The financial sector has greatly impacted the monetary well-being of consumers, traders, and financial institutions. In the current era, artificial intelligence is redefining the limits of the financial markets based on state-of-the-art machine learning and deep learning algorithms. There is extensive use of these techniques in financial instrument price prediction, market trend analysis, establishing investment opportunities, portfolio optimization, etc. Investors and traders are using machine learning and deep learning models for forecasting financial instrument movements. With the widespread adoption of AI in finance, it is imperative to summarize the recent machine learning and deep learning models, which motivated us to present this comprehensive review of the practical applications of machine learning in the financial industry. This article examines algorithms such as supervised and unsupervised machine learning algorithms, ensemble algorithms, time series analysis algorithms, and deep learning algorithms for stock price prediction and solving classification problems. The contributions of this review article are as follows: (a) it provides a description of machine learning and deep learning models used in the financial sector; (b) it provides a generic framework for stock price prediction and classification; and (c) it implements an ensemble model—“Random Forest + XG-Boost + LSTM”—for forecasting TAINIWALCHM and AGROPHOS stock prices and performs a comparative analysis with popular machine learning and deep learning models.

Interoperability in Electronic Health Records (EHR) is significant for the seamless sharing of information amongst different healthcare stakeholders. Interoperability in EHR aims to devise agreements in its interpretation, access, and storage with security, privacy, and trust. A study and survey of the state-of-the-art literature, prototypes, and projects in standardization of the EHR structure, privacy-preservation, and EHR sharing are very essential. The presented work conducts a systematic literature review to address four research questions. 1) What are the different standards for common interpretation, representation, and modeling of EHR to achieve semantic interoperability? 2) What are the different privacy-preservation techniques and security standards for EHR data storage? 3) How mature is blockchain technology for building interoperable, privacy-preserving solutions for EHR storage and sharing? 4) What is the state-of-the-art for cross-chain interoperability for EHR sharing? An exhaustive study of these questions establishes the potential of a blockchain-based EHR management framework in privacy preservation, access control and efficient storage. The study also unveils challenges in the adoption of blockchain in EHR management with the state-of-the-art maturity of cross-chain interoperable solutions for sharing EHR amongst stakeholders on different blockchain platforms. The research gaps culminate in proposing a blockchain-based EHR framework called as MyBlockEHR with privacy preservation and access control design. The proposed framework employs partitioning of EHR to on-chain and off-chain storages for performance guarantees with the retrieval of valid off-chain data. The framework is deployed on the Ethereum test network with Solidity smart contracts. It is observed that different test cases on the partitioning of the EHR data, yielded better read-write throughput and effective gas price than fully on-chain storage.

Electronic Health Records (EHR) serve as a solid documentation of health transactions and as a vital resource of information for healthcare stakeholders. EHR integrity and security issues, however, continue to be intractable. Blockchain-based EHR architectures, however, address the issues of integrity very effectively. In this work, we suggest a decentralized patient-centered healthcare data management (PCHDM) with a blockchain-based EHR framework to address issues of confidentiality, access control, and privacy of record. This patient-centric architecture keeps the patient at the center of control for secured storage of EHR data. It is effective in the storage environment with the interplanetary file system (IPFS) and blockchain technology. In order to control unauthorized users, the proposed secure password authentication-based key exchange (SPAKE) implements smart contract-based access control to EHR transactions and access policies. The experimental setup comprises four hyperledger fabric nodes with level DB database and IPFS off-chain storage. The framework was evaluated using the public hepatitis dataset, with parameters such as block creation time, transactional computational overhead with encryption key size, and uploading/downloading time with EHR size. The framework enables patient-centric access control of the EHR with the SPAKE encryption algorithm.

Aquaculture is growing industry from the perspective of sustainable food fulfillment and county's economic development. Technology oriented aquafarming is the solution for effective water quality monitoring and high yield production. Internet of Things (IoT) integrated aquaculture can cater to such requirements. This research article introduces a comprehensive method aimed at seamlessly incorporate IoT sensors into aquafarming environments, utilizing Arduino boards and communication modules. The proposed method measures accurate water quality parameters, such as temperature, pH levels, and Dissolved Oxygen (DO), which are essential for maintaining optimal conditions for suitable aquaculture environment. This method enables the real-time collection of critical data points that are essential prevent fish diseases and mortality with low human intervention and maintenance cost. The key contributions of the methodology are mentioned below.•Design and development of a compact and efficient Printed Circuit Board (PCB) to achieve accurate sensor data readings and reliable communication in an aqua environment.•Prevent fish disease and mortality rate through data-driven decision incorporating correlation of DO, pH, and temperature sensor data.•Conducted instrument calibration checks and cross-validated automated system data with manual observations through repeatability tests to ensure precise measurements of sensor parameters.

Early detection and timely breast cancer treatment improve survival rates and patients’ quality of life. Hence, many computer-assisted techniques based on artificial intelligence are being introduced into the traditional diagnostic workflow. This inclusion of automatic diagnostic systems speeds up diagnosis and helps medical professionals by relieving their work pressure. This study proposes a breast cancer detection framework based on a deep convolutional neural network. To mine useful information about breast cancer through breast histopathology images of the 40× magnification factor that are publicly available, the BreakHis dataset and IDC(Invasive ductal carcinoma) dataset are used. Pre-trained convolutional neural network (CNN) models EfficientNetB0, ResNet50, and Xception are tested for this study. The top layers of these architectures are replaced by custom layers to make the whole architecture specific to the breast cancer detection task. It is seen that the customized Xception model outperformed other frameworks. It gave an accuracy of 93.33% for the 40× zoom images of the BreakHis dataset. The networks are trained using 70% data consisting of BreakHis 40× histopathological images as training data and validated on 30% of the total 40× images as unseen testing and validation data. The histopathology image set is augmented by performing various image transforms. Dropout and batch normalization are used as regularization techniques. Further, the proposed model with enhanced pre-trained Xception CNN is fine-tuned and tested on a part of the IDC dataset. For the IDC dataset training, validation, and testing percentages are kept as 60%, 20%, and 20%, respectively. It obtained an accuracy of 88.08% for the IDC dataset for recognizing invasive ductal carcinoma from H&E-stained histopathological tissue samples of breast tissues. Weights learned during training on the BreakHis dataset are kept the same while training the model on IDC dataset. Thus, this study enhances and customizes functionality of pre-trained model as per the task of classification on the BreakHis and IDC datasets. This study also tries to apply the transfer learning approach for the designed model to another similar classification task.

The mechanical, physical and interfacial properties of aluminum alloys are improved by reinforcing the silicon carbide particles (SiC_p). Machinability of such alloys by traditional methods is challenging due to higher tool wear and surface roughness. The objective of research is to investigate the machinability of SiC_p reinforced Al6061 composite by Wire-Electrical Discharge Machining (wire-EDM). The effect of wire-EDM parameters namely current (I), pulse-on time (T_on), wire-speed (W_s), voltage (I_v) and pulse-off time (T_off) on material removal rate (MRR) is investigated and their settings are optimized for achieving the high MRR. The experiments are designed by using Taguchi L₁₆ orthogonal arrays. The MRR obtained at different experiments are analyzed using statistical tools. It is observed that all the chosen process parameters showed significant influence of on the MRR with contribution of 27.39%, 22.08%, 21.32%, 15.76% and 12.94% by I, I_v, T_off, T_on and W_s, respectively. At optimum settings, the Wire-EDM resulted in MRR of 65.21 mg/min and 62.41 mg/min for samples with 4% and 8% SiC_p. The results also indicated reinforcing SiC_p upto 8% showed marginally low influence on MRR. Microstructural investigation of the cut surface revealed the presence of craters with wave pattern on its surface. The top surface of the crater is featured by the recast layers connecting adjacent craters. Further, the statistical model is developed using linear regression to predict the MRR (R²—73.65%) and its predicting accuracy is verified by the confirmation trials. The statistical model is useful for predicting the MRR for different settings of the process parameters. The optimized settings can be used to improve the machining productivity by increasing the MRR while machining of Al6061-SiC_p (upto 8 wt. %) alloy by wire-EDM industries.