Input Attributes Research Articles

Design of an intelligent bean cultivation approach using computer vision, IoT and spatio-temporal deep learning structures

Crop health monitoring and weed removal are two crucial elements dictating efficient, productive and resilient cultivation. Due to frequent attacks by pest and pathogens, the crops become diseased resulting in degradation of the quality and quantity of the production. The process of continuous monitoring of crop health is challenging and requires the involvement of information and communication technologies (ICT). The outcome is precision agriculture where the Internet of Things (IoT) and Artificial Intelligence (AI) techniques are vital ingredients. The design of an integrated approach of precision agriculture based on IoT and AI is discussed here which is tailored for real time crop health monitoring and performs various other operations like weed detection, ambient air sensing, watering the vegetation automatically at regular intervals of time, spraying of pesticides etc. The proposed system is a combination of an IoT formed using sensors and devices, image processing and machine learning (ML)/ deep learning (DL) techniques confined to the cultivation of fifteen varieties of beans found in India. The work involves two intelligent learning models configured to capture spatio-temporal attributes of image samples and sensor inputs and for real time discrimination between healthy and diseased bean leaves, detection of weeds growing around the cultivation land and also for process control. The first approach employs a DL structure named EfficientNetB7 along with a Bidirectional Long Short Term Memory (BiLSTM) while the second method adopts a VGG16 with an integrated attention mechanism. Also experiments have been carried out using benchmark ML classifiers like Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Multi-Layer Perceptron (MLP) and Time Delay Neural Network (TDNN) combined with feature extraction techniques. Segmentation methods have been used to separate out the diseased sections of the leaves which are then used as apriori labels for the classifiers to reinforce the previously known details of the bean varieties. Subsequently, the trained networks are tested with bean leaf samples collected from cultivation farms. Results show that our proposed DL models could accurately predict the health state of the bean leaves with less computation time. With an automated approach of bean leaf health discrimination, weed detection and process control, the cost effectiveness of the overall effort is enhanced. Further, the sensor pack also provides precise thresholds at which water sprinkling could be initiated resulting in water conservation.

Improvement Performance of the Random Forest Method on Unbalanced Diabetes Data Classification Using Smote-Tomek Link

Most of the health data contained unbalanced data that affected the performance of the classification method. Unbalanced data causes the classification method to classify the majority data more and ignore the minority class. One of the health data that has unbalanced data is Pima Indian Diabetes. Diabetes is a deadly disease caused by the body's inability to produce enough insulin. Complications of diabetes can cause heart attacks and strokes. Early diagnosis of diabetes is needed to minimize the occurrence of more severe complications. In the diabetes dataset used, there is an imbalanced data between positive and negative diabetes classes. Diabetes negative class data (500 data) is more than diabetes positive class (268), so it can affect the performance of the classification method. Therefore, this study aims to apply the Smote-Tomeklink and Random Forest methods in the classification of diabetes. The research methodology used is the collection of diabetes data obtained from Kaggle, as many as 768 data with eight input attributes and 1 output attribute as a class, pre-processing data is used to balance the dataset with Smote-Tomeklink, classification using the random forest method, and performance evaluation based on accuracy, sensitivity, precision, and F1-score. Based on the tests conducted by dividing data using 10-fold cross-validation, the Random Forest algorithm with Smote-TomekLink gets the highest accuracy, sensitivity, precision, and F1-score compared to Random Forest with Smote. The Random Forest algorithm with Smote-Tomeklink has 86.4% accuracy, 88.2% sensitivity, 82.3% precision, and 85.1% F1-score. Thus, using Smote-Tomeklink can improve the performance of the random forest method based on accuracy, sensitivity, precision, and F1-score.

Accurate Prediction of Coronary Artery Disease Across Various Age Groups Using Machine Learning Algorithms

The healthcare sector is generally “information rich”. It is required to mine all the information for finding hidden patterns and making wise diagnostic decisions. In order to predict the data in databases and for medical research, particularly in the prediction of heart disease, sophisticated data mining methods are used. In this article, prediction systems for heart failure have been examined using a larger number of input attributes. The method analyses 13 variables, including medical words like sex, blood pressure, and cholesterol, to forecast the risk that a patient will develop heart disease. 13 attributes have so far been used for prediction.In this study, smoking and obesity were introduced as two more characteristics. In the existing we have used Naïve bayes, and Neural networking systems which are having less accuracy compared to the proposed system algorithms. On a database of heart diseases, the proposed data mining classification algorithms J48 Decision Trees, Bagging, and Adaboost are examined. Based on accuracy, these techniques’ performances are contrasted. According to our findings, the Adaboost, J48 decision tree and bagging accuracy are 92.1 percent, 91.62 percent, and 90.52 percent, respectively. Our investigation reveals that Adaboost, out of these three classification methods, accurately predicts heart failure.

Locally Specified CPT Soil Classification Based on Machine Learning Techniques

Cone penetration tests (CPTs) can provide highly accurate and detailed information and characteristics relevant to the stiffness, strength, and consolidation of tested geomaterials, but they do not directly recover real soil samples. Thus, when CPT results are applied to soil classification, experience-based classification charts or tables are generally used. However, such charts or tables have the inherent drawback of being derived from the test data applied to each classification method, which promotes their failure to cover the engineering features of soils from other places. This study proposes a machine learning approach using C4.5 decision tree algorithm to develop a locally specified CPT-based soil classification system. The findings demonstrate that a locally specified soil classification scheme can be attained by utilizing a simple and trained decision tree model with appropriate combinations of training data and input attributes. Additionally, it is confirmed that oversampling the minor classes makes the classification accuracy for data with highly unbalanced classes appear more balanced for each class.

Efficient numerical simulation on dielectric barrier discharges at atmospheric pressure integrated by deep neural network

Numerical simulation is an essential way to investigate the discharge behaviors of atmospheric low-temperature plasmas (LTPs). In this study, a deep neural network (DNN) with multiple hidden layers is constructed to surrogate the fluid model to investigate the discharge characteristics of atmospheric helium dielectric barrier discharges (DBDs) with very high computational efficiency, working as an example to show the ability and validity of DNN to explore LTPs. The DNN is trained by the well-formed training datasets obtained from a verified fluid model, and a designed loss function coupled in the DNN program is continuously optimized to achieve a better prediction performance. The predicted data show that the essential discharge characteristics of atmospheric DBDs such as the discharge current waveforms, spatial profiles of charged particles, and electric field can be yielded by the well-trained DNN program with great accuracy only in several seconds, and the predicted evolutionary discharge trends are consistent with the previous simulations and experimental observations. Additionally, the constructed DNN shows good generalization performance for multiple input attributes, which indicates a great potential promise for vastly extending the range of discharge parameters. This study provides a useful paradigm for future explorations of machine learning-based methods in the field of atmospheric LTP simulation without high-cost calculation.

From perception to behavior: The neural circuits underlying prey hunting in larval zebrafish.

A key challenge for neural systems is to extract relevant information from the environment and make appropriate behavioral responses. The larval zebrafish offers an exciting opportunity for studying these sensing processes and sensory-motor transformations. Prey hunting is an instinctual behavior of zebrafish that requires the brain to extract and combine different attributes of the sensory input and form appropriate motor outputs. Due to its small size and transparency the larval zebrafish brain allows optical recording of whole-brain activity to reveal the neural mechanisms involved in prey hunting and capture. In this review we discuss how the larval zebrafish brain processes visual information to identify and locate prey, the neural circuits governing the generation of motor commands in response to prey, how hunting behavior can be modulated by internal states and experience, and some outstanding questions for the field.

Perbandingan Metoda K-NN, Random Forest dan 1D CNN untuk Mengklasifikasi Data EEG Eye State

The use of machine learning / machine learning methods is very important in developing identification of the status of the human eye, especially in terms of processing Electroencephalogram (EEG) signals to identify eye status. In previous research the method used can be a combination method between supervised learning and unsupervised learning, or a single method using supervised learning. In this study, the EEG Eye State classification uses a single method with supervised learning, namely using the following methods: K-nearest neghbors (k-NN), random forest, and 1D Convolutional Neural Networks (1D CNNs). The performance of the three classifier methods is measured using four measures, namely: accuracy, recall, precision, and F1-Score. From the experimental results it was found that the k-NN method has the best performance compared to the other two methods in terms of the four measures used, where the value of each measure is: accuracy = 82.30%; recall=82.30%; precision= 82.36%; and F1-Score=82.30%. K-NN is more suitable for classifying EEG Eye State than the other two methods, because all input attributes are from the dataset. has a data type of real numbers.

Cervical Cancer Diagnostics Using Machine Learning Algorithms and Class Balancing Techniques

Objectives: Cervical cancer is present in most cases of squamous cell carcinoma. In most cases, it is the result of an infection with human papillomavirus or adenocarcinoma. This type of cancer is the third most common cancer of the female reproductive organs. The risk groups for cervical cancer are mostly younger women who frequently change partners, have early sexual intercourse, are infected with human papillomavirus (HPV), and who are nicotine addicts. In most cases, the cancer is asymptomatic until it has progressed to the later stages. Cervical cancer screening rates are low, especially in developing countries and in some minority groups. Due to these facts, the introduction of a tentative cervical cancer screening based on a questionnaire can enable more diagnoses of cervical cancer in the initial stages of the disease. Methods: In this research, publicly available cervical cancer data collected on 859 female patients are used. Each sample consists of 36 input attributes and four different outputs Hinselmann, Schiller, cytology, and biopsy. Due to the significant unbalance of the data set, class balancing techniques were used, and these are the Synthetic Minority Oversampling Technique, the ADAptive SYNthetic algorithm (ADASYN), SMOTEEN, random oversampling, and SMOTETOMEK. To obtain the mentioned target outputs, multiple artificial intelligence (AI) and machine learning (ML) methods are proposed. In this research, multiple classification algorithms such as logistic regression, multilayer perceptron (MLP), support vector machine (SVM), K-nearest neighbors (KNN), and several naive Bayes methods were used. Results: From the achieved results, it can be seen that the highest performances were achieved if MLP and KNN are used in combination with Random oversampling, SMOTEEN, and SMOTETOMEK. Such an approach has resulted in mean area under the receiver operating characteristic curve (AUC¯) and mean Matthew’s correlation coefficient (MCC¯) scores of higher than 0.95, regardless of which diagnostic method was used for output vector construction. Conclusions: According to the presented results, it can be concluded that there is a possibility for the utilization of artificial intelligence (AI) and machine learning (ML) techniques for the development of a tentative cervical cancer screening method, which is based on a questionnaire and an AI-based algorithm. Furthermore, it can be concluded that by using class balancing techniques, a certain performance boost can be achieved.

Importance analysis of decision making factors based on fuzzy decision trees

Classification is one important and commonly used Machine Learning technique. The classification effectiveness can be influenced by different factors and initial data used for the classifier induction and in the process of classification, including. The quality of measurements of the input attributes of new samples for the classification can affect the accuracy and reliability of the classification result. At the same time, the degree of influence of different attributes is not the same. There are some attributes that are most important for the classification because have a greater influence on the classification result than others. A new method for the determination of the most important attributes is proposed. This method is developed based on the approach of Importance Analysis, which is widely used in reliability engineering. The proposed method investigates the sensitivity of the classification from the input attributes and indicates the attributes for which changes have the most impact on the classification result. The attribute’s importance is evaluated by the special index which is known as structural importance in reliability engineering. This method application is illustrated in the paper by Fuzzy Decision Tree, but it can be used for any other classifiers induction. The use of a fuzzy classifier allows for taking into consideration of possible uncertainty of initial data.

Evaluation of principal component analysis for seismic attribute selection and self-organizing maps for seismic facies discrimination in the presence of gas hydrates

Mapping the lateral distribution and thickness of gas hydrates and associated free gas using even the best quality seismic surveys can be quite challenging. As the stability of gas hydrates within the Gas Hydrate Stability Zone (GHSZ) is controlled by temperature and pressure, and because their impedance can be different than those of the sedimentary matrix in which they occur, we often are able to identify a bottom simulating reflector (BSR) at the base of the GHSZ cutting across stratigraphic reflectors. However, when the stratigraphic reflectors are parallel to the ocean bottom, the BSR is easily confounded with a strong stratigraphic reflector. Seismic attributes and machine learning (ML) applied to facies analysis have been successful in quantitatively mapping patterns in seismic data. However, selecting an optimal combination of seismic attributes and training data to perform a robust seismic facies classification is highly dependent on the interpreter's skills. In this study, we apply principal component analysis (PCA) to select a suite of seismic attributes to be used as input for self-organizing maps (SOM) to identify BSRs and surrounding facies in a seismic volume located in the Blake Ridge, offshore South Carolina, USA. As PCA is based on mathematically variability unrelated to geology, we evaluate PCA as an attribute selection technique under three different training data selection strategies, finding that combining seismic attributes such as total energy, coherence, GLCM entropy, and peak magnitude as input for SOM represents an effective method to detect BSRs. Additionally, we note that using a smaller subset of samples representing the target four seismic facies when applying PCA to select input attributes for SOM offers optimal BSRs identification.

Efficient decision tree training with new data structure for secure multi-party computation

We propose a secure multi-party computation (MPC) protocol that constructs a secret-shared decision tree for a given secret-shared dataset. The previous MPC-based decision tree training protocol (Abspoel et al. 2021) requires $O(2^hmn log n)$ comparisons, being exponential in the tree height $h$ and with $n$ and $m$ being the number of rows and that of attributes in the dataset, respectively. The cause of the exponential number of comparisons in $h$ is that the decision tree training algorithm is based on the divide-and-conquer paradigm, where rows are padded after each split in order to hide the number of rows in the dataset. We resolve this issue via secure data structure that enables us to compute an aggregate value for every group while hiding the grouping information. By using this data structure, we can train a decision tree without padding to rows while hiding the size of the intermediate data. We specifically describes a decision tree training protocol that requires only $O(hmn log n)$ comparisons when the input attributes are continuous and the output attribute is binary. Note that the order is now linear in the tree height $h$. To demonstrate the practicality of our protocol, we implement it in an MPC framework based on a three-party secret sharing scheme. Our implementation results show that our protocol trains a decision tree with a height of 4 in 404 seconds for a dataset of $2^{20}$ rows and 11 attributes.

A New Distributed Echo State Network Integrated With an Auto-Encoder for Dynamic Soft Sensing

As dynamic industrial processes become increasingly complicated, it tends to be difficult to develop accurate soft sensors. Echo state networks (ESNs) as dynamic neural network (NN) models have been broadly used in developing dynamic soft sensors. However, when facing high-dimensional data, the dimension disaster problem might occur in the input space of ESNs. Furthermore, in ESNs, the number of reservoir nodes is large, causing collinearity between the reservoir outputs. To solve these problems, in this article, a new distributed ESN model integrated with auto-encoder (AE-DESNm) is proposed. In particular, AE-DESNm has distributed and independent input subnets. The dimensionality of each input subnet has been reduced, eliminating the dimension disaster problem. To obtain the distributed and independent input subnets of AE-DESNm, the first integer neighbor clustering hierarchy (FINCH) algorithm is used to cluster the input attributes of high-dimensional data. Each cluster corresponds to one input subnet. In addition, seeking to handle the collinearity issue in the reservoir outputs, auto-encoder (AE) is used to extract features from the reservoir outputs. Finally, the extracted features are modeled by an extreme learning machine (ELM) to estimate key variables. To verify the performance of AE-DESNm, a numerical example and a dataset from one real industrial process named purified terephthalic acid (PTA) production are used. Compared with other methods, the experimental results show that the proposed AE-DESNm can achieve much higher accuracy in soft sensor modeling for dynamic industrial processes.

A WSN Node Fault Diagnosis Model Based on BRB with Self-Adaptive Quality Factor

Wireless sensor networks (WSNs) operate in complex and harsh environments; thus, node faults are inevitable. Therefore, fault diagnosis of the WSNs node is essential. Affected by the harsh working environment of WSNs and wireless data transmission, the data collected by WSNs contain noisy data, leading to unreliable data among the data features extracted during fault diagnosis. To reduce the influence of unreliable data features on fault diagnosis accuracy, this paper proposes a belief rule base (BRB) with a self-adaptive quality factor (BRB-SAQF) fault diagnosis model. First, the data features required for WSN node fault diagnosis are extracted. Second, the quality factors of input attributes are introduced and calculated. Third, the model inference process with an attribute quality factor is designed. Fourth, the projection covariance matrix adaptation evolution strategy (P-CMA-ES) algorithm is used to optimize the model’s initial parameters. Finally, the effectiveness of the proposed model is verified by comparing the commonly used fault diagnosis methods for WSN nodes with the BRB method considering static attribute reliability (BRB-Sr). The experimental results show that BRB-SAQF can reduce the influence of unreliable data features. The self-adaptive quality factor calculation method is more reasonable and accurate than the static attribute reliability method.

Attribute-relevant distributed variational autoencoder integrated with LSTM for dynamic industrial soft sensing

Due to the complicated features of process data in terms of high dimension, nonlinearity and coupling, it tends to be a grand challenge to extract important features from complicated process for predicting quality variables using a reliable soft sensor model. Variational Autoencoder (VAE), one of the unsupervised deep learning methods, has been widely used for Gaussian-restricted feature extraction. Considering that the high-dimensional process variables may have different impacts on the predicted quality variable and process variables effect the prediction accuracy, a novel attribute-relevant distributed variational autoencoder (AR-DVAE) is first proposed to effectively extract features from input variables with different correlations. In AR-DVAE, by performing correlation analysis between the input variables and the quality variable, a distributed structure with two encoder subnets is constructed. In each encoder subnet, the input attributes have the same correlation with the output quality variable. As a consequence, the proposed AR-DVAE can extract features with dual channels. Next, a supervised regressor based on the long short-term memory machine shortened to LSTM is utilized for developing soft sensing between the extracted features and the quality variable. Case studies on two actual industrial processes are carried out to confirm the high accuracy of the presented AR-DVAE integrated with the LSTM soft sensing model.

Heart disease prediction using scaled conjugate gradient backpropagation of artificial neural network

Heart disease is a deadly disease in human life. The mortality rate from any disease is the highest in the world. Therefore, before reaching the final stage of this heart disease, all precautionary measures must be taken. For this reason without the help of any kind of traditional methods, if we can scientifically diagnose heart disease at an early stage through various decision support systems, then surely death rate of this disease will decrease in the whole world. Many researchers investigate the diagnosis of heart disease by creating various intelligent medical decision support systems. Artificial neural network concepts represent the highest predictive accuracy over medical data compared to other decision support systems. In this paper, we propose a better prediction method for the existence of heart disease through the scaled conjugate gradient backpropagation of artificial neural networks using K-fold cross-validation. For cardiac datasets, the University of California Irvine (UCI) Machine Learning Repository and IEEE data port have been used. For Cleveland processed heart dataset, the proposed system uses 13 input attributes and provides minimum 63.3803% and maximum 100% accurate results; similarly, for Cleveland Hungarian Statlog heart dataset, the proposed system uses 11 input attributes and provides minimum 88.4754% and maximum 100% accurate results by estimating the presence and absence of heart disease during testing.

Artificial Neural Network for Fault Diagnosis of Solar Photovoltaic Systems: A Survey

Solar energy is one of the most important renewable energy sources. Photovoltaic (PV) systems, as the most crucial conversion medium for solar energy, have been widely used in recent decades. For PV systems, faults that occur during operation need to be diagnosed and dealt with in a timely manner to ensure the reliability and efficiency of energy conversion. Therefore, an effective fault diagnosis method is essential. Artificial neural networks, a pivotal technique of artificial intelligence, have been developed and applied in many fields including the fault diagnosis of PV systems, due to their strong self-learning ability, good generalization performance, and high fault tolerance. This study reviews the recent research progress of ANN in PV system fault diagnosis. Different widely used ANN models, including MLP, PNN, RBF, CNN, and SAE, are discussed. Moreover, the input attributes of ANN models, the types of faults, and the diagnostic performance of ANN models are surveyed. Finally, the main challenges and development trends of ANN applied to the fault diagnosis of PV systems are outlined. This work can be used as a reference to study the application of ANN in the field of PV system fault diagnosis.

Improving variant prioritization in exome analysis by entropy-weighted ensemble of multiple tools.

Variant prioritization is a crucial step in the analysis of exome and genome sequencing. Multiple phenotype-driven tools have been developed to automate the variant prioritization process, but the efficacy of these tools in clinical setting with fuzzy phenotypic information and whether ensemble of these tools could outperform single algorithm remains to be assessed. A large rare disease cohort with heterogeneous phenotypic information, including a primary cohort of 1614 patients and a replication cohort of 1904 patients referred to exome sequencing, were recruited to assess the efficacy of variant prioritization and their ensemble. Three freely available tools-Exomiser, Xrare, and DeepPVP-and their ensemble were evaluated. The performance of all three tools was influenced by the attributes of phenotypic input. When combining these three tools by weighted-sum entropy method (EWE3), the ensemble outperformed any single algorithm, achieving a rate of 78% diagnostic variants in top 3 (13% improvement over current best performer, compared to Exomiser: 63%, Xrare: 65%, and DeepPVP: 51%), 88% in top 10 and 96% in top 30. The results were replicated in another independent cohort. Our study supports using entropy-weighted ensemble of multiple tools to improve variant prioritization and accelerate molecular diagnosis in exome/genome sequencing.

High-Throughput Non-Binary LDPC Decoder Architecture Using Parallel EMS Algorithm

Providing superior algorithm-level performance, the non-binary low-density parity-check (NB-LDPC) code is now expected to be one of the next-generation error-correction codes. However, it is hard to implement a high-throughput NB-LDPC decoder in practice due to its impractical processing complexity and the excessively long decoding time. Based on the previous extended min-sum (EMS) approach, in this work, we introduce the parallel EMS (pEMS) decoding algorithm that reduces the processing latency of each iteration by managing multiple message entries at a time. The previous two-phase node-level operation is modified to promote the proposed parallel processing without performance degradation, where the delay overheads are minimized by carefully optimizing the internal sorters with input attributes. In addition, the data accessing sequence is precisely adjusted to reduce the number of waiting cycles, further increasing the overall processing efficiency. Implemented in a 22-nm FinFET technology, as a result, the prototype two-parallel decoder for (160, 80) NB-LDPC codes operates at the speed of 950 MHz, achieving the decoding throughput of more than 7 Gb/s, which is 3.2 times faster than the state-of-the-art design.

Next-generation antivirus endowed with web-server Sandbox applied to audit fileless attack

Almost all malwares running on web-server are php codes. Then, the present paper creates a next generation antivirus (NGAV) expert in auditing threats web-based, specifically from php files, in real time. In our methodology, the malicious behaviors, of the personal computer, serve as input attributes of the statistical learning machines. In all, our dynamic feature extraction monitors 11,777 behaviors that the web fileless attack can do when launched directly from a malicious web-server to a listening service in a personal computer. Our NGAV achieves an average 99.95% accuracy in the distinction between benign and malware web scripts. Distinct initial conditions and kernels of neural networks classifiers are investigated in order to maximize the accuracy of our NGAV. Our NGAV can supply the limitations of the commercial antiviruses as for the detection of Web fileless attack. In opposition of analysis of individual events, our engine employs authorial Web-server Sandbox, machine learning, and artificial intelligence in order to identify malicious Web-sites.

Modelling monthly pan evaporation utilising Random Forest and deep learning algorithms

Evaporation is the primary aspect causing water loss in the hydrological cycle; therefore, water loss must be precisely measured. Evaporation is an intricate nonlinear process occurring as a result of several climatic aspects. The purpose of this research is to assess the feasibility of using Random Forest (RF) and two deep learning techniques, namely convolutional neural network (CNN), and deep neural network (DNN) to accurately estimate monthly pan evaporation rates. Month-based weather data gathered from four Malaysian weather stations during the 2000–2019 timeframe was used to train and evaluate the models. Several input attributes (predictor variables) were investigated to select the most suitable variables for machine learning models. Every approach was tested with several models, each with a different set of model aspects and input parameter combinations. The formulated ML approaches were benchmarked against two commonly used empirical methods: Stephens & Stewart and Thornthwaite. Model outcomes were assessed using standard statistical measures to determine their effectiveness in predicting evaporation. The results indicated that the three ML models developed in the study performed better than empirical models and could significantly improve the precision of monthly Ep estimates even with the identical input sets. The performance assessment metrics also show that the formulated CNN approach was acceptable for modelling monthly water loss due to evaporation with a higher degree of accuracy than other ML frameworks explored in this study. In addition, the CNN framework outperformed other AI techniques evaluated for the same areas using identical data inputs. The investigation’s findings in relation to the various performance criteria show that the proposed CNN model is capable of capturing the highly non-linearity of evaporation and could be regarded as an effective tool to predict evaporation.