the cloud only algorithm and another heuristic algorithm called fog‐cloud‐placement (FCP). Simulation results performed on real‐life workload traces reveal that the MHDL heuristic performs better as compared to other scheduling policies in the fog computing environment while meeting application privacy requirements.

Conceptual Design of Mobile Application for Post-disaster Rapid Assessment of Damaged Houses

The current rapid assessment of post-earthquake damaged houses has been done manually. The determination of the damage level is also very subjective. Moreover, the available time during a rapid assessment and limited number of enumerators lead to ineffective decisions for responses and assistances. There are several application had appeared trying to answer the problems, but still they have many types of data that need to be input and even need a lot of time to process. The system design to be simple, more user-friendly and time efficient to be operated during the assessment. This study is aimed to develop a conceptual design of a system to collect data of houses damaged by earthquake using mobile application which propose to work both online and offline. The system will consists of five components: mobile device, user, data center (web server and database), internet, and data processing center (administrator and manager to verify and analyze the data). The application design to be integrated with Google Maps containing concise data entry to facilitate users (trained users and common users) and to shorten the time of data collection. Final collected data will be presented through the website and perform descriptive and spatial analysis.

Integration of mCare and T2 Mood Tracker: Illustrating mHealth Usability Testing

Military operational requirements potentially limit access to behavioral health care for service members. Although mobile technology solutions are increasingly viable, a secure method for mobile data exchange between patients and providers has yet to be adopted in military health care. Usability testing is the industry standard prior to implementing new technology. This paper demonstrates usability testing on a secure data exchange system between mCare and T2 Mood Tracker. Sixteen civilian providers in an outpatient behavioral health clinic tested the mCare Provider Portal, and nine uniformed proxy patients tested the Mood Tracker app. The System Usability Scale (SUS) was used as an outcome measure, which is composed of usability and learnability sub-factors. Proxy patients rated the mobile app as acceptable on the SUS, with average usability and above average learnability. Providers had less favorable views of the mCare Provider Portal, which they rated as marginal across all domains. Participants expressed enthusiasm about the potential of the provider web portal/patient smartphone app system, but had concerns about technical difficulties and ethical issues when exchanging data electronically. The results suggest a willingness to use technology to share data between patients and providers, but also a need for refinement of system usability before full-scale implementation.

An Analysis of Energy Consumption in Mobile Cloud Computing

Mobile cloud computing (MCC) has been introduced to be a potential technology for mobile services and computing concept by an explosive growth of the mobile applications and emerging of cloud computing. The performance of mobile computing would be significantly improved by leveraging cloud computing and migrating mobile workloads for remote execution at the cloud. This paper presents a unique VM allocation and migration policy of mobile cloud. VM migration is known as the technique for the optimization of the energy consumption in mobile cloud data center. Thus, aim of this paper is for minimizing the SLA violation, energy consumption with a number of migrations, MBFD algorithm and SVM technique would be used for energy optimization using VM migration.

(Invited) Very Low Temperature Epitaxy of Group-IV Semiconductors for Use in Finfet, Stacked Nanowires and Monolithic 3D Integration

Microelectronic devices enable the continuous improvement in mobile data exchange and mobile communication. This exciting technological progress has been achieved by transistor scaling, resulting in an increased performance for lower energy consumption and cost. As CMOS device scaling proceeds, the number of epitaxial growth steps in device fabrication schemes increases. Examples are SiGe or Ge as high mobility channel materials [1-3], SiGe/Si or SiGe/Ge multi-layers to define nanowires in lateral Gate All Around (GAA) devices [3-5], and Source/Drain (S/D) stressor layers which also allow to reduce the S/D contact resistance [3,6-8]. In this contribution we will describe the characteristics of the epitaxial growth schemes as used for Fin and Gate-All-Around (GAA) devices. For Si- and SiGe-channel GAA devices, strained SiGe/Si multi-layers, which are used to define lateral nanowires, can be grown with conventional precursors (SiH4 or SiCl2H2 and GeH4). The compositional gradient is sufficiently steep to allow efficient wire release by selective SiGe or Si removal [2,5,9]. In case of Ge GAA, epitaxial growth of Ge-rich SiGe/Ge on SiGe Strain Relaxed Buffers is more challenging. Extremely low process temperatures are required to avoid strain relaxation. These layers need to be grown with higher order precursors, since conventional precursors become ineffective [4]. The epitaxial growth of ultra-thin Si layers on (strained) Ge fins or lateral nanowires used to passivate Ge surfaces in the high-k gate module has been discussed at the ECS Fall meeting of 2017 [10] and will not be covered in this presentation. A major challenge is to increase the active doping concentration in epitaxial S/D layers. Current scaling of gate and fin pitch reduces contact area and the contact resistance becomes a key contributor to device parasitics [7,11]. In addition, monolithic 3D integration, requires to reduce the thermal budget of the complete epitaxial growth scheme (including pre-epi surface cleaning). For Si:P, we demonstrated that P doping activation can be increased by post-epi anneals (>1e21 cm-3) without major strain loss [8]. Nearly similar active doping concentrations (up to 8e20 cm-3) are obtained by using Si3H8 instead of SiCl2H2 and low growth temperatures without the need for a post epi thermal treatment. For SiGe:B, we obtained similar active boron concentrations using conventional precursors [12,13]. Because of the low boron solubility in Ge, it is more challenging to fabricate S/D Ge pMOS contacts with the right lattice constant (to act as a stressor) and with a sufficiently high active doping concentration. Effort is ongoing to increase the active boron concentration by moving the growth process further away from equilibrium. This is done at low growth temperatures by either using Ge2H6 as high-order precursor or by assessing new materials such as GeSn. On blanket wafers, higher active doping concentrations have been reported but it is extremely challenging to translate this into a selective growth process without Sn precipitation. This triggered the research community to assess alternative dopants. For Ge, the Ga doping solubility is significantly higher than that of B. Epitaxial growth schemes are preferred above ion implantation as the latter one requires an unwanted high thermal budget for doping activation and on patterned wafers it does not allow conformal doping profiles. First Ge:Ga layers with a resistivity below 0.4 mΩ.cm have been grown without any detectable C incorporation. In addition, Ga + B co-doping enables to reduce the resistivity of SiGe:B:Ga, which confirms the potential of Ga as an add-on. Acknowledgements The imec core CMOS program members, European Commission, the TAKEMI5 ECSEL project, local authorities and the imec pilot line are acknowledged for their support. Air Liquide Advanced Materials is acknowledged for providing advanced precursor gases.

Research on air pollutant concentration prediction method based on self-adaptive neuro-fuzzy weighted extreme learning machine

In order to improve the prediction accuracy and real-time of the air pollutant concentration prediction, this paper proposes self-adaptive neuro-fuzzy weighted extreme learning machine (ANFIS-WELM) based on the weighted extreme learning machine (WELM) and the adaptive neuro-fuzzy inference system (ANFIS) combined air pollutant concentration prediction method. Firstly, Gaussian membership function parameters are selected to fuzzify the input values and calculate the membership degree of each input variable. Secondly, corresponding fuzzy rules are activated, and the firing strength is normalized to calculate the output matrix of hidden nodes. Then, the optimal parameters (C, M), weights are assigned to weighted ELM by using locally weighted linear regression, and the regularized WELM target formula with equality constraint is optimized by the Karush–Kuhn–Tucker (KKT) conditions, the output weight matrix is calculated, and finally the prediction output matrix is calculated. Based on the air pollutant concentration data collected in Datong, Taiwan, the data on the pollutants containing carbon monoxide (CO), nitric oxide (NO), PM2.5 (particulate matter) and PM10, are selected by different historical time series lengths, using genetic algorithm-backpropagation neural network (GA-BPNN), support vector regression (SVR), extreme learning machine (ELM), WELM, ANFIS, regularized extreme learning adaptive neuro-fuzzy inference system (R-ELANFIS) and ANFIS-WELM are built for predict the concentration of each pollutant collected by single monitoring point in single-step time series. The experimental results show that the ANFIS-WELM presented in this paper has better prediction accuracy and real-time performance, realizes the prediction of multi-step time series on the basis of the ANFIS-WELM, and realizes the engineering application of the ANFIS-WELM algorithm package on the self-developed mobile source emissions online monitoring data center software system.