Separate ANN Research Articles

Abstract PO2-07-03: Retrospective Validation Study of an Artificial Neural Network-Based Preoperative Decision-Support Tool for Noninvasive Lymph Node Staging (NILS) in Women with Primary Breast Cancer (ISRCTN14341750)

Abstract Background Surgical sentinel lymph node biopsy (SLNB) is routinely used to reliably stage axillary lymph nodes in early breast cancer (BC). However, SLNB may be associated with postoperative arm morbidities. For most patients with BC undergoing SLNB, the findings are benign, and the procedure is currently questioned. A decision-support tool for the prediction of benign sentinel lymph nodes based on preoperatively available data has been developed using artificial neural network modelling [1,2]. Methods This was a retrospective geographical and temporal validation study of the noninvasive lymph node staging (NILS) model, based on preoperatively available data from 586 women consecutively diagnosed with primary BC at two sites. Ten preoperative clinicopathological characteristics from each patient were entered into the web-based calculator (Table 1), and the probability of benign lymph nodes was predicted. Vascular invasion, the tenth feature of the NILS model, was difficult to determine preoperatively. Therefore, a separate ANN model was developed to impute this feature, using the other nine features of the NILS model as predictors. A user-friendly web implementation of the NILS model was tested in this study. The performance of the NILS model was assessed in terms of discrimination with the area under the receiver operating characteristic curve (AUC). The primary endpoint was axillary nodal status (discrimination, benign [N0] vs. metastatic axillary nodal status [N+]) determined by the NILS model compared to nodal status by definitive pathology. Results The mean age of the women in the cohort was 65 years, and most of them (93%) had luminal cancers (Table 2). Approximately three-fourths of the patients had no metastases in SLNB (N0 74%). The AUC for the predicted probabilities for the whole cohort was 0.6741 (95% confidence interval: 0.6255–0.7227). More than one in four patients (n=151, 26%) were identified as candidates for SLNB omission when applying the predefined cut-off for lymph node negativity from the development cohort (Table 3). Conclusion The performance of the NILS model was satisfactory. In approximately every fourth patient, SLNB could potentially be omitted. Considering the shift from postoperatively to preoperatively available predictors in this validation study, we have demonstrated the robustness of the NILS model. The clinical usability of the web interface will be evaluated before its clinical implementation. Trial registration Registered in the ISRCTN registry with study ID ISRCTN14341750.

Power Management Systems for Harmonic Elimination Using Hybrid Artificial Neural Networks Approaches

This study proposes two neural network-based approaches for computing the degrees required to generate pulse-width modulation (PWM) signals. The conventional method of using a lookup table to determine the orientations is replaced by these ANN models, which demonstrate superior performance across a range of modification indices. The first ANN is trained to estimate the phase angle based on input from the Empire Bird Optimizer, eliminating the need for a lookup table. A separate ANN is then trained using these configurations to generate the PWM signals. Experimental data on voltage level, inverter output current, and power flow are collected using a scope and power quality tester. The recommended hybrid ANN-based selective harmonic elimination PWM effectively removes low-order vibrations. The research is implemented in the MATLAB/Simulink platform, and the results indicate that the proposed system is efficient, accurately determining firing angles with minimal repetitions, and effectively addressing local minima values. The practical implementation of an eleven-level modular multilevel converter serves as the basis for this proposal, exemplified by an eleven-level H-bridge inverter.

User profiling for TV program recommendation based on hybrid television standards using controlled clustering with genetic algorithms and artificial neural networks

In this paper, an earlier method proposed by the authors to make smart recommendations utilizing artificial intelligence and the latest technologies developed for the television area is expanded further using controlled clustering with genetic algorithms CCGA . For this purpose, genetic algorithms GAs , artificial neural networks ANNs , and hybrid broadcast broadband television HbbTV are combined to get the users' television viewing habits and to create profiles. Then television programs are recommended to the users based on that profiling. The data gathered by the developed HbbTV application for previous studies are reused in this study. These data are employed to cluster users. The number of clusters is found by CCGA, a method proposed in this paper. For each cluster formed by CCGA, a separate ANN is designed to learn the viewing habits of the users of the corresponding cluster. The weight matrices are initialized also by GA. The recommendations produced using the proposed model are then presented by the same HbbTV application developed by the authors. Clustering with GAs gives better results when compared to the well-known K-means clustering algorithm.

Short-term prediction of border crossing time and traffic volume for commercial trucks: A case study for the Ambassador Bridge

Short-term forecasting of traffic characteristics, such as traffic flow, speed, travel time, and queue length, has gained considerable attention from transportation researchers and practitioners over past three decades. While past studies primarily focused on traffic characteristics on freeways or urban arterials this study places particular emphasis on modeling the crossing time over one of the busiest US–Canada bridges, the Ambassador Bridge. Using a month-long volume data from Remote Traffic Microwave Sensors and a yearlong Global Positioning System data for crossing time two sets of ANN models are designed, trained, and validated to perform short-term predictions of (1) the volume of trucks crossing the Ambassador Bridge and (2) the time it takes for the trucks to cross the bridge from one side to the other. The prediction of crossing time is contingent on truck volume on the bridge and therefore separate ANN models were trained to predict the volume. A multilayer feedforward neural network with backpropagation approach was used to train the ANN models. Predicted crossing times from the ANNs have a high correlation with the observed values. Evaluation indicators further confirmed the high forecasting capability of the trained ANN models. The ANN models from this study could be used for short-term forecasting of crossing time that would support operations of ITS technologies.

Performance Investigation of Unified Power Quality Conditioner Using Artificial Intelligent Controller

A neural network based synchronous reference frame theory (SRF) control strategy is proposed in this paper to compensate power quality issues in three phase three wire (3P3W) distribution system through Unified Power Quality conditioner (UPQC) for various balanced/Unbalanced load and balanced/unbalanced/distorted source conditions. The ANN controller is designed to replace the Low pass filters and Proportional-integral controllers of the conventional control strategy for UPQC. Separate ANN controller is implemented to maintain voltage across the capacitor under all varying conditions of source and load. The Proposed control strategy mitigates harmonic/reactive currents, ensures balanced and sinusoidal source current from the supply mains that are nearly in phase with the supply voltage in spite of unbalance in the three phase load currents and source voltage conditions, in 3P3W distribution systems. The performance of the proposed ANN controller for UPQC is validated and investigated through simulations using MATLAB software. The simulation results prove the efficacy of the proposed neural network based control strategy under varying source and load conditions.

A new hybrid day-ahead peak load forecasting method for Iran’s National Grid

This paper presents a new hybrid forecasting engine for day-ahead peak load prediction in Iran National Grid (ING). In this forecasting engine the seasonal data bases of the historical peak load demand on the similar days with their weather information given for three cities (Tehran, Tabriz and Ahvaz) have been used. Wavelet decomposition is used to capture low and high frequency components of each data base from original noisy signals. A separate ANN with an iterative training mechanism which is optimized by genetic algorithm is employed for each low and high frequency data base. A day-ahead peak demand is determined with the reconstruction of low and high frequency output components of each ANN. Simulation results show the effectiveness and the superiority of the proposed strategy when compared with other methods for daily peak load demand forecasting in ING and EUNITE test cases.

Short-Term Electricity Price Forecasting Using a Combination of Neural Networks and Fuzzy Inference

This paper presents an artificial neural network, ANN, based approach for estimating short-term wholesale electricity prices using past price and demand data. The objective is to utilize the piecewise continuous na-ture of electricity prices on the time domain by clustering the input data into time ranges where the variation trends are maintained. Due to the imprecise nature of cluster boundaries a fuzzy inference technique is em-ployed to handle data that lies at the intersections. As a necessary step in forecasting prices the anticipated electricity demand at the target time is estimated first using a separate ANN. The Australian New-South Wales electricity market data was used to test the system. The developed system shows considerable im-provement in performance compared with approaches that regard price data as a single continuous time se-ries, achieving MAPE of less than 2% for hours with steady prices and 8% for the clusters covering time pe-riods with price spikes.

Recent advances in the multi-stream HMM/ANN hybrid approach to noise robust ASR

In this article we review several successful extensions to the standard hidden-Markov-model/artificial neural network (HMM/ANN) hybrid, which have recently made important contributions to the field of noise robust automatic speech recognition. The first extension to the standard hybrid was the “multi-band hybrid”, in which a separate ANN is trained on each frequency sub-band, followed by some form of weighted combination of ANN state posterior probability outputs prior to decoding. However, due to the inaccurate assumption of sub-band independence, this system usually gives degraded performance, except in the case of narrow-band noise. All of the systems which we review overcome this independence assumption and give improved performance in noise, while also improving or not significantly degrading performance with clean speech. The “all-combinations multi-band” hybrid trains a separate ANN for each sub-band combination. This, however, typically requires a large number of ANNs. The “all-combinations multi-stream” hybrid trains an ANN expert for every combination of just a small number of complementary data streams. Multiple ANN posteriors combination using maximum a-posteriori (MAP) weighting gives rise to the further successful strategy of hypothesis level combination by MAP selection. An alternative strategy for exploiting the classification capacity of ANNs is the “tandem hybrid” approach in which one or more ANN classifiers are trained with multi-condition data to generate discriminative and noise robust features for input to a standard ASR system. The “multi-stream tandem hybrid” trains an ANN for a number of complementary feature streams, permitting multi-stream data fusion. The “narrow-band tandem hybrid” trains an ANN for a number of particularly narrow frequency sub-bands. This gives improved robustness to noises not seen during training. Of the systems presented, all of the multi-stream systems provide generic models for multi-modal data fusion. Test results for each system are presented and discussed.

Qualitative and quantitative analysis of volatile organic compounds using transient and steady-state responses of a thick-film tin oxide gas sensor array

Quantitative analysis of gases, by means of semiconductor sensor arrays and pattern-recognition techniques such as artificial neural networks, has been the goal of a great deal of work over the last few years. However, the lack of selectivity, repeatability and drifts of the sensors, have limited the applications of these systems to qualitative or semi-quantitative gas analysis. While the steady-state response of the sensors is usually the signal to be processed in such analysis systems, our method consists of processing both, transient and steady-state information. The sensor transient behaviour is characterised through the measure of its conductance rise time ( Tr), when there is a step change in the gas concentration. Tr is characteristic of each gas/sensor pair, concentration-independent and shows higher repeatability than the steady state measurements. An array of four thick-film tin oxide gas sensors and pattern-recognition techniques are used to discriminate and quantify among ethanol, toluene and o-xylene [concentration range: 25, 50 and 100 ppm]. A principal component analysis is carried out to show qualitatively that selectivity improves when the sensor behaviour is dynamically characterised. The steady-state and transient conductance of the array components are processed with artificial neural networks. In a first stage, a feed-forward back-propagation-trained ANN discriminates among the studied compounds. Afterwards, three separate ANN (one for each vapour) are used to quantify the previously identified compound. Processing data from the dynamic characterisation of the sensor array, considerably improves its identification performance, rising the discrimination success rate from a 66% when only steady-state signals are used up to 100%.