Handwriting difficulties (HWDs) in children have adverse effects on their confidence and academic progress. Detecting HWDs is the first crucial step toward clinical or teaching intervention for children with HWDs. To date, how to automatically detect HWDs is still a challenge, although digitizing tablets have provided an opportunity to automatically collect handwriting process information. Especially, to our best knowledge, there is no exploration into the potential of combining machine learning algorithms and the handwriting process information to automatically detect Chinese HWDs in children. To bridge the gap, we first conducted an experiment to collect sample data and then compared the performance of five commonly used classification algorithms (Decision tree, Support Vector Machine (SVM), Artificial Neural Network, Naïve Bayesian and k-Nearest Neighbor) in detecting HWDs. The results showed that: (1) only a small proportion (13%) of children had Chinese HWDs and each classification model on the imbalanced dataset (39 children at risk of HWDs versus 261 typical children) produced the results that were better than random guesses, indicating the possibility of using classification algorithms to detect Chinese HWDs; (2) the SVM model had the best performance in detecting Chinese HWDs among the five classification models; and (3) the performance of the SVM model, especially its sensitivity, could be significantly improved by employing the Synthetic Minority Oversampling Technique to handle the class-imbalanced data. This study gains new insights into which handwriting features are predictive of Chinese HWDs in children and proposes a method that can help the clinical and educational professionals to automatically detect children at risk of Chinese HWDs.

This paper presents a cascode-pair distributed amplifier design approach using 0.25 µm GaAs-based PHEMT MMIC technology, which covers 2-32 GHz. Electromagnetic simulation results show that this amplifier achieves 18 dB gain from 2 to 32 GHz and 0.5 dB gain flatness over the band. The reflected coefficients at the input and output ports are below -10 dB up to 27 GHz. The output power at 1 dB compression is greater than 24 dBm at 20 GHz. An appropriate feedback resistance can be utilized to improve P1 dB for about 6 dBm. The DOE (design of experiment) approach is carried out by a simulation tool for better performance and tolerance of the devices is also analyzed. The circuit configuration is capable of operating over ultra-broad band amplification.

This work explores generative models of handwritten digit images using natural elastic nets. The analysis aims to extract global features as well as distributed local features of handwritten digits. These features are expected to form a basis that is significant for discriminant analysis of handwritten digits and related analysis of character images or natural images.

This paper addresses the scheduling problem of a class of automated manufacturing systems with multiple resource requests. In the automated manufacturing system model, a set of jobs is to be processed and each job requires a sequence of operations. Each operation may need more than one resource type and multiple identical units with the same resource type. Upon the completion of an operation, resources needed in the next operation of the same job cannot be released and the remaining resources cannot be released until the start of the next operation. The scheduling problem is formulated by Timed Petri nets model under which the scheduling goal consists in sequencing the transition firing sequence in order to avoid the deadlock situation and to minimize the makespan. In the proposed genetic algorithm with deadlock-free constraint, Petri net transition sequence is coded and a deadlock detection method based on D-siphon technology is proposed to reschedule the sequence of transitions. The enabled transitions should be fired as early as possible and thus the quality of solutions can be improved. In the fitness computation procedure, a penalty item for the infeasible solution is involved to prevent the search process from converging to the infeasible solution. The method proposed in this paper can get a feasible scheduling strategy as well as enable the system to achieve good performance. Numerical results presented in the paper show the efficiency of the proposed algorithm.

By close analogy of annealing for solids, we devise a new algorithm, called APS, for the time evolution of both the state and the synapses of the Hopfield's neural network. Through constrainedly random perturbation of the synapses of the network, the evolution of the state will ignore the tremendous number of small minima and reach a good minimum. The synapses resemble the microstructure of a network. This new algorithm anneals the microstructure of the network through a thermal controlled process. And the algorithm allows us to obtain a good minimum of the Hopfield's model efficiently. We show the potential of this approach for optimization problems by applying it to the will-known traveling salesman problem. The performance of this new algorithm has been supported by many computer simulations.

The blind multichannel identification is useful in many applications. Although many approaches have been proposed to address this challenging problem, the adaptive filtering-based methods are attractive due to their computational efficiency and good convergence property. The multichannel normalized least mean-square (MCNLMS) algorithm is easy to implement, but it converges very slowly for a correlated input. The multichannel affine projection algorithm (MCAPA) is thus proposed to speed up the convergence. However, the convergence of the MCNLMS and MCAPA is still unsatisfactory in practice. In this paper, we propose a time-domain Kalman filtering approach to the blind multichannel identification problem. Specifically, the proposed adaptive Kalman filter is based on the cross relation method and also uses more past input vectors to explore the decorrelation property. Simulation results indicate that the proposed method outperforms the MCNLMS and MCAPA significantly in terms of the initial convergence and tracking capability.

The Synchronous Optical Network (SONET) technology offers technical possibilities to build high speed transport networks and enables the operator to react quickly to the customers' capacity requirements. Furthermore the advanced SONET equipment, with standardized control and operation features, provides opportunities for new services, such as broadband services, and cost-effective ways to enhance existing services, such as network survivability improvement. But SONET technology can also create a certain degree of complexity in building cost-efficient network, especially in case of SONET Self-Healing Ring (SHR). It is a challenge for network planner to find an effective way to select the most economical SONET ring, or combination of rings, for given demands between a set of nodes that are supposed to be connected in a certain type of ring configuration. Three types of ring are standard today: path unidirectional, 2-fiber line protection bidirectional and 4-fiber line protection bidirectional. For a given network, the choosing of ring architecture based on economical considerations involves two major factors. They are capacity requirement and equipment cost. Capacity requirements of different SONET ring architectures depend upon different conditions. While facility line rate, which is a key factor in deciding what kind self-healing ring can be deployed economically on these requirements. Routing decisions play a key role in deciding the ring capacities required, especially for bidirectional rings. In the paper, we will make the economic study on how SONET SHR architecture works out with a variety of demand patterns, to find criteria for ring selection. We first present two efficient demand loading algorithms for BSHR capacity calculation, and then analyze the results from their application on a variety of demand patterns. The economic study for SONET SHR networks based on different architectures are also discussed.

Montgomery algorithm has demonstrated its effectiveness in applications like cryptosystems. Most of the existing works on finding the Montgomery inverse of an element over the Galois field are based on the software implementation, which is then extended to derive the scalable hardware architecture. In this work, we consider a fundamental change at the algorithmic level and eliminate the potential problems in hardware implementation which makes the resulting modified Montgomery inverse algorithm over GF(2m) very suitable for hardware realization. Due to its structural simplicity, the modified algorithm can be easily mapped onto a high-speed and possibly low-complexity circuit. Experimental results show that our development can achieve both the area and speed advantages over the previous work when the inversion operation over GF(2m) is under consideration and the improvement becomes more significant when we increase the value of m as in the applications of cryptosystems. The salient property of our development sustains the high-speed operation as well as low hardware complexity over a wide range of m for commercial cryptographic applications and makes it suitable for both the scalable architecture and direct hardware implementation.

Researchers have already attributed a certain amount of variability and “drift” in an individual's handwriting pattern to mental workload, but this phenomenon has not been explored adequately. Especially, there still lacks an automated method for accurately predicting mental workload using handwriting features. To solve the problem, we first conducted an experiment to collect handwriting data under different mental workload conditions. Then, a predictive model (called SVM-GA) on two-level handwriting features (i.e., sentence- and stroke-level) was created by combining support vector machines and genetic algorithms. The results show that (1) the SVM-GA model can differentiate three mental workload conditions with accuracy of 87.36% and 82.34% for the child and adult data sets, respectively and (2) children demonstrate different changes in handwriting features from adults when experiencing mental workload.

In this paper, we investigate the system performance of decode and forward based bi-directional relaying based on symbol-wise XOR operation. This technique gives more freedom in selecting the modulation and coding scheme at relay stations, and significantly relaxes the transmission bottleneck. However, the performance degradation occurs when the modulation orders of both links differ from each other. To mitigate such an impact, we exploit a repetition coding scheme in conjunction with a redundant modulation code scheme by overlapping MCS levels. To this end, a system level simulation proves that the proposed scheme achieves about 43% capacity gain over bit-wise XOR based bi-directional relaying and gives additional 10% gain over symbol-wise XOR based bi-directional relaying.

In this paper, we propose a hybrid fine-tuned multi-objective memetic algorithm hybridizing different solution fitness evaluation methods for global exploitation and exploration. To search across all regions in objective space, the algorithm uses a widely diversified set of weights at each generation, and employs a simulated annealing to optimize each utility function. For broader exploration, a grid-based technique is adopted to discover the missing nondominated regions on existing tradeoff surface, and a Pareto-based local perturbation is performed to reproduce incrementing solutions trying to fill up the discontinuous areas. Additional advanced feature is that the procedure is made dynamic and adaptive to the online optimization conditions based on a function of improvement ratio to obtain better stability and convergence of the algorithm. Effectiveness of our approach is shown by applying it to multi-objective 0/1 knapsack problem (MOKP).

The proper allocation of network resources from a common physical substrate to a set of virtual networks (VNs) is one of the key technical challenges of network virtualization. While a variety of state-of-the-art algorithms have been proposed in an attempt to address this issue from different facets, the challenge still remains in the context of large-scale networks as the existing solutions mainly perform in a centralized manner which requires maintaining the overall and up-to-date information of the underlying substrate network. This implies the restricted scalability and computational efficiency when the network scale becomes large. This paper tackles the virtual network mapping problem and proposes a novel hierarchical algorithm in conjunction with a substrate network decomposition approach. By appropriately transforming the underlying substrate network into a collection of sub-networks, the hierarchical virtual network mapping algorithm can be carried out through a global virtual network mapping algorithm (GVNMA) and a local virtual network mapping algorithm (LVNMA) operated in the network central server and within individual sub-networks respectively with their cooperation and coordination as necessary. The proposed algorithm is assessed against the centralized approaches through a set of numerical simulation experiments for a range of network scenarios. The results show that the proposed hierarchical approach can be about 5-20 times faster for VN mapping tasks than conventional centralized approaches with acceptable communication overhead between GVNCA and LVNCA for all examined networks, whilst performs almost as well as the centralized solutions.

In this paper, we present the division algorithm (DA) for the computation of b=c/a over GF(2m) in two aspects. First, we derive a new formulation for the discrete-time Wiener-Hopf equation (DTWHE) Ab = c in GF(2) over any basis. Symmetry of the matrix A is observed on some special bases and a three-step procedure is developed to solve the symmetric DTWHE. Secondly, we extend a variant of Stein's binary algorithm and propose a novel iterative division algorithm EB*. Owing to its structural simplicity, this algorithm can be mapped onto a systolic array with high speed and low area complexity.

This letter proposes a novel nonlinear distortion for the unique identification of receiving room impulses in stereo acoustic echo cancellation when applying the frequency-domain adaptive filtering technique. This nonlinear distortion is effective in reducing the coherence between the two incoming audio channels and its influence on audio quality is inaudible.

Turbo coding is a powerful coding technique that can provide highly reliable data transmission at extremely low signal-to-noise ratios. Owing to the computational complexity of the employed decoding algorithm, the realization of turbo decoders usually takes a large amount of memory space and potentially long decoding delay. Therefore, an efficient memory management strategy becomes one of the key factors toward successfully implementing turbo decoders. This paper focuses on the development of general structures for efficient memory management of turbo decoders employing the sliding-window (Log-) MAP algorithm. Three different structures and the associated mathematic representations are derived to evaluate the required memory size, average decoding rate, and latency based on the speed and the number of the adopted processors. Comparative results show the dependency of the resulting performance based on a set of parameters; thus provide useful and general information on practical implementations of turbo decoders.

We present a systematic and efficient way of managing the path metric memory and simplifying its connection network to the add_compare_select unit (ACSU) for Viterbi decoder (VD) design. Using the derived equations for memory partition and add-compare-select (ACS) arrangement together with the extended in-place scheduling scheme proposed in this work, we can increase the memory bandwidth for conflict-free path metric accesses with hardwired interconnection between the path metric memory and ACSU. Compared with the existing work, the developed architecture possesses the following advantages: (1) Each partitioned memory bank can be treated as a local memory of a specific processing element, inside the ACSU, with hardwired interconnection, so that the interconnect complexity is reduced significantly. (2) The partitioned memory banks can be merged into only two pseudo-banks regardless of the number of adopted ACS processing elements. This not only greatly simplifies the design of address generation unit, but also makes smaller the physical size of required memory. (3) The implementation can be accomplished in a systematic way with regular and simple controlling circuitry. Experimental results demonstrate the effectiveness of the developed architecture and the benefit will be more apparent for convolutional codes with large memory order.

When wireless multi-media information which includes speech, image, data and so on are transmitted, the defference in information rate, required quality as well as traffic performance should be taken into account. A wireless spread spectrum system can achieve a flexible balance of these differences because of the inherent asynchronous capability of CDMA. In this paper, we propose a wireless multi-media CDMA system based on a processing gain control in a dynamic traffic channel. According to the priority of each medium and channel measurement information i.e. traffic, the optimal processing gain can be controlled by using Nonlinear Programming. Numerical results demonstrate that the proposed method possesses higher flexible capacity than TDMA in a dynamic multi-medea traffic channel.

Data-driven untying of a recursive autoencoder (RAE) is proposed for utterance intent classification for spoken dialogue systems. Although an RAE expresses a nonlinear operation on two neighboring child nodes in a parse tree in the application of spoken language understanding (SLU) of spoken dialogue systems, the nonlinear operation is considered to be intrinsically different depending on the types of child nodes. To reduce the gap between the single nonlinear operation of an RAE and intrinsically different operations depending on the node types, a data-driven untying of autoencoders using part-of-speech (PoS) tags at leaf nodes is proposed. When using the proposed method, the experimental results on two corpora: ATIS English data set and Japanese data set of a smartphone-based spoken dialogue system showed improved accuracies compared to when using the tied RAE, as well as a reasonable difference in untying between two languages.