Search

Precise stock market prediction is crucial for investors, but the volatility of the stock market is influenced by multiple factors such as public sentiments, business news, and related product volatility. While several algorithms have been proposed to predict the stock exchange index based on historical data, they are not ideal as external factors play a critical role in market volatility. To address this issue, we proposed a machine learning model that incorporates historical data with external factors such as social media sentiments, oil and gold trends, and financial news data to enhance prediction accuracy. Our study used HPQ, IBM, ORCL, and MSFT stock market datasets to validate the effectiveness of the proposed model, including an analysis of the impact of Covid19 on companies. Our experimental results showed the highest accuracy of 87.2% using oil and sentiment datasets. Additionally, we identified that social media significantly affects IBM stocks, and the GBM (Gradient Boosting Classifier) classifier produced consistent results.

Police and law enforcement agencies perform social media analysis to gain a better understanding of criminal social networks structures and to identify potential criminal activities. The use of data mining techniques in social media analysis, however, faces issues and challenges such as linkage-based structural analysis, association extraction, community or group detection, behaviour and mood analysis, sentiment analysis and dynamic analysis of streaming networks. This chapter describes the extension of our developed framework and propose an association model for extracting multilevel associations based on associative questioning. We also describe data mining techniques used to visualize these associations through a 2D crime cluster space. The developed framework provides a complete data analytic solution towards identifying and understanding associations between crime entities and thus expedites the crime matching process.

Police analysts increasingly use data analysis techniques to make decisions that have an impact on society. Previous research shows that excluding ethically sensitive information (features) such as name, surname, address etc. during the data analysis process has implications for accuracy and decision-making, which may have negative consequences affecting individuals or a group within society. To assess whether the use of ethically sensitive features has implications for decision-making, we identified two important aspects: (i) transparency of the feature selection, and (ii) a way of assessing the impact of the selected features. In this paper, we define ethically sensitive information from two aspects: (a) features that identify an individual, known as personally identifiable information, and (b) sensitive features that discriminate against the individual, known as prejudice information. We investigate whether the selection of these features has an impact on accurately identifying co-offenders. For this, we propose a privacy scale, which consists of a value for each feature depending on the label of their sensitivity. To explore this, we used an anonymized dataset received from a UK law enforcement agency. Ground truths samples with known co-offender were selected for this study. We used the clustering algorithm K-MODE and included and excluded features that included personal, prejudice and other attributes to assess the relationship between the privacy score of the combined input attributes and the accuracy of the clustering. The results suggest that the use of ethically sensitive features does have an impact on correctly identifying potential co-offenders more accurately.

Criminal Intelligence Analysis often requires a search different from the semantic and keyword based searching to reveal the associations among semantically and operationally connected objects within a crime knowledge base. In this paper we introduce associative search as a search along the networks of association between objects like people, places, other organizations, products, events, services, and so on. We also propose an associative search model based on the 5WH associated concepts of a crime, i.e. WHAT (what has happened), WHO (who was involved in the crime), WHEN (the temporal information of the crime), WHERE (the geo-spatial information of the crime) HOW (the modus-operandi used in committing a crime). We have employed Formal Concept Analysis theory to reveal the associations, highlighting Hot Spots, offender's profile and its associated offenders in a criminal activity.

Gestational trophoblastic neoplasia (GTN) comprise a spectrum of interrelated conditions originating from the placenta. With sensitive assays for human chorionic gonadotropin (β-hCG) and current approaches to chemotherapy, most women with GTN can be cured with preservation of reproductive potential. The purpose of this analysis was to address the outcome of GTN in patients from a tertiary care center of India.We undertook a retrospective and prospective review of GTN cases treated at our center over a period of 7 years from 2008 to 2014. Patients of GTN were assigned to low-risk or high-risk categories as per the FIGO scoring system. The low-risk group was treated with combination of actinomycin-D and methotrexate and the high-risk group received the Etoposide, Methotrexate, Actinomycin-D/ Cyclophosphamide, Vincristine (EMA/CO) regimen. Salvage therapy was Etoposide, Paclitaxel /Paclitaxel, Cisplatin (EP/TP). Treatment was continued for three cycles after normalization of β-hCG level, after which the patients were followed up regularly.In total, 41 GTN patients were treated at our institution during the above period; 17 were in the low-risk and 24 were in the high-risk category. The lung was the most common site of metastasis. All low-risk patients achieved complete remission. Among high-risk patients, one patient died while receiving first cycle chemotherapy, one patient relapsed, and 22 patients achieved complete remission. The single relapsed patient also achieved remission with second-line chemotherapy.Risk-stratified treatment of GTN was associated with acceptable toxicity and resulted in outcome that was comparable with international standards. The use of two-drug combination in low-risk patients is a better option especially in developing countries.

In recent years, few mechanistic models have been proposed for design optimization and predicting the performance of reserve flow cyclonic separators. However, there is not much literature available on design and performance evaluation of axial flow compact separator. The work presented in this paper demonstrates the use of stacked neural network to model the nonlinear process of gas–liquid separation through a novel designed axial flow compact separator (called as I-SEP in this study). We trained several standard back propagation training algorithms to predict the separation efficiency of the I-SEP; these base models are then combined to form a single composite model. Principle component regression techniques are used to estimate the weight of the participant trained neural networks in the composite model. It has shown in this work that combination of trained neural networks improves prediction accuracy of gas–liquid separation as compared with that of participant individual neural network models. The stacked neural network model produced satisfactory prediction on unseen experimental data and may be helpful to the operators in effectively controlling the separator by predicting the separation efficiency at the changing operating inlet condition. © 2014 Curtin University of Technology and John Wiley & Sons, Ltd.

Traditional on-site wastewater treatment systems have proven to be unsuitable in areas of low permeability subsoils, representing a risk to human health and the environment. With large areas being covered by low permeability tills, Ireland needs to consider alternative treatment and disposal options to be able to allow further development in these areas and to deal with polluting legacy sites. The paper describes the development and structure of a geographic information system (GIS)-based decision support toolset to evaluate possible alternative strategies for these sites. The programme takes as its initial input the location of an existing house located in an area of low permeability subsoils. Through a series of interconnected GIS geoprocesses the model outputs appropriate solutions for a site, ranking them in terms of environmental sustainability and cost. However, the final decisions are still dependent on on-site constraints so that each solution is accompanied by an alert message that provides additional information for the user to refine the output list according to the available local site-specific information.

The work presented in this paper highlights the development of a web based intelligent Geographical Information System (GIS) spatial decision support tool. Engineered over the Amazon cloud computing environment, the GIS system has been designed to enable local authorities in Ireland to identify solutions for the treatment of domestic waste water in areas of low permeability subsoil. The data used in the geo-spatial modelling includes the XY coordinates of existing treatment systems, topography, soils and subsoil, and road networks. Spatial modelling is performed through ESRI's ArcMap and published as a web service on ArcGIS Server 10.1. This decision support system is made available to the remote user over Amazon's EC2 as a GIS based web service, through Representational State Transfer (REST) architecture. The tool will assist local authorities to better manage domestic wastewater in low permeability areas, thereby reducing the likelihood of pollution of local surface waters. Wexford is the test area.

Input feature selection and appropriate weight estimation in combining trained neural network are one of the important key factors in neural stacked neural network based models. This study has investigated these problems through the information theory and linear estimation weight techniques. These techniques have implemented to model the non linear separation process model of a novel design compact separator. The separation efficiency of the compact separator used in this study was found to be dependent non -linearly on many input factors such as gas volume fraction, inlet mixture velocity, liquid and gas superficial velocity, inlet pressure, and Loss coefficient etc. The input parameters from all the candidate inputs were selected based on their Mutual Information with the separation efficiency. It is demonstrated that mutual information is better statistical method for input feature selection to train a neural network. Based on the mutual information a set of inputs were selected and several single trained neural networks having different architecture in terms of hidden neurons and training functions were combined together to improve the prediction accuracy. Three linear methods i.e. equal weigh ts; linear regression and principle component regression were used to combine the trained neural network. The performance of the combined neural network aggregated through principle component regression was found to better than neural network combined with equal weight and linear regression.

The removal of denser phase from the multiphase flow is one of fundamental and challenging task in oil and gas industry. It is because crude oil emerging from the well also contains natural gas, water and some time sand. Each of these needs to be separated out for economics reason before being transported to their destination. The available technology for multiphase separation includes gravity separators, centrifugal separators, filter vane separators and mist eliminators. However these separators are expensive in both operations and purchase. Compact or in line separators are one of suitable alternative because of their low cost, simplicity, easy handling and simple installation. The performance of such a newly designed gas liquid compact centrifugal separator is under study in the department of process and system engineering at Cranfield University UK. While several mechanistic models are available in literature for gravity separator, the neural network has not been used so far to predict the separation efficiency of the compact separator at least according to literature survey done by the author. This work describes an empirical model based on a variant of MLP neural network to predict the separation efficiency of a compact gas liquid separator. This model helps operator to effectively control the multiphase separator rig by predicting the separation efficiency at the changing operating inlet condition.