We investigated the characteristics of stock price manipulation. Two manipulation models were studied: pump-and-dump and spoof trading. Pump-and-dump is a procedure to buy a stock and push its price up. Then, the mani...
详细信息
We investigated the characteristics of stock price manipulation. Two manipulation models were studied: pump-and-dump and spoof trading. Pump-and-dump is a procedure to buy a stock and push its price up. Then, the manipulator dumps all of the stock he holds to make a profit. Spoof trading is a procedure to trick other investors that a stock should be bought or sold at the manipulated price. We constructed mathematical models that use level 2 data for both procedures, and used them to generate a training set consisting of buy/sell orders within on order book of 10 dept.s. Order cancellations, which are important indicators for price manipulation, are also visible in our level 2 data. In this paper, we consider a challenging scenario where we attempt to use less-detailed level 1 data to detect manipulations even though using level 2 data is more accurate. We implemented feedforward neural network models that have level 1 data, containing less-detailed information (no information about order cancellation), but is more accessible to investors as input. The neural network model achieved 88.28% for detecting pump-and-dump but it failed to model spoof trading effectively.
Developing mathematical model for a process is an important and integral step in control system design process. Mathematical models can be developed from fundamental physical laws (white-box approach), by performing e...
详细信息
ISBN:
(纸本)9781509036479
Developing mathematical model for a process is an important and integral step in control system design process. Mathematical models can be developed from fundamental physical laws (white-box approach), by performing experiments (black-box approach) or a combination of both (gray-box approach). This paper presents a black-box system identification of a laboratory boiler. A mathematical MIMO model matrix which describes the dynamic behavior of the drum level and drum pressure of lab-boiler setup with respect to steam and feed water as manipulated variables is presented. A complete system identification of lab-boiler setup, designed by these researchers, has been carried out based on the design-of-experiments (DoE) and validated model with the field measurements. In this paper, the identified boiler-model is characterized in the form of 2×2 process transfer function model matrix structure. This 2×2 model matrix defines the dynamics describing the effect of changes in the feed-water flow rate and steam-flow rate, on the boiler drum-level and drum-pressure. This model can be used to study various classical and advanced control-design and analysis through this lab boiler setup.
This paper is concerned with applicability of intelligent PID controller which is proposed by Fliss and Join recently. First, we analyze the stability regions of intelligent PID control systems when parameter ais vary...
详细信息
This paper proposes a SMD (surface mounting device) classification method for the PCB assembly inspection machines. The package types of SMD components should be classified to create the job program of the inspection ...
详细信息
This paper presents a visual touch recognition for NUKNatural User Interface) using Voronoi-tessellation algorithm. The proposed algorithms are three parts as follows: hand region extraction, hand feature point extrac...
详细信息
It presents a cascaded boost dc-to-dc converter employing a tapped-inductor to obtain a high voltage boosting ratio. It consists of two voltage boosting stages. Stage-I configures like boost converter, and Stage-II is...
详细信息
ISBN:
(纸本)9781479917631
It presents a cascaded boost dc-to-dc converter employing a tapped-inductor to obtain a high voltage boosting ratio. It consists of two voltage boosting stages. Stage-I configures like boost converter, and Stage-II is designed by using a tapped-inductor. Both stages have a cascaded connection to maximize a voltage boosting ratio between input and output voltage. After theoretical analysis, computer-aided simulation and experiment carries out to verify the validity of the proposed converter, and compares a voltage boosting ratio with conventional counterparts.
Different scripts are used for writing purposes. It is very much important to identify/know these scripts before an appropriate character recognition algorithm is chosen. This paper deals mainly on the various segment...
详细信息
Different scripts are used for writing purposes. It is very much important to identify/know these scripts before an appropriate character recognition algorithm is chosen. This paper deals mainly on the various segmentation techniques available for handwritten script recognition system. It is an important technique for image processing. Image segmentation provides meaningful objects of the image. Identification of a script in handwritten recognition system is really a challenging task in real world. Many researchers are indulged in the recognition of scripts from handwritten documents over four decades. This task becomes more and more challenging when it comes to multi lingual/script country like India. An input Image is preprocessed through various steps and segmented by different available techniques. This identification of script helps in optical Character Recognition systems (OCR).
This paper presents a technique of PID controller tuning for fractional order industrial process and proposes a Time-Response Specification Based Fitness (TRSBF) function required by Particle Swarm Optimization (PSO) ...
详细信息
ISBN:
(纸本)9781467382540
This paper presents a technique of PID controller tuning for fractional order industrial process and proposes a Time-Response Specification Based Fitness (TRSBF) function required by Particle Swarm Optimization (PSO) for the controller tuning. The results are compared with the conventional Integral Time Absolute Error (ITAE) based and analytic controllers. The performance and robustness is analyzed in time-domain and frequency-domain to establish the suitability of proposed fitness function. MATLAB/Simulink has been employed for PSO based tuning algorithm validation and comparison of parameters like peak overshoot, settling time, disturbance rejection time, stability in frequency domain, etc.
The paper aims to present an ultra-low power electrocardiogram (ECG) on chip with integrated fuzzy decision making (FDM) chip for body sensor networks. The proposed device is small in size, wearable, battery life. The...
详细信息
The paper aims to present an ultra-low power electrocardiogram (ECG) on chip with integrated fuzzy decision making (FDM) chip for body sensor networks. The proposed device is small in size, wearable, battery life. The proposed device has two designed chips: (1) ECG on Chip and 2) FDM chip. The ECG on chip contains an analog front end circuits, a 12-bit SAR ADC, a QRS detector and relevant control circuitry interfaces. The analog front end circuits accurately senses and digitizes the raw ECG signal, which is then filtered to extract the QRS complex with sampling frequency of 256 Hz. The obtained ECG details are sent to FDM chip for decision making where abnormalities are found and an alert signal is sent to the patient via microcontroller. The patient's ECG data is wirelessly transmitted to mobile phone or PC using ZigBee. The chip was designed and implemented in 0.35μm standard CMOS process. The digital circuits and SRAM operate at 3.3V. The total area of the device is about 6cm 2 and consumes about 8.5μW. Small size and low power consumption show the effectiveness of the proposed design suitable for wireless wearable ECG monitoring devices.
The primary objective is to investigate the applicability of spectral methods for designing feedback controllers for a closed loop system with an input shaper with time delays. The shaper is included in the feedback l...
详细信息
暂无评论