Search

In this paper, a 0.6 V subthsheshold CMOS voltage reference (CVR) achieving wide temperature range and high power supply ripple rejection (PSRR) is presented. The proposed CVR structure can compensate the high temperature leakage and current mirror induced mismatches so as to increase the operating temperature range. The generated reference voltage of the proposed CVR circuit is the threshold voltage difference of two NMOS transistors, leading to relatively small variations. Moreover, the enhanced current source helps achieve high PSRR. The proposed CVR circuit is implemented in a standard 0.18-μm CMOS technology. Measurement results show that, with one single trimming, a mean output of 344 mV with standard deviation of only 2.89 mV and average TC of 44.6 ppm/°C over a wide temperature range from −40 °C to 125 °C is achieved. The measured PSRR is −68 dB, −52 dB and −52 dB at 10 Hz, 100 kHz and 10 MHz, respectively. The measured line sensitivity (LS) is 0.06%/V with a power supply from 0.6 V to 2 V while consuming 19.8 nW at 0.6 V supply. The active area is 0.019 mm2.

For federated learning systems deployed in the wild, data flaws hosted on local agents are widely witnessed. On one hand, given a large amount (e.g. over 60%) of training data are corrupted by systematic sensor noise and environmental perturbations, the performances of federated model training can be degraded significantly. On the other hand, it is prohibitively expensive for either clients or service providers to set up manual sanitary checks to verify the quality of data instances. In our study, we echo this challenge by proposing a collaborative and privacy-preserving machine teaching method. Specifically, we use a few trusted instances provided by teachers as benign examples in the teaching process. Our collaborative teaching approach seeks jointly the optimal tuning on the distributed training set, such that the model learned from the tuned training set predicts labels of the trusted items correctly. The proposed method couples the process of teaching and learning and thus produces directly a robust prediction model despite the extremely pervasive systematic data corruption. The experimental study on real benchmark data sets demonstrates the validity of our method.

Measures of predictability in physiological signals based on entropy metrics have been widely used in the application domain of medical assessment and clinical diagnosis. In this paper, we propose a new entropy-based pattern learning by a combination of singular spectrum analysis (SSA) and entropy measures for assessment of physiological signals. Physiological signals are first represented as a series of SSA components, and then well-established entropy measures are extracted from the resulting SSA components that can help to facilitate the features extraction from physiological signals. The entropy measures of notable SSA components are used to form input features and fed into pattern classifier. To demonstrate its validity, applicability, and versatility, the proposed entropy-based pattern learning is used to perform medical assessments with three kinds of classical physiological signals, that is, electroencephalogram (EEG), electromyogram (EMG), and RR-interval signals. Experiments demonstrate that in all cases, the proposed entropy-based pattern learning can effectively capture specific biosignal patterns of physiological signals and achieve excellent identification performances for the assessments of EEG, EMG, and RR-interval signals. Besides, through the comparison of the identification performances for entropy-based pattern learning based on the physiological signals themselves and the SSA components, it is concluded that the discriminating power of entropy-based pattern learning based on the SSA components is much stronger than that based on the physiological signals themselves. Since it can be easily extended to any other physiological signal analysis, the proposed entropy-based pattern learning may use as an efficient approach to reveal biosignal patterns for medical assessment of physiological signals.

Despite of the pervasive existence of multi-label evasion attack, it is an open yet essential problem to characterize the origin of the adversarial vulnerability of a multi-label learning system and assess its attackability. In this study, we focus on non-targeted evasion attack against multi-label classifiers. The goal of the threat is to cause miss-classification with respect to as many labels as possible, with the same input perturbation. Our work gains in-depth understanding about the multi-label adversarial attack by first characterizing the transferability of the attack based on the functional properties of the multi-label classifier. We unveil how the transferability level of the attack determines the attackability of the classifier via establishing an information-theoretic analysis of the adversarial risk. Furthermore, we propose a transferability-centered attackability assessment, named Soft Attackability Estimator (SAE), to evaluate the intrinsic vulnerability level of the targeted multi-label classifier. This estimator is then integrated as a transferability-tuning regularization term into the multi-label learning paradigm to achieve adversarially robust classification. The experimental study on real-world data echos the theoretical analysis and verify the validity of the transferability-regularized multi-label learning method., Comment: Accepted in ECML-PKDD 2021

Evasion attack on discrete data is a challenging, while practically interesting research topic. It is intrinsically an NP-hard combinatorial optimization problem. Characterizing the conditions guaranteeing the solvability of an evasion attack task thus becomes the key to understand the adversarial threat. Our study is inspired by the weak submodularity theory. We characterize the attackability of a targeted classifier on discrete data in evasion attack by bridging the attackability measurement and the regularity of the targeted classifier. Based on our attackability analysis, we propose a computationally efficient orthogonal matching pursuit-guided attack method for evasion attack on discrete data. It provides provably computational efficiency and attack performances. Substantial experimental results on real-world datasets validate the proposed attackability conditions and the effectiveness of the proposed attack method.

Switched reluctance motor (SRM) has attracted attention of the motor industry due to its simple structure, high reliability and low cost. However, the inherent shortcoming of SRM, principally the torque ripple, limited its development. In this paper, the direct torque control (DTC) method for four-phase SRM will be researched. The relationship between space flux vector and voltage vector will be analyzed, and the switch on-off state principle will be established. The DTC control strategy is simulated by using Simulink, compared with the widely used traditional strategy -current chopper control (CCC). The simulation shows that DTC for four-phase (8/6) SRM can reduce the torque ripple with 73% compared to the traditional strategy.

Tremendous efforts have been dedicated to improving the effectiveness of multi-label learning with incomplete label assignments. Most of the current techniques assume that the input features of data instances are complete. Nevertheless, the co-occurrence of highly incomplete features and weak label assignments is a challenging and widely perceived issue in real-world multi-label learning applications due to a number of practical reasons including incomplete data collection, moderate labels from annotators, etc. Existing multi-label learning algorithms are not directly applicable when the observed features are highly incomplete. In this work, we attack this problem by proposing a weakly supervised multi-label learning approach, based on the idea of collaborative embedding. This approach provides a flexible framework to conduct efficient multi-label classification at both transductive and inductive mode by coupling the process of reconstructing missing features and weak label assignments in a joint optimisation framework. It is designed to collaboratively recover feature and label information, and extract the predictive association between the feature profile and the multi-label tag of the same data instance. Substantial experiments on public benchmark datasets and real security event data validate that our proposed method can provide distinctively more accurate transductive and inductive classification than other state-of-the-art algorithms.

Existing research has revealed that auditory attention can be tracked from ongoing electroencephalography (EEG) signals. The aim of this novel study was to investigate the identification of peoples’ attention to a specific auditory object from single-trial EEG signals via entropy measures and machine learning. Approximate entropy (ApEn), sample entropy (SampEn), composite multiscale entropy (CmpMSE) and fuzzy entropy (FuzzyEn) were used to extract the informative features of EEG signals under three kinds of auditory object-specific attention (Rest, Auditory Object1 Attention (AOA1) and Auditory Object2 Attention (AOA2)). The linear discriminant analysis and support vector machine (SVM), were used to construct two auditory attention classifiers. The statistical results of entropy measures indicated that there were significant differences in the values of ApEn, SampEn, CmpMSE and FuzzyEn between Rest, AOA1 and AOA2. For the SVM-based auditory attention classifier, the auditory object-specific attention of Rest, AOA1 and AOA2 could be identified from EEG signals using ApEn, SampEn, CmpMSE and FuzzyEn as features and the identification rates were significantly different from chance level. The optimal identification was achieved by the SVM-based auditory attention classifier using CmpMSE with the scale factor τ = 10. This study demonstrated a novel solution to identify the auditory object-specific attention from single-trial EEG signals without the need to access the auditory stimulus.

Purpose The development of e-grocery allows people to purchase food online and benefit from home delivery service. Nevertheless, a high rate of failed deliveries due to the customer’s absence causes significant loss of logistics efficiency, especially for perishable food. The purpose of this paper is to propose an innovative approach to use customer-related data to optimize e-grocery home delivery. The approach estimates the absence probability of a customer by mining electricity consumption data, in order to improve the success rate of delivery and optimize transportation. Design/methodology/approach The methodological approach consists of two stages: a data mining stage that estimates absence probabilities, and an optimization stage to optimize transportation. Findings Computational experiments reveal that the proposed approach could reduce the total travel distance by 3-20 percent, and theoretically increase the success rate of first-round delivery approximately by18-26 percent. Research limitations/implications The proposed approach combines two attractive research streams on data mining and transportation planning to provide a solution for e-commerce logistics. Practical implications This study gives an insight to e-grocery retailers and carriers on how to use customer-related data to improve home delivery effectiveness and efficiency. Social implications The proposed approach can be used to reduce environmental footprint generated by freight distribution in a city, and to improve customers’ experience on online shopping. Originality/value Being an experimental study, this work demonstrates the effectiveness of data-driven innovative solutions to e-grocery home delivery problem. The paper also provides a methodological approach to this line of research.

Tunnel FETs was selected as the carrier of digital standard cell design since its excellent characteristics in low power consumption. This experiment contains the principle and characteristic of the Tunnel FETs, and specific standard cell circuit design based on the given model. In this design, we completed several combinational logic cells and sequential logic cells, and did the simulation. From the result of the simulation, we find that TFET devices' speed is slower than MOS device, but the power consumption can reduce to less than 10% of the same size MOS device. Also, by comparing with the MOS devices, we made the corresponding layout design and DRC rule changes, and as one of the results, the area of TFET device is at least 30% larger the MOS device.

In this paper, we analyze a public dataset of electricity consumption collected over 3,800 households for one year and half. We show that some socio-economic factors are critical indicators to forecast households' daily peak (and total) load. By using a random forests model, we show that the daily load can be predicted accurately at a fine temporal granularity. Differently from many state-of-the-art techniques based on support vector machines, our model allows to derive a set of heuristic rules that are highly interpretable and easy to fuse with human experts domain knowledge. Lastly, we quantify the different importance of each socio-economic feature in the prediction task.

Statistical traffic data analysis is a hot topic in traffic management and control. In this field, current research progresses focus on analyzing traffic flows of individual links or local regions in a transportation network. Less attention are paid to the global view of traffic states over the entire network, which is important for modeling large-scale traffic scenes. Our aim is precisely to propose a new methodology for extracting spatio-temporal traffic patterns, ultimately for modeling large-scale traffic dynamics, and long-term traffic forecasting. We attack this issue by utilizing Locality-Preserving Non-negative Matrix Factorization (LPNMF) to derive low-dimensional representation of network-level traffic states. Clustering is performed on the compact LPNMF projections to unveil typical spatial patterns and temporal dynamics of network-level traffic states. We have tested the proposed method on simulated traffic data generated for a large-scale road network, and reported experimental results validate the ability of our approach for extracting meaningful large-scale space-time traffic patterns. Furthermore, the derived clustering results provide an intuitive understanding of spatial-temporal characteristics of traffic flows in the large-scale network, and a basis for potential long-term forecasting., Comment: IET Intelligent Transport Systems (2013)

Recent literatures have revealed that statistics of local texture measures can provide accurate descriptions of palmprint appearances. In this framework, one palmprint image is divided into local blocks with multiple spatial resolutions. The statistical texture descriptions of each block are then concatenated to form a multi-scale image representation. However, resultant high-dimensional statistical features lead to increasing of computational cost. In this paper, we tackle this problem by performing a coarse-to-fine cascade scheme, which makes use of information redundancy of statistical texture descriptions between different spatial scales. In contrast with non-cascade strategies, the proposed method reduces most of computational burden and achieves accurate classification simultaneously.

State-of-the-art palmprint recognition algorithms achieve high accuracy based on component based texture analysis. However, they are still sensitive to local variations of appearances introduced by deformation of skin surfaces or local contrast variations. To tackle this problem, this paper presents a novel palmprint representation named Spatial Bags of Local Layered Descriptors (SBLLD). This technique works by partitioning the whole palmprint image into sub-regions and describing distributions of layered palmprint descriptors inside each sub-region. Through the procedure of partitioning and disordering, local statistical palmprint descriptions and spatial information of palmprint patterns are integrated to achieve accurate image description. Furthermore, to remove irrelevant and attributes from the proposed feature representation, we apply a simple but efficient ranking based feature selection procedure to construct compact and descriptive statistical palmprint representation, which improves classification ability of the proposed method in a further step. Our idea is verified through verification test on large-scale PolyU Palmprint Database Version 2.0. Extensive experimental results testify efficiency of our proposed palmprint representation.

Automatic personal identification based on palmprints has been considered as a promising technology in biometrics family during recent years. In pursuit of accurate palmprint recognition approaches, it is a key issue to design proper image representation to describe skin textures in palm regions. According to previous achievements, directional texture measurement provides a powerful tool for depicting palmprint appearances. Most of successful approaches can be ranged into this framework. Following this idea, we propose a novel palmprint representation in this paper, which describes palmprint images by constructing rank correlation statistics of appearance patterns within local image areas. Promising experimental results on two large scale palmprint databases demonstrate that the proposed method achieves even better performances than the state-of-the-art approaches.

In this paper we present a preliminary study of palmprint image synthesis and propose a framework for synthesizing palmprint texture. We first extract principal lines of real palm- prints using edge detection and synthesize wrinkles and ridges of palm using patch-based sampling. Then we incorporate principal lines, wrinkles and ridges to obtain the final synthetic image. After that multiple images are derived from each artificial palm to simulate the intra-class images. Our approach can generate large palmprint databases which preserve inter-class and intra-class variations. Experimental results demonstrate that the synthetic images bear a close resemblance to real palmprints in terms of appearance as well as statistical properties, showing a promising usage in algorithms evaluation and comparison.

Palmprint recognition, as a new branch of biometric technology, has attracted much attention in recent years. Various palmprint representations have been proposed for recognition. Gabor feature has been recognized as one of the most effective representations for palmprint recognition, where Gabor phase and orientation feature representations are extensively studied. In this paper, we explore a novel Gabor magnitude feature-based method for palmprint recognition. The novelties are as follows: First, we propose an illumination normalization method for palmprint images to decrease the influence of illumination variations caused by different sensors and lighting conditions. Second, we propose to use Gabor magnitude features for palmprint representation. Third, we utilize AdaBoost learning to extract most effective features and apply Local Discriminant Analysis (LDA) to reduce the dimension further for palmprint recognition. Experimental results on three large palmprint databases demonstrate the effectiveness of proposed method. Compared with state-of-the-art Gabor-based methods, our method achieves higher accuracy.

This paper presents a novel real-time palmprint recognition system for cooperative user applications. This system is the first one achieving noncontact capturing and recognizing palmprint images under unconstrained scenes. Its novelties can be described in two aspects. The first is a novel design of image capturing device. The hardware can reduce influences of background objects and segment out hand regions efficiently. The second is a process of automatic hand detection and fast palmprint alignment, which aims to obtain normalized palmprint images for subsequent feature extraction. The palmprint recognition algorithm used in the system is based on accurate ordinal palmprint representation. By integrating power of the novel imaging device, the palmprint preprocessing approach and the palmprint recognition engine, the proposed system provides a friendly user interface and achieves a good performance under unconstrained scenes simultaneously.

There are increasing requirements for mobile personal identification, e.g. to protect identity theft in wireless applications. Based on built-in cameras of mobile devices, palmprint images may be captured and analyzed for individual authentication. However, current available palmprint recognition methods are not suitable for real-time implementations due to the limited computational resources of handheld devices, such as PDA or mobile phones. To solve this problem, in this paper, we propose a sum-difference ordinal filter to extract discriminative features of palmprint using only +/- operations on image intensities. It takes less than 200 ms for our algorithm to verify the identity of a palmprint image on a HP iPAQ PDA, about 1/10 of state-of-the-art methods ' complexity, while this approach also achieves high accuracy on the PolyU palmprint database. Thanks to the efficient palmprint feature encoding scheme, we develop a real-time embedded palmprint recognition system, working on the HP PDA.

Palmprint recognition, as a reliable personal identity check method, has been receiving increasing attention during recent years. According to previous work, local texture analysis supplies the most promising framework for palmprint image representation. In this paper, we propose a novel palmprint recognition method by combining statistical texture descriptions of local image regions and their spatial relations. In our method, for each image block, a spatial enhanced histogram of gradient directions is used to represent discriminative texture features. Furthermore, we measure similarity between two palmprint images using a simple graph matching scheme, making use of structural information. Experimental results on two large palmprint databases demonstrate the effectiveness of the proposed approach.

In this paper, we present a face and palmprint multimodal biometric identification method and system to improve the identification performance. Effective classifiers based on ordinal features are constructed for faces and palmprints, respectively. Then, the matching scores from the two classifiers are combined using several fusion strategies. Experimental results on a middle-scale data set have demonstrated the effectiveness of the proposed system.

Possible ionospheric disturbances relating to the May 12, 2008, Ms8.0 Wenchuan earthquake were identified by Global Positioning System (GPS)-derived total electron content (TEC), ionosonde observations, the global ionospheric map (GIM), and electron density profiles detected by the Constellation Observation System for Meteorology Ionosphere and Climate (COSMIC). We applied a statistical test to detect anomalous TEC signals and found that a unique enhancement in TEC, recorded at 16 GPS stations, appeared on May 9, 2008. The critical frequency at F2 peak (f0F2), observed by the Chinese ionosondes, and maximal plasma frequency, derived from COSMIC data, revealed a characteristic similar to GPS TEC variations. The GIM showed that the anomalous variations of May 9 were located southeast of the epicenter. Using GPS data from 13 stations near the epicenter, we analyzed the TEC variations of satellite orbit traces during 04:00–11:00 UT. We found that TEC decreased to the east and increased to the southeast of the epicenter during this period. Results showed that the abnormal disturbance on May 9 was probably an ionospheric precursor of the Wenchuan earthquake of May 12, 2008.

Palmprint recognition is an active member of biometrics in recent years. State-of-the-art algorithms of palmprint recognition describe appearances of palmprints efficiently through local texture analysis. Following this framework, we propose a novel approach of palmprint recognition in this paper, which represents palmprint images based on statistics and spatial arrangement of appearance descriptors within local image areas. In this method, we firstly design a robust descriptor to encode properties of palmprint appearances of local regions. The whole image is divided into non-overlapped blocks at increasingly fine resolutions successively, so as to describe the spatial layout in hierarchical scales. For a specific spatial resolution, local distributions of the proposed descriptors in the blocks are concatenated to represent structures of palmprint structures. Finally, distribution information of different resolutions is combined to provide complementary descriptive power. Promising experimental results demonstrate that the proposed method achieves even better performances than the state-of-the-art approaches.