scholarly journals Using an Efficient Technique Based on Dynamic Learning Period for Improving Delay in AI-Based Handover

2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
Saad Ijaz Majid ◽  
Syed Waqar Shah ◽  
Safdar Nawaz Khan Marwat ◽  
Abdul Hafeez ◽  
Haider Ali ◽  
...  
Keyword(s):  
Mobile Communications ◽  
High Speed ◽  
Coherence Time ◽  
Dynamic Learning ◽  
Intelligent Technique ◽  
Maximum Delay ◽  
Training Samples ◽  
Proposed Model ◽  
Improved Accuracy ◽  
Frequent Measurement

The future high-speed cellular networks require efficient and high-speed handover mechanisms. However, the traditional cellular handovers are based upon measurements of target cell radio strength which requires frequent measurement gaps. During these measurement windows, data transmission ceases each time, while target bearings are measured causing serious performance degradation. Therefore, prediction-based handover techniques are preferred in order to eliminate frequent measurement windows. Thus, this work proposes an ultrafast and efficient XGBoost-based predictive handover technique for next generation mobile communications. The ML algorithm in general prefers 70–30% of training and test data, respectively. However, always obtaining 70% of training samples in mobile communications is challenging because the channel remains correlated within coherence time only. Therefore, collecting training samples beyond coherence time limits performance and adds delay; thus, the proposed work trains the model within coherence time where this fixed data split of 70–30% makes the model exceed coherence time. Despite the fact that the proposed model gets starved of required training samples, still there is no loss in predication accuracy. The test results show a maximum delay improvement of up to 596 ms with enhanced performance efficiency of 68.70% depending upon the scenario. The proposed model reduces delay and improves efficiency by having an appropriate training period; thus, the intelligent technique activates faster with improved accuracy and eliminates delay in the algorithm to predict mmWaves’ signal strength in contrast to actually measuring them.

Bioluminescent proteins prediction with voting strategy.

2020 ◽  
Vol 15 ◽  
Author(s):  
Shulin Zhao ◽  
Ying Ju ◽  
Xiucai Ye ◽  
Jun Zhang ◽  
Shuguang Han
Keyword(s):  
Amino Acid ◽  
Model Building ◽  
Prediction Method ◽  
Pair Composition ◽  
Proposed Model ◽  
Counting Rules ◽  
Significant Phenomenon ◽  
Voting Strategy ◽  
Improved Accuracy ◽  
Selection Of

Background: Bioluminescence is a unique and significant phenomenon in nature. Bioluminescence is important for the lifecycle of some organisms and is valuable in biomedical research, including for gene expression analysis and bioluminescence imaging technology.In recent years, researchers have identified a number of methods for predicting bioluminescent proteins (BLPs), which have increased in accuracy, but could be further improved. Method: In this paper, we propose a new bioluminescent proteins prediction method based on a voting algorithm. We used four methods of feature extraction based on the amino acid sequence. We extracted 314 dimensional features in total from amino acid composition, physicochemical properties and k-spacer amino acid pair composition. In order to obtain the highest MCC value to establish the optimal prediction model, then used a voting algorithm to build the model.To create the best performing model, we discuss the selection of base classifiers and vote counting rules. Results: Our proposed model achieved 93.4% accuracy, 93.4% sensitivity and 91.7% specificity in the test set, which was better than any other method. We also improved a previous prediction of bioluminescent proteins in three lineages using our model building method, resulting in greatly improved accuracy.

ПРОЕКТИРОВАНИЕ МИКРОЭЛЕКТРОННОЙ АНАЛОГОВОЙ ЭКБ С УЛУЧШЕННЫМИ ХАРАКТЕРИСТИКАМИ В РАМКАХ СИНЕРГЕТИЧЕСКОЙ ПАРАДИГМЫ

2020 ◽  
Vol 96 (3s) ◽  
pp. 137-140
Author(s):  
А.А. Лебедев ◽  
А.С. Будяков ◽  
Е.М. Савченко
Keyword(s):  
High Speed ◽  
Op Amps ◽  
Synergistic Approach ◽  
Improved Accuracy

Рассматриваются два варианта построения интегральных ОУ: 1) промышленных ОУ типа LM124, не уязвимых к воздействию ТЗЧ; 2) быстродействующих ОУ с улучшенными точностными и скоростными характеристиками. В обоих случаях используется синергетический подход, основанный на введении в структуру аналога элемента с режимом обострения. Two options for the construction of integrated op-amps are considered: 1) industrial op-amps of the LM124 type, which are invulnerable to the effects of HCP; 2) high-speed op-amps with improved accuracy and speed characteristics. In both cases, a synergistic approach is used, based on the introduction of an element with an aggravation mode into the structure of the analogue.

scholarly journals Modeling the Excess Velocity of Low-Viscous Taylor Droplets in Square Microchannels

Fluids ◽  
2019 ◽  
Vol 4 (3) ◽  
pp. 162 ◽  
Author(s):  
Thorben Helmers ◽  
Philip Kemper ◽  
Jorg Thöming ◽  
Ulrich Mießner
Keyword(s):  
High Speed ◽  
Process Intensification ◽  
Continuous Phase ◽  
Channel Cross Section ◽  
Optimization Approach ◽  
Mean Flow ◽  
Bypass Flow ◽  
Wall Film ◽  
Proposed Model ◽  
The Mean

Microscopic multiphase flows have gained broad interest due to their capability to transfer processes into new operational windows and achieving significant process intensification. However, the hydrodynamic behavior of Taylor droplets is not yet entirely understood. In this work, we introduce a model to determine the excess velocity of Taylor droplets in square microchannels. This velocity difference between the droplet and the total superficial velocity of the flow has a direct influence on the droplet residence time and is linked to the pressure drop. Since the droplet does not occupy the entire channel cross-section, it enables the continuous phase to bypass the droplet through the corners. A consideration of the continuity equation generally relates the excess velocity to the mean flow velocity. We base the quantification of the bypass flow on a correlation for the droplet cap deformation from its static shape. The cap deformation reveals the forces of the flowing liquids exerted onto the interface and allows estimating the local driving pressure gradient for the bypass flow. The characterizing parameters are identified as the bypass length, the wall film thickness, the viscosity ratio between both phases and the C a number. The proposed model is adapted with a stochastic, metaheuristic optimization approach based on genetic algorithms. In addition, our model was successfully verified with high-speed camera measurements and published empirical data.

A fully automated method of human identification based on dental panoramic radiographs using a convolutional neural network

2021 ◽  
Author(s):  
Young Hyun Kim ◽  
Eun-Gyu Ha ◽  
Kug Jin Jeon ◽  
Chena Lee ◽  
Sang-Sun Han
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Speed ◽  
Large Scale ◽  
Oral Surgery ◽  
Human Identification ◽  
Running Time ◽  
Automated Method ◽  
Image Characteristics ◽  
Proposed Model

Objectives: This study aimed to develop a fully automated human identification method based on a convolutional neural network (CNN) with a large-scale dental panoramic radiograph (DPR) dataset. Methods: In total, 2,760 DPRs from 746 subjects who had 2 to 17 DPRs with various changes in image characteristics due to various dental treatments (tooth extraction, oral surgery, prosthetics, orthodontics, or tooth development) were collected. The test dataset included the latest DPR of each subject (746 images) and the other DPRs (2,014 images) were used for model training. A modified VGG16 model with two fully connected layers was applied for human identification. The proposed model was evaluated with rank-1, –3, and −5 accuracies, running time, and gradient-weighted class activation mapping (Grad-CAM)–applied images. Results: This model had rank-1,–3, and −5 accuracies of 82.84%, 89.14%, and 92.23%, respectively. All rank-1 accuracy values of the proposed model were above 80% regardless of changes in image characteristics. The average running time to train the proposed model was 60.9 sec per epoch, and the prediction time for 746 test DPRs was short (3.2 sec/image). The Grad-CAM technique verified that the model automatically identified humans by focusing on identifiable dental information. Conclusion: The proposed model showed good performance in fully automatic human identification despite differing image characteristics of DPRs acquired from the same patients. Our model is expected to assist in the fast and accurate identification by experts by comparing large amounts of images and proposing identification candidates at high speed.

Improving Performance of a Multi-Bit Arithmetic Logic Unit

2021 ◽  
Vol 26 (1) ◽  
pp. 40-53
Author(s):  
A.N. Yakunin ◽  
◽  
Aung Myo San ◽  
Khant Win ◽  
◽  
...  
Keyword(s):  
High Speed ◽  
Operating Time ◽  
Arithmetic Logic Unit ◽  
Maximum Delay ◽  
Sequential Organization ◽  
Quartus Ii ◽  
Logic Unit

In modern microprocessors to reduce the time resources the arithmetic-logic units (ALU) with an increased organization of arithmetic carry, characterized by high speed, compared to ALU with sequential organization of the arithmetic carry, are commonly used. However, while increasing the bit number of the input operands, the operating time of ALU of ALU with the accelerated arithmetic carry increases linearly depending on the number of bits. Therefore, the development of ALU, providing higher performance than the existing known solutions, is an actual task. In this work the analysis of ALU with sequential and accelerated organization of the arithmetic carry has been performed. To increase the speed of the operation, a multi-bit ALU has been developed. The simulation of ALU circuits has been executed in Altera Quartus –II CAD environment. The comparison has been performed by the number of logical elements and the maximum delay as a result of modeling the ALU circuits for 4, 8, 16, 32, and 64 bits. A scheme for checking the results has been implemented to confirm the reliability of developed ALU. As a result, it has been found that when performing operations with the 64-bit operands, the developed ALU reduces the maximum delay by 53 % compared to ALU with sequential arithmetic carry and by 35.5 % compared to ALU with the accelerated arithmetic carry, respectively.

scholarly journals Blockchain and Internet of Things in Higher Education.pdf

2020 ◽  
Author(s):  
Tanweer Alam ◽  
Mohamed Benaida
Keyword(s):  
Internet Of Things ◽  
Mobile Communications ◽  
High Speed ◽  
Wireless Networking ◽  
Research Area ◽  
The Internet ◽  
Web Pages ◽  
Main Research ◽  
Iot Platform ◽  
The Internet Of Things

Building the innovative blockchain-based architecture across the Internet of Things (IoT) platform for the education system could be an enticing mechanism to boost communication efficiency within the 5 G network. Wireless networking would have been the main research area allowing people to communicate without using the wires. It was established at the start of the Internet by retrieving the web pages to connect from one computer to another computer Moreover, high-speed, intelligent, powerful networks with numerous contemporary technologies, such as low power consumption, and so on, appear to be available in today's world to connect among each other. The extension of fog features on physical things under IoT is allowed in this situation. One of the complex tasks throughout the area of mobile communications would be to design a new virtualization framework based on blockchain across the Internet of Things architecture. The goal of this research is to connect a new study for an educational system that contains Blockchain to the internet of things or keeping things cryptographically secure on the internet. This research combines with its improved blockchain and IoT to create an efficient interaction system between students, teachers, employers, developers, facilitators and accreditors on the Internet. This specified framework is detailed research's great estimation.

High Speed Packet Access Broadband Mobile Communications

2009 ◽  
pp. 595-604
Author(s):  
Athanassios C. Iossifides ◽  
Spiros Louvros
Keyword(s):  
Mobile Communications ◽  
Rural Areas ◽  
High Speed ◽  
Data Transfer ◽  
Mobile Wimax ◽  
Major Step ◽  
Transfer Rates ◽  
Mobile Broadband ◽  
History Of ◽  
Broadband Market

Mobile broadband communications systems have already become a fact during the last few years. The evolution of 3G Universal Mobile Telecommunications Systems (UMTS) towards HSDPA/HSUPA systems have already posed a forceful solution for mobile broadband and multimedia services in the market, making a major step ahead of the main competitive technology, that is, WiMax systems based on IEEE 802.16 standard. According to the latest analyses (GSM Association, 2007; Little, 2007), while WiMax has gained considerable attention the last few years, HSPA is expected to dominate the mobile broadband market. The main reasons behind this forecast are: • HSPA is already active in a significant number of operators and is going to be established for the majority of mobile broadband networks worldwide over the next five years, while commercial WiMax systems are only making their first steps. • Mobile WiMax is a competitive technology for selection by operators in only a limited number of circumstances where conditions are favourable. Future mobile WiMax systems may potentially achieve higher data transfer rates than HSPA, though cell coverage for these rates is expected to be substantially smaller. In addition, WiMax technology is less capable in terms of voice traffic capacity, thus limiting market size and corresponding revenues. • In order to overcome the aforementioned disadvantages, WiMax commercial launches are expected to introduce a relative CAPEX disadvantage of at least 20–50% comparing to HSPA, in favorable cases, while there are indications of an increase by up to 5–10 times when accounting for rural areas deployments. The short commercial history of HSDPA (based on Rel.5 specifications of 3GPP) started in December of 2005 (first wide scale launch by Cingular Wireless, closely followed by Manx Telecom and Telekom Austria). Bite Lietuva (Lithuania) was the first operator that launched 3.6 Mbps. HSUPA was first demonstrated by Mobilkom Austria in November 2006 and soon launched commercially in Italia by 3 in December 2006. Mobilkom Austria launched the combination of HSDPA at 7.2 Mbps and HSUPA in February 2007. By September of 2007, less than two years after the first commercial launch, 141 operators in 65 countries (24 out of 27 in EU) have already gone commercial with HSDPA with 38 operators among them supporting a 3.6 Mbps downlink. In addition, devices supporting HSDPA/HSUPA services are rapidly enriched. 311 devices from 79 suppliers have already been available by September 2007, including handsets, data cards, USB modems, notebooks, wireless routers, and embedded modules (http://hspa.gsmworld.com).

A Probabilistic Routing Protocol in VANET

2010 ◽  
Vol 2 (4) ◽  
pp. 21-37 ◽  
Author(s):  
Gongjun Yan ◽  
Stephan Olariu ◽  
Shaharuddin Salleh
Keyword(s):  
Ad Hoc Networks ◽  
Routing Protocol ◽  
High Speed ◽  
Vehicular Ad Hoc Networks ◽  
Ad Hoc ◽  
Probability Model ◽  
Proposed Model ◽  
Probabilistic Routing ◽  
Hoc Networks ◽  
Manet Networks

The key attribute that distinguishes Vehicular Ad hoc Networks (VANET) from Mobile Ad hoc Networks (MANET) is scale. While MANET networks involve up to one hundred nodes and are short lived, being deployed in support of special-purpose operations, VANET networks involve millions of vehicles on thousands of kilometers of highways and city streets. Being mission-driven, MANET mobility is inherently limited by the application at hand. In most MANET applications, mobility occurs at low speed. By contrast, VANET networks involve vehicles that move at high speed, often well beyond what is reasonable or legally stipulated. Given the scale of its mobility and number of actors involved, the topology of VANET is changing constantly and, as a result, both individual links and routing paths are inherently unstable. Motivated by this latter truism, the authors propose a probability model for link duration based on realistic vehicular dynamics and radio propagation assumptions. The paper illustrates how the proposed model can be incorporated in a routing protocol, which results in paths that are easier to construct and maintain. Extensive simulation results confirm that this probabilistic routing protocol results in more easily maintainable paths.

scholarly journals Application of convolutional neural networks for stellar spectral classification

2019 ◽  
Vol 491 (2) ◽  
pp. 2280-2300 ◽  
Author(s):  
Kaushal Sharma ◽  
Ajit Kembhavi ◽  
Aniruddha Kembhavi ◽  
T Sivarani ◽  
Sheelu Abraham ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Spectral Classification ◽  
Stellar Spectra ◽  
The Past ◽  
Training Samples ◽  
Optical Region ◽  
Spectral Libraries ◽  
Improved Accuracy

ABSTRACT Due to the ever-expanding volume of observed spectroscopic data from surveys such as SDSS and LAMOST, it has become important to apply artificial intelligence (AI) techniques for analysing stellar spectra to solve spectral classification and regression problems like the determination of stellar atmospheric parameters Teff, $\rm {\log g}$, and [Fe/H]. We propose an automated approach for the classification of stellar spectra in the optical region using convolutional neural networks (CNNs). Traditional machine learning (ML) methods with ‘shallow’ architecture (usually up to two hidden layers) have been trained for these purposes in the past. However, deep learning methods with a larger number of hidden layers allow the use of finer details in the spectrum which results in improved accuracy and better generalization. Studying finer spectral signatures also enables us to determine accurate differential stellar parameters and find rare objects. We examine various machine and deep learning algorithms like artificial neural networks, Random Forest, and CNN to classify stellar spectra using the Jacoby Atlas, ELODIE, and MILES spectral libraries as training samples. We test the performance of the trained networks on the Indo-U.S. Library of Coudé Feed Stellar Spectra (CFLIB). We show that using CNNs, we are able to lower the error up to 1.23 spectral subclasses as compared to that of two subclasses achieved in the past studies with ML approach. We further apply the trained model to classify stellar spectra retrieved from the SDSS data base with SNR > 20.

scholarly journals A Robust Dynamic Classifier Selection Approach for Hyperspectral Images with Imprecise Label Information

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5262
Author(s):  
Meizhu Li ◽  
Shaoguang Huang ◽  
Jasper De Bock ◽  
Gert de Cooman ◽  
Aleksandra Pižurica
Keyword(s):  
Hyperspectral Image ◽  
Probability Distributions ◽  
Imprecise Probabilities ◽  
Data Sets ◽  
Classifier Selection ◽  
Training Samples ◽  
Proposed Model ◽  
Label Information ◽  
Dynamic Classifier Selection ◽  
The Individual

Supervised hyperspectral image (HSI) classification relies on accurate label information. However, it is not always possible to collect perfectly accurate labels for training samples. This motivates the development of classifiers that are sufficiently robust to some reasonable amounts of errors in data labels. Despite the growing importance of this aspect, it has not been sufficiently studied in the literature yet. In this paper, we analyze the effect of erroneous sample labels on probability distributions of the principal components of HSIs, and provide in this way a statistical analysis of the resulting uncertainty in classifiers. Building on the theory of imprecise probabilities, we develop a novel robust dynamic classifier selection (R-DCS) model for data classification with erroneous labels. Particularly, spectral and spatial features are extracted from HSIs to construct two individual classifiers for the dynamic selection, respectively. The proposed R-DCS model is based on the robustness of the classifiers’ predictions: the extent to which a classifier can be altered without changing its prediction. We provide three possible selection strategies for the proposed model with different computational complexities and apply them on three benchmark data sets. Experimental results demonstrate that the proposed model outperforms the individual classifiers it selects from and is more robust to errors in labels compared to widely adopted approaches.

Sign in / Sign up

Export Citation Format

Share Document