This paper proposes a new method for interpreting and simplifying a black box model of a deep random forest (RF) using a proposed rule elimination. In deep RF, a large number of decision trees are connected to multiple layers, thereby making an analysis difficult. It has a high performance similar to that of a deep neural network (DNN), but achieves a better generalizability. Therefore, in this study, we consider quantifying the feature contributions and frequency of the fully trained deep RF in the form of a decision rule set. The feature contributions provide a basis for determining how features affect the decision process in a rule set. Model simplification is achieved by eliminating unnecessary rules by measuring the feature contributions. Consequently, the simplified model has fewer parameters and rules than before. Experiment results have shown that a feature contribution analysis allows a black box model to be decomposed for quantitatively interpreting a rule set. The proposed method was successfully applied to various deep RF models and benchmark datasets while maintaining a robust performance despite the elimination of a large number of rules.

Probabilistic computing algorithms require electrically programmable stochasticity to encode arbitrary probability functions and controlled stochastic interaction or correlation between probabilistic (p-) bits. The latter is implemented with complex electronic components leaving a large footprint on a chip and dissipating excessive amount of energy. Here, we show an elegant implementation with just two dipole-coupled magneto-tunneling junctions (MTJ), with magnetostrictive soft layers, fabricated on a piezoelectric film. The resistance states of the two MTJs (high or low) encode the p-bit values (1 or 0) in the two streams. The first MTJ is driven to a resistance state with desired probability via a current or voltage that generates spin transfer torque, while the second MTJ’s resistance state is determined by dipole coupling with the first, thus correlating the second p-bit stream with the first. The effect of dipole coupling can be varied by generating local strain in the soft layer of the second MTJ with a local voltage (~ 0.2 V) and that varies the degree of anti-correlation between the resistance states of the two MTJs and hence between the two streams (from 0% to 100%). This paradigm generates the anti-correlation with “wireless” dipole coupling that consumes no footprint on a chip and dissipates no energy, and it controls the degree of anti-correlation with electrically generated strain that consumes minimal footprint and is extremely frugal in its use of energy. It can be extended to arbitrary number of bit streams. This realizes an “all-magnetic” platform for probabilistic computing.

Along with the deployment of the Face Recognition Systems (FRS), concerns were raised related to the vulnerability of those systems towards various attacks including morphed attacks. The morphed face attack involves two different face images in order to obtain via a morphing process a resulting attack image, which is sufficiently similar to both contributing data subjects. The obtained morphed image can successfully be verified against both subjects visually (by a human expert) and by a commercial FRS. The face morphing attack poses a severe security risk to the e-passport issuance process and to applications like border control, unless such attacks are detected and mitigated. In this work, we propose a new method to reliably detect a morphed face attack using a newly designed denoising framework. To this end, we design and introduce a new deep Multi-scale Context Aggregation Network (MS-CAN) to obtain denoised images, which is subsequently used to determine if an image is morphed or not. Extensive experiments are carried out on three different morphed face image datasets. The Morphing Attack Detection (MAD) performance of the proposed method is also benchmarked against 14 different state-of-the-art techniques using the ISO-IEC 30107-3 evaluation metrics. Based on the obtained quantitative results, the proposed method has indicated the best performance on all three datasets and also on cross-dataset experiments.

The results presented in the paper are based on simulations on benchmark spiking neural networks. The methodology is described in the paper.

Face recognition is widely employed in Automated Border Control (ABC) gates, which verify the face image on passport or electronic Machine Readable Travel Document (eMTRD) against the captured image to confirm the identity of the passport holder. In this paper, we present a robust morph detection algorithm that is based on differential morph detection. The proposed method decomposes the bona fide image captured from the ABC gate and the digital face image extracted from the eMRTD into the diffuse reconstructed image and a quantized normal map. The extracted features are further used to learn a linear classifier (SVM) to detect a morphing attack based on the assessment of differences between the bona fide image from the ABC gate and the digital face image extracted from the passport. Owing to the availability of multiple cameras within an ABC gate, we extend the proposed method to fuse the classification scores to generate the final decision on morph-attack-detection. To validate our proposed algorithm, we create a morph attack database with overall 588 images, where bona fide are captured in an indoor lighting environment with a Canon DSLR Camera with one sample per subject and correspondingly images from ABC gates. We benchmark our proposed method with the existing state-of-the-art and can state that the new approach significantly outperforms previous approaches in the ABC gate scenario.

In this chapter, we address the competent Autonomous Vehicles should have the ability to analyze the structure and unstructured environments and then to localize itself relative to surrounding things, where GPS, RFID or other similar means cannot give enough information about the location. Reliable SLAM is the most basic prerequisite for any further artificial intelligent tasks of an autonomous mobile robots. The goal of this paper is to simulate a SLAM process on the advanced software development. The model represents the system itself, whereas the simulation represents the operation of the system over time. And the software architecture will help us to focus our work to realize our wish with least trivial work. It is an open-source meta-operating system, which provides us tremendous tools for robotics related problems. Specifically, we address the advanced vehicles should have the ability to analyze the structured and unstructured environment based on solving the search-based planning and then we move to discuss interested in reinforcement learning-based model to optimal trajectory in order to apply to autonomous systems.

In this paper, we address the data sending and visualization in search-based planning using the open source software based on motion planning problems. First, we explore the computing architecture of software where we can communicate with other devices or sensors. It also is to understand the finding path problem by using the A-Start algorithm. By the way, it is integrated to ROS (Robot Operation System) and implemented in Nao Humanoid Robot based on solving the optimize the trajectories.

Over 20,000 fluorescence lifetime images from 10 patients were collected using a fibre-based custom fluorescence lifetime imaging endomicroscopy (FLIM) system. During the data collection, various measuring conditions were applied, including exposure time, optical wavelength, and lifetime extraction approaches to obtain diverse results rich in spatial and spectral resolution. The data for further processing was chosen with exposure time of 6 and 20 ns, excitation bands of 490-570 and 594-764 nm, and RLD. In addition, there are some images with sizes different than 128x128. In order to avoid any artificial errors on the lifetime images during the processing, only the lifetime images with 128x128 resolution were selected. After the selection, there were 10,155 and 11,363 frames of cancer and normal tissues respectively, and each frame contained one intensity and one corresponding lifetime image.

In this paper, we propose the simple method to optimize the datasets noise under the uncertainty applied to many applications in industry. Specifically, we use firstly the deep learning module at transfer learning based on using the mask-rcnn to detect the objects and segmentation effectively, then return the contours only. After that we address the shortest path for reduce the noise in order to increasing the highspeed in industrial applications. We illustrate adaptive many applications web applications such as mobile application where power computer is limited a source

A document by Rogério Negri . Click on the document to view its contents.

A document by Alexander Wiebel . Click on the document to view its contents.

The recent advances in vehicle industry and vehicle-to-everything communications are creating a huge potential market of intelligent vehicle applications, and exploiting vehicle mobility is of great importance in this field. Hence, this paper proposes a novel vehicle mobility prediction algorithm to support intelligent vehicle applications. First, a theoretical analysis is given to quantitatively reveal the predictability of vehicle mobility. Based on the knowledge earned from theoretical analysis, a deep recurrent neural network (RNN)-based algorithm called DeepVM is proposed to predict vehicle mobility in a future period of several or tens of minutes. Comprehensive evaluations have been carried out based on the real taxi mobility data in Tokyo, Japan. The results have not only proved the correctness of our theoretical analysis, but also validated that DeepVM can significantly improve the quality of vehicle mobility prediction compared with other state-of-art algorithms.

A document by Runnan He . Click on the document to view its contents.

The data used in this paper are given in the paper.

This manuscript was accepted for publication on IEEE Transactions on Geoscience and Remote Sensing. Abstract: In radar polarimetry, incoherent target decomposition techniques help extract scattering information from polarimetric SAR data. This is achieved either by fitting appropriate scattering models or by optimizing the received wave intensity through the diagonalization of the coherency (or covariance) matrix. As such, the received wave information depends on the received antenna configuration. Additionally, a polarimetric descriptor that is independent of the received antenna configuration might provide additional information which is missed by the individual elements of the coherency matrix. This implies that existing target characterization techniques might neglect this information. In this regard, we suitably utilize the 2D and 3D Barakat degree of polarization which is independent of the received antenna configuration to obtain distinct polarimetric information for target characterization. In this study, we introduce new roll-invariant scattering-type parameters for both full-polarimetric (FP) and compact-polarimetric (CP) SAR data. These new parameters jointly use the information of the 2D and 3D Barakat degree of polarization and the elements of the coherency (or covariance) matrix. We use these new scattering type parameters, which provide equivalent information as the Cloude alpha for FP SAR data and the ellipticity parameter chi for CP SAR data, to characterize various targets adequately. Additionally, we appropriately utilize these new scattering-type parameters to obtain unique non-model based three-component scattering power decomposition techniques. We obtain the even-bounce, and the odd-bounce scattering powers by modulating the total polarized power by a proper geometrical factor derived using the new scattering-type parameters for FP and CP SAR data. The diffused scattering power is obtained as the depolarized fraction of the total power. Moreover, due to the nature of its formulation, the decomposition scattering powers are nonnegative and roll-invariant while the total power is conserved. The proposed method is both qualitatively and quantitatively assessed utilizing the L-band ALOS-2 and C-band Radarsat-2 FP and the associated simulated CP SAR data.

Most ray tracing libraries allow the user to provide custom functionality that is executed when a potential ray surface interaction was encountered to determine if the interaction was valid or traversal should be continued. This is e.g. useful for alpha mask validation and allows the user to reuse existing ray object intersection routines rather than reimplementing them. Augmenting ray traversal with custom intersection logic requires some kind of callback mechanism that injects user code into existing library routines. With template libraries, this injection can happen statically since the user compiles the binary code herself. We present an implementation of this “custom intersector” approach and its integration into the C++ ray tracing template library Visionaray.

Internet of Things is realized by a large number of heterogeneous smart devices which sense, collect and share data with each other over the internet in order to control the physical world. Due to open nature, global connectivity and resource constrained nature of smart devices and wireless networks the Internet of Things is susceptible to various routing attacks. In this paper, we purpose an architecture of Ensemble Learning based Network Intrusion Detection System named ELNIDS for detecting routing attacks against IPv6 Routing Protocol for Low-Power and Lossy Networks. We implement four different ensemble based machine learning classifiers including Boosted Trees, Bagged Trees, Subspace Discriminant and RUSBoosted Trees. To evaluate proposed intrusion detection model we have used RPL-NIDDS17 dataset which contains packet traces of Sinkhole, Blackhole, Sybil, Clone ID, Selective Forwarding, Hello Flooding and Local Repair attacks. Simulation results show the effectiveness of the proposed architecture. We observe that ensemble of Boosted Trees achieve the highest Accuracy of 94.5% while Subspace Discriminant method achieves the lowest Accuracy of 77.8% among classifier validation methods. Similarly, an ensemble of RUSBoosted Trees achieves the highest Area under ROC value of 0.98 while lowest Area under ROC value of 0.87 is achieved by an ensemble of Subspace Discriminant among all classifier validation methods. All the implemented classifiers show acceptable performance results.

We propose two simple and effective spiking neuron models to improve the response time of the conventional spiking neural network. The proposed neuron models adaptively tune the presynaptic input current depending on the input received from its presynapses and subsequent neuron firing events. We analyze and derive the firing activity homeostatic convergence of the proposed models. We experimentally verify and compare the models on MNIST handwritten digits and FashionMNIST classification tasks. We show that the proposed neuron models significantly increase the response speed to the input signal.

A document by Zhao Zhang . Click on the document to view its contents.

In the era of digital revolution, a huge amount of data is being generated from different networks on a daily basis. Security of this data is of utmost importance. Intrusion Detection Systems are found to be one the best solutions towards detecting intrusions. Network Intrusion Detection Systems are employed as a defence system to secure networks. Various techniques for the effective development of these defence systems have been proposed in the literature. However, the research on the development of datasets used for training and testing purpose of such defence systems is equally concerned. Better datasets improve the online and offline intrusion detection capability of detection model. Benchmark datasets like KDD 99 and NSL-KDD cup 99 obsolete and do not contain network traces of modern attacks like Denial of Service, hence are unsuitable for the evaluation purpose. In this work, a detailed analysis of CIDDS-001 dataset has been done and presented. We have used different well-known machine learning techniques for analysing the complexity of the dataset. Eminent evaluation metrics including Detection Rate, Accuracy, False Positive Rate, Kappa statistics, Root mean squared error have been used to show the performance of employed machine learning techniques.

Advances in the design of multi-spectral cameras have led to great interests in a wide range of applications, from astronomy to autonomous driving. However, such cameras inherently suffer from a trade-off between the spatial and spectral resolution. In this paper, we propose to address this limitation by introducing a novel method to carry out super-resolution on raw mosaic images, multi-spectral or RGB Bayer, captured by modern real-time single-shot mo- saic sensors. To this end, we design a deep super-resolution architecture that benefits from a sequential feature pyramid along the depth of the network. This, in fact, is achieved by utilizing a convolutional LSTM (ConvLSTM) to learn the inter-dependencies between features at different receptive fields. Additionally, by investigating the effect of different attention mechanisms in our framework, we show that a ConvLSTM inspired module is able to provide superior at- tention in our context. Our extensive experiments and anal- yses evidence that our approach yields significant super- resolution quality, outperforming current state-of-the-art mosaic super-resolution methods on both Bayer and multi- spectral images. Additionally, to the best of our knowledge, our method is the first specialized method to super-resolve mosaic images, whether it be multi-spectral or Bayer.

Designing and implementing algorithms for medium and large scale quantum computers is not easy. In previous work we have suggested, and developed, the idea of using machine learning techniques to train a quantum system such that the desired process is “learned,” thus obviating the algorithm design difficulty. This works quite well for small systems. But the goal is macroscopic physical computation. Here, we implement our learned pairwise entanglement witness on Microsoft’s Q\#, one of the commercially available gate model quantum computer simulators; we perform statistical analysis to determine reliability and reproducibility; and we show that after training the system in stages for an incrementing number of qubits (2, 3, 4, \ldots) we can infer the pattern for mesoscopic $N$ from simulation results for three-, four-, five-, six-, and seven-qubit systems. Our results suggest a fruitful pathway for general quantum computer algorithm design and for practical computation on noisy intermediate scale quantum devices.

Relay node placement in wireless sensor networks for constrained environment is a critical task due to various unavoidable constraints. One of the most important constraints is unpredictable obstacles. Handling obstacles during relay node placement is complicated because of complexity involved to estimate the shape and size of obstacles. This paper presents an Obstacle-resistant relay node placement strategy (ORRNP). The proposed solution not only handles the obstacles but also estimates best locations for relay node placement in the network. It also does not involve any additional hardware (mobile robots) to estimate node locations thus can significantly reduce the deployment costs. Simulation results show the effectiveness of our proposed approach.

This study intends to review and discuss some topics around CiteScore (here abbreviated as CS) which is a new citation impact indicator of Scopus. Qualitative analysis of journals based on scientometric indicators has been usual and is a good way of rapid evaluation of them. Here, we use them to reach a conclusion. We believe that reliability of CiteScore-based quartile is more and this index is preferred because in comparison to IF-based quartile, there are some reasons of preference of CS. In addition, CS can provide a more natural perception on citations compared to SJR-based quartile computation. The result of this study can be considered as a proof that both types of SJR- and CiteScore-based quartiles should not be assumed as baseline of quality evaluations at the same time.