Search

Researchers face difficulties in finding relevant papers to their research interest as the number of scientific publication is rapidly increasing on the web. Scientific paper recommenders have emerged as a leading solution to help researchers by automatically suggesting relevant and useful publications. Several approaches have been proposed on improving recommender systems. However, most existing approaches depend on priori user profiles, and thus they cannot recommend papers to new user. Furthermore, the existing approaches utilize non-public contextual information, and thus it cannot adequately find similarities between papers due to copyright restrictions. Also, the existing approaches consider only single level paper-citation relation to identify similarities between papers. Considering the above challenges, this paper presents a collaborative filtering based recommendation approach for scientific papers that does not depend on priori user profiles and which utilizes only public contextual information. Using citation context, we utilized 2-level paper-citation relations to find hidden associations between papers. The rational underlying this approach is that, two papers are co-occurred with same cited paper(s) and two papers are co-occurring with same citing paper(s) are significantly similar to some extent. To evaluate the performance of the proposed approach, publicly available datasets are used to conduct extensive experiments. The experimental results demonstrate that the proposed approach has significantly outperforms the baseline approaches in terms of precision, recall, F1, mean average precision, and mean reciprocal rank, which are commonly used information retrieval metrics. The novelty of this study is that, with the proposed approach, researchers are able to find relevant and useful publications over the internet regardless of their previous research experiences and research area.

The existing plethora of document classification techniques exploits different data sources either from the content or metadata of research articles. Various journal publishers like Springer, Elsevier, IEEE, etc., do not provide open access to the content of research articles, whereas metadata is freely available there. Metadata like title, keyword, and abstract can serve as a better alternative to the content in various scenarios. In the current literature, researchers have assessed the role of some of the metadata individually. We believe that the collective contribution of metadata parameters can play a significant role in classifying research papers. This paper presents a comprehensive evaluation of the role of metadata, individually as well as in combinations to achieve the objective of research paper classification. Moreover, we have classified the research articles into ACM hierarchy root categories (e.g. general literature, hardware, software, etc.). In this comprehensive evaluation, we have assessed all the possible combinations of metadata features against different classifiers such as Random Forest, K Nearest Neighbor, and Decision Tree. The results of this research reveal that the title & keywords combination outperforms other combinations with an F-measure score of 0.88.

To improve the accuracy of user implicit rating prediction, we combine the traditional latent factor model (LFM) and bidirectional gated recurrent unit neural network (BiGRU) model to propose a hybrid model that deeply mines the latent semantics in the unstructured content of the text and generates a more accurate rating matrix. First, we utilize the user’s historical behavior (favorites records) to build a user rating matrix and decompose the matrix to obtain the latent factor vectors of users and literature. We also apply the BERT model for word embedding of the research papers to obtain the sequence of word vectors. Then, we apply the BiGRU with the user attention mechanism to mine the research paper textual content and to generate the new literature latent feature vectors that are used to replace the original literature latent factor vectors decomposed from the rating matrix. Finally, a new rating matrix is generated to obtain users’ ratings of noninteractive research papers and to generate the recommendation list according to the user latent factor vector. We design experiments on the real datasets and verify that the research paper recommendation model is superior to traditional recommendation models in terms of precision, recall, F1-value, coverage, popularity and diversity.

In this paper, we present a new scheme for implementing virtual keyboards, which uses only two to four motion-recognition rings per hand and a two-dimensional keyboard template (e.g., an A4 size paper with printed key positions). It has the benefit of portability, customizability, and low-cost when compared with existing approaches. Essentially, we have shown that wearing two wireless IoT rings on the middle phalanges of two fingers of each hand, users can input the alphabetic characters into a computing device by typing on a flat paper on a desk, and potentially in mid-air. We have demonstrated that two rings are sufficient in capturing the gestures and motions of all fingers in a typing hand for keystrokes recognition. A single wireless IoT ring, which weighs 7.8 grams, consists of a Bluetooth low energy (BLE) unit, a micro inertial measurement unit (mIMU), and a cell battery. The 3-axes attitude angles and the Z-axis acceleration of each ring are adopted as the features for keystroke recognition. The overall keystroke recognition accuracy rate can reach as high as 94.8% when two IoT rings are worn by a user on each hand; this accuracy rate increases to 98.6%, when four rings are worn on each typing hand.

Most existing studies and public datasets for handwritten Chinese text recognition are based on the regular documents with clean and blank background, lacking research reports for handwritten text recognition on challenging areas such as educational documents and financial bills. In this paper, we focus on examination paper text recognition and construct a challenging dataset named examination paper text (SCUT-EPT) dataset, which contains 50 000 text line images (40 000 for training and 10 000 for testing) selected from the examination papers of 2 986 volunteers. The proposed SCUT-EPT dataset presents numerous novel challenges, including character erasure, text line supplement, character/phrase switching, noised background, nonuniform word size, and unbalanced text length. In our experiments, the current advanced text recognition methods, such as convolutional recurrent neural network (CRNN) exhibits poor performance on the proposed SCUT-EPT dataset, proving the challenge and significance of the dataset. Nevertheless, through visualizing and error analysis, we observe that humans can avoid vast majority of the error predictions, which reveal the limitations and drawbacks of the current methods for handwritten Chinese text recognition (HCTR). Finally, three popular sequence transcription methods, connectionist temporal classification (CTC), attention mechanism, and cascaded attention-CTC are investigated for HCTR problem. It is interesting to observe that although the attention mechanism has been proved to be very effective in English scene text recognition, its performance is far inferior to the CTC method in the case of HCTR with large-scale character set.

The main purpose of this paper is to present the methodology for calculating the electromagnetic behaviour of real integrated circuit (IC) parts using a no-mesh local Finite Differential Method (FDM). Furthermore, the comparison of computational results and measurements is presented. All considerations are based on typical long transmission lines (TLs) in modern ICs. The obtained results have been analysed in detail and compared with measured values. The measurement data are de-embedded using the test board model. This problem is illustrated in this paper based on a practical example of the Multi-Conductor Transmission Lines test structure whose electrical responses to various excitations are presented and analysed in detail.

For current steganalysis of the image content-adaptive steganography, there are multiple problems to be improved, such as high difficulty and low accuracy, when detecting images with various contents and textures. For this problem, an improved steganalytic method is proposed in this paper based on the pre-classification and feature selection. First, using the features extracted based on the dependency analysis of image adjacent data, the images with various content and texture complexities are pre-classified as multiple clusters by the K-means algorithms. Then, the performance of existing various steganalytic features are analyzed for different clusters of images, and the optimal features for each cluster are selected for final classification. The experimental results show that the detection accuracy could be improved by the proposed method, and the rationality and availability are also verified. At the same time, the analysis and experimental results in this paper also show that the images with rich content and complex texture should be paid more attention both in steganography and in steganalysis.

Delivering confidential messages in wireless network is gaining continuous attraction as a fundamental building block for the Internet of things (IoT). This paper overviews the confidential message transmission techniques in broadcast channel (BC) where a transmitter serves multiple users by delivering confidential messages to their intended users. Each confidential message must be prevented from extracting its information by any unintended users. First, we consider a basic network consisting of two users. In the two-user BC, the secret dirty paper coding (S-DPC) achieves the secrecy capacity region. However, since the DPC requires a high computational complexity for characterizing the capacity region, two sub-optimal transmission techniques with low complexities are explained. Second, we extend our discussion to the network including more than two users. For $K$ -user BC with confidential messages, the optimal transmission scheme and the secrecy capacity region have not yet been derived. Instead of presenting the optimal scheme, we explain two sub-optimal transmission techniques and compare their features and performances. In conclusion, we discuss the open problems in the confidential message transmission for networks with more than two users.

Voice-over IP (VoIP) technology is a kind of digital transmission technology based on IP network. It is one of the important methods to use voice service in VoIP as steganographic carrier to ensure secure transmission. However, the traditional steganographic code has some problems, such as low embedding efficiency and weak concealment, which cannot meet the requirements of VoIP streaming media information hiding for the security of secret information. Therefore, a steganographic algorithm combining F5 and simplified wet paper code (SWPC) algorithm is proposed. The main idea is to embed secret messages in each row of the carrier matrix using the F5 algorithm, and then the SWPC algorithm is used to embed the columns according to the wet and dry characteristics of the wet paper code without affecting the results before row embedding. We use the VoIP streams encoded by the ITU-T G.729a codec as a carrier to verify the proposed scheme. The experimental results demonstrate that the proposed scheme can achieve relatively better IP speech data steganographic transparency and that it can outperform F5-WPC and SWPC approaches.

This paper examines the history of electrical engineering education, leveraging the concept of “expansive (dis)integration” to frame a number of key trends and challenges in the field. Our account is organized historically, starting with the origins and early development of electrical engineering education beginning in the late 1800s, and then tracing out the rise of new subfields and specialties during the inter-war and post-WWII periods. The development of computer engineering as a field is given special attention as a case study in disciplinary (dis)integration, while setting the stage for a discussion of broader trends associated with the rising influence of digital techniques and technologies across electrical engineering. The final sections of this paper report on some contemporary challenges and opportunities that may further transform the field in upcoming years and decades, with particular emphasis on issues of demographic diversity and perceptions of broader relevance and impact. The approach of this paper is largely historical, drawing on a wide variety of primary and secondary source materials. It is expected that this paper will be of interest to anyone who would like to know more about the historical development of electrical engineering education, including in relation to more contemporary currents in the field.

In the process of digital image acquisition, color inconsistency is a common issue due to the influence of photographic conditions. The inconsistency of color affects the quality of digital orthophoto products and subsequent applications significantly, and this issue remains challenging both in the academia and industry. This paper proposes a color equalization method for aerial image based on block adjustment and an improved color balance model based on the analysis of causes for color deviation. Two nonlinear functions are used to simulate the process of color deviation and correct the color of images. Due to the existence of error, the color corrected images still have minor deviations in the color of the overlapped regions. Therefore, this research introduces an error equation to address this issue and uses the least square principle to calculate the adjustment. The simulation experiments and real experiments are carried out on several groups of aerial image data respectively. The results show that the method not only achieves better visual effect but also has a higher adjustment precision. Finally, the rationality and parameters of the model proposed in this paper are discussed.

With the development of mature communication network technologies such as 5G, edge computing and slicing, business applications in areas such as Telematics and intelligent transportation also need the support of vehicle-road collaboration technologies. Due to the mobility of vehicles and the heterogeneity of communication interfaces, it brings many challenges for data transmission and processing of Telematics. Therefore, network resources, roadside unit devices and sunken edge nodes need to work together to guarantee real-time network communication. Thus, they can jointly help improve the quality of network services and user experience, and show the level of vehicle-road collaboration wisdom in terms of safety, efficiency and service. In view of the future 5G network-related technologies and C-V2X development trend, this paper provides a comprehensive technical solution framework for Telematics based on end-edge collaboration, combining network resource deployment optimization and edge caching technologies for video transmission tasks in Telematics application scenarios. By adding 5G base station type RSU and UAV mobile base station to work jointly, network resources are better allocated for scalable coded video, and a relatively better edge caching strategy is obtained based on user mobility analysis. Aiming to improve the network system performance, the vehicle-side, road-side and edge-side are jointly considered to improve the utilization efficiency of limited network resources. In this paper, we hope to provide a practical and effective service architecture for Telematics video application scenarios through a convergence scheme of network resource allocation and edge caching configuration.

In view of the lack of data association in spatiotemporal information analysis and the lack of spatiotemporal situation analysis in knowledge graphs, this paper combines the semantic web of the geographic knowledge graph with the visual analysis model of spatial information and puts forward the comprehensive utilization of the related technologies of the geographic knowledge graph and big data visual analysis. Then, it realizes the situational analysis of COVID-19 (Coronavirus Disease 2019) and the exploration of patient relationships through interactive collaborative analysis. The main contributions of the paper are as follows. (1) Based on the characteristics of the geographic knowledge graph, a patient entity model and an entity relationship type and knowledge representation method are proposed, and a knowledge graph of the spatiotemporal information of COVID-19 is constructed. (2) To analyse the COVID-19 patients’ situations and explore their relationships, an analytical framework is designed. The framework, combining the semantic web of the geographic knowledge graph and the visual analysis model of geographic information, allows one to analyse the semantic web by using the node attribute similarity calculation, key stage mining, community prediction and other methods. (3) An efficient epidemic prevention and anti-epidemic method, which is of referential significance, is proposed. It is based on experiments and the collaborative analysis of the semantic web and spatial information, allowing for real-time situational understanding, the discovery of patients’ relationships, the analysis of the spatiotemporal distribution of patients, super spreader mining, key node analysis, and the prevention and control of high-risk groups.

With a large number of distributed generation connected to the distribution network, the total supply capacity of the distribution network has been improved to a certain extent. However, due to the randomness of its output, it also brings some challenges to the reliable operation of the distribution network and the restoration of power supply after failure. Based on this, this paper proposes an active distribution network reconfiguration strategy with uncertain factors for maximum total supply capacity improvement. Firstly, the evaluation index of the maximum total supply capacity of distribution network is constructed, and the maximum total supply capacity index under the current operation mode is evaluated online through the calculation model of maximum total supply capacity based on N-1 security criterion. Then, the uncertainty of wind power, photovoltaic and electric vehicle DG and the stochastic model of prosumer load are considered, random variables are generated by Latin hypercube sampling (LHS) and their correlation is considered. Then, it introduces that the position of sectionalizing switch and tie switch can be adjusted according to the dispatching demand. Based on the evaluation index of maximum total supply capacity and DG output of uncertain factors, the active reconfiguration model of distribution network after fault is proposed. Finally, a calculation example illustrates the effectiveness and correctness of the model in this paper. It is demonstrated that the model can optimize the selection strategy of section switch and tie switch after the fault of distribution network, improve the utilization rate of distributed energy, and give full play to the power supply recovery potential of distribution network and reduce the outage time of prosumer groups.

Image classification needs to consider image degradations in practice because an image classification network trained with clean images works poorly for degraded images while digital images usually include some degradations such as JPEG compression. To tackle this problem, a common approach is training classification networks on degraded images with various levels of degradation, e.g. various quality factors for JPEG compression. However, the classification networks do not usually have enough accuracy for clean images because the classification networks have been averagely trained for various levels of degradation. This paper aims to construct a classification network of degraded images without sacrificing the performance of clean images. This paper proposes a network to learn the classification of degraded images and degradation levels of degraded images as multi-task learning. Learning the classification of degraded images is the main task of multi-task learning. On the other hand, learning degradation levels is a sub-task of multi-task learning and reinforces the classification ability. In the proposed network, a feature extractor of the classification is trained with image features acquired from a classification network of clean images by using consistency regularization with the cosine similarity loss. The experimental results using different types of degradations, including JPEG compression, Gaussian blur, Gaussian noise, and salt-and-pepper noise, show that our proposed network has enough ability to classify degraded images without sacrificing the performance for clean images.

Distress image retrieval for infrastructure maintenance via self-trained deep metric learning using experts’ knowledge is proposed in this paper. Since engineers take multiple images of a single distress part for inspection of road structures, it is necessary to construct a similar distress image retrieval method considering the input of multiple images to support determination of the level of deterioration. Thus, the construction of an image retrieval method while selecting an effective input from multiple images is described in this paper. The proposed method performs deep metric learning by using a small number of effective images labeled by experts’ knowledge with information about their effectiveness and a large number of unlabeled images via a self-training approach. Specifically, an end-to-end learning approach that performs retraining of the model by assigning pseudo-labels to these unlabeled images according to the output confidence of the model is achieved. Thus, the proposed method can select an effective image from multiple images that are input at the retrieval as a query image. This is the main contribution of this paper. As a result, the proposed method realizes highly accurate retrieval of similar distress images considering the actual situation of inspection in which multiple images of a distress part are input.

A human-centric emotion estimation method based on correlation maximization with consideration of changes with time in visual attention and brain activity when viewing images is proposed in this paper. Owing to the recent developments of many kinds of biological sensors, many researchers have focused on multimodal emotion estimation using both eye gaze data and brain activity data for improving the quality of emotion estimation. In this paper, a novel method that focuses on the following two points is introduced. First, in order to reduce the burden on users, we obtain brain activity data from users only in the training phase by using a projection matrix calculated by canonical correlation analysis (CCA) between gaze-based visual features and brain activity-based features. Next, for considering the changes with time in both visual attention and brain activity, we obtain novel features based on CCA-based projection in each time unit. In order to include these two points, the proposed method analyzes a fourth-order gaze and image tensor for which modes are pixel location, color channel and the changes with time in visual attention. Moreover, in each time unit, the proposed method performs CCA between gaze-based visual features and brain activity-based features to realize human-centric emotion estimation with a high level of accuracy. Experimental results show that accurate human emotion estimation is achieved by using our new human-centric image representation.

In this paper, we designed a registration framework that can be used to develop augmented reality environments, where all the real (including the users) and virtual elements are co-localized and registered in a common reference frame. The software is provided together with this paper, to contribute to the research community. The developed framework allows us to perform a quantitative assessment of interaction and egocentric perception in Augmented Reality (AR) environments. We assess perception and interaction in the peripersonal space through a 3D blind reaching task in a simple scenario and an interaction task in a kitchen scenario using both video (VST) and optical see-through (OST) head-worn technologies. Moreover, we carry out the same 3D blind reaching task in real condition (without head-mounted display and reaching real targets). This provides a baseline performance with which to compare the two augmented reality technologies. The blind reaching task results show an underestimation of distances with OST devices and smaller estimation errors in frontal spatial positions when the depth does not change. This happens with both OST and VST devices, compared with the real-world baseline. Such errors are compensated in the interaction kitchen scenario task. Thanks to the egocentric viewing geometry and the specific required task, which constrain the position perception on a table, both VST and OST have comparable and effective performance. Thus, our results show that such technologies have issues, though they can be effectively used in specific real tasks. This does not allow us to choose between VST and OST devices. Still, it provides a baseline and a registration framework for further studies and emphasizes the specificity of perception in interactive AR.

Fifth-Generation (5G) mobile cellular networks provide a promising platform for new, innovative and diverse IoT applications, such as ultra-reliable and low latency communication, real-time and dynamic data processing, intensive computation, and massive device connectivity. End-to-End (E2E) network slicing candidates present a promising approach to resource allocation and distribution that permit operators to flexibly provide scalable virtualized and dedicated logical networks over common physical infrastructure. Though network slicing promises the provision of services on demand, many of its use cases, such as self-driving cars and Google's Stadia, would require the integration of a Multi-Access Edge Computing (MEC) platform in 5G networks. Edge Computing is envisioned as one of the key drivers for 5G and Sixth-Generation (6G) mobile cellular networks, but its role in network slicing remains to be fully explored. We investigate MEC and network slicing for the provision of 5G service focused use cases. Recently, changes to the cloud-native 5G core are a focus with MEC use cases providing network scalability, elasticity, flexibility, and automation. A cloud-native microservices architecture, along with its potential use cases for 5G network slicing, is envisioned. This paper also elaborates on the recent advances made in enabling E2E network slicing, its enabling technologies, solutions, and current standardization efforts. Finally, this paper identifies open research issues and challenges and provides possible solutions and recommendations.

Nowadays, 5G is in its initial phase of commercialization. The 5G network will revolutionize the existing wireless network with its enhanced capabilities and novel features. 5G New Radio (5G NR), referred to as the global standardization of 5G, is presently under the $3^{\mathrm {rd}}$ Generation Partnership Project (3GPP) and can be operable over the wide range of frequency bands from less than 6GHz to mmWave (100GHz). 3GPP mainly focuses on the three major use cases of 5G NR that are comprised of Ultra-Reliable and Low Latency Communication (uRLLC), Massive Machine Type Communication (mMTC), Enhanced Mobile Broadband (eMBB). For meeting the targets of 5G NR, multiple features like scalable numerology, flexible spectrum, forward compatibility, and ultra-lean design are added as compared to the LTE systems. This paper presents a brief overview of the added features and key performance indicators of 5G NR. The issues related to the adaptation of higher modulation schemes and inter-RAT handover synchronization are well addressed in this paper. With the consideration of these challenges, a next-generation wireless communication architecture is proposed. The architecture acts as the platform for migration towards beyond 5G/6G networks. Along with this, various technologies and applications of 6G networks are also overviewed in this paper. 6G network will incorporate Artificial intelligence (AI) based services, edge computing, quantum computing, optical wireless communication, hybrid access, and tactile services. For enabling these diverse services, a virtualized network slicing based architecture of 6G is proposed. Various ongoing projects on 6G and its technologies are also listed in this paper.

The security strengths of block ciphers greatly rely on the confusion components which have the tendency to transform the data nonlinearly into the perplexed form. This paper proposes to put forward a novel scheme of generating cryptographically strong nonlinear confusion components of block ciphers, usually termed as substitution-boxes (S-boxes). The anticipated S-box design scheme is based on a novel five-dimensional (5-D) chaotic system analyzed in this paper. The proposed 5-D dynamical system consists of hyperchaotic phenomenon, KY dimension, conservativity, unstable equilibrium point, and complex phase attractors which are suited for cryptographic applications. The S-box based on hyperchaotic system is made to evolve in order to generate an optimized S-box for high nonlinearity score to make it robust against many linear attacks. The performance analysis of proposed S-box demonstrates that it has bijectivity, high nonlinearity; satisfied strict avalanche criterion and bits independent criterion; low differential and linear probabilities. Moreover, performance appraisal of proposed S-box justifies its better strength and features over many recently investigated S-boxes.

Due to the high penetration of renewable energy resources in microgrids (MGs), the grid inertia becomes low which leads to the grid to be vulnerable to large disturbances. The energy storage devices can play an important role to enhance the inertia of MGs. However, due to the high investment cost of storages or their dp/dt limitation, the installed energy storages cannot cover the challenge of high df/dt. A prominent solution to solve the problem is to use the inertia response of the wind generators. However, relatively high second frequency nadir is the main drawback of using the inertia response of the wind generators which may impose an extensive disturbance to MGs. Accordingly, a coordinated operation strategy for MGs between wind generator and hybrid energy storage (HES) system is proposed in this paper. In addition, to improve the inertia response of the MG; providing high-quality communication infrastructures with low delay and increasing the Ultracapacitor capacity have been paid attention. In this paper, the costs of the installed Ultracapacitor and quality of communication services are defined as the operation cost. Guaranteeing enough frequency damping for the MG with low operation cost are two conflict objectives. Therefore, a multi-objective optimization method is used to set the controllers’ values and reduce the operation cost. The results confirmed that the effectiveness of the proposed strategy to control hybrid power storage in coordination with the wind generator and the frequency recovery process is improved. Also, employing the optimum values guaranteed the frequency damping effectively with low operation cost. The Integral Absolute Error (IAE) value and operation cost are reduced by 13.6% and 32%, respectively. Also, the simulation results show that the maximum MG frequency deviation and maximum df/dt is well compatible with different standards in the presence of load perturbations and different wind speeds.

Though various applications such as flash memory, cache, storage systems, and even indexing for enterprise big data search, adopt hot data identification schemes, relatively little research has been expended into holistically examining alternative strategies. Rather, researchers tend to classify hot data simplistically by considering one or more frequency metrics, thereby disregarding recency, which is also an important consideration. In practice, different workloads mandate different treatment to achieve effective hot data decisions. This paper proposes a dynamic hot data identification scheme that adopts a workload stack distance approximation. Stack distance is a good recency measure, but it traditionally requires high computational complexity as well as additional space. Since stack distance calculation efficiency is a core component for our dynamic feature design, this paper additionally proposes a stack distance approximation algorithm that significantly reduces both computation and space requirements. To our knowledge, the proposed scheme is the first dynamic hot data identification scheme which judiciously assigns more weight to either recency or frequency based on workload characteristics. Our experiments with diverse realistic workloads demonstrate that our stack distance approximation achieves excellent accuracy (up to a 0.1% error rate) and our dynamic scheme improves performance by as much as 49.8%.

Network slicing is a key element in 5G networks. It allows a mobile network operator (MNO) to offer multiple logical networks tailored to the requirements of different industry verticals over a shared infrastructure. From the point of view of an MNO, a mobile virtual network operator (MVNO) is a particular type of vertical network requiring not only the provision of logical networks with specific infrastructure resources but also customized management capabilities to allow the MVNO to offer network slice-based services to its clients over the infrastructure of multiple MNOs. However, the lack of flexibility to provide a customized and efficient network slice management system per tenant under the current proposals of the 3rd Generation Partnership Project (3GPP) and European Telecommunications Standards Institute (ETSI) limits the possibilities of MVNOs. This paper addresses this requirement by proposing a novel virtualized multidomain and multiclient orchestration system aligned with the functionalities of the network slicing management framework proposed by the 3GPP and ETSI. In particular, there are three contributions of this paper: (i) an extended service-based architecture is designed to provide an isolated management system to different MVNOs; (ii) a novel high-level slice instance template is defined to specify management and isolation requirements supporting network slicing as a service model; and (iii) finally, a teleoperated driving use case is described to showcase how our proposal provides an MVNO with an independent management system to orchestrate several network slices in cross-domain environments.

Non-deferrable loads equipped with distributed energy resources, such as solar photovoltaic generation and energy storage, can offer a wide range of benefits to the power system, including load leveling, hedging against forecast uncertainty, and ancillary services. This paper presents a techno-economic approach to optimally equip a flexible energy resource, namely a battery energy storage system (BESS), with non-deferrable loads for capacity enhancement of a distribution grid. The proposed approach is generic in applicability, and includes two different optimization mathematical models. The first model quantifies the needed flexibility with non-deferrable loads, based on a consideration of distribution grid limitations, while the second model determines the optimal flexibility amount associated with non-deferrable loads considering investor profitability. Thereafter, a distribution operations model is developed to evaluate the impact of non-deferrable loads, equipped with an optimal size of BESS, on the distribution system loading capacity. An example of non-deferrable loads considered in this paper is that of the rapid charging loads of plug-in electric vehicles (PEVs) that cannot be controlled or shifted due to the short stay of PEVs at a charging facility. Hence, a probabilistic model for PEV rapid charging loads is first developed. Case studies and simulation findings, considering a 32-bus distribution system, demonstrate that the proposed approach helps reduces the impact of non-deferrable loads on a distribution system and enhances the system power margin, which defers the need for system upgrades.

Machine reading comprehension is a very challenging task, which aims to determine the answer span based on the given context and question. The newly developed pre-training language model has achieved a series of successes in various natural language understanding tasks with its powerful contextual representation ability. However, these pre-training language models generally lack the downstream processing structure for specific tasks, which limits further performance improvement. In order to solve this problem and deepen the model’s understanding of the question and context, this paper proposes S&I Reader. On the basis of the pre-training model, skimming, intensive reading, and gated mechanism modules are added to simulate the behavior of humans reading text and filtering information. Based on the idea of granular computing, a multi-granularity module for computing context granularity and sequence granularity is added to the model to simulate the behavior of human beings to understand the text from words to sentences, from parts to the whole. Compared with the previous machine reading comprehension model, our model structure is novel. The skimming module and multi-granularity module proposed in this paper are used to solve the problem that the previous model ignores the key information of the text and cannot understand the text with multi granularity. Experiments show that the model proposed in this paper is effective for both Chinese and English datasets. It can better understand the question and context and give a more accurate answer. The performance has made new progress on the basis of the baseline model.

Switch Allocation (SA) holds a critical stage in Network-on-Chip (NoC) routers, its performance gets affected adversely due to Head-of-Line (HoL) blocking. In traditionally used Input-Queued Routers (IQR), packets are arranged in a particular order in each Virtual Channel (VC). This implementation is vulnerable to HoL blocking, as the switch allocator can allocate only those packets which are available at the head in a VC. In this paper, Swapped Buffer (SB) Router architecture is proposed to schedule packets in input buffers by using SB registers. The VCs are designed as SBs, this allows the packets stored in SB registers along with the head packet of VC to participate in SA. The concept of the SB register minimizes the conflicts in SA and thus reduces HoL blocking, therefore improves the performance of NoC. This paper proposes a priority mechanism to prioritize the non-head packets as compared to head packets in case of conflict between them. Two methods have been proposed in this paper, to enhance the performance of the NoC router. First, a VC allocation technique is proposed to optimize the order of packets in the input buffer. Next, SB-Router is combined with the Fill VC allocation technique to further enhance the performance of NoC routers. The performance of the proposed router is evaluated and the experimental results indicate that our design achieves latency improvement of 68.75% over (Time-Series) TS-Router for uniform traffic at the injection rate of 0.42 flits/cycle for a 64 node mesh network with moderate power consumption and area usage. The performance improvement in packet latency for traces from Princeton Application Repository for Shared-Memory Computers (PARSEC) has also been evaluated. With the achieved reduction in latency, the proposed method has the potential to serve high-speed operations while mapping different applications on multiple core architectures.

Aiming at the low-voltage DC distribution network system and combining the characteristics of F2F structure and ISOP-DAB structure DC transformer, this paper proposes a DC transformer structure based on modular multilevel converter (MMC) and cascaded H-bridge. First of all, this paper analyzes several different cases. Case 1 proposes a type of equal carrier-phase-shift pulse-width modulation (CPS-PWM) of MMC, which can produce an equal five-level voltage waveform. In the meanwhile, another unequal CPS-PWM control is proposed to produce an unequal five-level voltage waveform. According to the descriptions of case 2, the quasi-square-wave-modulation method with a wide gain range can greatly reduce the insulation design difficulty of the intermediate AC side high-frequency transformer and the voltage stress on the AC side. Case 3 demonstrates the extended-phase-shift (EPS) control of three-port DC-DC converter. Combining the voltage sorting algorithm of voltage sequencing and cyclic switching, a strategy of voltage equalization for grouped capacitors is proposed. Considering the various application scenarios of actual working conditions, the soft switching characteristics and multi-port power characteristics of the DC transformer are analyzed. In order to verify the feasibility of the DC transformer structure and its control strategy, a simulation model was built in Matlab/Simulink and the results were verified. The results are in accordance with the theoretical analysis.

The airway tree is one of the most important part in human respiratory system. Airway segmentation plays a crucial role in pulmonary disease diagnosis, localization and surgical navigation. We propose a novel method to improve airway segmentation in thoracic computed tomography(CT) using deep learning. In order to take into account the multi-scale changes of the airway and achieve accurate airway segmentation, we design an end-to-end Tiny Atrous Convolutional Network (TACNet) based on 3D convolution neural network. In view of the difficulty of classification due to the numerous branches of airway, two evaluation factors, namely, the angle of airway bifurcation and the buffer length of airway bifurcation are designed, which are used for airway classification by combining the centerline extraction. We train TACNet on the inspirator thoracic CT scans with ground truth, which are generated by clinicians and evaluate on our own clinical data sets and EXACT’09 data sets. Compared with state-of-the-art airway segmentation algorithms, proposed algorithm in this paper achieve very competitive results in 20 test datasets of the EXACT’09 challenge. The experimental results show that the algorithm proposed in this paper has high robustness and advantages regardless of airway segmentation or airway classification. In 20 test datasets of the EXACT’09 challenge, the average airway tree length detection rate is the best in the public literatures.

This paper tackles the problem of detecting incongruities between headlines and body text, where a news headline is irrelevant or even in opposition to the information in its body. Our model, called the graph-based hierarchical dual encoder (GHDE), utilizes a graph neural network to efficiently learn the content similarity between news headlines and long body paragraphs. This paper also releases a million-item-scale dataset of incongruity labels that can be used for training. The experimental results show that the proposed graph-based neural network model outperforms previous state-of-the-art models by a substantial margin (5.3%) on the area under the receiver operating characteristic (AUROC) curve. Real-world experiments on recent news articles confirm that the trained model successfully detects headline incongruities. We discuss the implications of these findings for combating infodemics and news fatigue.

A malicious attack may endanger human life or pollute environment on a cyber-physical system (CPS). However, successfully attacking a CPS needs not only the knowledge of information technology (IT) but also the domain knowledge of the system’s operation technology (OT). Therefore, it is critical to identify the vulnerabilities of a CPS. This paper proposes a systematic method for the security verification of a CPS, focusing on OT by using model checking with UPPAAL, so as to enhance cyber security. In our security analysis, we considered unsafe situations to be the result of a potentially effective security attack. Thus, we suggested a systematic method to generate security constraints based on the safety constraints (or safety checks) of the CPS and then enhance these security constraints by security verification using model checking with UPPAAL. UPPAAL’s simulation tool can perform a detailed search for each state in various possible model combinations and can explore human-computer interactions more deeply. The contributions of our method are as follows: First, a systematic method is proposed to generate security constraints based on the overall safety requirements at the OT level. Second, the security constraints thus generated can be used for run-time monitoring to identify the possible security attacks when they are violated. Third, this paper proposes to augment normal system modeling with a suggested Attack Module to simulate the potential OT attacks. Finally, the verification results may be used in the following twofold directions: to identify the vulnerabilities for possible design improvements and to suggest the further additions of security constraints.

Automation of Radio Access Network (RAN) operation is a fundamental feature to manage sustainable and efficient Beyond Fifth-generation wireless (5G) networks, in the context of the Next Generation Self-Organizing Network (NG-SON) vision. Machine Learning (ML) is already identified as the key ingredient of this vision, with new standardized and open architectures, like Open-RAN (O-RAN), taking momentum. In this paper, we propose models based on single-task and Multi-Task Learning (MTL) paradigms to address two RAN use cases, handover management and initial Modulation and Coding Scheme (MCS) selection. Traditional handover schemes have the drawback of taking into account the quality of the signals from the serving, and the target cell, before the handover. Also, initial MCS at the start of the session and after a handover usually is handled conservatively. The proposed ML solutions allow to address these drawbacks by 1) considering the expected Quality of Experience (QoE) resulting from the decision of a target cell to handover, as the driving principle of the handover decision and 2) using the experience extracted from network data to make smarter initial MCS allocations. In this line, we implement a realistic cellular simulation scenario by incorporating coverage holes to build an extensive database to train and test the proposed models. The results show that the ML-based models outperform the 3rd Generation Partnership Project (3GPP) standardized handover and initial MCS selection approaches by improving the QoE of users resulting from a handover and the throughput obtained upon establishing a new connection with a network. Besides that, using the obtained results, this paper extensively discusses the merits of leveraging the MTL model to address different, but related multiple RAN functions because it allows reusing a common learning architecture for multiple RAN use cases, which provides significant implementation advantages., This work was supported in part by under Grant PID2020-113832RB-C22 (ORIGIN)/AEI/10.13039/501100011033, and in part by Huawei Technologies, Sweden AB.

In this study, a novel method about building Deep Knowledge Graph for the Plant Insect Pest and Disease, namely DKG-PIPD, was proposed. Specifically, the semi-automatic extraction of semi-structured and unstructured knowledge was carried out on the basis of domain ontology, and the knowledge graph was stored in the third-party knowledge database according to the corpus characteristic of the plant insect pest and disease, to realize the visual display of entity interactive relationship and knowledge inference. Furthermore, DKG-PIPD performed joint extraction about the entity and the relationship in unstructured knowledge in a corpus tagging method that is suitable for domain data. In this way, the entity and the relationship were annotated synchronically, and the triplet can be obtained directly through label matching and label mapping, which not only effectively improved the annotation efficiency, but also solved the problem of one-versus-many overlapping relation extraction. In addition, DKG-PIPD used a novel end-to-end model to train and predict on the crawled dataset. The experimental contrast results with other classical benchmark methods demonstrated the effectiveness of the proposed method. Moreover, the related work in this paper first introduced the general architecture required for the building of knowledge graph, and then summarized its key points, that is, named entity recognition, entity relationship extraction and knowledge inference using deep learning are emphatically introduced. Finally, the improvement direction of this paper was also introduced in the discussion section.

In this paper, we propose an efficient attention module for visible and thermal infrared (TIR) matching deep learning networks. This method judges the right or wrong of heterogeneous sensor matching through the proposed deep learning model and increases the matching rate through the attention module using the edge-utilizing structure. This paper contributes to three aspects: 1) The first aspect is Convolutional Neural Network (CNN) structure comparisons for heterogeneous sensor registration. We consider the matching network as a classification problem when stacked heterogeneous sensor data become input of a single CNN network. Therefore, this paper shows result that is related with not only the network designed for heterogeneous sensor matching, but also various deep learning networks used for classification. 2) the second is a consideration for efficient attention module. The experiments show the module can replace lots of convolution blocks and the results achieve more better performance. The attention module uses a $1\times $ k filter and a k $\times $ 1 filter to extract horizontal and vertical edges and convolves two paths using them. 3) The third is suitable deep learning model for aerial complex visible and TIR data registration. To compare the various methods, we describe the calibration process of aerial visible and TIR data obtained directly from a drone. By using the calibrated data, this paper presents an AVIR attention block-based architecture that shows optimal matching results with minimal addition of parameters.

Vehicular Ad hoc Networks (VANETs) are emerging technologies with the primary purpose of establishing Vehicular communications. Available protocols for data dissemination in VANETs are faced with issues like discontinuous connections, uncertainty about receiving messages, collisions, and latency. In this paper, a new method is presented for the dissemination of advertising and infotainment messages. The proposed method has used store carry and forward (SCF), rateless coding, and a new handshake mechanism to solve discontinuous connections, uncertainty about receiving messages, and collision problems, respectively. In this paper, changing the Road Side Unit (RSU) message over time and its impact on the network is proposed as a new step in evaluating data dissemination methods. Our results showed that if changing the RSU message happened very rapidly, the network performance will almost be eliminated; to address this problem and due to the advertising nature of messages, the use of overhearing has been suggested. To the best of our knowledge, this is the first time that message overhearing has been used in VANET. Extensive and accurate simulations results show that the proposed method for 2, 3, 5, and 10 messages: (i) reduces the overhead of handshake on average 70% 63%, 48%, and 3%, (ii) increases the number of delivered packets on average 5%, 22%, 75%, and 84%, and (iii) increases the range of data dissemination on average 47%, 187%, 661%, and 2962%, respectively. With the mentioned improvements, the proposed method can also significantly reduce the latency of disseminating messages between vehicles.

Grain-128AEAD is a lightweight authenticated encryption stream cipher and one of the finalists in the National Institute of Standards and Technology (NIST) Lightweight Cryptography (LWC) project. This paper provides an independent third-party analysis of Grain-128AEAD against fault attacks. We investigate the application of three differential fault attack models on Grain-128AEAD. All these attacks can recover the initial state of Grain-128AEAD. First, we demonstrate an attack using a bit-flipping fault that requires access to 27.80 faulty outputs to recover the initial state. Then, we demonstrate an attack with a more relaxed assumption of a random fault with a probabilistic approach. Our probabilistic random fault attack requires access to 211.60 faulty outputs and 210.45 fault injections to recover the initial state with a success rate over 99%. Both of the above two attacks are based on precise control on the fault target. Finally, we apply a random fault attack with a deterministic approach (can conclusively determine the random fault value) and using different precision controls. For the precise control, we use existing approaches that have been applied to other ciphers, such as Tiaoxin-346. We also propose a technique for less stringent precision models, such as moderate control and no control, which are more practical than the precise control. Our result indicates that the deterministic random fault attack with a precise control requires an average of 27.64 fault injections and a data complexity of 28.80. The deterministic random fault attack with moderate control requires a weak assumption on the fault injection and hence, is the best attack presented in this paper; and is expected to require about 29.39 fault injections with a data complexity of about 212.98. All the attacks discussed in this paper are verified experimentally.

In the process of power transmission and distribution, non-technical losses are usually caused by users’ abnormal power consumption behavior. It will not only affect the dispatch and operation of the distribution network, bring hidden dangers to the security of the power grid, but also damage the operating costs of power companies and disrupt the operation of the power market. Aiming at users’ abnormal electricity consumption behavior, this paper proposes a model based on particle swarm optimization and long-short term memory with the attention mechanism (PSO-Attention-LSTM). Firstly, according to the actual electricity theft behavior, six typical electricity theft modes are summarized, and 4 composite modes are obtained by combining them, so as to comprehensively test the detection performance of the model for various electricity theft behaviors. Secondly, a detection model based on PSO-Attention-LSTM is proposed, and the model is built using the TensorFlow framework. The model uses the attention mechanism to give different weights to the hidden state of LSTM, which reduces the loss of historical information, strengthens important information and suppresses useless information. Use PSO to solve the difficult problem of model parameter selection, and optimize the hyperparameters to improve the model performance. Finally, the data set of the University of Massachusetts was used for simulation and compared with convolutional neural network-long short term memory (CNN-LSTM), attention mechanism-based long short term memory (Attention-LSTM), LSTM, gated recurrent unit (GRU), support vector regression (SVR), random forest (RF) and linear regression (LR) to verify the effectiveness and accuracy of the method used in this article. In this paper, Matlab software is used to analyze and visualize the detection result data.

Music is a heavenly way of expressing feelings about the world. The language of music has vast diversity. For centuries, people have indulged in debates to stratisfy between Western and Indian Classical Music. But through this paper, an understanding can be fabricated while differentiating the types of Indian Classical Music. Classical music is one of the essential characteristics of Indian Cultural Heritage. Indian Classical Music is divided into two major parts, i.e. Hindustani and Carnatic. Models have been sculptured and trained to classify between Hindustani and Carnatic Music. In this paper, two approaches are used to implement classification models. MFCCs are used as features and implemented models like DNN (1 Layer, 2 Layers, 3 Layers), CNN (1 Layer, 2 Layers, 3 Layers), RNN-LSTM, SVM (Sigmoid, Polynomial & Gaussian Kernel) as one approach. A 3 channels input is created by merging features like MFCC, Spectrogram and Scalogram and implemented models like VGG-16, CNN (1 Layer, 2 Layers, 3 Layers), ResNet-50 as another approach. 3 Layered CNN and RNN-LSTM model performed best among all the approaches.

To prevent privacy leakage, cloud services need to take corresponding methods, so participants often face the dilemma of service utility and privacy protection. In this paper, we propose a dynamic adaptive access control model based on trust permission and privacy protection to solve the problem of privacy disclosure and utility in the cloud service. Firstly, we add the concept of obligation and purpose into access control and establish the privacy information tree and privacy policy tree. Secondly, we establish a new trust evaluation and give the corresponding weight algorithm. Thirdly, we quantify the privacy information with the normal space and correlation coefficient method. Further, we propose a tradeoff relationship model between trust permission and privacy protection, each participant can select the corresponding parameters according to the actual requirement and personal preference. Experimental analysis and comparison results verify the feasibility, effectiveness, and superiority of our method. Finally, we summarize the work of this paper and point out the future development direction.

This paper aims to provide an in-depth study of the detection of historical alarm subsequences, which are frequently used as an initial step for alarm flood analysis methods. Therefore, state-of-the-art approaches are comprehensively examined, evaluated, and compared. To overcome the limitations of these methods, a novel approach is presented, which uses outlier detection in time distances between alarm events (activation and return to normal) and an alarm coactivation constraint. The effectiveness and performance of the examined methods are illustrated by means of an openly accessible dataset, which is introduced in this paper. It is based on the “Tennessee-Eastman-Process”, a benchmark in process automation. The intent is to provide a suitable dataset for the development and evaluation of alarm management methods in complex industrial processes using both quantitative and qualitative information from different sources. It is shown that the integration of supplementary information is beneficial for the overall performance and robustness of the detection method proposed here. This method allows for a more accurate detection of coherent historical abnormal situations, including phases with active root-cause disturbances and the normalization phases that follow their termination. Furthermore, the proposed method has the advantage that the detection results are less influenced by the alarm count, the propagation velocity, the duration of the situation, and the time distance between two causally independent situations in comparison to state-of-the-art approaches.

The aim of this paper is to design, analyze and optimize the “Multi-Stack Slotless Axial Flux Switching Permanent Magnet Machine”. In the design process, mathematical models are implemented, and the Finite Element Method (FEM) is performed to analyze the machine performances. The paper aims to minimize the occurrence of cogging torque and torque ripple in the multi-stack slotless stator AFPM machine. As a consequence, it reduces the vibrations in the machine and increases its life span. Multi-stack slotless stator AFPM machine with a right-angled trapezoid-shaped PM is proposed and comparison is done with conventional shape AFPM machine. In order to examine the performance of multi-stack slotless stator AFPM machine Finite Element Analysis (FEA) is used. To further enhance the characteristics of the designed machine with the proposed right-angled PM shape, optimization is done by considering inner and outer pole pitch as the design variables. In optimization process, krigging method assigned with Latin Hyper-cube Sampling and a genetic algorithm (GA) is performed due to suitability with non-linear data. Then, finite element analysis by JMAG-Designer is performed to verify the results. It is determined that optimized model has achieved 65% reduction in torque ripples as compared with the conventional design. Hence, this work attempts to optimize the performance of the AFPM machine.

An intrusion detection system (IDS) is an important protection instrument for detecting complex network attacks. Various machine learning (ML) or deep learning (DL) algorithms have been proposed for implementing anomaly-based IDS (AIDS). Our review of the AIDS literature identifies some issues in related work, including the randomness of the selected algorithms, parameters, and testing criteria, the application of old datasets, or shallow analyses and validation of the results. This paper comprehensively reviews previous studies on AIDS by using a set of criteria with different datasets and types of attacks to set benchmarking outcomes that can reveal the suitable AIDS algorithms, parameters, and testing criteria. Specifically, this paper applies 10 popular supervised and unsupervised ML algorithms for identifying effective and efficient ML-AIDS of networks and computers. These supervised ML algorithms include the artificial neural network (ANN), decision tree (DT), k-nearest neighbor (k-NN), naive Bayes (NB), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) algorithms, whereas the unsupervised ML algorithms include the expectation-maximization (EM), k-means, and self-organizing maps (SOM) algorithms. Several models of these algorithms are introduced, and the turning and training parameters of each algorithm are examined to achieve an optimal classifier evaluation. Unlike previous studies, this study evaluates the performance of AIDS by measuring the true positive and negative rates, accuracy, precision, recall, and F-Score of 31 ML-AIDS models. The training and testing time for ML-AIDS models are also considered in measuring their performance efficiency given that time complexity is an important factor in AIDSs. The ML-AIDS models are tested by using a recent and highly unbalanced multiclass CICIDS2017 dataset that involves real-world network attacks. In general, the k-NN-AIDS, DT-AIDS, and NB-AIDS models obtain the best results and show a greater capability in detecting web attacks compared with other models that demonstrate irregular and inferior results.

Distribution network connected distributed energy resources (DER) are able to provide various flexibility services for distribution system operators (DSOs) and transmission system operators (TSOs). These local and system-wide flexibility services offered by DER can support the frequency ( $f$ ) and voltage ( $U$ ) management of a future power system with large amounts of weather-dependent renewable generation and electric vehicles. Depending on the magnitude of frequency deviation, other active network management-based frequency control services for TSOs could also be provided by DSOs in coordination with adaptive control of DER. This paper proposes utilisation of demand response based on frequency-dependent HV/MV transformer on-load tap-changer (OLTC) operation in case of larger frequency deviations. The main principle underlying the proposed scheme lies in the voltage dependency of the distribution network connected loads. In this paper, it is also proposed to, simultaneously with frequency-dependent OLTC control, utilise reverse reactive power -voltage (QU) - and adaptive active power -voltage (PU) -droops with distribution network connected DER units during these larger frequency deviations, in order to enable better frequency support service for TSOs from DSO networks. The effectivity and potential of the proposed schemes are shown through PSCAD simulations. In addition, this paper also presents a holistic and collaborative view of potential future frequency control services which are provided by DSO network-connected resources for TSOs at different frequency deviation levels.

In this paper, we show that adversarial training time attacks by a few pixel modifications can cause undesirable overfitting in neural networks for both discriminative and generative models. We propose an evolutionary algorithm to search for an optimal pixel attack using a novel cost function inspired by domain adaptation literature to design our training time attack. The proposed cost function explicitly maximizes the generalization gap and domain divergence between clean and corrupted images. Empirical evaluations demonstrate that our adversarial training attack can achieve significantly low testing accuracy (with high training accuracy) on multiple datasets by just perturbing a single pixel in the training images. Even under the use of popular regularization techniques, we identify a significant performance drop compared to clean data training. Our attack is more successful than previous pixel-based training time attacks on state-of-the-art Convolutional Neural Networks (CNNs) architectures, as evidenced by significantly lower testing accuracy. Interestingly, we find that the choice of optimization plays an essential role in robustness against our attack. We empirically observe that Stochastic Gradient Descent (SGD) is resilient to the proposed adversarial training attack, different from adaptive optimization techniques such as the popular Adam optimizer. We identify that such vulnerabilities are caused due to over-reliance on the cross-entropy (CE) loss on highly predictive features. Therefore, we propose a robust loss function that maximizes the mutual information between latent features and input images, in addition to optimizing the CE loss. Finally, we show that the discriminator in Generative Adversarial Networks (GANs) can also be attacked by our proposed training time attack resulting in poor generative performance. Our paper is one of the first works to design attacks for generative models.

Increasing human activities have caused serious disturbance to global forest resources, so how to accurately identify individual trees has become an important task of forest resources investigation. In order to get the accurate number of individual trees, this paper took coniferous forest and mixed coniferous and broad-leaved forest as experimental samples, as well as Digital Orthophoto Map and airborne LiDAR Point Cloud as research data. We propose a deep Learning individual tree segmentation method based on RetinaNet model and PCS algorithm by doing comparative analysis (classical Watershed Algorithm and Layer Stacking Algorithm) at the plots (with high, medium, and low densities). The experimental results show that the method proposed in this paper can solve the problem of individual tree segmentation in high density forest and improve its degree of automation. Compared with Watershed algorithm and Layer stacking algorithm, F-Measure is improved by 6%-29% and 7%-20%, respectively. In other words, the results of individual tree segmentation presented in this paper can not only improve the precision of individual tree segmentation, but also maintain a high detection rate, which can meet the accuracy and high efficiency of individual tree extraction, so as to meet the needs for modern forestry investigation.

The key to an accurate understanding of terrain is to extract the informative features from the multi-modal data obtained from different devices. Sensors, such as RGB cameras, depth sensors, vibration sensors, and microphones, are used as the multi-modal data. Many studies have explored ways to use them, especially in the robotics field. Some papers have successfully introduced single-modal or multi-modal methods. However, in practice, robots can be faced with extreme conditions; microphones do not work well in crowded scenes, and an RGB camera cannot capture terrains well in the dark. In this paper, we present a novel framework using the multi-modal variational autoencoder and the Gaussian mixture model clustering algorithm on image data and audio data for terrain type clustering by forcing the features to be closer together in the feature space. Our method enables the terrain type clustering even if one of the modalities (either image or audio) is missing at the test-time. We evaluated the clustering accuracy with a conventional multi-modal terrain type clustering method and we conducted ablation studies to show the effectiveness of our approach.

As a basic task in the field of computer vision, target detection has been concerned by many researchers. The performance of target detection method is also directly related to the research in many advanced semantic fields. Current general target detection methods are not effective in small target detection, so this paper studies the problem of small target detection and proposes a small target detection method based on deep learning with considerate feature and effectively expanded sample size. Firstly, according to the characteristics of convolutional neural network, we improve the current deep network architecture which performs well in target detection, and introduce considerate multi-feature and multi-scale detection. Then, we transform the high-resolution images obtained on the Internet by combining two groups of sampling method, so that the feature distribution of the high-resolution target is closer to that of the low-resolution target, thus effectively expanding the training data set, solving the problem that small target data is difficult to be labeled and effectively avoiding overfitting. The results show the effectiveness of the improved method in small target detection. In addition, in view of the shortage of small target detection review literature, this paper gives a comprehensive and detailed introduction to the field of small target detection in terms of related work and future work.

A Switched-Capacitor Multilevel Inverter (SCMLI) topology is proposed here, which can generate up to fifteen levels with one unit and can be extended further for getting higher levels. The proposed SCMLI has a lesser number of switching devices with respect to other recently proposed structures presented in this paper. It also has the capacitor self-balancing property. Power loss analysis has also been done using PLECS software. Maximum efficiency of 96.33 % has been achieved. A generalized comparative study has also been carried out with the newly presented topologies in different research articles considering several parameters. In order to validate the structure presented in this paper, simulation is done in Matlab®2018a, and the simulation results obtained are verified using an experimental prototype.

Deep convolutional neural networks (DCNNs) have attracted extensive attention in synthetic aperture radar (SAR) image target detection. However, there is usually a lack of labeled data in SAR images which results in difficulties to improve the detection performance with DCNN based methods. Transfer learning borrows generic knowledge from other tasks for the target task and can be an effective solution to the small sample problem, but the features’ generality and specificity across various models are not discussed in target detection. In addition, conventional DCNN based models have too many parameters related to the prior information of the targets which increase the difficulty of transfer learning between different tasks. In this paper, we mainly conduct research in three folds to address these mentioned issues. First, the generality and specificity of features in different network models are analyzed in the field of SAR target detection. Second, a transitive transfer framework is developed for detection under small sample condition. Third, an anchor free rotatable detector with flexible structure is designed for SAR images detection to suit the transfer detection framework proposed in this paper and a reasonable explanation is given for its upper hand with small samples. Experimental results demonstrate that: 1) transitive transfer framework is valid in SAR target detection; 2) the anchor free detector in this framework is superior to the anchor based one; 3) the proposed detector achieves better performance under small sample condition by comparison with state-of-the-art methods.

This paper focuses on how to represent the testing face images for multi-feature face recognition. The choice of feature is critical for face recognition. The different features of the sample contribute differently to face recognition. The joint similar and specific learning (JSSL) has been effectively applied in multi-feature face recognition. In the JSSL, although the representation coefficient is divided into the similar coefficient and the specific coefficient, there is the disadvantage that the training images cannot represent the testing images well, because there are probable expressions, illuminations and disguises in the testing images. We think that the intra-class variations of one person can be linearly represented by those of other people. In order to solve well the disadvantage of JSSL, in the paper, we extend JSSL and propose the extended joint similar and specific learning (EJSSL) for multi-feature face recognition. EJSSL constructs the intra-class variant dictionary to represent the probable variation between the training images and the testing images. EJSSL uses the training images and the intra-class variant dictionary to effectively represent the testing images. The proposed EJSSL method is perfectly experimented on some available face databases, and its performance is superior to many current face recognition methods.