PbS quantum dots (QDs), prepared by the successive ionic layer adsorption and reaction (SILAR) method, are incorporated in perovskite solar cells based on CH3NH3PbI3. Enhanced light absorption in the ...wavelength range of 330–1400 nm is observed, and the cell prepared with 2 SILAR coating cycles exhibits the best photovoltaic performance. It is observed that the PbS QDs can reduce the TiO2 decomposition damage to the CH3NH3PbI3 films and promote the stability of the modified perovskite solar cells. Charge transfer dynamics in the perovskite solar cells is studied with intensity modulated photocurrent/photovoltage spectroscopy, and improved charge diffusion lengths are obtained for the modified cells, with the best value of 0.86 μm obtained for the device prepared with 2 SILAR coating cycles. This improvement could be attributed to the enhanced electron transport and reduced electron recombination processes in the device structures after incorporating PbS QDs.
•PbS quantum dots used as co-sensitizers in solar cells based on CH3NH3PbI3.•Improved light absorption after incorporating PbS QDs.•Improved photovoltaic performance of PbS QD-modified perovskite solar cells.•Improved electron transport after incorporating PbS QDs in perovskite solar cells.
During deep mining, the excavation disturbance stress path is the domination factor for the stability of the surrounding rock mass as well as the ground pressure. One of the important parameters of ...the stress path is the loading or unloading rate of the disturbed rock or coal, which depended on the mining rate. To achieve a well understanding of the mining rate and its effect on the coal behavior, a preliminary case investigation of the mechanical properties of the coal at the various mining rates in both the laboratory scale and field scale was performed. Based on the uniaxial compression test and the digital image correlation (DIC) method, the mechanical behavior of the coal samples, such as the evolution of the strength, surface deformation, crack propagation, and elastic strain energy of the coal under the various loading rates were analyzed. A threshold range of the loading rate has been observed. The uniaxial compressive strength (UCS) and releasable elastic strain energy (Ue) increase with increasing loading rate when the loading rate is below the threshold. Otherwise, the UCS and Ue may decrease with the loading rate. Under the low loading rate (≤0.05 mm/min), the tensile deformation of the original defects could result in crack coalescence, whereas failure of the coal matrix is the key contributor to the crack coalescence under the high loading rate (greater than0.05 mm/min). Afterwards, with the consideration of the bearing capacity (UCS) and energy release of the mining-disturbed coal mass (Ue), a power exponential relationship between the mining rate (MR) in the field and the critical loading rate (vc) in the laboratory was proposed. The application potential of the formulas was then validated against the field monitored data. Finally, based on the critical loading rate, the released strain energy, and the monitored pressure on the roof supports, a reasonable mining rate MR for the Ji15-31030 working face was determined to be approximately 3 m/d.
As shallow coal resources are gradually depleted, resource exploitation extends from the shallow into the deep, where the mechanical properties of the coal rocks change significantly. To study the ...mechanical properties and mining-induced response characteristics of deep coal rocks. On a laboratory scale, laboratory tests and mining mechanics simulations were conducted on coal samples recovered from 1000 m or deeper using a rock mechanics testing system called MTS815 Flex Test GT. On the engineering scale, considering the roadway Ji-14-31050, buried in Pingdingshan Coal Mine No. 12 as the research base, four parameters—anchor bolt stress, borehole stress, roof displacement, and roadway convergence distortion—were monitored to study the mining-induced mechanical response characteristics of the coal rocks. The laboratory-scale study showed that the tensile strength and deformation of the deep coal rocks were generally small when destroyed; the tensile strength was in the range of 0.07–0.15 MPa, indicating low strength and high brittleness; the average compression strength of the coal rocks at 1000 m or deeper was 111.7 MPa, which was significantly greater than that of coal rocks at shallower depths. The axial strain and volumetric strain of the deep coal rocks were also greater than those of the shallow coal rocks, indicating significant plasticity. Under the conditions of pillarless mining, the axial deformation, lateral deformation, and volume deformation of deep coal samples all show a large deformation platform near the peak stress, corresponding to the area in which the volumetric deformation showed a trend of expansion; furthermore, the peak stress was significantly lower in this area. The study on the engineering scale showed the coal mining-affected area (approximately 70 m) along the mining direction of the Ji-14-31050 coal mining face with a depth of over 1000 m in the Pingdingshan No. 12 mine was obviously larger than that of the shallow coal seams. As the mining face advanced, the anchor bolt stress, the roof separation, and the roadway section deformation showed similar patterns of increasing variation. In an area 30-m away from the mining face, the supporting pressure peaked, and the anchoring stress, roof separation, and tunnel cross-sectional deformation all changed significantly, displaying the surging phenomenon. At the same time, the roadway sidewall deformation was significantly greater than the deformation between the roof and floor. Clearly, as the mining depth extended deeper, the mining-induced stress field became increasingly more intense, and the coal mining-affected area increased noticeably. Meanwhile, the surrounding rock deformation and roof separation increased significantly, making it more difficult to control the stability of the rocks surrounding the roadway. The results of this study can provide guidance for roadway support, engineering design and mining technology optimization when mining at 1000 m or deeper.
The current advances in cloud-based services have significantly enhanced individual satisfaction in numerous modern life areas. Particularly, the recent spectacular innovations in the wireless body ...area networks (WBAN) domain have made e-Care services rise as a promising application field, which definitely improves the quality of the medical system. However, the forwarded data from the limited connectivity range of WBAN via a smart device (e.g., smartphone) to the application provider (AP) should be secured from an unapproved access and alteration (attacker) that could prompt catastrophic consequences. Therefore, several schemes have been proposed to guarantee data integrity and privacy during their transmission between the client/controller (C) and the AP. Thereby, numerous effective cryptosystem solutions based on a bilinear pairing approach are available in the literature to address the mentioned security issues. Unfortunately, the related solution presents security shortcomings, where AP can with ease impersonate a given C. Hence, this existing scheme cannot fully guarantee C's data privacy and integrity. Therefore, we propose our contribution to address this data security issue (impersonation) through a secured and efficient remote batch authentication scheme that genuinely ascertains the identity of C and AP. Practically, the proposed cryptosystem is based on an efficient combination of elliptical curve cryptography (ECC) and bilinear pairing schemes. Furthermore, our proposed solution reduces the communication and computational costs by providing an efficient data aggregation and batch authentication for limited device's resources in WBAN. These additional features (data aggregation and batch authentication) are the core improvements of our scheme that have great merit for limited energy environments like WBAN.
Time series classification and forecasting have long been studied with the traditional statistical methods. Recently, deep learning achieved remarkable successes in areas such as image, text, video, ...audio processing, etc. However, research studies conducted with deep neural networks in these fields are not abundant. Therefore, in this paper, we aim to propose and evaluate several state-of-the-art neural network models in these fields. We first review the basics of representative models, namely long short-term memory and its variants, the temporal convolutional network and the generative adversarial network. Then, long short-term memory with autoencoder and attention-based models, the temporal convolutional network and the generative adversarial model are proposed and applied to time series classification and forecasting. Gaussian sliding window weights are proposed to speed the training process up. Finally, the performances of the proposed methods are assessed using five optimizers and loss functions with the public benchmark datasets, and comparisons between the proposed temporal convolutional network and several classical models are conducted. Experiments show the proposed models' effectiveness and confirm that the temporal convolutional network is superior to long short-term memory models in sequence modeling. We conclude that the proposed temporal convolutional network reduces time consumption to around 80% compared to others while retaining the same accuracy. The unstable training process for generative adversarial network is circumvented by tuning hyperparameters and carefully choosing the appropriate optimizer of "Adam". The proposed generative adversarial network also achieves comparable forecasting accuracy with traditional methods.
•A new statistical LW-index for labeled feature set is proposed.•An new filter algorithm, i.e. SFS-LW, is presented.•It can obtain similar classification accuracy as the wrapper methods.•It is nearly ...ten times faster than the wrapper methods.
The wrapper feature selection method can achieve high classification accuracy. However, the cross-validation scheme of the wrapper method in evaluation phase is very expensive regarding computing resource consumption. In this paper, we propose a new statistical measure named as LW-index which could replace the expensive cross-validation scheme to evaluate the feature subset. Then, a new feature selection method, which is the combination of the proposed LW-index with Sequence Forward Search algorithm (SFS-LW), is presented in this paper. Further, we show through plenty of experiments conducted on nine UCI datasets that the proposed method can obtain similar classification accuracy as the wrapper method with centroid-based classifier or support vector machine, and its computation cost is approximate to the compared filter methods.
•We propose a novel framework that combines deep learning with blockchain to provide learning over decentralized data sources.•We design a customized smart contract to establish a secure large-scale ...real-time data sharing among different data providers.•We modify the RCNN by integrating the Region of Interest (ROI) pooling layer to detect the region of interest and train in a decentralized manner network.•Finally, an intensive empirical study is conducted to validate our proposed method through the blockchain and deep neural network.
Deep learning, for image data processing, has been widely used to solve a variety of problems related to medical practices. However, researchers are constantly struggling to introduce ever efficient classification models. Recent studies show that deep learning can perform better and generalize well when trained using a large amount of data. Organizations such as hospitals, testing labs, research centers, etc. can share their data and collaboratively build a better learning model. Every organization wants to retain the privacy of their data, while on the other hand, these organizations want accurate and efficient learning models for various applications. The concern for privacy in medical data limits the sharing of data among multiple organizations due to some ethical and legal issues. To retain privacy and enable data sharing, we present a unique method that combines locally learned deep learning models over the blockchain to improve the prediction of lung cancer in health-care systems by filling the defined gap. There are several challenges involved in sharing that data while maintaining privacy. In this paper, we identify and address such challenges. The contribution of our work is four-fold: (i) We propose a method to secure medical data by only sharing the weights of the trained deep learning model via smart contract. (ii) To deal with different sized computed tomography (CT) images from various sources, we adopted the Bat algorithm and data augmentation to reduce the noise and overfitting for the global learning model. (iii) We distribute the local deep learning model wights to the blockchain decentralized network to train a global model. iv) We propose a recurrent convolutional neural network (RCNN) to estimate the region of interest (ROI) in theCT images. An extensive empirical study has been conducted to verify the significance of our proposed method for better prediction of cancer in the early stage. Experimental results of the proposed model can show that our proposed technique can detect the lung cancer nodules and also achieve better performance.
This paper reviews studies on neural networks in aerodynamic data modeling. In this paper, we analyze the shortcomings of computational fluid dynamics (CFD) and traditional reduced-order models ...(ROMs). Subsequently, the history and fundamental methodologies of neural networks are introduced. Furthermore, we classify the neural networks based studies in aerodynamic data modeling and illustrate comparisons among them. These studies demonstrate that neural networks are effective approaches to aerodynamic data modeling. Finally, we identify three important trends for future studies in aerodynamic data modeling: a) the transformation method and physics informed models will be combined to solve high-dimensional partial differential equations; b) in the research area of steady aerodynamic response predictions, model-oriented studies and data-integration-oriented studies will become the future research directions, while in unsteady aerodynamic response predictions, radial basis function neural networks (RBFNNs) are the best tools for capturing the nonlinear characteristics of flow data, and convolutional neural networks (CNNs) are expected to replace long short-term memories (LSTMs) to capture the temporal characteristics of flow data; and c) in the field of steady or unsteady flow field reconstructions, the CNN-based conditional generative adversarial networks (cGANs) will be the best frameworks in which to discover the spatiotemporal distribution of flow field data.
Internet of things (IoT) is revolutionizing this world with its evolving applications in various aspects of life such as sensing, healthcare, remote monitoring, and so on. Android devices and ...applications are working hand to hand to realize dreams of the IoT. Recently, there is a rapid increase in threats and malware attacks on Android-based devices. Moreover, due to extensive exploitation of the Android platform in the IoT devices creates a task challenging of securing such kind of malware activities. This paper presents a novel framework that combines the advantages of both machine learning techniques and blockchain technology to improve the malware detection for Android IoT devices. The proposed technique is implemented using a sequential approach, which includes clustering, classification, and blockchain. Machine learning automatically extracts the malware information using clustering and classification technique and store the information into the blockchain. Thereby, all malware information stored in the blockchain history can be communicated through the network, and therefore any latest malware can be detected effectively. The implementation of the clustering technique includes calculation of weights for each feature set, the development of parametric study for optimization and simultaneously iterative reduction of unnecessary features having small weights. The classification algorithm is implemented to extract the various features of Android malware using naive Bayes classifier. Moreover, the naive Bayes classifier is based on decision trees for extracting more important features to provide classification and regression for achieving high accuracy and robustness. Finally, our proposed framework uses the permissioned blockchain to store authentic information of extracted features in a distributed malware database blocks to increase the run-time detection of malware with more speed and accuracy, and further to announce malware information for all users.
Access Control Lists (ACL) are critical to protecting network and cyber-physical systems. Traditional firewalls mostly use reactive methods to enforce ACLs, so that new ACL updates cannot take effect ...immediately. In this paper, based on our previous work, we propose CPACK, an intelligent cyber-physical access control kit, which uses a smart algorithm to upgrade the ACL list. CPACK adopts a proactive way to enforce ACL and reacts to a new ACL update and network view update in real time. We implement CPACK on both Floodlight and ONOS controller. We then conduct a large number of experiments to compare CPACK with the Floodlight firewall application. The experimental results show that CPACK has a better performance than the existing Floodlight firewall application. CPACK is also integrated into the new version of Floodlight and ONOS controller.