A Deep Learning Approach for Maximum Activity Links in D2D Communications.

Mobile cellular communications are experiencing an exponential growth in traffic load on Long Term Evolution (LTE) eNode B (eNB) components. Such load can be significantly contained by directly sharing content among nearby users through device-to-device (D2D) communications, so that repeated downloads of the same data can be avoided as much as possible. Accordingly, for the purpose of improving the efficiency of content sharing and decreasing the load on the eNB, it is important to maximize the number of simultaneous D2D transmissions. Specially, maximizing the number of D2D links can not only improve spectrum and energy efficiency but can also reduce transmission delay. However, enabling maximum D2D links in a cellular network poses two major challenges. First, the interference between the D2D and cellular communications could critically affect their performance. Second, the minimum quality of service (QoS) requirement of cellular and D2D communication must be guaranteed. Therefore, a selection of active links is critical to gain the maximum number of D2D links. This can be formulated as a classical integer linear programming problem (link scheduling) that is known to be NP-hard. This paper proposes to obtain a set of network features via deep learning for solving this challenging problem. The idea is to optimize the D2D link schedule problem with a deep neural network (DNN). This makes a significant time reduction for delay-sensitive operations, since the computational overhead is mainly spent in the training process of the model. The simulation performed on a randomly generated link schedule problem showed that our algorithm is capable of finding satisfactory D2D link scheduling solutions by reducing computation time up to 90% without significantly affecting their accuracy.

Treatment of stabilized landfill leachate by Fenton-like process using Fe3O4 particles decorated Zr-pillared bentonite.

Fe3O4 particles decorated Zr pillared bentonite (Fe3O4/Zr-B) were successfully synthesized, which were used to treat stabilized landfill leachate by Fenton-like process. The organics removal and biodegradability were both significantly improved owing to good catalytic stability of the magnetically recoverable catalyst. With the catalyst dosage of 1.0 mg L-1, initial pH of 2 and peroxide concentration of 0.1 mmol L-1, the COD removal efficiency increased to 68% and BOD5/COD of 0.27 was achieved. According to the results of the GC-MS, Fenton-like reaction with Fe3O4/Zr-B had an excellent removal performance for almost all the heterocyclic compounds. The 3D-EEM fluorescence spectra indicated that the fluorescence intensity was dramatically reduced and the UV humic-like and fulvic-like substances were removed effectively during the catalytic degradation. It seemed advisable to implement this process as a pre-treatment to facilitate the further biological treatment.

Fairness-Aware Resource Allocation in Multi-Hop Wireless Powered Communication Networks with User Cooperation.

In wireless powered communication networks (WPCNs), the harvested energy varies greatly among user nodes (UNs), resulting in throughput unfairness. Since the harvested energy is limited, each UN must strategically allocate the energy used for forwarding the other nodes’ information and for transmitting its own information, which further aggravates the global unfairness in terms of throughput. In this paper, we leverage user cooperation in multi-hop transmission to improve the throughput fairness. We formulate the fairness problem as the max-min throughput with resource allocation, which is NP-hard. We design an approximate algorithm to address this problem. The theoretical proof and the simulation results both show that the proposed algorithm provides tight upper and lower bounds for the optimal solution. Compared with the benchmark methods, our proposed method significantly enhances the throughput fairness for WPCNs.

Electromagnetic Acoustic Detection of Pipe Defects Hidden above T-Type Support Structures with Circumferential Shear Horizontal Guided Wave.

When pipe defects are generated above the T-type support structure location, it is difficult to distinguish the reflection signals caused by the weld bead at the support structure from the reflection echoes of pipe defects. Therefore, in order to effectively detect pipe defects, a waveform subtraction method with a circumferential shear horizontal (CSH) guided wave is proposed, which is generated by an electromagnetic acoustic transducer (EMAT). First, a CSH0 guided wave mode with a center frequency of 500 kHz is selected to establish a three-dimensional model with and without pipe defects above the support structure. Following this, the influence of different widths of support structures on the echo signal is compared. Moreover, simulation and experimental results are used to compare the influence of different welding qualities on the detection results. Finally, the waveform subtraction method is used to process the simulation and experimental signals, and the influence of pipe defects with different lengths and depths is discussed. The results show that the non-through crack defect of 5 mm × 1 mm (length × depth) can be detected. The results show that this method can effectively detect the cracks by eliminating the influence of the weld echo, which provides a new concept for the detection of the defect above the support structure.

Mapping specific groundwater nitrate concentrations from spatial data using machine learning: A case study of chongqing, China.

Groundwater resources is not only important essential water resources but also imperative connectors within the intricate framework of the ecological environment. High nitrate concentrations in groundwater can exerting adverse impacts on human health. It is imperative to accurately delineate the distribution characteristics of groundwater nitrate concentrations. Four different machine learning models (Gradient Boosting Regression (GB), Random Forest Regression (RF), Extreme Gradient Boosting Regression (XG) and Adaptive Boosting Regression (AD)) which combine spatial environmental data and different radius contributing area was developed to predict the distribution of nitrate concentration in groundwater. The models use 595 groundwater samples and included topography, remote sensing, hydrogeological and hydrological, climate, nitrate input, and socio-economic predictor. Gradient Boosting Regression model outperforms the other models (R2 = 0.627, MAE = 0.529, RMSE = 0.705, PICP = 0.924 for test dataset) under 500 m radius contributing area. A high-resolution (1 km) groundwater nitrate concentration distribution map reveal in the majority of the study area, groundwater nitrate concentrations are below 1 mg/L and high nitrate concentration (>10 mg/L) proportion in southeast, northeast and central main urban area karst valley regions is 1.89%, 0.91%, and 0.38% respectively. In study area, hydrogeological conditions, soil parameters, nitrogen input factors, and percentage of arable land are among the most influential explanatory factors. This work, serving as the inaugural application of utilizing effective spatial methods for predicting groundwater nitrate concentrations in Chongqing city, furnish decision-making support for the prevention and control of groundwater pollution, particularly in areas primarily dependent on groundwater for water supply and holds profound significance as a milestone achievement.

Enhanced performance of acridine degradation and power generation by microbial fuel cell with g-C3N4/PANI-DA/CF anode.

Microbial fuel cell (MFC) has attracted much attention in treating organic wastewater due to its double functions of degrading organics and generating electricity with microorganisms as biocatalysts. Unfortunately, some organics with biological toxicity such as acridine could inhibit the growth and activity of the microorganisms on the anode so that the double functions of MFC would recede. Enhancing microbial activity by using new biocompatible materials as anodes is prospective to solve problem. A novel anode was achieved by electrodepositing g-C3N4 sheets to the carbon felt (CF) modified with polyaniline-dopamine composite film, and used to treat wastewater containing acridine for the first time. After the operation of 13 d, MFC loading with the composite anode showed a degradation efficiency of 98.3% in 150 mg L-1 acridine, while that of CF-MFC was 55.8%. Moreover, MFC loading the modified anode obtained a maximum power density of 1976 ±â€¯47 mW m-2, 140.1% higher than that of CF-MFC. Further analysis revealed that the functional microorganisms associated with acridine degradation such as Achromobacter and Alcaligenes were enriched on the g-C3N4/PANI-DA/CF anode. Moreover, the composite anode could improve the activity of microorganisms and elicit them to generate conductive nanowires, which was beneficial to transferring electrons from microbes to anode over long distances, suggesting a promising prospect application in MFC.

Domain Adaptive Box-Supervised Instance Segmentation Network for Mitosis Detection.

The number of mitotic cells present in histopathological slides is an important predictor of tumor proliferation in the diagnosis of breast cancer. However, the current approaches can hardly perform precise pixel-level prediction for mitosis datasets with only weak labels (i.e., only provide the centroid location of mitotic cells), and take no account of the large domain gap across histopathological slides from different pathology laboratories. In this work, we propose a Domain adaptive Box-supervised Instance segmentation Network (DBIN) to address the above issues. In DBIN, we propose a high-performance Box-supervised Instance-Aware (BIA) head with the core idea of redesigning three box-supervised mask loss terms. Furthermore, we add a Pseudo-Mask-supervised Semantic (PMS) head for enriching characteristics extracted from underlying feature maps. Besides, we align the pixel-level feature distributions between source and target domains by a Cross-Domain Adaptive Module (CDAM), so as to adapt the detector learned from one lab can work well on unlabeled data from another lab. The proposed method achieves state-of-the-art performance across four mainstream datasets. A series of analysis and experiments show that our proposed BIA and PMS head can accomplish mitosis pixel-wise localization under weak supervision, and we can boost the generalization ability of our model by CDAM.

Effects of Different Natural Factors on Rheological Properties of SBS Modified Asphalt.

Typical climatic environments such as UV radiation, high temperature and strong wind in cold and arid regions have a significant effect on asphalt aging. The intent of this work is to reveal the evolution law of natural aging of SBS-modified asphalt under the complex adverse climate environment in cold and arid regions. Furthermore, the contribution rate of various environmental factors of natural aging of asphalt in cold and arid regions was analyzed. Based on rheological parameters, this paper characterized the influence of natural aging on the viscoelastic properties, rutting resistance at a high temperature, fatigue resistance and cracking resistance at a low temperature of SBS-modified asphalt. The evolution law of natural aging performance of SBS-modified asphalt was revealed. A quantitative evaluation index (CIi) of natural aging contribution rate of asphalt was put forward and the contribution rate of various environmental factors to asphalt natural aging was analyzed. The results showed that the effects of simulated aging and natural aging on asphalt properties were similar. After aging, the viscoelastic properties of asphalt were deteriorated, and the risk of fatigue cracking and low temperature cracking was increased. It also enhanced the deformation resistance of asphalt and increased the rutting resistance at high temperature. The aging contribution index CIi obtained based on rheological parameters such as complex modulus and rutting factor could directly reflect the influence of different natural factors on the performance of asphalt during aging. Among them, the effect of thermal oxygen was more obvious on the natural aging of SBS-modified asphalt.

Crowd Scene Analysis Encounters High Density and Scale Variation.

Crowd scene analysis receives growing attention due to its wide applications. Grasping the accurate crowd location is important for identifying high-risk regions. In this article, we propose a Compressed Sensing based Output Encoding (CSOE) scheme, which casts detecting pixel coordinates of small objects into a task of signal regression in encoding signal space. To prevent gradient vanishing, we derive our own sparse reconstruction backpropagation rule that is adaptive to distinct implementations of sparse reconstruction and makes the whole model end-to-end trainable. With the support of CSOE and the backpropagation rule, the proposed method shows more robustness to deep model training error, which is especially harmful to crowd counting and localization. The proposed method achieves state-of-the-art performance across four mainstream datasets, especially achieves excellent results in highly crowded scenes. A series of analysis and experiments support our claim that regression in CSOE space is better than traditionally detecting coordinates of small objects in pixel space for highly crowded scenes.

Deploying and scaling distributed parallel deep neural networks on the Tianhe-3 prototype system.

Due to the increase in computing power, it is possible to improve the feature extraction and data fitting capabilities of DNN networks by increasing their depth and model complexity. However, the big data and complex models greatly increase the training overhead of DNN, so accelerating their training process becomes a key task. The Tianhe-3 peak speed is designed to target E-class, and the huge computing power provides a potential opportunity for DNN training. We implement and extend LeNet, AlexNet, VGG, and ResNet model training for a single MT-2000+ and FT-2000+ compute nodes, as well as extended multi-node clusters, and propose an improved gradient synchronization process for Dynamic Allreduce communication optimization strategy for the gradient synchronization process base on the ARM architecture features of the Tianhe-3 prototype, providing experimental data and theoretical basis for further enhancing and improving the performance of the Tianhe-3 prototype in large-scale distributed training of neural networks.

Microscopic Properties of Hydrogen Peroxide Activated Crumb Rubber and Its Influence on the Rheological Properties of Crumb Rubber Modified Asphalt.

Crumb rubber modified (CRM) asphalt binder has been affirmed to improve resistance to rutting, moisture susceptibility, low-temperature cracking, and asphalt durability. However, CRM has poor compatibility with asphalt since crumb rubber molecules are vulcanized. The objective of this study was to develop a new method to prepare activated crumb rubber using hydrogen peroxide (H2O2) solution and to explore the rheological properties of H2O2 activated CRM (ACRM) asphalt. Three different percentages of H2O2 solution were used to activate crumb rubber. The surface properties of oxidized rubber were analysed using scanning electron microscopy. Moreover, the pore structure in rubber powder was investigated. The rheological properties of bitumen samples obtained from treated and untreated rubber were characterized by conducting dynamic shear rheometer tests. The test results show that the average pore size of the crumb rubber after activation with H2O2 solution is significantly smaller than that of the inactivated crumb rubber, and the volume and surface area of the crumb rubber pores change with H2O2 solution activation in a certain pattern. With the increase in H2O2 solution content, the contact surface between the particles increases, the floccules and pores of the powder increase, and the interface degree between the crumb rubber powder and the asphalt is strengthened. Solubility of the rubber hydrocarbon and the release ability of the carbon black particles from the crumb rubber in the asphalt binder increase, but the mechanical properties of the crumb rubber, including the strength, elasticity, and wear resistance, decrease. As a result, a reduction is observed in the elasticity, viscosity, high-temperature rutting resistance, and elasticity of the ACRM asphalt.

Catalytic micro-ozonation by Fe3O4 nanoparticles @ cow-dung ash for advanced treatment of biologically pre-treated leachate.

In this work, the biologically pre-treated leachate was subjected to catalytic micro-ozonation using cow-dung ash composites loaded with Fe3O4 nanoparticles (nano-Fe3O4@CDA) as the catalyst. The optimal conditions used were nano-Fe3O4@CDA dosage of 0.8 g/L, input ozone of 3.0 g/L, and reaction time of 120 min. This environment yielded the following results: The COD and color number (CN) removal reached 53% and 89%, respectively, and the BOD5/COD increased from 0.05 to 0.32. The catalytic micro-ozonation partially degraded the refractory substances into intermediates with lower molecular weight. The percentage of phenolic compounds decreased sharply from 28.08% to 8.56%, largely due to the opening of the ring as well as to the formation of organic intermediates with a low molecular weight. Based on the results culled from the electron paramagnetic resonance (EPR), it is evident that the nano-Fe3O4@CDA catalyst can accelerate in order to generate OH. This was the main mechanism involved in its excellent ability to degrade refractory pollutants. These results demonstrated the potential use of nano-Fe3O4@CDA as a catalyst in the catalytic micro-ozonation process.

DOMe: A deduplication optimization method for the NewSQL database backups.

Reducing duplicated data of database backups is an important application scenario for data deduplication technology. NewSQL is an emerging database system and is now being used more and more widely. NewSQL systems need to improve data reliability by periodically backing up in-memory data, resulting in a lot of duplicated data. The traditional deduplication method is not optimized for the NewSQL server system and cannot take full advantage of hardware resources to optimize deduplication performance. A recent research pointed out that the future NewSQL server will have thousands of CPU cores, large DRAM and huge NVRAM. Therefore, how to utilize these hardware resources to optimize the performance of data deduplication is an important issue. To solve this problem, we propose a deduplication optimization method (DOMe) for NewSQL system backup. To take advantage of the large number of CPU cores in the NewSQL server to optimize deduplication performance, DOMe parallelizes the deduplication method based on the fork-join framework. The fingerprint index, which is the key data structure in the deduplication process, is implemented as pure in-memory hash table, which makes full use of the large DRAM in NewSQL system, eliminating the performance bottleneck problem of fingerprint index existing in traditional deduplication method. The H-store is used as a typical NewSQL database system to implement DOMe method. DOMe is experimentally analyzed by two representative backup data. The experimental results show that: 1) DOMe can reduce the duplicated NewSQL backup data. 2) DOMe significantly improves deduplication performance by parallelizing CDC algorithms. In the case of the theoretical speedup ratio of the server is 20.8, the speedup ratio of DOMe can achieve up to 18; 3) DOMe improved the deduplication throughput by 1.5 times through the pure in-memory index optimization method.