Deep Learning-Aided Multicarrier Systems Luong, Thien Van; Ko, Youngwook; Matthaiou, Michail ...
IEEE transactions on wireless communications,
2021-March, 2021-3-00, 20210301, Letnik:
20, Številka:
3
Journal Article
Recenzirano
Odprti dostop
This paper proposes a deep learning (DL)-aided multicarrier (MC) system operating on fading channels, where both modulation and demodulation blocks are modeled by deep neural networks (DNNs), ...regarded as the encoder and decoder of an autoencoder (AE) architecture, respectively. Unlike existing AE-based systems, which incorporate domain knowledge of a channel equalizer to suppress the effects of wireless channels, the proposed scheme, termed as MC-AE, directly feeds the decoder with the channel state information and received signal, which are then processed in a fully data-driven manner. This new approach enables MC-AE to jointly learn the encoder and decoder to optimize the diversity and coding gains over fading channels. In particular, the block error rate of MC-AE is analyzed to show its higher performance gains than existing hand-crafted baselines, such as various recent index modulation-based MC schemes. We then extend MC-AE to multiuser scenarios, wherein the resultant system is termed as MU-MC-AE. Accordingly, two novel DNN structures for uplink and downlink MU-MC-AE transmissions are proposed, along with a novel cost function that ensures a fast training convergence and fairness among users. Finally, simulation results are provided to show the superiority of the proposed DL-based schemes over current baselines, in terms of both the error performance and receiver complexity.
Display omitted
•Porous ε-MnO2 microcubes prepared by glucose-urea-assisted hydrothermal synthesis.•Urea and glucose as the morphology-directing and soft-template agents, respectively.•Obtained ...materials exhibit great porosity, reducibility, lattice oxygen reactivity and Mn4+ fraction.•Mutual effects of porosity, reducibility, lattice oxygen reactivity and Mn4+ fraction on catalytic performance.•Long-term stability of ε-MnO2 at 245 °C for 10 h at GHSV = 60,000 h−1.
3D architectures porous epsilon-type manganese dioxide (ε-MnO2) microcubes (PEMD) are successfully prepared by a glucose-urea-assisted hydrothermal synthesis of MnCO3-carbon composites followed by annealing. It turns out that urea essentially assists in building the cubic shape while glucose plays a crucial role to form carbon inside the microcrystals, which are latterly removed by annealing to generate the porous structure. As a result, ε-MnO2 materials possessing extraordinary features including the high porosity, reducibility, lattice oxygen reactivity and Mn4+ fraction, are feasible tailored. These unique properties, all together, significantly improve the catalytic performances of complete oxidation of toluene. Thus, it is found that the optimal catalyst (manganese-glucose-urea ratio of 6-2-6) synthesized at 180 °C exhibits an excellent activity for the complete oxidation of toluene (T90 = 243 °C, lower 10 °C than that of pristine ε-MnO2) and stability up to 10 h.
In the maintenance optimisation framework, grouping maintenance is a promising solution for maintenance planning of multi-component systems, in which maintenance activities are performed together to ...reduce maintenance costs. One of the most widely identified challenges in real applications of grouping maintenance is that it may disturb the maintenance workload balance (smoothness), causing many difficulties in production and/or labour scheduling and inventory management. In this study, we propose a joint optimisation approach for maintenance grouping and workload balancing to address the above challenge. First, a mathematical model of the joint optimisation problem was derived. A multi-objective grouping optimisation approach based on the Weighted Sum model and Genetic Algorithm was implemented to determine the Pareto-optimal grouping solution. The proposed approach was applied to a real case study of an automotive plant comprising 40 production lines with 1090 components. The results highlighted the advantages, effectiveness, and flexibility of the proposed maintenance approach in real-world applications.
Bis(3-indolyl)methanes (BIM) are highly valuable and appear in the core structure of many natural products and pharmacologically active compounds (anticancer, anti-inflammatory, antiobesity, ...antimetastatic, antimicrobial, etc.). Herein, we have disclosed an air stable and highly efficient CuFe2O4 heterogeneous catalyst for alkylation of indoles with alcohols to give bis(3-indolyl)methanes in very good yields. The CuFe2O4 catalyst has been found to be magnetically recycled at least five times without losing significant catalytic activity.
Display omitted
•An efficient CuFe2O4 nanoparticles catalyst for the alkylation of indoles with alcohols.•O2 in air was found to be the oxidant in the oxidation of alcohol to aldehyde.•The utilization of challenging aliphatic alcohols as alkylating reagents was explored.•The CuFe2O4 catalyst was recycled at least five times without losing the significant catalytic activity.
Display omitted
•A natural laterite from Vietnam effectively removed arsenic from groundwater.•Thermodynamic constant ∆G° negative but ∆H° and ∆S° positive for As(III) and As(V).•A community water ...filter system was successfully designed using the laterite.•The filter reduced high arsenic levels in groundwater to below WHO drinking water level.
In the Red River Delta, Vietnam, arsenic (As) contamination of groundwater is a serious problem where more than seventeen million people are affected. Millions of people in this area are unable to access clean water from the existing centralized water treatment systems. They also cannot afford to buy expensive household water filters. Similar dangerous situations exist in many other countries and for this reason there is an urgent need to develop a cost-effective decentralized filtration system using new low-cost adsorbents for removing arsenic. In this study, seven locally available low-cost materials were tested for arsenic removal by conducting batch adsorption experiments. Of these materials, a natural laterite (48.7% Fe2O3 and 18.2% Al2O3) from Thach That (NLTT) was deemed the most suitable adsorbent based on arsenic removal performance, local availability, stability/low risk and cost (US$ 0.10/kg). Results demonstrated that the adsorption process was less dependent on the solution pH from 2.0 to 10. The coexisting anions competed with As(III) and As(V) in the order, phosphate > silicate > bicarbonate > sulphate > chloride. The adsorption process reached a fast equilibrium at approximately 120–360 min, depending on the initial arsenic concentrations. The Langmuir maximum adsorption capacities of NLTT at 30 °C were 512 μg/g for As(III) and 580 μg/g for As(V), respectively. Thermodynamic study conducted at 10 °C, 30 °C, and 50 °C suggested that the adsorption process of As(III) and As(V) was spontaneous and endothermic in nature. A water filtration system packed with NLTT was tested in a childcare centre in the most disadvantaged community in Ha Nam province, Vietnam, to determine arsenic removal performance in an operation lasting six months. Findings showed that the system reduced total arsenic concentration in groundwater from 122 to 237 μg/L to below the Vietnam drinking water standard of 10 μg/L.
This paper proposes a multiple-input multiple-output (MIMO) transmission scheme for M-ary modulations, called Spatially Modulated Orthogonal Space-Time Block Coding (SM-OSTBC), based on the concept ...of Spatial Constellation (SC) codewords introduced by Le at el. . In the proposed scheme, transmit codeword matrices are generated by multiplying SC matrices with codewords constructed from Orthogonal Space-time Block Codes (O-STBC). The maximum spectral efficiency of the proposed scheme is equal to (n_T-2+ log_2 M) bpcu, where n_T is the number of transmit antennas and M is the modulation order. The SC matrices provide a means of carrying information bits together with the O-STBC codewords and allow the SM-OSTBC scheme to achieve second-order transmit diversity by satisfying the non-vanishing determinant property. A systematic method to design the SC codewords for an even number of transmit antennas greater than 3 is presented. A single-stream maximum-likelihood (ML) decoder, which requires a low computational complexity thanks to the structure of the SM-OSTBC codewords and to the orthogonality of the O-STBCs, and a sphere decoder with further reduced signal processing complexity are developed. The bit error rate (BER) performance of the proposed scheme is studied by using both theoretical union bound analysis and computer simulations. Finally, simulation results are presented in order to compare BER performance, energy efficiency and decoding complexity of the proposed scheme with those of several existing MIMO transmission schemes.
Diabetes leads to health problems for hundreds of millions of people globally every year. Available medical records of patients quantify symptoms, body features, and clinical laboratory test values, ...which can be used to perform biostatistics analysis aimed at finding patterns or features undetectable by current practice. In this work, we proposed a machine learning model to predict the early onset of diabetes patients. It is a novel wrapper-based feature selection utilizing Grey Wolf Optimization (GWO) and an Adaptive Particle Swam Optimization (APSO) to optimize the Multilayer Perceptron (MLP) to reduce the number of required input attributes. Moreover, we also compared the results achieved using this method and several conventional machine learning algorithms approaches such as Support Vector Machine (SVM), Decision Tree (DT), K-Nearest Neighbor (KNN), Naïve Bayesian Classifier (NBC), Random Forest Classifier (RFC), Logistic Regression (LR). Computational results of our proposed method show not only that much fewer features are needed, but also higher prediction accuracy can be achieved (96% for GWO - MLP and 97% for APGWO - MLP). This work has the potential to be applicable to clinical practice and become a supporting tool for doctors/physicians.
This paper presents information on the gross alpha and gross beta activity concentrations of two hundred twenty-six groundwater samples collected by gas flow proportional counters in southern ...Vietnam. The gross alpha results in the water samples ranged from 0.024 to 0.748 Bq L
with a mean of 0.183 ± 0.034 Bq L
, and the gross beta results in the water samples ranged from 0.027-0.632 Bq L
with a mean of 0.152 ± 0.015 Bq L
. The values obtained in this work were compared with those previously published for various regions or countries. Next, untreated and treated groundwater samples were analyzed to assess their influences on the treatment process. The results showed that there were differences in the minimum detection concentrations and the mean activity values between the untreated and treated groundwater samples (The p-value of the mean comparison tests is significant with p < 0.05). In both sample groups, there was a strong positive correlation of the gross alpha versus the gross beta results (r > 0.6). This means that among the radionuclides, the major sources of beta radiation are uranium and thorium decay series radionuclides. Finally, the annual effective dose for adults (>17 years) was calculated based on the assumption that major radionuclides have the highest effective dose conversion factors. In general, the results for Pb-210, Ra-226, and Ra-228 were observed to be lower than the recommended reference values established by the World Health Organization and the International Atomic Energy Agency, except for the value of Po-210.
This two-part paper aims to provide a comprehensive survey on how emerging technologies, e.g., wireless and networking, artificial intelligence (AI) can enable, encourage, and even enforce social ...distancing practice. In Part I, an extensive background of social distancing is provided, and enabling wireless technologies are thoroughly surveyed. In this Part II, emerging technologies such as machine learning, computer vision, thermal, ultrasound, etc., are introduced. These technologies open many new solutions and directions to deal with problems in social distancing, e.g., symptom prediction, detection and monitoring quarantined people, and contact tracing. Finally, we discuss open issues and challenges (e.g., privacy-preserving, scheduling, and incentive mechanisms) in implementing social distancing in practice. As an example, instead of reacting with ad-hoc responses to COVID-19-like pandemics in the future, smart infrastructures (e.g., next-generation wireless systems like 6G, smart home/building, smart city, intelligent transportation systems) should incorporate a pandemic mode in their standard architectures/designs.
This paper analyzes the bit error rate (BER) of multicarrier index keying—orthogonal frequency division multiplexing (MCIK-OFDM) with selection combining (SC) diversity reception. Particularly, we ...propose a generalized framework to derive the BER for both the low-complexity greedy detector (GD) and maximum likelihood (ML) detector. Based on this, closed-form expressions for the BERs of MCIK-OFDM with the SC using either the ML or the GD are derived in presence of the channel state information (CSI) imperfection. The asymptotic analysis is presented to gain helpful insights into effects of different CSI conditions on the BERs of these two detectors. More importantly, we theoretically provide opportunities for using the GD instead of the ML under each specific CSI uncertainty, which depend on the number of receiver antennas and the
M
-ary modulation size. Finally, extensive simulation results are provided in order to validate our theoretical expressions and analysis.