Search

Three-dimensional profilometry tends to be less effective at measuring discontinuous surfaces. To overcome this problem, an optimized profilometry based on fringe projection is proposed in this paper. Due to the limitation of the shooting angle, there are projection blind spots on the surface of discontinuous objects. Since the noises and unwrapping errors are always localized at the projection blind spots, an algorithm is designed to determine the blind spots automatically with the light intensity difference information. Besides, in order to improve the measurement accuracy, a processing scheme is introduced to deal with the local height distortion introduced by the dual-frequency grating profilometry. Lots of measurement tests on various surfaces are carried out to assess the optimized profilometry, and experimental results indicate that the modified profilometry system works more robust with high reliability and accuracy in measuring different kinds of surfaces, especially discontinuous ones.

Different clinicopathologic characteristics could contribute to inconsistent prognoses of small breast neoplasms (T1a/T1b). This study was done to conduct a retrospective analysis and establish a clinical prediction model to predict individual survival outcomes of patients with small carcinomas of the breast.Based on the Surveillance, Epidemiology, and End Results (SEER) database, eligible patients with small breast carcinomas were analyzed. Univariate analysis and multivariate analysis were performed to clarify the indicators of overall survival. Pooling risk factors enabled nomograms to be constructed and further predicted 3-year, 5-year, and 10-year survival of patients with small breast cancer. The model was internally validated for discrimination and calibration.A total of 17,543 patients with small breast neoplasms diagnosed between 2013 and 2016 were enrolled. Histologic grade, lymph node stage, estrogen receptor or progesterone receptor status, and molecular subtypes of breast cancer were regarded as the risk factors of prognosis in a Cox proportional hazards model (P .05). A nomogram was constructed to give predictive accuracy toward individual survival rate of patients with small breast neoplasms.This prognostic model provided a robust and effective method to predict the prognosis of patients with small breast cancer.

With the advances and growth of various wireless technologies, it is imperative to implement robust Intrusion Detection Systems (IDS). This paper proposes the implementation of Deep Gated Recurrent Unit (DGRU) Based classifier as well as a wrapper-based feature extraction algorithm for Wireless IDS. We assess the performance of the DRGU IDS using the NSL-KDD benchmark dataset. Furthermore, we compare our framework to several popular algorithms including Artificial Neural Networks, Deep Long–Short Term Memory, Random Forest, Naive Bayes and Feed Forward Deep Neural Networks. The experimental outcomes demonstrate that the DGRU IDS displays a significant increase in performance over existing methods.

The mains signal is a complex fusion of various electrical equipment load signals in a building. In the non-intrusive load monitoring recognition, our main aim is to be able to extract as much load features as possible from the complex aggregate mains signal in a simpler way through a computer vision-based approach as opposed to the powers series signal approach. Power series methods, which are one dimensional in nature, suffer from poor aggregate and load signal feature localization necessitating a larger training dataset spanning very long time periods and normally require signal formatting and pre-processing. We use Gramian angular summation fields to transform the power series into a reduced image dataset that contains a rich set of localized signal features. A computer vision approach allows us to capture as much information as possible, and then propose an image-based mains load recognition system with high performance. In this paper for the entire recognition system, we use convolutional neural networks that very well adapted to vision recognition. The load signal image disaggregation is achieved through the powerful stacked denoising autoencoder noise extraction network. To test the proposed system, some simulations and comparisons are carried out and the results show that our easier to handle method can achieve acceptable performance.

As the world’s population grows and energy demand increases, it is necessary to increase the scale of the electrical system, which is more complicated. Consequently, adopting automatic generation control (AGC) scheme to meet the demand becomes inevitable. In this article, the fusion of flower pollinated algorithm (FPA) and pathfinder algorithm (PFA), named hereafter as $h$ FPAPFA, is proposed to achieve maximum control efficiency by combining the exploitation of FPA with the exploration capacity of PFA. The proposed $h$ FPAPFA is meant to regulate two unequal multi-area interconnected power system with different generating units such as thermal, hydro, wind power and diesel plants. The proposed control scheme aims to achieve this by using the new algorithm to optimize the fractional-order set-point weighted PID (FOSWPID) parameters under time domain-based fitness functions namely, integral time square error (ITSE) and integral time absolute error (ITAE) while simultaneously minimizing the power losses. Employing the same interconnected power systems, a comparative study with some recent approaches in renowned journals is conducted. The performance of the proposed method is observed under diverse load conditions scenarios. Moreover, three nonlinearities including boiler dynamics, the governor dead band (GDB) and generation rate constraints (GRC) are further integrated into the system from a pragmatic context. Finally, sensitivity tests involving various parameter changes and the introduction of random step load perturbations are carried out. From the results, the proposed approach outperformed other approaches under different load condition scenarios, incorporation of nonlinearities and random load perturbation, demonstrating the proposed technique’s efficacy and reliability.

Lung cancer is the second most common form of cancer in both men and women. It is responsible for at least 25% of all cancer-related deaths in the United States alone. Accurate and early diagnosis of this form of cancer can increase the rate of survival. Computed tomography (CT) imaging is one of the most accurate techniques for diagnosing the disease. In order to improve the classification accuracy of pulmonary lesions indicating lung cancer, this paper presents an improved method for training a densely connected convolutional network (DenseNet). The optimized setting ensures that code prediction error and reconstruction error within hidden layers are simultaneously minimized. To achieve this and improve the classification accuracy of the DenseNet, we propose an improved predictive sparse decomposition (PSD) approach for extracting sparse features from the medical images. The sparse decomposition is achieved by using a linear combination of basis functions over the L2 norm. The effect of dropout and hidden layer expansion on the classification accuracy of the DenseNet is also investigated. CT scans of human lung samples are obtained from The Cancer Imaging Archive (TCIA) hosted by the University of Arkansas for Medical Sciences (UAMS). The proposed method outperforms seven other neural network architectures and machine learning algorithms with a classification accuracy of 95%.

Purpose Storage systems are deemed to be unable to provide revenue commensurate with the resources invested in them, thus discouraging their incorporation within power networks. In prosumer microgrids, storage systems can provide revenue from reduced grid consumption, energy arbitraging or when serving as back-up power. This study aims to examine stacking these revenue streams with the aim of making storage systems financially viable for inclusion in prosumer microgrids. Design/methodology/approach With the aim of reducing self-consumption and maximising revenue, the prosumer microgrid incorporating hybrid energy storage systems (HESS) and solar PV power is solved using the CPLEX solver of the Advanced Interactive Multidimensional Modeling Software (AIMMS). The financial analysis of the results is carried out to provide the payback periods of different system configurations of the prosumer microgrid. Findings The findings reveal that the payback period of the three HESS when minimising grid expenses during self-consumption alone and when compared with stacked revenue streams shows an improvement from 4.8–11.2 years to 2.4–6.6 years. With stacked HESS revenues, the supercapacitor-lithium ion battery HESS gave the shortest payback period of 2.31 years when solar PV power is at 75% penetration level. Originality/value Existing literature has considered revenue streams of storage systems at the electrical power transmission and distribution levels, but not for prosumer microgrids in particular. This study has captured these benefits and verified the profitability of stacking revenue from HESS to prosumer microgrids, using a case study.

Adenocarcinoma at the gastroesophageal junction (ACGEJ) has dismal clinical outcomes, and there are currently few specific effective therapies because of limited knowledge on its genomic and transcriptomic alterations. The present study investigates genomic and transcriptomic changes in ACGEJ from Chinese patients and analyzes their drug vulnerabilities and associations with the survival time. Here we show that the major genomic changes of Chinese ACGEJ patients are chromosome instability promoted tumorigenic focal copy-number variations and COSMIC Signature 17-featured single nucleotide variations. We provide a comprehensive profile of genetic changes that are potentially vulnerable to existing therapeutic agents and identify Signature 17-correlated IFN-α response pathway as a prognostic marker that might have practical value for clinical prognosis of ACGEJ. These findings further our understanding on the molecular biology of ACGEJ and may help develop more effective therapeutic strategies., Adenocarcinoma at the gastroesophageal junction has a dismal prognosis and few drug options. Here, the authors present genomic and transcriptomic features and potential therapeutic targets and prognostic biomarkers of Chinese and Caucasian tumours, and reveal the molecular similarities.

Accurate optic cup and optic disc (OC, OD) segmentation is the prerequisite for cup-disc ratio (CDR) calculation. In this paper, a new full convolutional neural network (FCN) with multi-scale residual module is proposed. Firstly, polar coordinate transformation was introduced to balance the CDR with space constraints, and CLAHE was implemented in fundus images for contrast enhancement. Secondly, W-Net-R model was proposed as the main framework, while the standard convolution unit was replaced by the multi-scale residual module. Finally, the multi-label cost function is utilized to guide its functioning. In the experiment, the REFUGE dataset was used for training, validation and testing. We obtained 0.979 and 0.904 for OD and OC segmentations on MIoU, which indicates a relative improvement of 4.04% and 3.55%, comparing with that of U-Net, respectively. Experiment results proved that our proposed method is superior to other state-of-the-art schemes on OC and OD segmentation, and could be a potential prospective tool for early screening of glaucoma.

Algorithms are used to optimize both single and multi-objective system limits. This research aimed to detect the optimal location and size of the DGs, which can significantly minimize power loss and improve the stability of the voltage. The research uses binary particle swarm optimization and shuffled frog leap (BPSO-SLFA) algorithms for simulation and testing of an optimal power flow (OPF) on 33 and 69 bus radial distribution system. The result shows that the algorithms give better DG allocation and minimizes the power losses but at the nascent stage of advancement. The power losses associated with the system have significantly reduced up to 31.8244kW using multi-DGs reconfiguration placement. The outcomes are established to verify the potency of the recommend algorithm to minimize losses, general improvement in voltage profiles and cost saving for various distribution system. However, the proposed methodology can be used as a reliable method in DG settings and sizing in distribution network system which produce better outputs rather than hybrid grey wolf optimization (GWO) and hybrid big bang big crunch.

In a smart home, the nonintrusive load monitoring recognition scheme normally achieves high appliance recognition performance in the case where the appliance signals have widely varying power levels and signature characteristics. However, it becomes more difficult to recognize appliances with equal or very close power specifications, often with almost identical signature characteristics. In literature, complex methods based on transient event detection and multiple classifiers that operate on different hand crafted features of the signal have been proposed to tackle this issue. In this paper, we propose a deep learning approach that dispenses with the complex transient event detection and hand crafting of signal features to provide high performance recognition of close tolerance appliances. The appliance classification is premised on the deep multilayer perceptron having three appliance signal parameters as input to increase the number of trainable samples and hence accuracy. In the case where we have limited data, we implement a transfer learning-based appliance classification strategy. With the view of obtaining an appropriate high performing disaggregation deep learning network for the said problem, we explore individually three deep learning disaggregation algorithms based on the multiple parallel structure convolutional neural networks, the recurrent neural network with parallel dense layers for a shared input, and the hybrid convolutional recurrent neural network. We disaggregate a total of three signal parameters per appliance in each case. To evaluate the performance of the proposed method, some simulations and comparisons have been carried out, and the results show that the proposed method can achieve promising performance.

Ischemic stroke is a serious cardiovascular disease with high morbidity and mortality rates that affects millions of people worldwide.Currently, the only therapy with proven efficacy for acute ischemic stroke is alteplase, however, it still has many shortcomings and limitations. Therefore,we screen new compounds from traditional Chinese medicine to explore their efficacy against ischemic reperfusion injury. Procyanidins, a natural productextracted from grapes seed, which have been shown can ameliorate cerebral ischemic injury. However, the underlying mechanism is still not very clear. Theaim of this study was to investigate the effect of procyanidins on middle cerebral artery occlusion/reperfusion (MCAO/R)-mediated cerebral ischemic injuryand its underlying possible mechanisms. SD rats were used to evaluate the effect of procyanidins on MCAO/R induced cerebral ischemic injury in vivo. Histological analysis was used toassess neuronal apoptosis. Cell signaling was assayed by Western blot. In this study, we found that procyanidins can significantly ameliorate the middle cerebral artery occlusion/reperfusion (MCAO/R)-mediatedneurological deficits, and relieved brain edema, cerebral infarction volume, histopathological damage and apoptosis in rats. In addition, procyanidins canalso markedly inhibit MCAO/R and oxygen-glucose deprivation/reoxygenation (OGD/R)-mediated activation of TLR4-p38-NF-κB-NLRP3 signalingpathway in vitro and in vivo. Moreover, procyanidins can inhibit MCAO/R and OGD/R-induced the production of inflammatory cytokines such asinterleukin-1β (IL-1β) in vitro and in vivo. Besides, treatment with TLR4 inhibitor (Cli-095) in BV2 cell also shows the same effect. Altogether, these data suggested that procyanidins exerted a potential neuroprotective effect may by inhibit the TLR4-p38-NF-κB-NLRP3signaling pathway in the brain in MCAO/R rats.

Wireless networks have evolved over the years and they have become some of the most prominent communication media. These networks generally transmit large volumes of information at any given time. This has engendered a number of security threats and privacy concerns. This paper presents a Deep Long Short-Term Memory (DLSTM) based classifier for wireless intrusion detection system (IDS). Using the NSL-KDD dataset, we compare the DLSTM IDS to existing methods such as Deep Feed Forward Neural Networks, Support Vector Machines, k-Nearest Neighbors, Random Forests and Naive Bayes. The experimental results suggest that the DLSTM IDS outperformed existing approaches.

Heart disease is the leading cause of death globally. The most common type of heart disease is coronary heart disease, which occurs when there is a build-up of plaque inside the arteries that supply blood to the heart, making blood circulation difficult. The prediction of heart disease is a challenge in clinical machine learning. Early detection of people at risk of the disease is vital in preventing its progression. This paper proposes a deep learning approach to achieve improved prediction of heart disease. An enhanced stacked sparse autoencoder network (SSAE) is developed to achieve efficient feature learning. The network consists of multiple sparse autoencoders and a softmax classifier. Additionally, in deep learning models, the algorithm’s parameters need to be optimized appropriately to obtain efficient performance. Hence, we propose a particle swarm optimization (PSO) based technique to tune the parameters of the stacked sparse autoencoder. The optimization by the PSO improves the feature learning and classification performance of the SSAE. Meanwhile, the multilayer architecture of autoencoders usually leads to internal covariate shift, a problem that affects the generalization ability of the network, hence, batch normalization is introduced to prevent this problem. The experimental results show that the proposed method effectively predicts heart disease by obtaining a classification accuracy of 0.973 and 0.961 on the Framingham and Cleveland heart disease datasets, respectively, thereby outperforming other machine learning methods and similar studies.

Load frequency control or automatic generation control is one of the main operations that take place daily when considering a modern power system or not. The objectives of load frequency control are to maintain power balance between interconnected areas and to control the power flow in the tie-lines. Electric power cannot be stocked in large quantity that why its production must be equal to the consumption in each time. This equation constituted the key for a good management of any power system and introduces the need of more controllers when taking into account the integration of renewable energy sources into the traditional power system. More controllers are presented in the literature and the presents work proposes a review of those called traditional and those who combined the traditional controller and artificial intelligence algorithms. Keywords: Load frequency control, Power system, Controllers, Artificial intelligence

The increase in the price of fossil fuel due to its rarity and emissions means more integration of renewable energy sources (RESs) is required to improve economic management of the grid. This study analyses a combination of the tie-line power between conventional power sources and the renewable energy system and its frequency deviations which are known as area control error. The minimisation of the tie-line by optimal control is affected in such a way that the frequency and tie-line power error can be minimised while maintaining the power balance between generation and load. The tie-line connected to the microgrid consists of two main parts, namely the conventional source and the renewable energy source, each made up of a synchronous generator. The control application of the active power and frequency to a network is referred to as load frequency control (LFC) with the storage system as an integral part of RES. The simulation results show the performance of the proposed optimal control model in microgrid during the changing loads' condition, where the energy storage system applied to optimal control has shown a quick response to frequency deviation, which is close to 80%.

Industry 4.0 has evolved and created a huge interest in automation and data analytics in manufacturing technologies. Internet of Things (IoT) and Cyber Physical System (CPS) are some of the recent topics of interest in the manufacturing sector. Steel manufacturing process relies on monitoring strategies such as fault detection to reduce number of errors which can lead to huge losses. Proper fault diagnosis can assist in accurate decision-making. We use in this study predictive analysis to help solve the complex challenges faced in industrial data. Random Forest, Artificial Neural Networks and Support Vector Machines are used to train and test our industrial data. We evaluate how ensemble methods compare to classical machine learning algorithms. Finally we evaluate our models’ performance and significance. Random Forest outperformed other ML methods in our study.

In recent years, the increased use of wireless networks for the transmission of large volumes of information has generated a myriad of security threats and privacy concerns; consequently, there has been the development of a number of preventive and protective measures including intrusion detection systems (IDS). Intrusion detection mechanisms play a pivotal role in securing computer and network systems; however, for various IDS, the performance remains a major issue. Moreover, the accuracy of existing methodologies for IDS using machine learning is heavily affected when the feature space grows. In this paper, we propose a IDS based on deep learning using feed forward deep neural networks (FFDNNs) coupled with a filter-based feature selection algorithm. The FFDNN-IDS is evaluated using the well-known NSL-knowledge discovery and data mining (NSL-KDD) dataset and it is compared to the following existing machine learning methods: support vectors machines, decision tree, K-Nearest Neighbor, and Naïve Bayes. The experimental results prove that the FFDNN-IDS achieves an increase in accuracy in comparison to other methods.

Power from the distributed energy renewable sources DER’s must be controlled to match the load requirements. A control scheme should be adopted to regulate the power flow from the DERS to maintain quality and reliability of supply. Integration of this DER’s that are fundamentally active transforms the distribution network further into a multi-source system allowing two-way power flows. Major concerns associated with these are voltage and frequency imbalance in the system. In this paper, different faults in a smart grid are characterized and classified. Methods used to identify these faults are systematically reviewed and reported with a view of identifying the challenges and the trends.

A ceaseless supply of electricity is essential for all developmental sectors and even more important nowadays, as the globe evolves through a call for artificially intelligent systems in the fourth industrial revolution. Power interruptions lead to unpleasant human situations as well as great losses within all health, education, and industrial facilities requiring constant electricity. For this reason, we propose the design of an automatic transfer switch (ATS) for power transfer applications to maximize uptime. The ATS ensures the transfer of power between two power sources, hydroelectric and solar, during blackouts or power failures. The design is principally based on an Arduino Mega 2560, triacs, LEDs, as well as an LCD, SD card, Bluetooth, and GSM modules. The Arduino is powerful enough to support all the ATS modules and sustain the combined system processes required for the ATS’s automatic operation. Triacs, which are semiconductor switching devices, were utilized for high-speed switching between the two power supplies. The LEDs and LCD played a signalization role, indicating the state of the ATS at all times. Also, the SD card stores the system’s generated data whilst the Bluetooth modules ensure wireless connectivity between the ATS and a mobile device. The GSM module is for short messages (SMS). The results prove the functioning of the designed ATS, which ensures the transfer of power between two power sources with switching speeds less than 2.58 msec during blackouts or power failures. Furthermore, the ATS is a reliable, fast, and automatic system capable of protecting its internal components from surges. The proposed ATS is validated based on simulations, and the results show that the proposed ATS is promising.

This paper presents a load demand management of interconnected distributed generation (DG) working on islanded mode. The development of technology related to network integration and the use of energy renewable source continues to attract researches, today these sources can generate over a thousand kilowatts, that why it important to look after the management of load supplied by the DG specially when working in islanded mode. The proposed load management model took into account the energy from the storage system and the tie-lines power flow transfer constraints applying the optimal control theory. The proposed methodology considers two loads types: critical and non0critical and proposes a load management of DG interconnected system. All optimization problems were solved using Matlab environment.

This paper dealt with the off-grid household energy system improvement by developing a control based on battery storage system embedded with an ultracapacitor. The hybrid energy system is constituted with photo-voltaic arrays, battery, ultracapacitor, and active load. Non-conventional sources of energy such as photo-voltaic generation is characterized by high variability of parameters due to their dependency to the weather and variable active demand power (load). Partial charge or discharge cycles can happen which has a detrimental effect on energy storage system life span and rating. The ultracapacitor based storage energy system provides the greatest power demanded to keep the reliability and the good level of energy quality on the short time and log-time duration. A high of energy supply can be obtained in an isolated household system generation. Optimization model was developed to combine the battery coupled with an ultracapacitor.

Many real-world machine learning applications require building models using highly imbalanced datasets. Usually, in medical datasets, the healthy patients or samples are dominant, making them the majority class, while the sick patients are few, making them the minority class. Researchers have proposed numerous machine learning methods to predict medical diagnosis. Still, the class imbalance problem makes it difficult for classifiers to adequately learn and distinguish between the minority and majority classes. Cost-sensitive learning and resampling techniques are used to deal with the class imbalance problem. This research focuses on developing robust cost-sensitive classifiers by modifying the objective functions of some well-known algorithms, such as logistic regression, decision tree, extreme gradient boosting, and random forest, which are then used to efficiently predict medical diagnosis. Meanwhile, as opposed to resampling techniques, our approach does not alter the original data distribution. Firstly, we implement the standard versions of these algorithms to provide a baseline for performance comparison. Secondly, we develop their corresponding cost-sensitive algorithms. For the proposed approaches, it is not necessary to change the distribution of the original data as the modified algorithms consider the imbalanced class distribution during training, thereby resulting in more reliable performance than when the data is resampled. Four popular medical datasets, including the Pima Indians Diabetes, Haberman Breast Cancer, Cervical Cancer Risk Factors, and Chronic Kidney Disease datasets, are used in the experiments to validate the performance of the proposed approach. The experimental results show that the cost-sensitive methods yield superior performance compared to the standard algorithms.

Computer networks intrusion detection systems (IDSs) and intrusion prevention systems (IPSs) are critical aspects that contribute to the success of an organization. Over the past years, IDSs and IPSs using different approaches have been developed and implemented to ensure that computer networks within enterprises are secure, reliable and available. In this paper, we focus on IDSs that are built using machine learning (ML) techniques. IDSs based on ML methods are effective and accurate in detecting networks attacks. However, the performance of these systems decreases for high dimensional data spaces. Therefore, it is crucial to implement an appropriate feature extraction method that can prune some of the features that do not possess a great impact in the classification process. Moreover, many of the ML based IDSs suffer from an increase in false positive rate and a low detection accuracy when the models are trained on highly imbalanced datasets. In this paper, we present an analysis the UNSW-NB15 intrusion detection dataset that will be used for training and testing our models. Moreover, we apply a filter-based feature reduction technique using the XGBoost algorithm. We then implement the following ML approaches using the reduced feature space: Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Logistic Regression (LR), Artificial Neural Network (ANN) and Decision Tree (DT). In our experiments, we considered both the binary and multiclass classification configurations. The results demonstrated that the XGBoost-based feature selection method allows for methods such as the DT to increase its test accuracy from 88.13 to 90.85% for the binary classification scheme.

Modern power systems are increasingly becoming more complex and thus become vulnerable to voltage collapse due to constant increase in load demand and introduction of new operation enhancement technologies. In this study, an approach which is based on network structural properties of a power system is proposed for the identification of critical nodes that are liable to voltage instability. The proposed Network Structurally Based Closeness Centrality (NSBCC) is formulated based on the admittance matrix between the interconnection of load to load nodes in a power system. The vertex (node) that has the highest value of NSBCC is taken as the critical node of the system. To demonstrate the significance of the concept formulated, the comparative analysis of the proposed NSBCC with the conventional techniques such as Electrical Closeness Centrality (ECC), Closeness Voltage Centrality (CVC) and Modal Analysis is performed. The effectiveness of all the approaches presented is tested on both IEEE 30 bus and the Southern Indian 10-bus power systems. Results of simulation obtained show that the proposed NSBCC could serve as valuable tool for rapid real time voltage stability assessment in a power system.

This paper examines the role of demand response aggregators in minimizing the cost of electricity generation by distribution utilities in a day-ahead electricity market. In this paper, 2500 standard South African homes are considered as end users. Five clusters (and aggregators) are considered with 500 homes in each cluster. Two cases are analysed: (1) Utilization of renewable energy sources (RES) is implemented by the distribution supply operator (DSO), where it meets excess demand for end users during peak hours by purchasing electricity from the renewable sources of the energy market, and (2) Utilization of RES is implemented by end users alone, and it is assumed that every household has one plug-in electric vehicle (PEV). The aggregators then compete with each other for the most cost-effective energy usage profile, the aggregator with the least energy demand wins the bid. In both cases, energy pricing is estimated according to the day-ahead energy market. A typical day during winter in Johannesburg is considered for the simulation using a genetic algorithm (GA). Results obtained demonstrate the effectiveness of demand response aggregators in maximizing the benefits on both sides of the electricity supply chain.

Purpose. To identify the characteristics of the physical and mental health status of patients with pituitary adenomas, explore the postoperative reversibility of impaired health status, and assess the impact of clinical characteristics, hormone levels, anxiety, depression, and disease stigma on health status. Methods. We prospectively enrolled 147 and 138 patients with nonfunctioning and secretory pituitary adenomas, respectively. Health status was evaluated in 8 domains using the 36-item Short-Form Health Survey before and 3 months after transsphenoidal surgery. The Self-Rating Anxiety Scale, the Self-Rating Depression Scale, and the Stigma Scale for Chronic Illness were used to assess the psychological status. Results. Compared with the healthy population reference values, general physical and mental health, social functioning, and role limitations due to physical and psychological health problems were all found to be significantly impaired in the adenoma patients. Health status was worse in patients with adrenocorticotropic hormone- (ACTH-) secreting and growth hormone- (GH-) secreting adenomas than in patients with nonfunctioning adenomas. Among the patients, 11.6% had anxiety and 30.9% had depression. Higher scores for anxiety, depression, and disease stigma; older age; higher body mass index; and tumor recurrence were independent risk factors for health status impairment in at least one domain. Physical function impairment and role limitations caused by physical health problems became worse after surgery, whereas the mental component of health status remained the same. Conclusion. Health status was impaired in patients with pituitary adenomas, especially secretory adenomas. Physical function and role limitations were worse 3 months after surgery than before surgery. Mental problems, old age, obesity, and tumor recurrence reduced health status.

Non-intrusive-load-monitoring (NILM) is normally based on power series analysis. In the load classification stage we use an image based deep convolutional neural network (DCNN) which is modelled on the biological visual cortex thereby achieving extremely high levels of object recognition and classification. However, the downsize to the DCNN is the requirement of a large image training dataset, translational invariance and loss during max pooling of information captured in small signal perturbations. In this paper to reduce the training dataset, provide appliance signature equivariance recognition and replace max pooling with routing by agreement for improved NILM recognition and classification we use Hinton’s capsule network (CapsNet). Disaggregated appliance current, real power and power factor signals are converted to two-dimensional (2D) images and then complementary fused together for increased recognition accuracy before final input into the CapsNet. We implement the Discrete Wavelet Transform (DWT) since it is able to transform within a large frequency band portfolio and fuses well low pixel images. By using image fusion technique we show that for only fifteen images per appliance and with no data augmentation we are able to achieve average prediction accuracies of up to 93.75% and hence consolidate the validity of the CapsNet in the NILM recognition and classification scheme for limited data memory and improved recognition.

In this paper a two stage method is proposed to effectively predict heart disease. The first stage involves training an improved sparse autoencoder (SAE), an unsupervised neural network, to learn the best representation of the training data. The second stage involves using an artificial neural network (ANN) to predict the health status based on the learned records. The SAE was optimized so as to train an efficient model. The experimental result shows that the proposed method improves the performance of the ANN classifier, and is more robust as compared to other methods and similar scholarly works. Keywords: Sparse autoencoder, Deep learning, Unsupervised learning, ANN, Heart disease

Storage systems can be deployed on varying scales by different stakeholders. The stakeholders in grid-tied scenarios include residential, industrial or commercial consumers, distribution network operators, or transmission system network operators. For the purposes of this study, the distribution network operator has been selected as the primary beneficiary of the storage system. This study examines the economic benefits of investing in storage systems for distribution network operators. The consideration for time-of-use (ToU) rates, as they influence the operation of the storage system and in turn, the profit obtainable from a storage-in-distribution-network system, is considered. The economic analysis of the payback period for the investment in storage systems when the storage system provides energy arbitrage services only has been analysed under the ToU tariff schemes. For the distribution network operator owning a storage system, the payback period, when storage systems are incorporated into the network, ranges from 83 to 5 years when there is an increase in variation of consumer tariffs from 1 to 10% of the present electricity costs. Sensitivity analysis for other storage technology options is also considered and presented.

Operational planning of prosumer microgrids with solar and wind energy sources is quite a complex task considering the intermittency of these sources and energy import/export from prosumers. Reserv...

This study proposes a multi-objective mathematical optimisation model which includes minimisation of the investment costs of new offshore wind farm units, investment costs of new transmission lines, fuel costs, emissions of the fossil fuel generators as well as the maximisation of incentives for new generating units. The mathematical model can be used to determine the optimal expansion planning for generation and transmission facilities with consideration of the impact of location and feed-in tariffs for offshore wind power on the overall system capacity and efficiency. The proposed model is solved using CPLEX 12.6.3 solver in advanced interactive multidimensional modelling system and tested on the modified Garver 6-bus test system and the IEEE 24-bus reliability test system. Simulation results indicate that improving the incentive support scheme and minimisation of the total cost will improve the effective utilisation of offshore power.

The unpredictable nature of renewable power, coupled with the influx of prosumers has made accurate power forecasts in microgrids (MGs) more difficult to obtain. A direct consequence of this is the need for additional spinning reserve (SR) capacity to compensate for resulting power imbalances. Due to the economic and environmental concerns, increasing conventional generation to meet this additional SR capacity is undesirable. The aggregation of prosumer behind-the-meter resources for the provision of SR is proposed in this study, and a mathematical model for the proposed scheme is developed. This scheme is formulated as a constrained optimisation problem, whose solution maintains power supply and demand balance whilst reserving a virtual spinning capacity. The formulation is linearised and solved using the CPLEX 12.6.3 solver in the Advanced Interactive Multidimensional Modelling System environment. A 14-bus MG test system is used to validate the proposed scheme, and results show the benefits of using prosumer behind-the-meter resources to provide ancillary services like SR.

The introduction of new operation enhancement technologies plus increasing application of power electronics, coupled with the continuous increase in load demand, has increased the risk of power net...

This paper presents a management and control of energy stored for a distributed generation working on islanded mode. Constituted essentially with weather depending generations sources, the distributed generation systems are subject to uncertainties and vulnerable to external disturbances. To mitigate these issues the energy storage system is one of the components most used. The objective function has been modelled as a combinatorial model based on optimal control strategy and particle swarm optimisation algorithm. An optimal management and control of energy stored model are proposed as research contributions. The proposed model helped to anticipate any imbalance condition of the three distributed generations interconnected and avoided unplanned load shedding by controlling the load frequency variation in the tie-lines. The scheme considers the battery state of charge, generation rate and power flows in the tie-lines as system constraints. To show the effectiveness of the proposed control management model simulation results are proposed.

Background Goal-directed hemodynamic therapy (GDHT) has been used in the clinical setting for years. However, the evidence for the beneficial effect of GDHT on postoperative recovery remains inconsistent. The aim of this systematic review and meta-analysis was to evaluate the effect of perioperative GDHT in comparison with conventional fluid therapy on postoperative recovery in adults undergoing major abdominal surgery. Methods Randomized controlled trials (RCTs) in which researchers evaluated the effect of perioperative use of GDHT on postoperative recovery in comparison with conventional fluid therapy following abdominal surgery in adults (i.e., >16 years) were considered. The effect sizes with 95% CIs were calculated. Results Forty-five eligible RCTs were included. Perioperative GDHT was associated with a significant reduction in short-term mortality (risk ratio [RR] 0.75, 95% CI 0.61–0.91, p = 0.004, I 2 = 0), long-term mortality (RR 0.80, 95% CI 0.64–0.99, p = 0.04, I 2 = 4%), and overall complication rates (RR 0.76, 95% CI 0.68–0.85, p

To realize the sustainable development, the manufactories/plants must have efficient management/schedule plan and control methods for systems from the aspects of economy, environment and social community. The optimization algorithms are necessary to obtain the optimal or sub-optimal solutions for the manufactories/plants. As one of the most important systems, the power systems play very important role in world. Most of the generators consume the natural resources such as coal, gas, petrol and nuclear materials, and it is very important that the generators do not waste the natural resources and meet the needs of human beings. Hence it is very important to get an optimal or acceptable sub-optimal dynamical economic dispatch, which determines the optimal generation scheme to meet the predicted load demand over a time horizon satisfying the constraint such as ramp-rate limits of generators between time intervals, for a power system which may involve conventional generators and some other alternate sources (solar, wind) of energy. Since power systems are very complicated and there are many constraints, it is difficult to find the optimal solution(s) based on the classical mathematical methods. In the past several decades, there are many kinds of evolutionary optimization algorithms which have been proposed. As one of the nature-inspired meta-heuristic algorithms, Particle Swarm Optimization (PSO) and its variants have shown its advantages in many applications. In this paper we propose a random dimension velocity updated PSO. Simulations are used to test the proposed PSO based several benchmark functions and then the proposed PSO is applied to the dynamic economic dispatch problems of power system. All the simulation results prove the efficiency of the proposed method.

Tuberculosis (TB) is classified as one of the top ten reasons for death from an infectious agent. This paper is to investigate the accuracy of two methods to detect Pulmonary Tuberculosis based on the patient chest X-ray images using Convolutional Neural Networks (CNN). Various image preprocessing methods are tested to find the combination that yields the highest accuracy. Moreover, a hybrid approach using the original statistical computer-aided detection method combined with Neural Networks was also investigated. Simulations have been carried out based on 406 normal images & 394 abnormal images. The simulations show that a cropped region of interest coupled with contrast enhancement yields excellent results. When further enhancing the images with the hybrid method even better results are achieved.

Asymmetrical three-phase short circuit faults occur more often than symmetrical three-phase short circuits faults. The asymmetrical three-phase short circuit faults can be line-to-line faults, double line-to-earth faults or line-to-earth faults. Symmetric components technique and computer methods like time-domain fault analysis as well as quasi steady-state fault analysis are the main traditional methods found in the literature for computing the faults. Some recent software like ETAP (Electrical Transient Analysis Program), Easy-Power and Matlab can also assist in predicting, calculating and generating signals (plotting) of short circuit faults. However, the computation of asymmetrical three-phase short circuit faults in the real world often involves the presence of noise, non-linearity, uncertain and dynamic environments. These various conditions interfere with the evaluation processes of these methods and software tools. This paper presents a survey of comprehensive investigation and analysis of the various algorithms, computer applications and software used to compute asymmetrical three-phase short circuit faults. Various methods and algorithms employ different levels of abstraction. Their strengths and weaknesses are explored in depth and various suggestions are given respectively.

SummaryWhole-genome sequencing has identified many amplified genes in esophageal squamous-cell carcinoma (ESCC); however, their roles and the clinical relevance have yet elucidated. Here we show TP53-induced glycolysis and apoptosis regulator (TIGAR) is a major player in ESCC progression and chemoresistance. TIGAR reprograms glucose metabolism from glycolysis to the glutamine pathway through AMP-activated kinase, and its overexpression is correlated with poor disease outcomes. Tigar knockout mice have reduced ESCC growth and tumor burden. Treatment of TIGAR-overexpressed ESCC cell xenografts and patient-derived tumor xenografts in mice with combination of glutaminase inhibitor and chemotherapeutic agents achieves significant more efficacy than chemotherapy alone. These findings shed light on an important role of TIGAR in ESCC and provide evidence for targeted treatment of TIGAR-overexpressed ESCC.SignificanceEffective and target therapies are required for ESCC, one of the most common types of digestive OR cancer. Little has been known about the biology of ESCC progression or potential molecular targets OR for treatment. Whole-genome sequencing and RNA sequencing studies in ESCC have identified OR many recurrent copy number gain genes; however, the roles and druggable relevance of these OR genes remains poorly understood. Herein we demonstrate that TIGAR overexpression leads to OR metabolic remodeling, promoting ESCC progression and resistance to chemotherapeutic agents. OR Inhibiting the glutamine pathway significantly represses TIGAR-overexpressing ESCC growth and OR enhances tumor cell sensitization to cytotoxic agents. These findings might provide the rationale OR for clinical trials testing glutamine pathway inhibitors in combination with chemotherapy in OR TIGAR-expressing ESCC.

Microgrid is the whole of loads and distributed generation units located at varying distances but close to each other. Power sharing control amongst distributed generation units is the main issues in the microgrids. Two techniques exists to conduct power sharing, in form of load current or active or reactive power sharing. Most of the researchers usually assume a single load in their microgrid system. The model proposed in this paper consider two microgrid interconnected, with multi loads. An optimisation of active power sharing model has been proposed. The effectiveness of the proposed method is evaluated using MatLab environment.

Direct Current (DC) motors are broadly used in various industrial applications such as robotics, automobiles, toys and for many other motoring purposes. This is attributable to their extraordinary flexibility, durability and low implementation cost. It is essential to control the speed, position, torque and other variables of the DC motor to achieve the needed performance depending on the area of application. Many classical techniques have been used in the past to control the DC motor, however, such methods typically take a long time, particularly when used for complex nonlinear systems. The application of metaheuristic algorithms as a means of implementing Artificial Intelligence (AI) in this area has proven to be highly effective in overcoming these shortcomings. In recent decades, metaheuristic algorithms have become increasingly prevalent due to their tremendous success in addressing a number real-world optimization challenges in various fields of human activities extending from economic, pharmaceutical and industrial applications to intellectual applications. This review, therefore, presents the optimization of the PID controller with metaheuristic algorithms for controlling the DC motor drives. A short description for each algorithm is presented along with papers published in various renowned journals. For a robust review, the application of various forms of PID controller, as well as different types of DC motors are examined. Finally, the paper presents some open issues and future directions for research.

In the past decade, wired and wireless computer networks have substantially evolved because of the rapid development of technologies such as the Internet of Things (IoT), wireless handled devices, vehicular networks, 4G and 5G, cyber-physical systems, etc. These technologies exchange large amount of data, and as a result, they are prone to several malicious actions, attacks and security threats that can compromise the availability and integrity of information or services. Therefore, the security and protection of the various communication infrastructures using an intrusion detection system (IDS) is of critical importance. In this research, we propose a Feed-Forward Deep Neural Network (FFDNN) wireless IDS system using a Wrapper Based Feature Extraction Unit (WFEU). The extraction method of the WFEU uses the Extra Trees algorithm in order to generate a reduced optimal feature vector. The effectiveness and efficiency of the WFEU-FFDNN is studied based on the UNSW-NB15 and the AWID intrusion detection datasets. Furthermore, the WFEU-FFDNN is compared to standard machine learning (ML) algorithms that include Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB), Decision Tree (DT) and k-Nearest Neighbor (kNN). The experimental studies include binary and multiclass types of attacks. The results suggested that the proposed WFEU-FFDNN has greater detection accuracy than other approaches. In the instance of the UNSW-NB15, the WFEU generated an optimal feature vector consisting of 22 attributes. Using this input vector; our approach achieved overall accuracies of 87.10% and 77.16% for the binary and multiclass classification schemes, respectively. In the instance of the AWID, a reduced input vector of 26 attributes was generated by the WFEU, and the experiments demonstrated that our method obtained overall accuracies of 99.66% and 99.77% for the binary and the multiclass classification configurations, respectively.

Heart disease is the leading cause of death globally, and early detection is crucial in preventing the progression of the disease. In this paper, an improved machine learning method is proposed for the prediction of heart disease risk. The technique involves randomly partitioning the dataset into smaller subsets using a mean based splitting approach. The various partitions are then modeled using classification and regression tree (CART). A homogeneous ensemble is then created from the different CART models using an accuracy based weighted aging classifier ensemble, which is a modification of the weighted aging classifier ensemble (WAE). The approach ensures optimal performance is achieved. The experimental results on the Cleveland and Framingham datasets achieved classification accuracies of 93% and 91%, respectively, which outperformed other machine learning algorithms and similar scholarly works. The receiver operating characteristic curves further validates the improved performance of the proposed ensemble learning approach. The results show that heart disease risk can be predicted effectively by the proposed ensemble.

Numerous potential advantages to the requirements and effectiveness of the supplied electricity can be accomplished by the installation of distributed generation units. In order to take full advantage of these benefits, it is essential to position the Distributed Generation (DG) units in appropriate locations. Otherwise, their installation may have an adverse effect on the quality of energy and system operation. Several optimization techniques have been created over the years to optimize distributed generation integration. Optimization techniques are therefore constantly changing and have been the main attention of many fresh types of research lately. This article evaluates cutting-edge techniques of optimizing the issue of positioning and sizing distributed generation units from renewable energy sources based on recent papers that have already been applied to distribution system optimization. Furthermore, this article pointed out the environmental, economic, technological and regulatory drivers that lead to a rapid interest in the DG system based on renewable sources. A summary of popular meta-heuristic optimization tools discussed in table form with merits and demerits to increase fresh prospective paths to multi-approach that have not yet been studied.