Search

In the original publication [...]

In this paper, we used the single-photon emission computerized tomography (SPECT) imaging technique to visualize the deficiency of dopamine-generated patterns inside the brain. These patterns are used to establish a patient’s disease progression, which helps distinguish the patients into different categories. Furthermore, we used a convolutional neural network (CNN) model to classify the patients based on the dopamine level inside the brain. The dataset used throughout this paper is the Parkinson’s progressive markers initiative (PPMI) dataset. The collected dataset was pre-processed and data amplification was performed to balance the imbalanced dataset. A CNN-based neural network was defined to classify input SPECT images into four categories. The motivation behind the proposed model is to reduce the number of resources consumed while maintaining the performance of the classification model. This will help the healthcare ecosystem run the classification model on mobile devices. The proposed model contains 14 layers with input layers, convolutional layers, max-pool layers, flatten layers, and dense layers with different dimensions. The dense layer classifies the patients into four different categories, including PSD, healthy control, scans without evidence of dopaminergic deficit (SWEDD), and GenReg PSD from the entire SPECT imaging dataset, which is used to establish the disease progression of different patients using SPECT images. The proposed model is trained with a large dataset with 58,692 images for training and 11,738 images for validation, and 7826 for testing. The proposed model outperforms the classification models from the surveyed papers. The proposed model’s accuracy is 0.889, recall is 0.9012, the precision is 0.9104, and the F1-score is 0.9057.

Throughout the history of modern finance, very few financial instruments have been as strikingly volatile as cryptocurrencies. The long-term prospects of cryptocurrencies remain uncertain; however, taking advantage of recent advances in neural networks and volatility, we show that the trading algorithms reinforced by short-term price predictions are bankable. Traditional trading algorithms and indicators are often based on mean reversal strategies that do not advantage price predictions. Furthermore, deterministic models cannot capture market volatility even after incorporating price predictions. Thus motivated by these issues, we integrate randomness in the price prediction models to simulate stochastic behavior. This paper proposes hybrid trading strategies that take advantage of the traditional mean reversal strategies alongside robust price predictions from stochastic neural networks. We trained stochastic neural networks to predict prices based on market data and social sentiment. The backtesting was conducted on three cryptocurrencies: Bitcoin, Ethereum, and Litecoin, for over 600 days from August 2017 to December 2019. We show that the proposed trading algorithms are better when compared to the traditional buy and hold strategy in terms of both stability and returns.

In the paper, a coordinated control methodology of single-phase (1-P) end-users switching operations on the phases of an active electric distribution network (AEDN) has been proposed to obtain a minimum unbalance degree at the coupling common point (CCP) level with the main distribution system. The phase load balancing (PLB) process considers the smart devices that switch the 1-P end-users (consumers and prosumers) from one phase to another to compensate for the phase load unbalance. The proposed methodology has been tested successfully in an AEDN belonging to a Romanian Distribution Network Operator (DNO) containing 114 end-users (104 consumers/10 prosumers) integrated into the Smart Metering System (SMS). The optimal solution leads to a value of the objective function by 1.00, represented by the unbalance factor (UF), which could be identified with the ideal target. A comparative analysis was conducted considering other possible PLB cases (the consumer-level PLB and prosumer-level PLB), obtaining similar values of the UF (1.027 vs. 1.028), slightly higher than in the hybrid-level PLB. Additionally, the significant technical benefits were quantified through an energy-saving of 58.73% and decreasing the phase voltage unbalance rate by 91% compared to the initial case (without PLB). These results emphasized the positive impact of the proposed coordinated control methodology on the PLB process and evidenced its effectiveness and applicability in the AEDNs.

Demand Side Management (DSM) is becoming necessary in residential electricity distribution networks where local electricity trading is implemented. Amongst the DSM tools, Demand Response (DR) is used to engage the consumers in the market by voluntary disconnection of high consumption receptors at peak demand hours. As a part of the transition to Smart Grids, there is a high interest in DR applications for residential consumers connected in intelligent grids which allow remote controlling of receptors by electricity distribution system operators and Home Energy Management Systems (HEMS) at consumer homes. This paper proposes a novel algorithm for multi-objective DR optimization in low voltage distribution networks with unbalanced loads, that takes into account individual consumer comfort settings and several technical objectives for the network operator. Phase load balancing, two approaches for minimum comfort disturbance of consumers and two alternatives for network loss reduction are proposed as objectives for DR. An original and faster method of replacing load flow calculations in the evaluation of the feasible solutions is proposed. A case study demonstrates the capabilities of the algorithm.

In the electric distribution systems, the “Smart Grid” concept is implemented to encourage energy savings and integration of the innovative technologies, helping the distribution network operators (DNOs) in choosing the investment plans which lead to the optimal operation of the networks and increasing the energy efficiency. In this context, a new phase load balancing algorithm was proposed to be implemented in the low voltage distribution networks with hybrid structures of the consumption points (switchable and non-switchable consumers). It can work in both operation modes (real-time and off-line), uploading information from different databases of the DNO which contain: The consumers’ characteristics, the real loads of the consumers integrated into the smart metering system (SMS), and the typical load profiles for the consumers non-integrated in the SMS. The algorithm was tested in a real network, having a hybrid structure of the consumption points, on a by 24-h interval. The obtained results were analyzed and compared with other algorithms from the heuristic (minimum count of loads adjustment algorithm) and the metaheuristic (particle swarm optimization and genetic algorithms) categories. The best performances were provided by the proposed algorithm, such that the unbalance coefficient had the smallest value (1.0017). The phase load balancing led to the following technical effects: decrease of the average current in the neutral conductor and the energy losses with 94%, respectively 61.75%, and increase of the minimum value of the phase voltage at the farthest pillar with 7.14%, compared to the unbalanced case.

A growing number of households benefit from government subsidies to install renewable generation facilities such as PV panels, used to gain independence from the grid and provide cheap energy. In the Romanian electricity market, these prosumers can sell their generation surplus only at regulated prices, back to the grid. A way to increase the number of prosumers is to allow them to make higher profit by selling this surplus back into the local network. This would also be an advantage for the consumers, who could pay less for electricity exempt from network tariffs and benefit from lower prices resulting from the competition between prosumers. One way of enabling this type of trade is to use peer-to-peer contracts traded in local markets, run at microgrid (μG) level. This paper presents a new trading platform based on smart peer-to-peer (P2P) contracts for prosumers energy surplus trading in a real local microgrid. Several trading scenarios are proposed, which give the possibility to perform trading based on participants’ locations, instantaneous active power demand, maximum daily energy demand, and the principle of first come first served implemented in an anonymous blockchain trading ledger. The developed scheme is tested on a low-voltage (LV) microgrid model to check its feasibility of deployment in a real network. A comparative analysis between the proposed scenarios, regarding traded quatities and financial benefits is performed.

At complex industrial sites, the high number of large consumers that make the technological process chain requires direct supply from the main high-voltage grid. Often, for operational flexibility and redundancy, the main external supply is complemented with small local generation units. When a contingency occurs in the grid and the main supply is cut off, the local generators are used to keep in operation the critical consumers until the safe shutdown of the entire process can be achieved. In these scenarios, in order to keep the balance between local generation and consumption, the classic approach is to use under-frequency load-shedding schemes. This paper proposes a new load-shedding algorithm that uses particle swarm optimization and forecasted load data to provide a low-cost alternative to under-frequency methods. The algorithm is built using the requirements and input data provided by a real industrial site from Romania. The results show that local generation and critical consumption can be kept in stable operation for the time interval required for the safe shutdown of the running processes.

Artificial intelligence has been utilized extensively in the healthcare sector for the last few decades to simplify medical procedures, such as diagnosis, prognosis, drug discovery, and many more. With the spread of the COVID-19 pandemic, more methods for detecting and treating COVID-19 infections have been developed. Several projects involving considerable artificial intelligence use have been researched and put into practice. Crowdsensing is an example of an application in which artificial intelligence is employed to detect the presence of a virus in an individual based on their physiological parameters. A solution is proposed to detect the potential COVID-19 carrier in crowded premises of a closed campus area, for example, hospitals, corridors, company premises, and so on. Sensor-based wearable devices are utilized to obtain measurements of various physiological indicators (or parameters) of an individual. A machine-learning-based model is proposed for COVID-19 prediction with these parameters as input. The wearable device dataset was used to train four different machine learning algorithms. The support vector machine, which performed the best, received an F1-score of 96.64% and an accuracy score of 96.57%. Moreover, the wearable device is used to retrieve the coordinates of a potential COVID-19 carrier, and the YOLOv5 object detection method is used to do real-time visual tracking on a closed-circuit television video feed.

A fall detection system is vital for the safety of older people, as it contacts emergency services when it detects a person has fallen. There have been various approaches to detect falls, such as using a single tri-axial accelerometer to detect falls or fixing sensors on the walls of a room to detect falls in a particular area. These approaches have two major drawbacks: either (i) they use a single sensor, which is insufficient to detect falls, or (ii) they are attached to a wall that does not detect a person falling outside its region. Hence, to provide a robust method for detecting falls, the proposed approach uses three different sensors for fall detection, which are placed at five different locations on the subject’s body to gather the data used for training purposes. The UMAFall dataset is used to attain sensor readings to train the models for fall detection. Five models are trained corresponding to the five sensors models, and a majority voting classifier is used to determine the output. Accuracy of 93.5%, 93.5%, 97.2%, 94.6%, and 93.1% is achieved on each of the five sensors models, and 92.54% is the overall accuracy achieved by the majority voting classifier. The XAI technique called LIME is incorporated into the system in order to explain the model’s outputs and improve the model’s interpretability.

The global climate change mitigation efforts have increased the efforts of national governments to incentivize local households in adopting PV panels for local electricity generation. Since PV generation is available during the daytime, at off-peak hours, the optimal management of such installations often considers local storage that can defer the use of local generation to a later time. The energy stored in batteries located in optimal places in the network can be used by the utility to improve the operation conditions in the network. This paper proposes a metaheuristic approach based on a genetic algorithm that considers three different scenarios of using energy storage for reducing the energy losses in the network. Two cases considers the battery placement and operation under the direct control of the network operator, with single and multiple bus and phase placement locations. Here, the aim was to maximize the benefit for the whole network. The third case considers selfish prosumer battery management, where the storage owner uses the batteries only for their own benefit. The optimal design of the genetic algorithm and of the solution encoding allows for a comparative study of the results, highlighting the important strengths and weaknesses of each scenario. A case study is performed in a real distribution system.