Diagnosis of Oral Squamous Cell Carcinoma Using Deep Neural Networks and Binary Particle Swarm Optimization on Histopathological Images: An AIoMT Approach.

Overall prediction of oral cavity squamous cell carcinoma (OCSCC) remains inadequate, as more than half of patients with oral cavity cancer are detected at later stages. It is generally accepted that the differential diagnosis of OCSCC is usually difficult and requires expertise and experience. Diagnosis from biopsy tissue is a complex process, and it is slow, costly, and prone to human error. To overcome these problems, a computer-aided diagnosis (CAD) approach was proposed in this work. A dataset comprising two categories, normal epithelium of the oral cavity (NEOR) and squamous cell carcinoma of the oral cavity (OSCC), was used. Feature extraction was performed from this dataset using four deep learning (DL) models (VGG16, AlexNet, ResNet50, and Inception V3) to realize artificial intelligence of medial things (AIoMT). Binary Particle Swarm Optimization (BPSO) was used to select the best features. The effects of Reinhard stain normalization on performance were also investigated. After the best features were extracted and selected, they were classified using the XGBoost. The best classification accuracy of 96.3% was obtained when using Inception V3 with BPSO. This approach significantly contributes to improving the diagnostic efficiency of OCSCC patients using histopathological images while reducing diagnostic costs.

Time-Aware Missing Healthcare Data Prediction Based on ARIMA Model.

Healthcare uses state-of-the-art technologies (such as wearable devices, blood glucose meters, electrocardiographs), which results in the generation of large amounts of data. Healthcare data is essential in patient management and plays a critical role in transforming healthcare services, medical scheme design, and scientific research. Missing data is a challenging problem in healthcare due to system failure and untimely filing, resulting in inaccurate diagnosis treatment anomalies. Therefore, there is a need to accurately predict and impute missing data as only complete data could provide a scientific and comprehensive basis for patients, doctors, and researchers. However, traditional approaches in this paradigm often neglect the effect of the time factor on forecasting results. This paper proposes a time-aware missing healthcare data prediction approach based on the autoregressive integrated moving average (ARIMA) model. We combine a truncated singular value decomposition (SVD) with the ARIMA model to improve the prediction efficiency of the ARIMA model and remove data redundancy and noise. Through the improved ARIMA model, our proposed approach (named MHDP SVD_ARIMA) can capture underlying pattern of healthcare data changes with time and accurately predict missing data. The experiments conducted on the WISDM dataset show that MHDP SVD_ARIMA approach is effective and efficient in predicting missing healthcare data.

Control System Development and Implementation of a CNC Laser Engraver for Environmental Use with Remote Imaging.

This article is aimed at studying the features of the control systems development for a small-sized Computer Numerical Control (CNC) portative laser engraver. The CNC is implemented in mobile maintenance and repair platforms for remote sensing of the environment where the wild environment may not allow us to access the animals and places. The proposed work in this paper is based on recent research, which shows that applying the automated CNC speeds up the processes of repair, modernizes the equipment size, and significantly reduces the economic costs; accordingly, the authors developed a block diagram of a portable CNC laser engraver. The choice of the hardware was also made, taking into account the possibility of quick replacement in the field, which reduces the repair time and the cost of the developed layout. A control system based on the selected modules was synthesized, and a stability check was carried out using MatLab tools. To check the correctness of the developed control system, the authors developed and assembled an experimental layout to illustrate the results of engraving on such a layout. Finally, the stability and sensitivity of the proposed system have been obtained and proved that the system works in a comfortable zone of stability. The obtained results show that the proposed CNC laser engraver has achieved the expected improvements (high speed, small size, short production and repairing time, minimum human influence factor, and achieving a better outcome).

Deep learning-based microarray cancer classification and ensemble gene selection approach.

Malignancies and diseases of various genetic origins can be diagnosed and classified with microarray data. There are many obstacles to overcome due to the large size of the gene and the small number of samples in the microarray. A combination strategy for gene expression in a variety of diseases is described in this paper, consisting of two steps: identifying the most effective genes via soft ensembling and classifying them with a novel deep neural network. The feature selection approach combines three strategies to select wrapper genes and rank them according to the k-nearest neighbour algorithm, resulting in a very generalisable model with low error levels. Using soft ensembling, the most effective subsets of genes were identified from three microarray datasets of diffuse large cell lymphoma, leukaemia, and prostate cancer. A stacked deep neural network was used to classify all three datasets, achieving an average accuracy of 97.51%, 99.6%, and 96.34%, respectively. In addition, two previously unreported datasets from small, round blue cell tumors (SRBCTs)and multiple sclerosis-related brain tissue lesions were examined to show the generalisability of the model method.

RST-DE: Rough Sets-Based New Differential Evolution Algorithm for Scalable Big Data Feature Selection in Distributed Computing Platforms.

In data analysis, data scientists usually focus on the size of data instead of features selection. Owing to the extreme growth of internet resources data are growing exponentially with more features, which leads to big data dimensionality problems. The high volume of features contains much of redundant data, which may affect the feature classification in terms of accuracy. In the current scenario, feature selection attracts the research community to identify and to remove irrelevant features with more scalability and accuracy. To accommodate this, in this research study, we present a novel feature selection framework that is implemented on Hadoop and Apache Spark platform. In contrast, the proposed model also includes rough sets and differential evolution (DE) algorithm, where rough sets are used to find the minimum features, but rough sets do not consider the degree of overlying in the data. Therefore, DE algorithm is used to find the most optimal features. The proposed model is studied with Random Forest and Naive Bayes classifiers on five well-known data sets and compared with existing feature selection models presented in the literature. The results show that the proposed model performs well in terms of scalability and accuracy.

Towards Energy-Efficient and Delay-Optimized Opportunistic Routing in Underwater Acoustic Sensor Networks for IoUT Platforms: An Overview and New Suggestions.

In underwater acoustic sensor networks (UASNs), the reliable transfer of data from the source nodes located underwater to the destination nodes at the surface through the network of intermediate nodes is a significant challenge due to various unique characteristics of UASN such as continuous mobility of sensor nodes, increased propagation delay, restriction in energy, and heightened interference. Recently, the location-based opportunistic routing protocols seem to show potential by providing commendable quality of service (QoS) in the underwater environment. This study initially reviews all the latest location-based opportunistic routing protocols proposed for UASNs and discusses its possible limitations and challenges. Most of the existing works focus either on improving the QoS or on energy efficiency, and the few hybrid protocols that focus on both parameters are too complex with increased overhead and lack techniques to overcome communication voids. Further, this study proposes and discusses an easy-to-implement energy-efficient location-based opportunistic routing protocol (EELORP) that can work efficiently for various applications of UASN-assisted Internet of Underwater Things (IoUTs) platforms with reduced delay. We simulate the protocol in Aqua-Sim, and the results obtained show better performance than existing protocols in terms of QoS and energy efficiency.

Big Data-Enabled Analysis of DRGs-Based Payment on Stroke Patients in Jiaozuo, China.

Stroke is the first leading cause of mortality in China with annual 2 million deaths. According to the National Health Commission of the People's Republic of China, the annual in-hospital costs for the stroke patients in China reach ¥20.71 billion. Moreover, multivariate stepwise linear regression is a prevalent big data analysis tool employing the statistical significance to determine the explanatory variables. In light of this fact, this paper aims to analyze the pertinent influence factors of diagnosis related groups- (DRGs-) based stroke patients on the in-hospital costs in Jiaozuo city of Henan province, China, to provide the theoretical guidance for medical payment and medical resource allocation in Jiaozuo city of Henan province, China. All medical data records of 3,590 stroke patients were from the First Affiliated Hospital of Henan Polytechnic University between 1 January 2019 and 31 December 2019, which is a Class A tertiary comprehensive hospital in Jiaozuo city. By using the classical statistical and multivariate linear regression analysis of big data related algorithms, this study is conducted to investigate the influence factors of the stroke patients on in-hospital costs, such as age, gender, length of stay (LoS), and outcomes. The essential findings of this paper are shown as follows: (1) age, LoS, and outcomes have significant effects on the in-hospital costs of stroke patients; (2) gender is not a statistically significant influence factor on the in-hospital costs of the stroke patients; (3) DRGs classification of the stroke patients manifests not only a reduced mean LoS but also a peculiar shape of the distribution of LoS.

Determination of the optimal location for constructing solar photovoltaic farms based on multi-criteria decision system and Dempster-Shafer theory.

Considering environmental concerns regarding air pollution which is induced by burning fossil fuels to generate electrical power, utilizing solar energy as a green and sustainable energy source is of great interest. This study proposes a novel framework to determine the optimal location for constructing solar photovoltaic (PV) farms. To locate the suitable areas for PV farms, firstly, a fuzzy-based method is utilized to homogenize the input parameters, thereafter, the analytical hierarchy process (AHP) and Dempster-Shafer (DS) methods are independently used. In the AHP method, the proper weight for each input parameter is generated utilizing a pairwise comparison matrix. However, the DS method identifies output in different confident levels. Finally, southeast of Fars province in Iran as a region with high sunny hours in the year is selected, and the applicability of proposed methods is examined. The results show that 32% of the case study is located at high and good suitability classes in the fuzzy_AHP method. However, it is 18.56%, 16.70%, 16.32% according to 95%, 99% and 99.5% confident levels in the fuzzy_DS method, respectively. Comparisons of the fuzzy_AHP and fuzzy_DS methods at 20 points with various solar radiation intensities and the number of dusty days parameters indicate that the fuzzy_DS method can more reliably determine the optimal PV farm locations. Additionally, as the fuzzy_DS method determines the optimal locations with different confident levels, this method can benefit decision-makers to determine the risks associated with selecting a specific site for constructing solar PV farms.

Using adaptive neuro-fuzzy inference system and multiple linear regression to estimate orange taste.

In this research, some characteristic qualities of orange fruits such as vitamin C and acid content; weight; fruit and skin diameter; and red (R), green (G), and blue (B) values of the RGB color model for 70 samples were used to predict the taste of orange grown in Darab, southeast of Fars Province, Iran, by multiple linear regression (MLR) and adaptive neuro-fuzzy inference system (ANFIS). To use MLR, firstly the most important input data were selected, and then, the best model to predict the taste of orange was applied. In this research, methodology of ANFIS consisted of selection of dependent orange taste, fuzzification, fuzzy inference rule, membership function, and defuzzification process. The predictive capability of these models was evaluated by various descriptive statistical indicators such as mean square error (MSE) and determination coefficient (R 2). The results showed that the prediction performance of the MLR model has a strong significant relationship between orange taste and vitamin C (0.897**), red color (0.901**), and blue color (0.713*). Also, the results of ANFIS model showed that with low error for train and check data increased the most accuracy for prediction of orange taste. Moreover, the results indicated that the success rate of taste determination for orange is higher by using ANFIS compared to the MLR. This research was to provide valuable information for orange taste.