Relevant bibliographies by topics / DL systems / Journal articles
To see the other types of publications on this topic, follow the link: DL systems.

Journal articles on the topic 'DL systems'

Author: Grafiati
Published: 4 June 2021
Last updated: 14 February 2022

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'DL systems.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Parlitz, U., and L. Kocarev. "Using Surrogate Data Analysis for Unmasking Chaotic Communication Systems." International Journal of Bifurcation and Chaos 07, no. 02 (February 1997): 407–13. http://dx.doi.org/10.1142/s0218127497000273.

Full text
Abstract:
Synchronization-based communication systems are presented using hyperchaotic attractors with Lyapunov dimensions DL = 10.02 and DL = 100.02. The transmitted signal containing the encoded message is subject to surrogate data tests in order to unmask and identify the transmission of informations. Using moderate data sets (16K samples) the tests are able to detect the chaotic carrier in the case of the attractor with DL = 10.02 but not for DL = 100.02. These results thus indicate limits for both, the privacy of chaotic communication systems and surrogate data tests.
APA, Harvard, Vancouver, ISO, and other styles
2

Masłowska, Joanna, and Longin Chruściński. "Potentiometric studies on complexes in Cr(III)-l-aspartic acid-dl-methionine or dl-ethionine systems." Polyhedron 5, no. 5 (1986): 1131–34. http://dx.doi.org/10.1016/s0277-5387(00)84313-2.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Sanaye, Sepehr, and Mohammad Hekmatian. "Comparison of demand limiting and load leveling operating modes of ice cold energy storage (ICES) in an air-conditioning system." Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering 234, no. 1 (December 10, 2019): 137–56. http://dx.doi.org/10.1177/0954408919890434.

Full text
Abstract:
Application of ice cold energy storage (ICES) is for reducing power consumption in air-conditioning systems. ICES systems have two full and partial operating modes. Partial operating mode of ICES system is modeled here at two demand limiting (POM-DL) and load leveling (POM-LL) conditions. After energy, exergy, and economic and environmental modeling/analysis of POM-DL and POM-LL, multi-objective (exergy and total cost) genetic algorithm (GA) optimization technique is applied to find the optimum values of objective functions and system design parameters. Then, the performance of POM-DL and POM-LL systems is compared. For our case study, the acquired results show 11.20% and 10.94% reduction in electricity consumption for POM-DL and POM-LL systems, respectively, in comparison with that for a traditional VCR (an electrical chiller). Furthermore, these systems reduce 13.58% and 12.36% electricity cost by shifting the electricity consumption of cooling system from on peak (ONP) hours to off peak (OFP) hours for POM-DL and POM-LL, respectively.
APA, Harvard, Vancouver, ISO, and other styles
4

Fraga-Lamas, Paula, Lucía Ramos, Víctor Mondéjar-Guerra, and Tiago M. Fernández-Caramés. "A Review on IoT Deep Learning UAV Systems for Autonomous Obstacle Detection and Collision Avoidance." Remote Sensing 11, no. 18 (September 14, 2019): 2144. http://dx.doi.org/10.3390/rs11182144.

Full text
Abstract:
Advances in Unmanned Aerial Vehicles (UAVs), also known as drones, offer unprecedented opportunities to boost a wide array of large-scale Internet of Things (IoT) applications. Nevertheless, UAV platforms still face important limitations mainly related to autonomy and weight that impact their remote sensing capabilities when capturing and processing the data required for developing autonomous and robust real-time obstacle detection and avoidance systems. In this regard, Deep Learning (DL) techniques have arisen as a promising alternative for improving real-time obstacle detection and collision avoidance for highly autonomous UAVs. This article reviews the most recent developments on DL Unmanned Aerial Systems (UASs) and provides a detailed explanation on the main DL techniques. Moreover, the latest DL-UAV communication architectures are studied and their most common hardware is analyzed. Furthermore, this article enumerates the most relevant open challenges for current DL-UAV solutions, thus allowing future researchers to define a roadmap for devising the new generation affordable autonomous DL-UAV IoT solutions.
APA, Harvard, Vancouver, ISO, and other styles
5

Cabanes, Quentin, Benaoumeur Senouci, and Amar Ramdane-Cherif. "Embedded Deep Learning Prototyping Approach for Cyber-Physical Systems: Smart LIDAR Case Study." Journal of Sensor and Actuator Networks 10, no. 1 (February 24, 2021): 18. http://dx.doi.org/10.3390/jsan10010018.

Full text
Abstract:
Cyber-Physical Systems (CPSs) are a mature research technology topic that deals with Artificial Intelligence (AI) and Embedded Systems (ES). They interact with the physical world via sensors/actuators to solve problems in several applications (robotics, transportation, health, etc.). These CPSs deal with data analysis, which need powerful algorithms combined with robust hardware architectures. On one hand, Deep Learning (DL) is proposed as the main solution algorithm. On the other hand, the standard design and prototyping methodologies for ES are not adapted to modern DL-based CPS. In this paper, we investigate AI design for CPS around embedded DL. The main contribution of this work is threefold: (1) We define an embedded DL methodology based on a Multi-CPU/FPGA platform. (2) We propose a new hardware design architecture of a Neural Network Processor (NNP) for DL algorithms. The computation time of a feed forward sequence is estimated to 23 ns for each parameter. (3) We validate the proposed methodology and the DL-based NNP using a smart LIDAR application use-case. The input of our NNP is a voxel grid hardware computed from 3D point cloud. Finally, the results show that our NNP is able to process Dense Neural Network (DNN) architecture without bias.
APA, Harvard, Vancouver, ISO, and other styles
6

Alwan, Nuha A. S., and Zahir M. Hussain. "Deep Learning Control for Digital Feedback Systems: Improved Performance with Robustness against Parameter Change." Electronics 10, no. 11 (May 24, 2021): 1245. http://dx.doi.org/10.3390/electronics10111245.

Full text
Abstract:
Training data for a deep learning (DL) neural network (NN) controller are obtained from the input and output signals of a conventional digital controller that is designed to provide the suitable control signal to a specified plant within a feedback digital control system. It is found that if the DL controller is sufficiently deep (four hidden layers), it can outperform the conventional controller in terms of settling time of the system output transient response to a unit-step reference signal. That is, the DL controller introduces a damping effect. Moreover, it does not need to be retrained to operate with a reference signal of different magnitude, or under system parameter change. Such properties make the DL control more attractive for applications that may undergo parameter variation, such as sensor networks. The promising results of robustness against parameter changes are calling for future research in the direction of robust DL control.
APA, Harvard, Vancouver, ISO, and other styles
7

Khatoon, Zubaida, and Kabir-ud-Din. "Potentiometric investigations on the cadmium(II)-amino acid-imidazole systems (amino acid = glycine, DL-α-alanine or DL-valine)." Polyhedron 9, no. 20 (January 1990): 2437–42. http://dx.doi.org/10.1016/s0277-5387(00)86775-3.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Berman, Daniel, Anna Buczak, Jeffrey Chavis, and Cherita Corbett. "A Survey of Deep Learning Methods for Cyber Security." Information 10, no. 4 (April 2, 2019): 122. http://dx.doi.org/10.3390/info10040122.

Full text
Abstract:
This survey paper describes a literature review of deep learning (DL) methods for cyber security applications. A short tutorial-style description of each DL method is provided, including deep autoencoders, restricted Boltzmann machines, recurrent neural networks, generative adversarial networks, and several others. Then we discuss how each of the DL methods is used for security applications. We cover a broad array of attack types including malware, spam, insider threats, network intrusions, false data injection, and malicious domain names used by botnets.
APA, Harvard, Vancouver, ISO, and other styles
9

Hattemer, Andrew, and Sami Wardat. "Evaluation of Hematocrit Influence on Self-Monitoring of Blood Glucose Based on ISO 15197:2013: Comparison of a Novel System With Five Systems With Different Hematocrit Ranges." Journal of Diabetes Science and Technology 12, no. 2 (January 29, 2018): 333–40. http://dx.doi.org/10.1177/1932296818757550.

Full text
Abstract:
Introduction: ISO 15197:2013 recommends testing procedures and acceptance criteria for the evaluation of influence quantities such as hematocrit on measurement results with systems for self-monitoring of blood glucose (SMBG). In this study, hematocrit influence was evaluated for a novel SMBG system (system A) and five other systems with different hematocrit ranges based on ISO 15197:2013. Methods: Test procedures were performed with one test strip lot for each system. Each system was tested within the hematocrit range indicated in the manufacturer’s labeling (system A: 10-65%, B: 15-65%, C: 20-60%, D: 35-60%, E: 30-60%, F: 30-55%). According to ISO 15197:2013, clause 6.4.2, venous blood samples were used for the evaluation of hematocrit influence. The evaluation was performed for three glucose concentration categories (30-50 mg/dL, 96-144 mg/dL, and 280-420 mg/dL). For each glucose concentration category, at least five different hematocrit levels were investigated. Results: The novel system A and systems B, E, and F complied with the tested lot with the defined criteria and showed ≤10 mg/dL and ≤10% difference between the test sample and the respective control sample with a hematocrit value of 42% ± 2% for BG concentrations <100 mg/dL and ≥100 mg/dL, respectively. Two systems showed >10% difference at glucose concentrations ≥100 mg/dL. Conclusions: Remarkable hematocrit influence within the labeled hematocrit range was obtained in two systems with the tested reagent system lot. Adequate SMBG systems should be carefully chosen by patients and their health care professionals, particularly for patients with increased and decreased hematocrit values.
APA, Harvard, Vancouver, ISO, and other styles
10

ABARBANEL, HENRY D. I., and MIKHAIL M. SUSHCHIK. "LOCAL OR DYNAMICAL DIMENSIONS OF NONLINEAR SYSTEMS INFERRED FROM OBSERVATIONS." International Journal of Bifurcation and Chaos 03, no. 03 (June 1993): 543–50. http://dx.doi.org/10.1142/s0218127493000428.

Full text
Abstract:
In time delay reconstruction of the phase space of a system from observed scalar data, one requires a time lag and an integer embedding dimension. The minimum embedding dimension, dE, may be larger than the actual local dimension of the underlying dynamics, dL. The embedding theorem only guarantees that the attractor of the system is unfolded in the integer dE greater than 2dA with dA being the attractor dimension. We present two methods for determining the dimension, dL≤dE, of the underlying dynamics. The first relies on the local Lyapunov exponents of the dynamics, and the second seeks an optimum dimension for prediction of the time series for steps forward and then backward in time. We demonstrate these methods on several examples. Model building of the dynamics should take place in the dL-dimensional space.
APA, Harvard, Vancouver, ISO, and other styles
11

Hu, Bo, Inés Arana, and Ernesto Compatangelo. "Facilitating DL-based hybrid reasoning with inference fusion." Knowledge-Based Systems 16, no. 5-6 (July 2003): 253–60. http://dx.doi.org/10.1016/s0950-7051(03)00026-1.

Full text
APA, Harvard, Vancouver, ISO, and other styles
12

Tikhomirov, A., A. Trufanov, A. Naji, N. Kinash, R. Umerov, and Z. Umerova. "DL SYSTEMS IN THE ARAB WORLD: SOME ECONOMIC AND SOCIAL ISSUES." Information Technologies in Education, no. 16 (June 12, 2013): 178–83. http://dx.doi.org/10.14308/ite000444.

Full text
APA, Harvard, Vancouver, ISO, and other styles
13

Hou, Weihao, Jinlong Sun, Guan Gui, Tomoaki Ohtsuki, Ahmet M. Elbir, Haris Gacanin, and Hikmet Sari. "Federated Learning for DL-CSI Prediction in FDD Massive MIMO Systems." IEEE Wireless Communications Letters 10, no. 8 (August 2021): 1810–14. http://dx.doi.org/10.1109/lwc.2021.3081695.

Full text
APA, Harvard, Vancouver, ISO, and other styles
14

Kato, Satoru, Kazuhiro Mawatari, Kayo Sugitani, and Yuhko Yasui. "DL-α-aminoadipate is a toxin to Müller cells." Progress in Retinal and Eye Research 15, no. 2 (January 1996): 435–56. http://dx.doi.org/10.1016/1350-9462(96)00010-9.

Full text
APA, Harvard, Vancouver, ISO, and other styles
15

Roussey, Catherine, François Pinet, and Michel Schneider. "Representations of Topological Relations Between Simple Regions in Description Logics." International Journal of Agricultural and Environmental Information Systems 4, no. 2 (April 2013): 50–69. http://dx.doi.org/10.4018/jaeis.2013040105.

Full text
Abstract:
This paper proposes an operational approach to (1) formalize, in Description Logics (DL), the topological relations between simple regions and (2) automatically check whether a set of relations is consistent. The solution allows for the use of traditional DL reasoners (Pellet, Fact++, etc.) to check the consistency of relations and detect the sources of error. The solution does not require any specific extension of the DL or reasoner. The authors demonstrate how to apply this approach with Protégé and Fact++. Different spatial relations in agricultural and environmental applications are also provided to illustrate the possible uses of our method.
APA, Harvard, Vancouver, ISO, and other styles
16

Harn, Lein, Jian Ren, and Changlu Lin. "Design of DL-based certificateless digital signatures." Journal of Systems and Software 82, no. 5 (May 2009): 789–93. http://dx.doi.org/10.1016/j.jss.2008.11.844.

Full text
APA, Harvard, Vancouver, ISO, and other styles
17

Mukhamedyarova, Lilia I., Sergey G. Bezryadin, Elena Yu Klukvina, Vladimir V. Chevela, and Valentina Yu Ivanova. "Composition, stability and stereo effects of zirconium(IV) dl-tartrate formation." Butlerov Communications 57, no. 2 (February 28, 2019): 28–34. http://dx.doi.org/10.37952/roi-jbc-01/19-57-2-28.

Full text
Abstract:
The system of zirconium (IV) – dl-tartaric acid for metal: ligand 1: 1, 1: 2 and 1: 3 ratios in aqueous solution has been studied by means of using potentiometric titration method in combination with mathematical modeling. The comparison of Bjerrum functions from pH for zirconium(IV) systems: d-tartaric acid and zirconium (IV): dl-tartaric acid, has revealed the following features in the behavior of the curves: the degree of titration for the complexes at a fixed pH value for systems with dl-tartaric acid is more than for d-acid. The CPESSP software complex has calculated the composition, stability constants and molar fractions of zirconium(IV) tartrate accumulation. It has been also found that at a ratio of 1: 1 for Zr (IV) and ligand (H4Tart) ions in the system under study ZrHTart+ is formed, which is tetramerized into Zr4Tart40 and, further, tetranuclear particles of varying degrees of deprotonization are formed, as well as mononuclear forms. In a strongly alkaline pH environment > 10, Bjerrum curves for d- and dl-tartaric acids overlap each other and correspond to hydroxocomplexes of varying degrees of titration. For the 1: 2 ratio, the composition of the complexes for the zirconium(IV) – dl-H4T system is slightly different; compared to the zirconium(IV) – dH4T system, differences are clearly observed for both low and high concentrations. Based on these data, a complex formation scheme in the Zr(IV) – dl-tartaric acid system has been proposed for all the ratios studied. The characteristics of stereoselective diastereomer formation have been calculated. It has been revealed that in the medium of racemic tartrate, ddd- and lll-Zr(H2Tart)2(HTart)3-forms, as well as Zr(H2Tart)(НTart)24-Zr(HTart)35- are formed on a stereoselective basis.
APA, Harvard, Vancouver, ISO, and other styles
18

Singeh, Feria Wirba, A. Abrizah, and K. Kiran. "Bringing the digital library success factors into the realm of the technology-organization-environment framework." Electronic Library 38, no. 3 (June 30, 2020): 659–75. http://dx.doi.org/10.1108/el-08-2019-0187.

Full text
Abstract:
Purpose The purpose of this paper is to describe a new benchmarking framework on the factors that influence digital library (DL) adoption by aligning them with the constructs of DL models to establish the likely critical success factors (CSFs) for DL implementation. Design/methodology/approach Concept mapping is used to illustrate the relationship between the information systems success model and DL frameworks. Technology organisation and environment (TOE) framework was chosen as the central theme and was mapped with the three DL frameworks reviewed (5S framework; the Zachman Framework for Enterprise Architecture and the DELOS DL reference model) to come up with the likely success dimensions for DLs. A set of possible success factors was assembled from the literature on previous studies relating to factors that are critical to the success of information systems and DLs. The description of each DL potential success factors was finally developed as an item statement with verification from the literature review. Findings A total of 53 success factors items were assembled from literature represented by the final ten constructs of the CSFs; 16 items characterise DL technology, 13 items denote DL organisation and 24 items symbolise DL environment. Findings show that these factors may be good determinants for an effective implementation of DLs. Research limitations/implications The outcome can positively influence the implementation of DLs worldwide. Originality/value This is the first study in library science that incorporates TOE with DL frameworks to come up with the success factors of DL implementation.
APA, Harvard, Vancouver, ISO, and other styles
19

Thapa, Niraj, Zhipeng Liu, Dukka B. KC, Balakrishna Gokaraju, and Kaushik Roy. "Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection Systems." Future Internet 12, no. 10 (September 30, 2020): 167. http://dx.doi.org/10.3390/fi12100167.

Full text
Abstract:
The development of robust anomaly-based network detection systems, which are preferred over static signal-based network intrusion, is vital for cybersecurity. The development of a flexible and dynamic security system is required to tackle the new attacks. Current intrusion detection systems (IDSs) suffer to attain both the high detection rate and low false alarm rate. To address this issue, in this paper, we propose an IDS using different machine learning (ML) and deep learning (DL) models. This paper presents a comparative analysis of different ML models and DL models on Coburg intrusion detection datasets (CIDDSs). First, we compare different ML- and DL-based models on the CIDDS dataset. Second, we propose an ensemble model that combines the best ML and DL models to achieve high-performance metrics. Finally, we benchmarked our best models with the CIC-IDS2017 dataset and compared them with state-of-the-art models. While the popular IDS datasets like KDD99 and NSL-KDD fail to represent the recent attacks and suffer from network biases, CIDDS, used in this research, encompasses labeled flow-based data in a simulated office environment with both updated attacks and normal usage. Furthermore, both accuracy and interpretability must be considered while implementing AI models. Both ML and DL models achieved an accuracy of 99% on the CIDDS dataset with a high detection rate, low false alarm rate, and relatively low training costs. Feature importance was also studied using the Classification and regression tree (CART) model. Our models performed well in 10-fold cross-validation and independent testing. CART and convolutional neural network (CNN) with embedding achieved slightly better performance on the CIC-IDS2017 dataset compared to previous models. Together, these results suggest that both ML and DL methods are robust and complementary techniques as an effective network intrusion detection system.
APA, Harvard, Vancouver, ISO, and other styles
20

Kim, Jaehun. "Increasing trust in complex machine learning systems." ACM SIGIR Forum 55, no. 1 (June 2021): 1–3. http://dx.doi.org/10.1145/3476415.3476435.

Full text
Abstract:
Machine learning (ML) has become a core technology for many real-world applications. Modern ML models are applied to unprecedentedly complex and difficult challenges, including very large and subjective problems. For instance, applications towards multimedia understanding have been advanced substantially. Here, it is already prevalent that cultural/artistic objects such as music and videos are analyzed and served to users according to their preference, enabled through ML techniques. One of the most recent breakthroughs in ML is Deep Learning (DL), which has been immensely adopted to tackle such complex problems. DL allows for higher learning capacity, making end-to-end learning possible, which reduces the need for substantial engineering effort, while achieving high effectiveness. At the same time, this also makes DL models more complex than conventional ML models. Reports in several domains indicate that such more complex ML models may have potentially critical hidden problems: various biases embedded in the training data can emerge in the prediction, extremely sensitive models can make unaccountable mistakes. Furthermore, the black-box nature of the DL models hinders the interpretation of the mechanisms behind them. Such unexpected drawbacks result in a significant impact on the trustworthiness of the systems in which the ML models are equipped as the core apparatus. In this thesis, a series of studies investigates aspects of trustworthiness for complex ML applications, namely the reliability and explainability. Specifically, we focus on music as the primary domain of interest, considering its complexity and subjectivity. Due to this nature of music, ML models for music are necessarily complex for achieving meaningful effectiveness. As such, the reliability and explainability of music ML models are crucial in the field. The first main chapter of the thesis investigates the transferability of the neural network in the Music Information Retrieval (MIR) context. Transfer learning, where the pre-trained ML models are used as off-the-shelf modules for the task at hand, has become one of the major ML practices. It is helpful since a substantial amount of the information is already encoded in the pre-trained models, which allows the model to achieve high effectiveness even when the amount of the dataset for the current task is scarce. However, this may not always be true if the "source" task which pre-trained the model shares little commonality with the "target" task at hand. An experiment including multiple "source" tasks and "target" tasks was conducted to examine the conditions which have a positive effect on the transferability. The result of the experiment suggests that the number of source tasks is a major factor of transferability. Simultaneously, it is less evident that there is a single source task that is universally effective on multiple target tasks. Overall, we conclude that considering multiple pre-trained models or pre-training a model employing heterogeneous source tasks can increase the chance for successful transfer learning. The second major work investigates the robustness of the DL models in the transfer learning context. The hypothesis is that the DL models can be susceptible to imperceptible noise on the input. This may drastically shift the analysis of similarity among inputs, which is undesirable for tasks such as information retrieval. Several DL models pre-trained in MIR tasks are examined for a set of plausible perturbations in a real-world setup. Based on a proposed sensitivity measure, the experimental results indicate that all the DL models were substantially vulnerable to perturbations, compared to a traditional feature encoder. They also suggest that the experimental framework can be used to test the pre-trained DL models for measuring robustness. In the final main chapter, the explainability of black-box ML models is discussed. In particular, the chapter focuses on the evaluation of the explanation derived from model-agnostic explanation methods. With black-box ML models having become common practice, model-agnostic explanation methods have been developed to explain a prediction. However, the evaluation of such explanations is still an open problem. The work introduces an evaluation framework that measures the quality of the explanations employing fidelity and complexity. Fidelity refers to the explained mechanism's coherence to the black-box model, while complexity is the length of the explanation. Throughout the thesis, we gave special attention to the experimental design, such that robust conclusions can be reached. Furthermore, we focused on delivering machine learning framework and evaluation frameworks. This is crucial, as we intend that the experimental design and results will be reusable in general ML practice. As it implies, we also aim our findings to be applicable beyond the music applications such as computer vision or natural language processing. Trustworthiness in ML is not a domain-specific problem. Thus, it is vital for both researchers and practitioners from diverse problem spaces to increase awareness of complex ML systems' trustworthiness. We believe the research reported in this thesis provides meaningful stepping stones towards the trustworthiness of ML.
APA, Harvard, Vancouver, ISO, and other styles
21

Chen, Jianguo, Kenli Li, Keqin Li, Philip S. Yu, and Zeng Zeng. "Dynamic Bicycle Dispatching of Dockless Public Bicycle-sharing Systems Using Multi-objective Reinforcement Learning." ACM Transactions on Cyber-Physical Systems 5, no. 4 (October 31, 2021): 1–24. http://dx.doi.org/10.1145/3447623.

Full text
Abstract:
As a new generation of Public Bicycle-sharing Systems (PBS), the Dockless PBS (DL-PBS) is an important application of cyber-physical systems and intelligent transportation. How to use artificial intelligence to provide efficient bicycle dispatching solutions based on dynamic bicycle rental demand is an essential issue for DL-PBS. In this article, we propose MORL-BD, a dynamic bicycle dispatching algorithm based on multi-objective reinforcement learning to provide the optimal bicycle dispatching solution for DL-PBS. We model the DL-PBS system from the perspective of cyber-physical systems and use deep learning to predict the layout of bicycle parking spots and the dynamic demand of bicycle dispatching. We define the multi-route bicycle dispatching problem as a multi-objective optimization problem by considering the optimization objectives of dispatching costs, dispatch truck's initial load, workload balance among the trucks, and the dynamic balance of bicycle supply and demand. On this basis, the collaborative multi-route bicycle dispatching problem among multiple dispatch trucks is modeled as a multi-agent and multi-objective reinforcement learning model. All dispatch paths between parking spots are defined as state spaces, and the reciprocal of dispatching costs is defined as a reward. Each dispatch truck is equipped with an agent to learn the optimal dispatch path in the dynamic DL-PBS network. We create an elite list to store the Pareto optimal solutions of bicycle dispatch paths found in each action, and finally get the Pareto frontier. Experimental results on the actual DL-PBS show that compared with existing methods, MORL-BD can find a higher quality Pareto frontier with less execution time.
APA, Harvard, Vancouver, ISO, and other styles
22

Sánchez, Pedro, Patricio Letelier, and Isidro Ramos. "Animating Formal Specifications with Inheritance in a DL-Based Framework." Requirements Engineering 4, no. 4 (December 1, 1999): 198–209. http://dx.doi.org/10.1007/s007660050020.

Full text
APA, Harvard, Vancouver, ISO, and other styles
23

Alsmadi, Mutasem K. "The students’ acceptance of learning management systems in Saudi Arabian Universities." International Journal of Electrical and Computer Engineering (IJECE) 10, no. 4 (August 1, 2020): 4155. http://dx.doi.org/10.11591/ijece.v10i4.pp4155-4161.

Full text
Abstract:
For distance learners, continuous official education is very important for improving knowledge and learning experience in order to meet the career challenges in the modern world. This work studies the success factors which affect the use of LMS and evaluates the ability to apply the proposed model in the field of distance learning (DL) particularly in higher education. The survey was carried out on higher education learners who were included in the DL instructions. This work has utilized a questionnaire that was modified from literature to inspect three measurements, system design, system usage, and system outcome. Utilizing the obtained survey data for students of DL (N=149), the path analysis discovered that the design of the system has a significant effect on the satisfaction of users and intention for using LMS which affects the use of the system. Consequently, the satisfaction of users and the system used has a great impact on the net benefit.
APA, Harvard, Vancouver, ISO, and other styles
24

Burguière, Pierre, Sandrine Auger, Marie-Françoise Hullo, Antoine Danchin, and Isabelle Martin-Verstraete. "Three Different Systems Participate in l-Cystine Uptake in Bacillus subtilis." Journal of Bacteriology 186, no. 15 (August 1, 2004): 4875–84. http://dx.doi.org/10.1128/jb.186.15.4875-4884.2004.

Full text
Abstract:
ABSTRACT The symporter YhcL and two ATP binding cassette transporters, YtmJKLMN and YckKJI, were shown to mediate l-cystine uptake in Bacillus subtilis. A triple ΔyhcL ΔytmJKLMN ΔyckK mutant was unable to grow in the presence of l-cystine and to take up l-cystine. We propose that yhcL, ytmJKLMN, and yckKJI should be renamed tcyP, tcyJKLMN, and tcyABC, respectively. The l-cystine uptake by YhcL (Km = 0.6 μM) was strongly inhibited by seleno-dl-cystine, while the transport due to the YtmJKLMN system (Km = 2.5 μM) also drastically decreased in the presence of dl-cystathionine, l-djenkolic acid, or S-methyl-l-cysteine. Accordingly, a ΔytmJKLMN mutant did not grow in the presence of 100 μM dl-cystathionine, 100 μM l-djenkolic acid, or 100 μM S-methyl-l-cysteine. The expression of the ytmI operon and the yhcL gene was regulated in response to sulfur availability, while the level of expression of the yckK gene remained low under all the conditions tested.
APA, Harvard, Vancouver, ISO, and other styles
25

Hassanien, Hossam El-Din, and Ahmed Elragal. "Deep Learning for Enterprise Systems Implementation Lifecycle Challenges: Research Directions." Informatics 8, no. 1 (February 20, 2021): 11. http://dx.doi.org/10.3390/informatics8010011.

Full text
Abstract:
Transforming the state-of-the-art definition and anatomy of enterprise systems (ESs) seems to some academics and practitioners as an unavoidable destiny. Value depletion lead by early retirement and/or replacement of ESs solutions has been a constant throughout the past decade. That did drive an enormous amount of research that works on addressing the problems leading to the resource drain. The resource waste had persisted throughout the ESs implementation lifecycle phases and dimensions especially post-live phases; leading to depleting the value of the social and technical dimensions of the lifecycle. Parallel to this research stream, the momentum gained by deep learning (DL) algorithms and platforms has been exponentially growing to fuel the advancements toward artificial intelligence and automated augmentation. Correspondingly, this paper is set out to present five key research directions through which DL would take part as a contributor towards the transformation of the ESs state-of-the-art. The paper reviews the ESs implementation lifecycle challenges and the intersection with DL research conducted on ESs by analyzing and synthesizing key basket journals (list of the Association of Information Systems). The paper also presents results from several experiments showcasing the effectiveness of DL in adding a level of augmentation to ESs by analyzing a large set of data extracted from the Atlassian Jira Software Issue Tracking System across different ecosystems. The paper then concludes by presenting the research directions and discussing socio-technical research courses that work on key frontiers identified within this scholarly work.
APA, Harvard, Vancouver, ISO, and other styles
26

Pleus, Stefan, Nina Jendrike, Annette Baumstark, Jochen Mende, Cornelia Haug, and Guido Freckmann. "Evaluation of Analytical Performance of Three Blood Glucose Monitoring Systems: System Accuracy, Measurement Repeatability, and Intermediate Measurement Precision." Journal of Diabetes Science and Technology 13, no. 1 (October 5, 2018): 111–17. http://dx.doi.org/10.1177/1932296818804837.

Full text
Abstract:
Introduction: Blood glucose monitoring systems (BGMS) should provide sufficient analytical quality to allow adequate therapy for diabetes patients. Besides system accuracy, measurement precision is an important aspect of a BGMS’ analytical quality. Methods: Based on ISO 15197:2013/EN ISO 15197:2015, system accuracy, measurement repeatability, and intermediate measurement precision were assessed. ISO 15197:2013 system accuracy criteria require that ⩾95% of individual BGMS’ test strip lot results shall fall within ±15 mg/dl or ±15% of corresponding comparison method results (at glucose concentrations <100 mg/dl and ⩾100 mg/dl, respectively), and that ⩾99% of results fall within consensus error grid (CEG) zones A and B. Measurement repeatability was assessed using venous blood samples, whereas intermediate measurement precision was assessed using control solution samples. Standard deviation (SD) and coefficient of variation (CV) were calculated for glucose concentrations <100 mg/dl and ⩾100 mg/dl, respectively. Precision acceptance criteria are not specified by ISO 15197:2013. Results: All three BGMS fulfilled system accuracy criteria with 96% to 98% of individual test strip lot’s results falling within the acceptable accuracy limits. All measurement results fell within CEG zones A and B. For measurement repeatability, SD was ⩽3.3 mg/dl, and CV was ⩽3.9% for the investigated BGMS. Assessment of intermediate measurement precision showed SD ⩽1.3 mg/dl and CV ⩽3.0%. Conclusion: All three BGMS fulfilled system accuracy criteria of ISO 15197:2013. In absence of acceptance criteria, precision results were found to be consistent with the manufacturer’s labeling of the investigated devices.
APA, Harvard, Vancouver, ISO, and other styles
27

Kalinina, N. V., T. P. Kustova, and L. B. Kochetova. "Arenesulfonylation of dl-serine, l-proline, l-threonine, and dl-methionine in systems 1,4-dioxane—water and propan-2-ol—water." Russian Chemical Bulletin 59, no. 5 (May 2010): 922–26. http://dx.doi.org/10.1007/s11172-010-0186-0.

Full text
APA, Harvard, Vancouver, ISO, and other styles
28

Beraldo, Dario. "Deligne–Lusztig duality on the stack of local systems." Journal für die reine und angewandte Mathematik (Crelles Journal) 2021, no. 778 (July 1, 2021): 31–63. http://dx.doi.org/10.1515/crelle-2021-0030.

Full text
Abstract:
Abstract In the setting of the geometric Langlands conjecture, we argue that the phenomenon of divergence at infinity on Bun G {\operatorname{Bun}_{G}} (that is, the difference between ! {!} -extensions and * {*} -extensions) is controlled, Langlands-dually, by the locus of semisimple G ˇ {{\check{G}}} -local systems. To see this, we first rephrase the question in terms of Deligne–Lusztig duality and then study the Deligne–Lusztig functor 𝖣𝖫 G spec {\mathsf{DL}_{G}^{\mathrm{spec}}} acting on the spectral Langlands DG category IndCoh 𝒩 ⁢ ( LS G ) {{\mathrm{IndCoh}}_{\mathcal{N}}({\mathrm{LS}}_{G})} . We prove that 𝖣𝖫 G spec {\mathsf{DL}_{G}^{\mathrm{spec}}} is the projection IndCoh 𝒩 ⁢ ( LS G ) ↠ QCoh ⁢ ( LS G ) {{\mathrm{IndCoh}}_{\mathcal{N}}({\mathrm{LS}}_{G})\twoheadrightarrow{\mathrm{% QCoh}}({\mathrm{LS}}_{G})} , followed by the action of a coherent D-module St G ∈ 𝔇 ⁢ ( LS G ) {{\mathrm{St}}_{G}\in\mathfrak{D}({\mathrm{LS}}_{G})} , which we call the Steinberg D-module. We argue that St G {{\mathrm{St}}_{G}} might be regarded as the dualizing sheaf of the locus of semisimple G-local systems. We also show that 𝖣𝖫 G spec {\mathsf{DL}_{G}^{\mathrm{spec}}} , while far from being conservative, is fully faithful on the subcategory of compact objects.
APA, Harvard, Vancouver, ISO, and other styles
29

Guerrieri, Marco, and Giuseppe Parla. "Deep Learning and YOLOv3 Systems for Automatic Traffic Data Measurement by Moving Car Observer Technique." Infrastructures 6, no. 9 (September 18, 2021): 134. http://dx.doi.org/10.3390/infrastructures6090134.

Full text
Abstract:
Macroscopic traffic flow variables estimation is of fundamental interest in the planning, designing and controlling of highway facilities. This article presents a novel automatic traffic data acquirement method, called MOM-DL, based on the moving observer method (MOM), deep learning and YOLOv3 algorithm. The proposed method is able to automatically detect vehicles in a traffic stream and estimate the traffic variables flow q, space mean speed vs. and vehicle density k for highways in stationary and homogeneous traffic conditions. The first application of the MOM-DL technique concerns a segment of an Italian highway. In the experiments, a survey vehicle equipped with a camera has been used. Using deep learning and YOLOv3 the vehicles detection and the counting processes have been carried out for the analyzed highway segment. The traffic flow variables have been calculated by the Wardrop relationships. The first results demonstrate that the MOM and MOM-DL methods are in good agreement with each other despite some errors arising with MOM-DL during the vehicle detection step due to a variety of reasons. However, the values of macroscopic traffic variables estimated by means of the Drakes’ traffic flow model together with the proposed method (MOM-DL) are very close to those obtained by the traditional one (MOM), being the maximum percentage variation less than 3%.
APA, Harvard, Vancouver, ISO, and other styles
30

Sheikh, Mahmood, Sheikh Abdul Khaliq, Iqbal Azhar, and Ejaz Mohiuddin. "Impact of Physical Activity on Fasting, Random Blood Sugar and HbA1C in Type – II Diabetic Patients." RADS Journal of Pharmacy and Pharmaceutical Sciences 8, no. 2 (November 11, 2020): 98–105. http://dx.doi.org/10.37962/jpps.v8i2.363.

Full text
Abstract:
Objective: Aim of the study is to evaluate the impact of physical activities on fasting, random blood sugar and HbA1C on patients getting treatment with different systems of medicine. Methods: Prospective cross sectional study was conducted in outpatient facilities of Karachi from July 2017 to July 2018 with treatment duration of at least one year. 195 type – II Diabetic patients with confirm diagnosis enrolled in the study. Study has three arms of anti-diabetic treatment; herbal, homeopathic and allopathic. Outcome measures are Fasting Blood Sugar (FBS), Random Blood Sugar (RBS) and HbA1C with and without exercise. Results: In exercise group, mean reduction of FBS in patients; Allopathic=138.31±46.11 mg/dl, homeopathic=100±00 mg/dl, herbal=121.11±19.64 mg/dl, combination=135.20±40.85 mg/dl. Mean reduction of RBS; Allopathic=186.25±58.77 mg/dl, homeopathic=140.00±00 mg/dl, herbal=198.88±49.60 mg/dl, combination=231.90±64.10 mg/dl. Mean reduction of HbA1C; Allopathic=7.53±1.97%, herbal=6.47±0.335%, combination=7.21±1.147%. In patients not doing exercise, mean reduction of FBS in patients; Allopathic=183.80±85.49 mg/dl, homeopathic=119.00±47.71 mg/dl, herbal=131.00±17.68 mg/dl, combination=134.37±49.88 mg/dl. Mean reduction of RBS; Allopathic=240.08±92.76 mg/dl, homeopathic=163.00±32.33 mg/dl, herbal=193.66±46.42 mg/dl, combination=212.67±87.21 mg/dl. Mean reduction of HbA1C; Allopathic=8.89±2.04%, homeopathic=6.40±00%, herbal=6.54±0.398%, combination=7.10±1.53%. FBS is significantly better controlled by allopathic system compare to homeopathic (p=0.004), herbal (p=0.0001), combination (p=0.0001). RBS is significantly better controlled by allopathic system compare to homeopathic (p=0.006), herbal (p=0.017). Homeopathic system significantly better control RBS compare to combination treatment (p=0.036). Conclusion: Physical activities and exercises can provide better control on FBS, RBS HbA1C. Allopathic and combination systems of medicine have better glycemic control in type – II Diabetes Mellitus patients involve in physical activities.
APA, Harvard, Vancouver, ISO, and other styles
31

Quiroga, Luz M., Brian Hilligoss, Javed Mostafa, Zuzana Hlavackova, Leslie Wood, Xin Chen, and Shona R. Dippie. "Digital libraries for consumer health information (SIG DL)." Proceedings of the American Society for Information Science and Technology 41, no. 1 (September 22, 2005): 571–72. http://dx.doi.org/10.1002/meet.1450410181.

Full text
APA, Harvard, Vancouver, ISO, and other styles
32

Lukowa, Anna, and Venkatkumar Venkatasubramanian. "Centralized UL/DL Resource Allocation for Flexible TDD Systems With Interference Cancellation." IEEE Transactions on Vehicular Technology 68, no. 3 (March 2019): 2443–58. http://dx.doi.org/10.1109/tvt.2019.2893061.

Full text
APA, Harvard, Vancouver, ISO, and other styles
33

Offir, B., and Y. Lev. "Teacher‐Learner Interaction in the Process of Operating DL (Distance Learning) Systems." Educational Media International 36, no. 2 (June 1999): 132–36. http://dx.doi.org/10.1080/0952398990360207.

Full text
APA, Harvard, Vancouver, ISO, and other styles
34

Patel, Priyanka, and Amit Thakkar. "The upsurge of deep learning for computer vision applications." International Journal of Electrical and Computer Engineering (IJECE) 10, no. 1 (February 1, 2020): 538. http://dx.doi.org/10.11591/ijece.v10i1.pp538-548.

Full text
Abstract:
Artificial intelligence (AI) is additionally serving to a brand new breed of corporations disrupt industries from restorative examination to horticulture. Computers can’t nevertheless replace humans, however, they will work superbly taking care of the everyday tangle of our lives. The era is reconstructing big business and has been on the rise in recent years which has grounded with the success of deep learning (DL). Cyber-security, Auto and health industry are three industries innovating with AI and DL technologies and also Banking, retail, finance, robotics, manufacturing. The healthcare industry is one of the earliest adopters of AI and DL. DL accomplishing exceptional dimensions levels of accurateness to the point where DL algorithms can outperform humans at classifying videos & images. The major drivers that caused the breakthrough of deep neural networks are the provision of giant amounts of coaching information, powerful machine infrastructure, and advances in academia. DL is heavily employed in each academe to review intelligence and within the trade-in building intelligent systems to help humans in varied tasks. Thereby DL systems begin to crush not solely classical ways, but additionally, human benchmarks in numerous tasks like image classification, action detection, natural language processing, signal process, and linguistic communication process.
APA, Harvard, Vancouver, ISO, and other styles
35

Gardezi, Syed Jamal Safdar, Ahmed Elazab, Baiying Lei, and Tianfu Wang. "Breast Cancer Detection and Diagnosis Using Mammographic Data: Systematic Review." Journal of Medical Internet Research 21, no. 7 (July 26, 2019): e14464. http://dx.doi.org/10.2196/14464.

Full text
Abstract:
Background Machine learning (ML) has become a vital part of medical imaging research. ML methods have evolved over the years from manual seeded inputs to automatic initializations. The advancements in the field of ML have led to more intelligent and self-reliant computer-aided diagnosis (CAD) systems, as the learning ability of ML methods has been constantly improving. More and more automated methods are emerging with deep feature learning and representations. Recent advancements of ML with deeper and extensive representation approaches, commonly known as deep learning (DL) approaches, have made a very significant impact on improving the diagnostics capabilities of the CAD systems. Objective This review aimed to survey both traditional ML and DL literature with particular application for breast cancer diagnosis. The review also provided a brief insight into some well-known DL networks. Methods In this paper, we present an overview of ML and DL techniques with particular application for breast cancer. Specifically, we search the PubMed, Google Scholar, MEDLINE, ScienceDirect, Springer, and Web of Science databases and retrieve the studies in DL for the past 5 years that have used multiview mammogram datasets. Results The analysis of traditional ML reveals the limited usage of the methods, whereas the DL methods have great potential for implementation in clinical analysis and improve the diagnostic capability of existing CAD systems. Conclusions From the literature, it can be found that heterogeneous breast densities make masses more challenging to detect and classify compared with calcifications. The traditional ML methods present confined approaches limited to either particular density type or datasets. Although the DL methods show promising improvements in breast cancer diagnosis, there are still issues of data scarcity and computational cost, which have been overcome to a significant extent by applying data augmentation and improved computational power of DL algorithms.
APA, Harvard, Vancouver, ISO, and other styles
36

Bayoudhi, Leila, Najla Sassi, and Wassim Jaziri. "How to Repair Inconsistency in OWL 2 DL Ontology Versions?" Data & Knowledge Engineering 116 (July 2018): 138–58. http://dx.doi.org/10.1016/j.datak.2018.05.010.

Full text
APA, Harvard, Vancouver, ISO, and other styles
37

Tomita, Nozomi, Shoji Imai, Yusuke Kanayama, Issaku Kawashima, and Hiroaki Kumano. "Use of Multichannel Near Infrared Spectroscopy to Study Relationships Between Brain Regions and Neurocognitive Tasks of Selective/Divided Attention and 2-Back Working Memory." Perceptual and Motor Skills 124, no. 3 (March 27, 2017): 703–20. http://dx.doi.org/10.1177/0031512517700054.

Full text
Abstract:
While dichotic listening (DL) was originally intended to measure bottom-up selective attention, it has also become a tool for measuring top-down selective attention. This study investigated the brain regions related to top-down selective and divided attention DL tasks and a 2-back task using alphanumeric and Japanese numeric sounds. Thirty-six healthy participants underwent near-infrared spectroscopy scanning while performing a top-down selective attentional DL task, a top-down divided attentional DL task, and a 2-back task. Pearson’s correlations were calculated to show relationships between oxy-Hb concentration in each brain region and the score of each cognitive task. Different brain regions were activated during the DL and 2-back tasks. Brain regions activated in the top-down selective attention DL task were the left inferior prefrontal gyrus and left pars opercularis. The left temporopolar area was activated in the top-down divided attention DL task, and the left frontopolar area and left dorsolateral prefrontal cortex were activated in the 2-back task. As further evidence for the finding that each task measured different cognitive and brain area functions, neither the percentages of correct answers for the three tasks nor the response times for the selective attentional task and the divided attentional task were correlated to one another. Thus, the DL and 2-back tasks used in this study can assess multiple areas of cognitive, brain-related dysfunction to explore their relationship to different psychiatric and neurodevelopmental disorders.
APA, Harvard, Vancouver, ISO, and other styles
38

Cusick, C. G., and J. H. Kaas. "Cortical connections of area 18 and dorsolateral visual cortex in squirrel monkeys." Visual Neuroscience 1, no. 2 (March 1988): 211–37. http://dx.doi.org/10.1017/s0952523800001486.

Full text
Abstract:
AbstractCortical connections of area 18 (V-II) and part of the dorsolateral visual area (DL) were determined in squirrel monkeys with single and multiple injections of the sensitive bidirectional tracer, wheat germ agglutinin conjugated to horseradish peroxidase (WGA-HRP). Injections were placed into portions of area 18 or DL on the dorsolateral surface of the brain, patterns of label were examined in brain sections cut parallel to the surface of physically flattened cortex, and comparisons were made with alternate brain sections reacted for cytochrome oxidase (CO) or stained for myelinated fibers. Major results are as follows. (1) Area 18 was identified by a characteristic alternation of dense and light CO bands crossing its width; the middle temporal visual area (MT) was CO dense; the dorsolateral area (DL) was less reactive, with rostral DL (DLR) lighter than caudal DL (DLC); area 17 had clear CO puffs in the supragranular layers. (2) Intrinsic connections revealed in area 18 included a narrow 100–200 μm fringe of less dense label around each injection core, label unevenly distributed in small clumps within 1–2 mm of injection sites, and clumps of transported label up to 6 mm from injection sites. (3) Single and multiple injections in area 18 produced patterns of labeled cells and terminations in area 17 that ranged from lattice- to puff-like in surface-view distribution. With multiple area 18 injections, regions of area 17 could be found where transported label was concentrated in CO puffs, avoided the CO puffs, or overlapped both puff and interpuff divisions of cortex. The labeled regions of area 17 were somewhat larger than the injection sites, suggesting some convergence from area 17 to area 18. (4) The major rostral connections of area 18 were with caudal DL (DLC). Rostral DL (DLR) was largely free of transported label. Single injection sites in area 18 resulted in several large clumps of label separated by regions of sparse or no label in DLC. Injections in lateral area 18 produced lateral foci of label in DL, while more medial injections produced more medial foci. However, following multiple injections into area 18 that included the representation of central vision, a continuous 2–3-mm-wide band of infragranular labeled cells extended from area 18 caudally to MT rostrally in the presumed location of central vision in DLC and DLR. (5) Injections in area 18 produced foci of label in MT. Label was more dorsal in MT with more dorsal injection sites in area 18. (6) Injections in area 18 resulted in sparse label in cortex within the inferior temporal sulcus and in cortex in the location of the frontal eye field. (7) Callosal connections of area 18 were with areas 17, 18, DL, and sparsely with MT. Multiple injections in area 18 produced a narrow, dense strip of label along the contralateral 17/18 border. Most of this label was in area 18, but small protrusions of label extended into area 17, and small separate foci of label were found displaced slightly into area 17. Fingers of callosal connections extended rostrally from the caudal border to cross up to half of the width of medial area 18 and the entire width of lateral area 18 where central vision is represented. Patchy callosal connections were found with DLC. (8) Injections in caudal DL confirmed the observation from area 18 injections that major connections of DLC are with area 18. Injections in DLR produced scattered, small foci of label in area 18 near the rostral border, as well as puffs of intrinsic connections, connections with MT, and with cortex rostral to area 18 medially.The major conclusion stemming from the present results is that the DL region consists of at least two fields, with the caudal portion, DLC, receiving major inputs from area 18, and the rostral portion, DLR, having little input from area 18.
APA, Harvard, Vancouver, ISO, and other styles
39

Zhang, Xiaowang. "Forgetting for distance-based reasoning and repair in DL-Lite." Knowledge-Based Systems 107 (September 2016): 246–60. http://dx.doi.org/10.1016/j.knosys.2016.06.020.

Full text
APA, Harvard, Vancouver, ISO, and other styles
40

Gomes, Paulo R. B., André L. F. de Almeida, João Paulo C. L. da Costa, and Rafael T. de Sousa. "Joint DL and UL Channel Estimation for Millimeter Wave MIMO Systems Using Tensor Modeling." Wireless Communications and Mobile Computing 2019 (September 15, 2019): 1–13. http://dx.doi.org/10.1155/2019/4858137.

Full text
Abstract:
In this paper, we address the problem of joint downlink (DL) and uplink (UL) channel estimation for millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems. Assuming a closed-loop and multifrequency-based channel training framework in which pilot signals received by multiple antenna mobile stations (MSs) are coded and spread in the frequency domain via multiple adjacent subcarriers, we propose two tensor-based semiblind receivers by capitalizing on the multilinear structure and sparse feature of the received signal at the BS equipped with a hybrid analog-digital beamforming (HB) architecture. As a first processing stage, the joint estimation of the compressed DL and UL channel matrices can be obtained in an iterative way by means of an alternating least squares (ALS) algorithm that capitalizes on a parallel factors model for the received signals. Alternatively, for more restricted scenarios, a closed-form solution is also proposed. From the estimated effective channel matrices, the users’ channel parameters such as angles of departure (AoD), angles of arrival (AoA), and path gains are then estimated in a second processing stage by solving independent compressed sensing (CS) problems (one for each MS). In contrast to the classical approach in the literature, in which the DL and UL channel estimation problems are usually considered as two separate problems, our idea is to jointly estimate both the DL and UL channels as a single problem by concentrating most of the processing burden for channel estimation at the BS side. Simulation results demonstrate that the proposed receivers achieve a performance close to the classical approach that is applied on DL and UL communication links separately, with the advantage of avoiding complex computations for channel estimation at the MS side as well as dedicated feedback channels for each MS, which are attractive features for massive MIMO systems.
APA, Harvard, Vancouver, ISO, and other styles
41

Ting, Daniel Shu Wei, Louis R. Pasquale, Lily Peng, John Peter Campbell, Aaron Y. Lee, Rajiv Raman, Gavin Siew Wei Tan, Leopold Schmetterer, Pearse A. Keane, and Tien Yin Wong. "Artificial intelligence and deep learning in ophthalmology." British Journal of Ophthalmology 103, no. 2 (October 25, 2018): 167–75. http://dx.doi.org/10.1136/bjophthalmol-2018-313173.

Full text
Abstract:
Artificial intelligence (AI) based on deep learning (DL) has sparked tremendous global interest in recent years. DL has been widely adopted in image recognition, speech recognition and natural language processing, but is only beginning to impact on healthcare. In ophthalmology, DL has been applied to fundus photographs, optical coherence tomography and visual fields, achieving robust classification performance in the detection of diabetic retinopathy and retinopathy of prematurity, the glaucoma-like disc, macular oedema and age-related macular degeneration. DL in ocular imaging may be used in conjunction with telemedicine as a possible solution to screen, diagnose and monitor major eye diseases for patients in primary care and community settings. Nonetheless, there are also potential challenges with DL application in ophthalmology, including clinical and technical challenges, explainability of the algorithm results, medicolegal issues, and physician and patient acceptance of the AI ‘black-box’ algorithms. DL could potentially revolutionise how ophthalmology is practised in the future. This review provides a summary of the state-of-the-art DL systems described for ophthalmic applications, potential challenges in clinical deployment and the path forward.
APA, Harvard, Vancouver, ISO, and other styles
42

Chiu, Yu-Chiao, Hung-I. Harry Chen, Aparna Gorthi, Milad Mostavi, Siyuan Zheng, Yufei Huang, and Yidong Chen. "Deep learning of pharmacogenomics resources: moving towards precision oncology." Briefings in Bioinformatics 21, no. 6 (December 8, 2019): 2066–83. http://dx.doi.org/10.1093/bib/bbz144.

Full text
Abstract:
Abstract The recent accumulation of cancer genomic data provides an opportunity to understand how a tumor’s genomic characteristics can affect its responses to drugs. This field, called pharmacogenomics, is a key area in the development of precision oncology. Deep learning (DL) methodology has emerged as a powerful technique to characterize and learn from rapidly accumulating pharmacogenomics data. We introduce the fundamentals and typical model architectures of DL. We review the use of DL in classification of cancers and cancer subtypes (diagnosis and treatment stratification of patients), prediction of drug response and drug synergy for individual tumors (treatment prioritization for a patient), drug repositioning and discovery and the study of mechanism/mode of action of treatments. For each topic, we summarize current genomics and pharmacogenomics data resources such as pan-cancer genomics data for cancer cell lines (CCLs) and tumors, and systematic pharmacologic screens of CCLs. By revisiting the published literature, including our in-house analyses, we demonstrate the unprecedented capability of DL enabled by rapid accumulation of data resources to decipher complex drug response patterns, thus potentially improving cancer medicine. Overall, this review provides an in-depth summary of state-of-the-art DL methods and up-to-date pharmacogenomics resources and future opportunities and challenges to realize the goal of precision oncology.
APA, Harvard, Vancouver, ISO, and other styles
43

Liu, Xiulei, Bo Cheng, Jianxin Liao, Payam Barnaghi, Li Wan, and Jingyu Wang. "OMI-DL: An Ontology Matching Framework." IEEE Transactions on Services Computing 9, no. 4 (July 1, 2016): 580–93. http://dx.doi.org/10.1109/tsc.2015.2410794.

Full text
APA, Harvard, Vancouver, ISO, and other styles
44

SCHNORR, C. "Enhancing the security of perfect blind DL-signatures." Information Sciences 176, no. 10 (May 22, 2006): 1305–20. http://dx.doi.org/10.1016/j.ins.2005.04.007.

Full text
APA, Harvard, Vancouver, ISO, and other styles
45

Mitra, Avijit, Bhanu Pratap Singh Rawat, David D. McManus, and Hong Yu. "Relation Classification for Bleeding Events From Electronic Health Records Using Deep Learning Systems: An Empirical Study." JMIR Medical Informatics 9, no. 7 (July 2, 2021): e27527. http://dx.doi.org/10.2196/27527.

Full text
Abstract:
Background Accurate detection of bleeding events from electronic health records (EHRs) is crucial for identifying and characterizing different common and serious medical problems. To extract such information from EHRs, it is essential to identify the relations between bleeding events and related clinical entities (eg, bleeding anatomic sites and lab tests). With the advent of natural language processing (NLP) and deep learning (DL)-based techniques, many studies have focused on their applicability for various clinical applications. However, no prior work has utilized DL to extract relations between bleeding events and relevant entities. Objective In this study, we aimed to evaluate multiple DL systems on a novel EHR data set for bleeding event–related relation classification. Methods We first expert annotated a new data set of 1046 deidentified EHR notes for bleeding events and their attributes. On this data set, we evaluated three state-of-the-art DL architectures for the bleeding event relation classification task, namely, convolutional neural network (CNN), attention-guided graph convolutional network (AGGCN), and Bidirectional Encoder Representations from Transformers (BERT). We used three BERT-based models, namely, BERT pretrained on biomedical data (BioBERT), BioBERT pretrained on clinical text (Bio+Clinical BERT), and BioBERT pretrained on EHR notes (EhrBERT). Results Our experiments showed that the BERT-based models significantly outperformed the CNN and AGGCN models. Specifically, BioBERT achieved a macro F1 score of 0.842, outperforming both the AGGCN (macro F1 score, 0.828) and CNN models (macro F1 score, 0.763) by 1.4% (P<.001) and 7.9% (P<.001), respectively. Conclusions In this comprehensive study, we explored and compared different DL systems to classify relations between bleeding events and other medical concepts. On our corpus, BERT-based models outperformed other DL models for identifying the relations of bleeding-related entities. In addition to pretrained contextualized word representation, BERT-based models benefited from the use of target entity representation over traditional sequence representation
APA, Harvard, Vancouver, ISO, and other styles
46

Sang, Tzu-Hsien, and You-Cheng Xu. "Clipping Noise Compensation with Neural Networks in OFDM Systems." Signals 1, no. 1 (August 3, 2020): 100–109. http://dx.doi.org/10.3390/signals1010005.

Full text
Abstract:
The application of deep learning (DL) to solve physical layer issues has emerged as a prominent topic. In this paper, the mitigation of clipping effects for orthogonal frequency division multiplexing (OFDM) systems with the help of a Neural Network (NN) is investigated. Unlike conventional clipping recovery algorithms, which involve costly iterative procedures, the DL-based method learns to directly reconstruct the clipped part of the signal while the unclipped part is protected. Furthermore, an interpretation of the learned weight matrices of the neural network is presented. It is observed that parts of the network, in effect, implement transformations very similar to the (Inverse) Discrete Fourier Transform (DFT/IDFT) to provide information in both the time and frequency domains. The simulation results show that the proposed method outperforms existing algorithms for recovering clipped OFDM signals in terms of both mean square error (MSE) and Bit Error Rate (BER).
APA, Harvard, Vancouver, ISO, and other styles
47

Liu, Qing, Jiajia Guo, Chao-Kai Wen, and Shi Jin. "Adversarial attack on DL-based massive MIMO CSI feedback." Journal of Communications and Networks 22, no. 3 (June 2020): 230–35. http://dx.doi.org/10.1109/jcn.2020.000016.

Full text
APA, Harvard, Vancouver, ISO, and other styles
48

Pleus, Stefan, Annette Baumstark, Nina Jendrike, Jochen Mende, Manuela Link, Eva Zschornack, Cornelia Haug, and Guido Freckmann. "System accuracy evaluation of 18 CE-marked current-generation blood glucose monitoring systems based on EN ISO 15197:2015." BMJ Open Diabetes Research & Care 8, no. 1 (January 2020): e001067. http://dx.doi.org/10.1136/bmjdrc-2019-001067.

Full text
Abstract:
ObjectiveAccuracy of 18 current-generation blood glucose monitoring systems (BGMS) available in Europe was evaluated applying criteria adapted from EN ISO 15197:2015 with one reagent system lot. BGMS were selected based on market research data.Research design and methodsThe BGMS ABRA, Accu-Chek Guide, AURUM, CareSens Dual, CERA-CHEK 1CODE, ContourNext One, eBsensor, FreeStyle Freedom Lite, GL50 evo, GlucoCheck GOLD, GlucoMen areo 2K, GluNEO, MyStar DoseCoach, OneTouch Verio Flex, Pic GlucoTest, Rightest GM700S, TRUEyou, and WaveSense JAZZ Wireless were tested using capillary blood from 100 different subjects and assessing the percentage of results within ±15 mg/dL (0.83 mmol/L) or 15% of comparison method results for BG concentrations below or above 100 mg/dL (5.55 mmol/L), respectively. In addition, the minimal deviation from comparison method results within which ≥95% of results of the respective BGMS were found was calculated.ResultsIn total, 14 BGMS had ≥95% of results within ±15 mg/dL (0.83 mmol/L) or ±15% and 3 BGMS had ≥95% of results within ±10 mg/dL (0.55 mmol/L) or ±10% of the results obtained with the comparison method. The smallest deviation from comparison method results within which ≥95% of results were found was ±7.7 mg/dL (0.43 mmol/L) or ±7.7%; the highest deviation was ±19.7 mg/dL (1.09 mmol/L) or ±19.7%.ConclusionsThis accuracy evaluation shows that not all CE-labeled BGMS fulfill accuracy requirements of ISO 15197 reliably and that there is considerable variation even among BGMS fulfilling these criteria. This safety-related information should be taken into account by patients and healthcare professionals when making therapy decisions.Trial registration numberNCT03737188.
APA, Harvard, Vancouver, ISO, and other styles
49

Zha, Xiong, Hua Peng, Xin Qin, Guang Li, and Sihan Yang. "A Deep Learning Framework for Signal Detection and Modulation Classification." Sensors 19, no. 18 (September 19, 2019): 4042. http://dx.doi.org/10.3390/s19184042.

Full text
Abstract:
Deep learning (DL) is a powerful technique which has achieved great success in many applications. However, its usage in communication systems has not been well explored. This paper investigates algorithms for multi-signals detection and modulation classification, which are significant in many communication systems. In this work, a DL framework for multi-signals detection and modulation recognition is proposed. Compared to some existing methods, the signal modulation format, center frequency, and start-stop time can be obtained from the proposed scheme. Furthermore, two types of networks are built: (1) Single shot multibox detector (SSD) networks for signal detection and (2) multi-inputs convolutional neural networks (CNNs) for modulation recognition. Additionally, the importance of signal representation to different tasks is investigated. Experimental results demonstrate that the DL framework is capable of detecting and recognizing signals. And compared to the traditional methods and other deep network techniques, the current built DL framework can achieve better performance.
APA, Harvard, Vancouver, ISO, and other styles
50

Ji, Wei, Feng Zhang, and Ling Qiu. "Multipath Extraction Based UL/DL Channel Estimation for FDD Massive MIMO-OFDM Systems." IEEE Access 9 (2021): 75349–61. http://dx.doi.org/10.1109/access.2021.3081497.

Full text
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the bibliographies on the topic 'DL systems' for other source types:
Dissertations / Theses Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography