Search

The increasing popularity of ride-hailing services has led to a growing need for optimal utilization of resources and minimization of passenger wait times. A major prerequisite for this goal is to develop accurate taxi demand prediction models. In this study, we propose a novel approach for district-centric online taxi demand prediction. We first used historical data and Pearson coefficient to identify correlated districts. In order to dynamically weight the importance of related districts, we utilized an architecture which is based on attention mechanism. Next, for demand prediction in each district we used an LSTM network and finally to refine the prediction models we used the Gradient Boosting algorithm. To evaluate the effectiveness of our approach, we leverage the real data of Snapp!, a ride-hailing service in Iran. Results confirm that the proposed model outperforms the state-of-the-art methods in terms of prediction error.

Profit maximization and risk mitigation require good financial market predictions. Financial markets have a correlated nature, which means that there are some shared patterns between them; therefore, learning about one market might help understand the behavior of others. End-to-end training techniques have proven successful in financial markets, but they have flaws, such as picking up noise and failing to account for the complicated relationships across markets. We present a promising model for predicting financial markets using the correlation between the two markets, which draws inspiration from the recent progress in disentanglement learning. This model learns to disentangle representations of features shared between markets from specific representations, and removes features that cause interference. We utilized a dilated convolutional neural network as an encoder to extract features while using self-attention and cross-attention to capture specifics and shared patterns. Our model uses Dynamic Time Warping (DTW) to minimize the similarity between specific and shared patterns. It also combines DTW’s alignment-based similarity with the Mean Square Error (MSE) to determine the optimal balance between alignment and prediction accuracy. We conducted our experiments using datasets that included the closing prices of Apple, Samsung, Bitcoin, Ethereum, Meta platforms, and the X platform. Spearman’s rank correlation coefficient was used to evaluate the disentanglement by describing the relationship between the extracted representations. The findings confirm that our model surpasses state-of-the-art approaches in prediction error, financial risk assessment, correlation evolution, and prediction net curves, thereby giving market participants more trust in their decisions.

Markov Chain Monte Carlo (MCMC) approaches are widely used for tuning model parameters to fit process measurements. While modern probabilistic programming languages (PPLs) such as Stan, PyMC, and Turing have made it easier to implement efficient MCMC samplers, configuring them for high dimensional and multi-modal parameter distributions remains a challenging task. In Pandey and Lie (2022), the No-U-Turn Sampler (NUTS) was employed via Turing to estimate parameters of an air-cooled synchronous generator model using real-world experimental data, but the produced posterior distributions were excessively narrow. The present study extends the findings in Pandey and Lie (2022) by producing more realistic parameter estimates using the same data. To accomplish this, the study first reviews the basics of MCMC; it offers some general advice for choosing appropriate settings for MCMC to ensure successful estimation, as well a discussion of the impact of measurement data on the computation of posteriors. The study then implements the simple classical MCMC technique, Metropolis, from scratch to estimate the generator model parameters, providing more insight into MCMC — its fundamental process and terminology. Finally, the knowledge gained is applied to select appropriate settings for NUTS — implemented via Turing — that yield more accurate parameter estimates.

An implantable cardioverter-defibrillator (ICD) is a device that must detect VT and VF arrhythmias on time and treat them. In this project, three CNN networks are designed to introduce the practical methods of using deep learning in heart electrophysiology signals processing. This project presents two speedy intelligent detection methods of ventricular fibrillation and ventricular tachycardia arrhythmias for ICD devices. It also provides another quick, innovative diagnosis method for use in intelligent electrocardiograph devices to detect abnormal cardiac signals. The first network is 1D-CNN for smart electrocardiographic devices to detect abnormal ECG signals. Dataset MIT-BIH has been used to train this network. This network with the most optimal number of parameters due to high detection speed has a high accuracy of 91%. The second and third networks are 2D-CNNs for use in implantable defibrillators. For the second network, a data set of 20 patients with cardiac arrhythmia and 20 patients without cardiac arrhythmia in an 8-month period of ICD check-up has been prepared. The third network is trained using the Spontaneous Ventricular Tachyarrhythmia Database. The second and third networks are designed to detect EGM signals in VF and VT modes with the optimal number of parameters and 100% accuracy in the second network and 90% in the third network. All three designed networks are in an optimal condition regarding the number of parameters and layers, so they have optimal speed and energy consumption.

The occurrence of low-frequency electromechanical oscillations is a major problem in the effective operation of power systems. The scrutiny of these oscillations provides substantial information about power system stability and security. In this paper, a new method is introduced based on a combination of synchrosqueezed wavelet transform and the stochastic subspace identification (SSI) algorithm to investigate the low-frequency electromechanical oscillations of large-scale power systems. Then, the estimated modes of the power system are used for the design of the power system stabilizer and the flexible alternating current transmission system (FACTS) device. In this optimization problem, the control parameters are set using a hybrid approach composed of the Prony and residual methods and the modified fruit fly optimization algorithm. The proposed mode estimation method and the controller design are simulated in MATLAB using two test case systems, namely IEEE 2-ar-ea 4-generator and New England-New York 68-bus 16-genera-tor systems. The simulation results demonstrate the high performance of the proposed method in estimation of local and interarea modes, and indicate the improvements in oscillation damping and power system stability.

This paper presents a new method for robot interception planning based on the proportional navigation. Guidance laws are basically developed for aerospace applications where a pursuer impacts a target using these methods, however in the robotic application it is required to have a smooth grasp between the robot and the goal. In this method, a new term is considered for longitude axis to have the control on the final approaching velocity. The proposed method not only ensures the position and velocity match (also referred to as rendezvous) but also can be used to set the final closing velocity to any desired value. Approaching velocity can be zero for grasping the goal or a specific known velocity for hitting it in a controlled manner. It is shown that the capture region of the proposed approach is wider that other proportional navigation based methods. The proposed method is implemented on Qbot-2 and its performance is experimentally validated.

The planning of public transport operations is an essential component of urban transport management systems that aims to provide the most efficient, safe and effective way to support movement of people. Improving the customer journey experience is a key focus, as cities grow and sustainable public transport becomes more critical. This has led to an increased interest in Automatic Passenger Counting (APC) technologies that provide real-time estimates of occupancy in order to support better planning and customer information. The proliferation of sensors and power-efficient miniaturized computing capabilities offer a range of low-cost and versatile APC choices. However, it is important to understand the various design and implementation considerations and trade-offs of the APC technologies in the context of transport operation scenarios they are deployed in. In this paper, we present outcomes of a field study that evaluated the four APC solutions video, floor-based sensing, WiFi and Infrared sensing. We present an evaluations methodology that authentically captures operating conditions while providing a robust way to assess APC solutions. While most technologies achieve over 70% accuracy in some settings, the differences between weekend trips with longer legs and weekday services with short distances between stops lead to stark variations in the performances.

This study presents the effects of the vibration and thermal cycling on the fatigue life of a power Metal Oxide Semiconductor Field Effect Transistor (MOSFET) in a power converter circuit. The fatigue mechanism in per loading mode was investigated separately and based on the overlap approach, the synchronous effects were analyzed. The solder creeps' attitudes are depended on the fatigue life for the thermal loops. The success of the deposited strain per thermal loop is in direct relation with the fatigue lifetime. The main source of the stress in the packaging process is the differences between the components' thermal coefficients. To evaluate the effects of the vibration on the fatigue life for the solder layers, the RMS value of the peeling stress was considered. According to the results, the maximum stress and main affected points realized at the corners of the layers. It has been identified that the assembling of the thermal effects and mechanical loads are quickened the failure rate at the solder joints for this device. The Finite Element Method (FEM) is used for the simulation and the results confirm the estimated crack formation places in the layers.

An Improved Sinusoidal Pulse Width Modulation (ISPWM) technique carried out to obtain pure sine waves for voltage and current signals in Quasi Z-Sourc Inverters (QZSIs) in the load side is given in this study. This switching method can be examined to two and multi-phase approaches simply through the addition of the same controller structure to per phase. This is the main advantage of the proposed converter to obtain higher voltage gains at the output ends of this inverter. The idea is to generate a positive rectified voltage at the output point of the QZSI and positive and negative rectified voltages at the output terminals of the QZSI in two-phase approaches to improve the quality of the output voltage of the F-Bridge Inverter (FBI). These rectified voltages are applied to the Full-Bridge Inverter (FBI) block and pure sine waves to obtain the load current and voltages. 1.34% of the Total Harmonic Distortion (THD) for the output voltage has been reported in the one-phase system while 0.88% of THD has been obtained in the two-phase approach. Besides, the reliability of the QZSI was tested through the Mean Time to Failure (MTTF) analysis with the values of the proposed components. The calculations show a very good result for the long-life of the converter. All experimental and simulations steps have been obtained for the same values of the components to support and confirm the accuracy and correctness of the proposed IMSPW. For the states of single-phase and two-phase converters, a 50 Hz sine-wave with 220 V and 440 V peak to peak amplitude has been acquired. Evaluations of the quality of the voltage and current waveforms related to different active (Resistive, P) and reactive (combination of Resistance and Inductance, QL) loads have been carried out. Experimental results show confirmation for all simulation and mathematical results.

This article proposes a two-stage reliability-based model for the economic dispatch (ED) of thermal units (TUs) and wind turbines (WTs) in the presence of a demand-side response program (DSRP). In the first stage, the well-being analysis (WBS) is performed to determine the power generation and spinning reserve (SR) of the TUs regarding the timely power generation of WTs. In the second stage, the adoption of the responsive load consumption with various conditions of the generation system in the power pool market is established using the cost of expected energy not served criterion. This optimization problem is solved at two stages using the genetic algorithm. To validate the proposed model, numerical studies have been applied to the generation part of 24-Bus IEEE standard test power system including 11 TUs, one wind farm, and 1000 EVs. It is found from simulation results that an 8%–10% shift and increase in the energy consumption with responsive loads (RLs) participation especially EVs during low-load and off-peak hours can lead to more than 53.83% saving in total reliability cost of power system. In addition, the daily smooth load profile causes to savings in total load ED on TUs in the presence of WTs due to removing the unnecessary startup and shot-down costs during a day. [ABSTRACT FROM AUTHOR]