Set Of Input Vectors Research Articles

Efficient System Identification of a Two-Wheeled Robot (TWR) Using Feed-Forward Neural Networks

System identification of a Two-Wheeled Robot (TWR) through nonlinear dynamics is carried out in this paper using a data-driven approach. An Artificial Neural Network (ANN) is used as a kinematic estimator for predicting the TWR’s degree of movement in the directions of x and y and the angle of rotation Ψ along the z-axis by giving a set of input vectors in terms of linear velocity ‘V’ (i.e., generated through the angular velocity ‘ω’ of a DC motor). The DC motor rotates the TWR’s wheels that have a wheel radius of ‘r’. Training datasets are achieved via simulating nonlinear kinematics of the TWR in a MATLAB Simulink environment by varying the linear scale sets of ‘V’ and ‘(r ± ∆r)’. Perturbation of the TWR’s wheel radius at ∆r = 10% is introduced to cater to the robustness of the TWR wheel kinematics. A trained ANN accurately modeled the kinematics of the TWR. The performance indicators are regression analysis and mean square value, whose achieved values met the targeted values of 1 and 0.01, respectively.

Accurate Reliability Boundary Evaluation of Approximate Arithmetic Circuit

Approximate arithmetic circuit (AAC) has emerged as a promising high-performance and energy-efficient circuit paradigm, which can be used in many applications with inherent error tolerance. To guarantee the usability of AACs and the availability of resilient applications, it is necessary to analyze the reliability of AACs. Most current literature focus on the error characteristics of AACs and few methods can be applied to estimate the reliability of AACs. These methods mostly have exponential time complexities and evaluate the average reliability assuming the input combinations are equally likely. In reality, the primary input (PI) signals can be given with any probability from 0 to 1. In this article, we assume that the PIs have random signal probabilities and propose approaches to reliability boundary estimation for AACs. First, we propose a new efficient and accurate method to evaluate the reliability of AACs. The method mainly calculates the AAC reliability for an input vector set, and furthermore, during the calculation, the correlation problem is considered to increase accuracy. Then, based upon the proposed AAC reliability evaluation method, we present the approaches to finding the reliability boundary. Randomly given signal probabilities of every PI, two heuristic search algorithms are utilized to find the lowest reliability. A comparison of the results on three series of AACs and the circuits in the EvoApprox8b library confirms that the proposed reliability evaluation method is more accurate and efficient than the previous method. Further experiments verify the plausibility of the calculated reliability boundary of AACs.

Reversible Logic Based MOS Current Mode Logic Implementation in Digital Circuits

Now a days, MOS Current Mode Logic (MCML) has emerged as a better alternative to Complementary Metal Oxide Semiconductor (CMOS) logic in digital circuits. Recent works have only traditional logic gates that have issues with information loss. Reversible logic is incorporated with MOS Current Mode Logic (MCML) in this proposed work to solve this problem, which is used for multiplier design, D Flip-Flop (DFF) and register. The minimization of power and area is the main aim of the work. In reversible logic, the count of outputs and inputs is retained as the same value for creating one-to-one mapping. A unique output vector set can be generated for each input vector set and information loss is also prevented. In reversible MCML based multiplier, reversible logic full adder is utilized to minimize the area and power. D flip-flops based on reversible MCML are often designed to store information that is then combined to form a reversible MCML based register. The proposed reversible MCML multiplier attains average power of 0.683~mW, Reversible MCML based DFF achieves 0.56 μW and Reversible MCML based 8-bit register attains 04.04 μW. The result shows that the proposed Reversible MCML based multiplier, Reversible MCML based D flip-flop and Reversible MCML based register achieves better performance in terms of current, power dissipation, average power and area.

Solving the Schrödinger equation using program synthesis.

We demonstrate that a program synthesis approach based on a linear code representation can be used to generate algorithms that approximate the ground-state solutions of one-dimensional time-independent Schrödinger equations constructed with bound polynomial potential energy surfaces (PESs). Here, an algorithm is constructed as a linear series of instructions operating on a set of input vectors, matrices, and constants that define the problem characteristics, such as the PES. Discrete optimization is performed using simulated annealing in order to identify sequences of code-lines, operating on the program inputs that can reproduce the expected ground-state wavefunctions ψ(x) for a set of target PESs. The outcome of this optimization is not simply a mathematical function approximating ψ(x) but is, instead, a complete algorithm that converts the input vectors describing the system into a ground-state solution of the Schrödinger equation. These initial results pointthe way toward an alternative route for developing novel algorithms for quantum chemistry applications.

Developing Benchmarks for Radiation Testing of Microcontroller Arithmetic Units Using ATPG

Reliability-focused benchmarks are used to test systems in harsh operating conditions, including space and terrestrial radiation environment. The sensitivity to single-event effects of a microprocessor in a radiation environment depends on the set of input vectors used at the time of testing due to logical masking. This article analyzes the impact of the input test set on the cross section of the microprocessor and proposes a mechanism to derive a high-quality input test set using automatic test pattern generation (ATPG) for radiation testing of microprocessor's arithmetic and logical units.

BM-RCGL: Benchmarking Approach for Localization of Reliability-Critical Gates in Combinational Logic Blocks

Accurate and effective localization of reliability-critical gates (RCGs) is one of the important prerequisites for low-cost circuit fault tolerance in the early stages of circuit design. This article introduces an accurate and effective approach for localizing RCGs in combinational logic blocks through a benchmarking technique. In the proposed approach, uniform non-Bernoulli sequences are used to produce a set of input vectors for driving circuits. A full-period linear congruential algorithm is employed to generate a sequence that provides the sampled order for the RCGs to be analyzed. This ensures that each gate in the circuit is treated as fairly as possible. To accelerate the localization process, an input-vector-based pruning technique combined with a counting method is also introduced to identify the specified number of RCGs. Then, the criticality of gate reliability for each RCG is measured through benchmarking. A clustering algorithm carries out the convergence checking for the proposed approach. The performance of the proposed approach was evaluated in terms of accuracy, stability, and time-space overhead by various simulations on 74-series circuits and ISCAS-85 benchmark circuits. The results show that its accuracy is close to that of the Monte Carlo model and its stability is better than that of other approximate methods. Moreover, compared with approximate methods, the time overhead of our approach is advantageous in the presence of similar memory overheads.

Setting up Reference Variants to Comply With Current Boundary Settings in Finite Set Model Predictive PMSM Control

Finite control set model predictive control (FCS-MPC), especially the reference-voltage-vector-based model predictive control (MPC) (RVV-MPC), considers a limited set of input vectors. However, the control performance is not satisfactory enough due to a severe lack of voltage input variants. In particular, additional restraints, such as limiting the currents within setting boundaries, could not be supported with RVV-MPC. In this article, to truly comply with the boundary settings, a reference variant FCS-MPC approach is introduced. In the proposed strategy, reference currents are considered under the maximum torque per current (MTPC) control. As boundary settings could not be supported in RVV-MPC, it is better to search for the optimal current reference that is feasible within the imposed boundaries. Therefore, rather than fixing the current reference, a well-considered neighborhood of the MTPC reference is introduced, and these variants are processed, resulting in a set of optimal candidate inputs. As multiple, but still finite, optimal solutions become possible, additional efforts can be made within the objective function to restrain the current and reduce the torque ripple. The size of the current reference space can be automatically adapted to generate current references that correspond to truly bounded current vectors. A trade-off is then made between control performance and meeting the boundary settings.

Conceptualisation of Cyberattack prediction with deep learning

The state of the cyberspace portends uncertainty for the future Internet and its accelerated number of users. New paradigms add more concerns with big data collected through device sensors divulging large amounts of information, which can be used for targeted attacks. Though a plethora of extant approaches, models and algorithms have provided the basis for cyberattack predictions, there is the need to consider new models and algorithms, which are based on data representations other than task-specific techniques. Deep learning, which is underpinned by representation learning, has found widespread relevance in computer vision, speech recognition, natural language processing, audio recognition, and drug design. However, its non-linear information processing architecture can be adapted towards learning the different data representations of network traffic to classify benign and malicious network packets. In this paper, we model cyberattack prediction as a classification problem. Furthermore, the deep learning architecture was co-opted into a new model using rectified linear units (ReLU) as the activation function in the hidden layers of a deep feed forward neural network. Our approach achieves a greedy layer-by-layer learning process that best represents the features useful for predicting cyberattacks in a dataset of benign and malign traffic. The underlying algorithm of the model also performs feature selection, dimensionality reduction, and clustering at the initial stage, to generate a set of input vectors called hyper-features. The model is evaluated using CICIDS2017 and UNSW_NB15 datasets on a Python environment test bed. Results obtained from experimentation show that our model demonstrates superior performance over similar models.

Algorithm for determining the optimum number of clusters on the basis of the Kohonen neural network

The article discusses the possibilities of using artificial intelligence systems to solve clustering problems. The value of the optimality criterion for various combinations of the number of clusters and the number of neurons of the output network layer is determined. Self-organizing maps (SOM, Self Organizing Maps), developed by T. Kohonen and representing a powerful tool combining two important paradigms of data analysis - clustering and projecting, visualization of multidimensional data on a plane are considered. An example of the location of cluster nuclei after training the Kohonen neural network for different values of the number of neurons in the source layer is given. Comparing the speed of modern computers with the speed of the Kohonen neural network, with other types of neural networks, allows you to conduct a large number of network exercises in a short time, so you can use one of many methods to determine the maximum value of the function. The results of experimental studies to determine the criterion of optimality are presented in the article for different combinations of the number of clusters and the number of neurons in the original layer of the network. According to the method at the initial stage, a set of input vectors is formed, each of which includes three values. A general sequence of actions is formulated to calculate the optimal number of neurons in the output layer of the Kohonen network. The methodology presented in the article is a further development of teaching methods without a teacher. The technique proposed in the article avoids the need to specify the number of outputs of the Kohonen neural network and can be widely used both in solving data mining problems and in recognizing new unknown classes and situations in different fields.

Neural Network Based Classification of Melanocytic Lesions in Dermoscopy: Role of Input Vector Encoding

DOI: 10.26650/electrica.2018.97856 Melanocytic lesions are the main cause of death from skin cancer, and early diagnosis is the key to decreasing the mortality rate. This study assesses the role of input-vector encoding in neural network-based classification of melanocytic lesions in dermoscopy. Twelve dermoscopic measures from 200 melanocytic lesions are encoded by compact encoding, adrenocortical dysplasia (ACD) encoding, 1-of-N encoding, normalized encoding, and raw encoding, resulting in five different input-vector sets. Feed-forward neural networks with one hidden layer and one output layer are designed with several neurons in the hidden layer, ranging from two to twenty-two for each type of input-vector set, to classify a melanocytic lesion into common nevus, atypical nevus, and melanoma. Accordingly, 105 networks are designed and trained using supervised learning and then tested by performing a 10-fold cross validation. All the neural networks achieve high sensitivities, specificities, and accuracies in classification. However, the network with seven neurons in the hidden layer and raw encoded dermoscopic measures as the input vector realizes the highest sensitivity (97.0%), specificity (98.1%), and accuracy (98.0%). The practical use of the network can facilitate lesion classification by retaining the needed expertise and minimizing diagnostic variability among dermatologists.

Multi-class recognition of objects technical condition by classifier based on probabilistic neural network

The paper deals with the efficiency study of the classifier developed based on the probabilistic neural network for multi-class diagnostics of a complex spatial object in the presence of multi-site damage. For recognition, the multidimensional diagnostic feature vector is used, the values of the features may have a deviation of ±5 % for the defect-free condition of an object, and exceed the permissible deviation in case of occurrence and development of damage. For the vector containing 5 diagnostic features, 6 classes of technical condition of an object are substantiated. Formation of sets of training and test input vectors, used for the classifier training and testing is performed. In order to evaluate the multi-class recognition efficiency, the coefficient, which is a percentage of the probability of correct classification of test vectors, is used. The analysis of the dependence of the efficiency coefficient on the characteristics of the classifier and the set of training vectors is carried out. It is found that error-free multi-class recognition of the object condition over the entire set of input vectors with different values of deviation of feature elements is provided in the range of values of the classifier parameter spread of [0,02; 0.07]. It is revealed that the greater the diagnostic feature deviation in test vectors, the greater the influence of the dimension of the set of training vectors on the multi-class recognition efficiency. The minimum size of the set of training vectors (68 vectors) and the limit value of diagnostic feature deviation in test vectors (17 %), which provide error-free multi-class recognition by the developed classifier are determined.

Robustness regions for measures of risk aggregation

Abstract One of risk measures’ key purposes is to consistently rank and distinguish between different risk profiles. From a practical perspective, a risk measure should also be robust, that is, insensitive to small perturbations in input assumptions. It is known in the literature [14, 39], that strong assumptions on the risk measure’s ability to distinguish between risks may lead to a lack of robustness. We address the trade-off between robustness and consistent risk ranking by specifying the regions in the space of distribution functions, where law-invariant convex risk measures are indeed robust. Examples include the set of random variables with bounded second moment and those that are less volatile (in convex order) than random variables in a given uniformly integrable set. Typically, a risk measure is evaluated on the output of an aggregation function defined on a set of random input vectors. Extending the definition of robustness to this setting, we find that law-invariant convex risk measures are robust for any aggregation function that satisfies a linear growth condition in the tail, provided that the set of possible marginals is uniformly integrable. Thus, we obtain that all law-invariant convex risk measures possess the aggregation-robustness property introduced by [26] and further studied by [40]. This is in contrast to the widely-used, non-convex, risk measure Value-at-Risk, whose robustness in a risk aggregation context requires restricting the possible dependence structures of the input vectors.

Functional Test Generation for Hard-to-Reach States Using Path Constraint Solving

Test generation for hard-to-reach states is important in functional verification. In this paper, we present a path constraint solving-based test generation method (PACOST) which operates in an abstraction-guided semiformal verification framework to cover hard-to-reach states. PACOST combines concrete simulation and symbolic simulation on the design under verification for path constraint extraction and mutation, and uses a sequential path constraint extractor to generate a set of valid input vectors for exploring different simulation paths with different next states. It then works on a target state-oriented abstract model to select the next state with the smallest abstract distance. In addition, the value of register variables in control logic can be controlled by analyzing the data dependence between variables, which helps the simulation converge to the target states. Experimental results show that PACOST can generate shorter traces reaching hard-to-reach states, in comparison with previous abstraction-guided semiformal methods.

Feature Subspace Estimation for Resolving Dimensionality Mismatch in Practical Color-Based Face Recognition Systems

Recently, considerable research efforts have been devoted to effective utilization of facial color information for improved recognition performance. Of all color-based face recognition (FR) methods, the most widely used approach is a color FR method using input-level fusion. In this method, augmented input vectors of the color images are first generated by concatenating different color components (including both luminance and chrominance information) by column order at the input level and feature subspace is then trained with a set of augmented input vectors. However, in practical applications, a testing image could be captured as a grayscale image, rather than as a color image, mainly caused by different, heterogeneous image acquisition environment. A grayscale testing image causes so-called dimensionality mismatch between the trained feature subspace and testing input vector. Disparity in dimensionality negatively impacts the reliable FR performance and even imposes a significant restriction on carrying out FR operations in practical color FR systems. To resolve the dimensionality mismatch, we propose a novel approach to estimate new feature subspace, suitable for recognizing a grayscale testing image. In particular, new feature subspace is estimated from a given feature subspace created using color training images. The effectiveness of proposed solution has been successfully tested on four public face databases (DBs) such as CMU, FERET, XM2VTSDB, and ORL DBs. Extensive and comparative experiments showed that the proposed solution works well for resolving dimensionality mismatch of importance in real-life color FR systems.

GP made faster with semantic surrogate modelling

Genetic Programming (GP) is known to be expensive in cases where the fitness evaluation is computationally demanding, i.e., object detection, programmatic compression, image processing applications. The paper introduces a method that reduces the amount of fitness evaluations that are required to obtain good solutions. We consider the supervised learning setting, where a training set of input vectors are collectively mapped to a vector of outputs, and then a loss function is used to map the vector of outputs to a scalar fitness value. Saving of fitness evaluations is achieved through the use of two components. The first component is surrogate model that predicts trees output for a particular input vector xi based on the similarity between xi and other input vectors in the training set for which the candidate solution has been already evaluated with. The second component, is a simple linear equation to control the size of a sub-training set that is used to train GP trees. This linear equation allows the size of the sub-training set to dynamically increase or decrease based on the status of the search. The proposed method referred to as SSGP. Empirical results in 17 different problems, from three different categories, demonstrate that SSGP is able to obtain solutions of similar quality with those obtained using several benchmark GP systems, but with a much smaller computation time. The simplicity of the proposed method and the ease of its implementation is one of the most appealing aspects of its future utility.

Effective staging of fibrosis by the selected texture features of liver: Which one is better, CT or MR imaging?

PurposeTexture patterns of hepatic fibrosis are one of the important biomarkers to diagnose and classify chronic liver disease from initial to end stage on computed tomography (CT) or magnetic resonance (MR) images. Computer-aided diagnosis (CAD) of liver cirrhosis using texture features has become popular in recent research advances. To date, however, properly selecting effective texture features and image parameters is still mostly undetermined and not well-defined. In this study, different types of datasets acquired from CT and MR images are investigated to select the optimal parameters and features for the proper classification of fibrosis. MethodsA total of 149 patients were scanned by multi-detector computed tomography (MDCT) and 218 patients were scanned using 1.5T and 3T superconducting MR scanners for an abdominal examination. All cases were verified by needle biopsies as the gold standard of our experiment, ranging from 0 (no fibrosis) to 5 (cirrhosis). For each case, at least four sequenced phase images are acquired by CT or MR scanners: pre-contrast, arterial, portal venous and equilibrium phase. For both imaging modalities, 15 texture features calculated from gray level co-occurrence matrix (GLCM) are extracted within an ROI in liver as one set of input vectors. Each combination of these input subsets is checked by using support vector machine (SVM) with leave-one-case-out method to differentiate fibrosis into two groups: non-cirrhosis or cirrhosis. In addition, 10 ROIs in the liver are manually selected in a disperse manner by experienced radiologist from each sequenced image and each of the 15 features are averaged across the 10 ROIs for each case to reduce the validation time. The number of input items is selected from the various combinations of 15 features, from which the accuracy rate (AR) is calculated by counting the percentage of correct answers on each combination of features aggregated to determine a liver stage score and then compared to the gold standard. ResultsAccording to the accuracy rate (AR) calculated from each combination, the optimal number of texture features to classify liver fibrosis degree ranges from 4 to 7, no matter which modality was utilized. The overall performance calculated by the average sum of maximum AR value of all 15 features is 66.83% in CT images, while 68.14%, and 71.98% in MR images, respectively; among the 15 texture features, mean gray value and entropy are the most commonly used features in all 3 imaging datasets. The correlation feature has the lowest AR value and was removed as an effective feature in all datasets. AR value tends to increase with the injection of contrast agency, and both CT and MR images reach the highest AR performance during the equilibrium phase. ConclusionsComparing the accuracy of classification with two imaging modalities, the MR images have an advantage over CT images with regards to AR performance of the 15 selected texture features, while 3T MRI is better than 1.5T MRI to classify liver fibrosis. Finally, the texture analysis is more effective during equilibrium phase than in any of the other phased images.

Predicting energy consumption of multiproduct pipeline using artificial neural networks

In this paper artificial neural network is introduced to forecast the daily electricity consumption of a multiproduct pipeline which is used to drive oil pumps. Forecasting electricity energy consumption is complicated since there are so many parameters affecting the energy consumption. Two different sets of input vectors are selected from these parameters by detailed analysis of energy consumption in this study, and two corresponding multilayer perceptron artificial neural network (MLP ANN) models are developed. To enhance the generalization ability, the numbers of hidden layers and neurons, activation functions and training algorithm of each model are optimized by the trial-and-error process step by step. The performances of the two proposed MLP ANN models are evaluated on real data of a Chinese multiproduct pipeline, and compared with two linear regression and two support vector machine (SVM) models which are produced using different inputs. Results show that the two MLP ANN models have very high accuracy for prediction and better forecasting performance than the other models. The proposed input vectors and MLP ANN models are useful not only in the effective evaluation of batch scheduling and pumping operation, but also in the energy consumption target setting.

Where Do Features Come From?

It is possible to learn multiple layers of non-linear features by backpropagating error derivatives through a feedforward neural network. This is a very effective learning procedure when there is a huge amount of labeled training data, but for many learning tasks very few labeled examples are available. In an effort to overcome the need for labeled data, several different generative models were developed that learned interesting features by modeling the higher order statistical structure of a set of input vectors. One of these generative models, the restricted Boltzmann machine (RBM), has no connections between its hidden units and this makes perceptual inference and learning much simpler. More significantly, after a layer of hidden features has been learned, the activities of these features can be used as training data for another RBM. By applying this idea recursively, it is possible to learn a deep hierarchy of progressively more complicated features without requiring any labeled data. This deep hierarchy can then be treated as a feedforward neural network which can be discriminatively fine-tuned using backpropagation. Using a stack of RBMs to initialize the weights of a feedforward neural network allows backpropagation to work effectively in much deeper networks and it leads to much better generalization. A stack of RBMs can also be used to initialize a deep Boltzmann machine that has many hidden layers. Combining this initialization method with a new method for fine-tuning the weights finally leads to the first efficient way of training Boltzmann machines with many hidden layers and millions of weights.

Graph Machine Based-QSAR Approach for Modeling Thermodynamic Properties of Amines: Application to CO2Capture in Postcombustion

Amine scrubbing is usually considered as the most efficient technology for CO<sub>2<sub/> mitigation through postcombustion Carbon Capture and Storage (CCS). However, optimization of the amine structure to improve the solvent properties requires to sample a large number of possible candidates and hence to gather a large amount of experimental data. In this context, the use of QSAR (Quantitative Structure Activity Relationship) statistical modeling is a powerful tool as it performs a mapping of a set of input vectors (i.e. the characteristics or the properties of the molecules under consideration) to a set of output vectors (i.e. their targeted properties). In this work, we used a high throughput screening experimental device to measure CO<sub>2<sub/> solubility data on a set of 46 amine aqueous solutions. Absorption isotherms are represented using a thermodynamic model based on two thermodynamic constants, pKa<sup>*<sup/> and pKc<sup>*<sup/> , accounting for the main chemical reactions occurring in the liquid phase between amine and CO<sub>2<sub/>. Then, we used a statistical approach named Graph Machines at the same time to cluster the molecules and to model the variation of the acidity constant pKa<sup>*<sup/> as a function of the molecular structure. The originality of our approach is the use of graphs to represent molecules in multidimensional spaces and simultaneously construct predictive models of their physicochemical properties based on these graphs. This approach is applied in this paper to predict the thermodynamic properties of a set of 5 new molecules.

Scalable Hardware Trojan Diagnosis

Hardware Trojans (HTs) pose a significant threat to the modern and pending integrated circuit (IC). Due to the diversity of HTs and intrinsic process variation (PV) in IC design, detecting and locating HTs is challenging. Several approaches have been proposed to address the problem, but they are either incapable of detecting various types of HTs or unable to handle very large circuits. We have developed a scalable HT detection and diagnosis approach that uses segmentation and gate level characterization (GLC). We ensure the detection of arbitrary malicious circuitry by measuring the overall leakage current for a set of different input vectors. In order to address the scalability issue, we employ a segmentation method that divides the large circuit into small sub-circuits using input vector selection. We develop a segment selection model in terms of properties of segments and their effects on GLC accuracy. The model parameters are calibrated by sampled data from the GLC process. Based on the selected segments we are able to detect and diagnose HTs by tracing gate level leakage power. We evaluate our approach on several ISCAS85/ISCAS89/ITC99 benchmarks. The simulation results show that our approach is capable of detecting and diagnosing HTs accurately on large circuits.