Machine Learning Mechanisms Research Articles

Fatigue life prediction of cold expansion hole using physics-enhanced data-driven method

Cold expansion (CE) serves as a practical surface enhancement to improve the fatigue life of hole structures by improving surface integrity in both macro-scale and micro-scale. Due to the inaccessibility and high cost of experimental measurements, the physical relation between surface integrity and fatigue life are always implicit, serving as the major challenge for accurate life prediction. To address this issue, a novel method is proposed by introducing physical information to traditional data-driven method, where surface integrity enriched by multi-scale simulation is mapped to fatigue life via machine learning (ML) mechanism. As integrated to four typical ML algorithms, the proposed physics-enhanced data-driven method exhibit outstanding capability for accuracy improvement, decreasing the scatter band by amplitude between 27.3 % and 71.4 %. The proposed method offers a promising option for fatigue life prediction on surface treated structures with limited physical information.

Node and relevant data selection in distributed predictive analytics: A query-centric approach

Distributed Predictive Analytics (DPA) refers to constructing predictive models based on data distributed across nodes. DPA reduces the need for data centralization, thus, alleviating concerns about data privacy, decreasing the load on central servers, and minimizing communication overhead. However, data collected by nodes are inherently different; each node can have different distributions, volumes, access patterns, and features space. This heterogeneity hinders the development of accurate models in a distributed fashion. Many state-of-the-art methods adopt random node selection as a straightforward approach. Such method is particularly ineffective when dealing with data and access pattern heterogeneity, as it increases the likelihood of selecting nodes with low-quality or irrelevant data for DPA. Consequently, it is only after training models over randomly selected nodes that the most suitable ones can be identified based on the predictive performance. This results in more time and resource consumption, and increased network load. In this work, holistic knowledge of nodes’ data characteristics and access patterns is crucial. Such knowledge enables the successful selection of a subset of suitable nodes for each DPA task (query) before model training. Our method engages the most suitable nodes by predicting their relevant distributed data and learning predictive models per query. We introduce a novel DPA query-centric mechanism for node and relevant data selection. We contribute with (i) predictive selection mechanisms based on the availability and relevance of data per DPA query and (ii) various distributed machine learning mechanisms that engage the most suitable nodes for model training. We evaluate the efficiency of our mechanism and provide a comparative assessment with other methods found in the literature. Our experiments showcase that our mechanism significantly outperforms other approaches being applicable in DPA.

Enhanced Indoor Positioning System Using Ultra-Wideband Technology and Machine Learning Algorithms for Energy-Efficient Warehouse Management

The following article presents a proprietary real-time localization system using temporal analysis techniques and detection and localization algorithms supported by machine learning mechanisms. It covers both the technological aspects, such as proprietary electronics, and the overall architecture of the system for managing human and fixed assets. Its origins lie in the ever-increasing degree of automation in the management of company processes and the energy optimization associated with reducing the execution time of tasks in an intelligent building supported by in-building navigation. The positioning and tracking of objects in the presented system was realized using ultra-wideband radio tag technology. An exceptional focus has been placed on reducing the energy requirements of the components in order to maximize battery runtime, generate savings in terms of more efficient management of other energy consumers in the building and increase the equipment’s overall lifespan.

Automated Detection and Management of Leaf Diseases in Plants using Image Processing and Machine Learning

This paper presents a system designed to detect and monitor diseases found on the leaves of plants through the aid of image processing and machine learning mechanisms. The system can diagnose the problem from the images it receives from leaves and recommend specific treatment. Common users are able to front-end an image of the leaf through a simple web interface that feeds the images into a central database. In response to an image query, the system uses the GLCM method to feed texture characteristics in and to employ K - means clustering in segmenting disease regions. After this, a Support Vector Machine (SVM) polynomial kernel-based classifier is used for the multi-class classification of the diseases of the leaves. It also has features that entails information on the diseases identified and treatment plans for them, improving disease control plans. Experimental assessments show that the developed system is truly capable of analyzing the peculiarity of diseased leaves and categorizing the diseases with high prediction accuracy, pointing to a promising application of the proposed system in agricultural industry and plant pathology science. Some possible enhancements for the future could be the expansion of more functionalities or creating a mobile app aimed at enhancing the program’s usage. The proposed system will not only help in moving the agricultural industry forward by providing a dependable, easy to use, error-free system for early diagnosis of diseases and taking initial steps in the mitigation process but also result in improved quality and quantity of produce.

A two-layer heuristic for patient sequencing in the operating room theatre considering multiple resource phases

In this paper, we study the surgery scheduling problem in the operating room theatre. The problem considers the sequencing of patients and calculation of their start times with splitting of surgeries into resource phases to facilitate the efficient use of different types of resources. We propose a dedicated two-layer heuristic to compose an operational patient and resource schedule. The first optimisation layer applies an evolutionary heuristic to devise patient schedules while considering the scheduling of the operating surgeons and rooms. This step employs a machine-learning mechanism predicting the feasibility of chromosomes, which improves the algorithm’s efficiency and effectiveness, and relies on novel local search operators to find high-quality solutions. The second layer devises the schedule of the other resources using a decomposition-based heuristic. Computational experiments are conducted to show the performance of the proposed two-layer heuristic and validate its design choices. We benchmark the proposed algorithm with other optimisation procedures and show the contribution of considering multiple resource phases for real-life decision-making.

Machine Learning and Hybrid Model Building Mechanism for Forecasting Agricultural Market Behaviour: A Case Study of Vegetable Crops

A strategic market intelligence mechanism is essential for stakeholders to make well-informed decisions on production, pricing, and marketing strategies; however, the complex behaviour of agricultural markets, coupled with the presence of non-stationarity, non-normality, and non-linearity in the arrivals and prices of perishable agricultural commodities pose challenges for traditional statistical models in modelling and forecasting. This study sought to overcome these challenges by employing machine learning and hybrid models for vegetable crops. Machine learning techniques, known for their flexibility with non-stationary, non-normal, and non-linear data, were showcased in the empirical illustration, highlighting their effectiveness. The trends of arrivals and prices were found to be significantly positive (p<0.01) for tomato and capsicum. Time delay neural network (TDNN) and hybrid models outperformed the seasonal ARIMA models based on lower RMSE and MAPE for the modelling and forecasting. Utilizing the best-fit models, the prices of tomato and capsicum were forecasted to be highest during June 2024 with ?2267 and 2623 per q. This study contributed to the growing body of applications of machine learning in agricultural systems. It will help develop a robust market intelligence mechanism to address uncertainties in agricultural markets.

Python code for modeling ARIMA-LSTM architecture with random forest algorithm

Over conventional statistical models, machine learning mechanisms are establishing themselves as a potential area for modeling and forecasting complex time series. Because it can integrate several forecasting methodologies’ capabilities, hybrid time series models are fundamental in data science. Here, we present a Python script that builds a combined architecture of the ARIMA-LSTM model with random forest technique to generate a high-accuracy prediction. This script is a step-by-step process to create a statistical and then machine learning model through statistical assumption.

Intrusion Detection System

Our project introduces an Integrated Intrusion Detection System (IDS) designed to bolster network and system security through a multi-faceted approach. This comprehensive IDS seamlessly combined Machine Learning, Anomaly Detection, File Scanning, and DDoS Prevention mechanisms to offer robust defense against diverse cyber threats. At the heart of the system lies the Machine Learning component, which continuously adapts to the evolving threat landscape. By analyzing network traffic and system behavior, it identifies both known and emerging threats in real-time, reducing reliance on traditional signature-based detection methods and allowing organizations to proactively stay ahead of cybercriminals. Anomaly Detection constantly monitors network and system activity, comparing it against established baselines. Any deviations from these baselines trigger alerts, facilitating swift responses to unusual activities that may indicate security breaches. File Scanning is another vital component ensuring data integrity and preventing malware infiltration or data exfiltration. It conducts thorough file analysis, checking for suspicious code, behavior, or unauthorized access, and offers continuous monitoring to detect anomalies in real-time. Additionally, our IDS includes Distributed Denial of Service (DDoS) Prevention mechanisms. By detecting and mitigating DDoS attacks, the system ensures the continuous availability of network resources and services even under intense traffic loads. This integrated approach to intrusion detection and prevention leverages Machine Learning, Honeypots, Anomaly Detection, File Scanning, and DDoS Prevention, empowering organizations to safeguard critical assets, maintain data integrity, and ensure network security in today's dynamic and perilous digital landscape. Our IDS solution serves as a valuable addition to the cybersecurity toolkit for organizations seeking comprehensive security against a wide range of threats.

Statistical pathways to low-carbon cities: Analyzing renewable integration, energy-efficient design, and job creation

To address the existing gap in understanding the intricate dynamics of resource management in Cloud Fog Computing (CFC)-driven Smart Grids (SG), this study introduces an innovative adaptive framework integrating Genetic Optimization Algorithm (GOA) and Cuckoo Search Optimization Algorithm (CSOA), aiming to optimize response times and enhance overall efficiency. In the domain of contemporary energy grids, the implementation of intelligent grids (IG) has ushered in a new era of dependable, streamlined, eco-friendly, and economically viable electric services. These grids constitute a fundamental facet of present-day energy resources. Moreover, the advent of cloud and mist computing (CMC) provides on-demand access to computational resources. Overcoming associated challenges, CMC not only delivers advantages like cost-effectiveness, energy conservation, scalability, flexibility, and adaptability but also presents an innovative model for resource management in IG. This study introduces a CMC-driven strategy for managing resources in IG by digitally replicating key grid components. The proposed framework aims to furnish diverse computational services for resource management within IG through a hierarchical arrangement of CMCs. Additionally, this investigation scrutinizes and simulates two optimization approaches: the cuckoo search and grasshopper optimization algorithms. These algorithms operate on an adaptive machine learning mechanism designed to balance the load, and the study meticulously compares their efficacy. These algorithms operate on an adaptive machine learning mechanism designed to balance the load, and the study meticulously compares their efficacy in the context of Renewable Integration, Energy-Efficient Design, and Job Creation.

Valuation of Stocks by Integrating Discounted Cash Flow With Imitation Learning and Guided Policy

The valuation of discounted cash flow (DCF) is one of the most appropriate methods to measure a company’s value, and it is also a fundamental method according to Warren Buffett to value a stock for investment. DCF analysis requires the estimations of the future free cash flow (FCF) and the weighted average cost of capital. However, these factors are often subject to an appraiser’s bias. To obtain a more objective DCF analysis, in this study, we develop a machine learning mechanism: imitation learning, which encompasses a teacher to demonstrate state-action pairs. To facilitate imitation learning, we adopt a guided policy search with the chronological order of a Levy distribution. This distribution can cover the stages of growth, decay, and long fat tail that correspond to a business life cycle. In this way, learning the trajectory of FCF can optimize the fitness between the FCF and the chronological order of a Levy distribution. The fitness achieved allows us to monitor the data by fitting the chronological order for the correct stage. The results show that regarding the Sharpe ratio and precision of DCF valuation, our approach outperforms the popular classification models -random forest and long short-term memory network. Code is available at https://github.com/YuanLongPeng/DCFValuation. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Appraisers own knowledge for valuation of stocks to project FCFs and WACC. The knowledge has a broad spectrum, such as prospect of economic growth and competition in the industry. Threat of substitute products. This study proposed a method to automate the process of valuation by learning FCFs and WACC from data. The result of valuation is reproducible and free of the bias of appraisers.

An integrated energy storage framework with significant energy management and absorption mechanism for machine learning assisted electric vehicle application

Regarding environmental friendliness, low maintenance needs, and statuses as a renewable technology, Hybrid Electric Vehicles (HEV) have become more and more popular around the world. In this, the energy management system is crucial for the effective storage of power and regulation of the energy flow system. As a result, Hybrid Energy Storage Systems (HESS) has increased interest due to their superior capabilities in system performance and battery capacity when compared to solo energy sources. Additionally, the primary problem interaction applications, including such battery electric vehicles, are the energy storage system. Multiple energy storage technologies, including battery packs, flywheels, super-capacitors and fuel cells, are combined into a HESS due to their complementing properties. The goal of this setup is to make renewable energy sources more reliable by storing power generated from intermittent sources or by providing backup energy generation from traditional energy sources. A HESS could be utilized as an alternate energy storage system to help them make up for their lack of power density. HESS needs a smart Energy Management System (EMS) to function properly since it combines the dynamic characteristics of a battery and a SuperCapacitor (SC). The motive of the study is to suggest an actual power management control system to accomplish these objectives. The plan is built using a wavelet transform, deep learning mechanism, and fuzzy logic together. A useful tool for separating the various frequency elements of a load's power requirements to reflect the properties of a battery or supercapacitor is the wavelet transform. It is challenging to immediately apply it in a system, though. Because of this, the traditional optimization-model-based facility energy management system encounters substantial difficulties with online forecast and calculation. To solve this problem, the paper proposes a ML technique dependent on a Long Short-Term Memory (LSTM). The suggested control system structure allows for the separation of the offline and online stages of the LSTM technique. The LSTM is being used to map states (inputs) to decisions (outputs) based on system training during the offline stage. As a result, the supercapacitor receives an online calculation and distribution of the high-frequency power requirement. The SOC of the supercapacitor is kept within the appropriate range via fuzzy logic control. To evaluate the efficacy of the suggested energy management control technique, a 70 V battery with 92 V supercapacitor hybrid energy storage devices for hardware platforms have been created.

Intelligent Event-Triggered Control Supervised by Mini-Batch Machine Learning and Data Compression Mechanism for T-S Fuzzy NCSs Under DoS Attacks

Intelligent Event-Triggered Control Supervised by Mini-Batch Machine Learning and Data Compression Mechanism for T-S Fuzzy NCSs Under DoS Attacks

Generic IoT for Smart Buildings and Field-Level Automation—Challenges, Threats, Approaches, and Solutions

Smart home and building systems are popular solutions that support maintaining comfort and safety and improve energy efficiency in buildings. However, dynamically developing distributed network technologies, in particular the Internet of Things (IoT), are increasingly entering the above-mentioned application areas of building automation, offering new functional possibilities. The result of these processes is the emergence of many different solutions that combine field-level and information and communications technology (ICT) networks in various configurations and architectures. New paradigms are also emerging, such as edge and fog computing, providing support for local monitoring and control networks in the implementation of advanced functions and algorithms, including machine learning and artificial intelligence mechanisms. This paper collects state-of-the-art information in these areas, providing a systematic review of the literature and case studies with an analysis of selected development trends. The author systematized this information in the context of the potential development of building automation systems. Based on the conclusions of this analysis and discussion, a framework for the development of the Generic IoT paradigm in smart home and building applications has been proposed, along with a strengths, weaknesses, opportunities, and threats (SWOT) analysis of its usability. Future works are proposed as well.

Multi-domain, Autonomous Measurement Buoy as an Element of the Water Quality Monitoring and Early Warning System in Rivers and Water Reservoirs

This article presents a novel, innovative, open multi-domain platform for early warning against adverse events in reservoirs and watercourses, which can measure temperature, pH, redox, conductivity, turbidity, chlorophyll and phycocyanin. These parameters are key indicators of cyanobacteria bloom. This platform allows remote and distributed monitoring of important locations on lakes and rivers. The station's design enables the use of both wired sensors directly connected to the station and wireless data collection from locally dispersed measurement points that communicate with the station-buoy. The data aggregation system is open, and the technological solution of the station is universal, which means it can use different sensors for chemical and biological parameters that are required by, for example, the Water Framework Directive, from the market and industry standards. The platform also has built-in machine learning and data analysis mechanisms that can optimise the number of stations needed to achieve the desired level of data acquisition. The sensor dispersion and station autonomy ensure the flexibility and scalability of the measurements.

A Comprehensive Review on Sediment Transport, Flow Dynamics, and Hazards in Steep Channels

The hydrological channel networks of the steep mountains are extensively designated and organized geographic systems and are very complicated. They are composed of granular beds that are uneven and are subjected to fluid forces that fluctuate spatially and temporally. The flow and movement of sediment in these streams are significantly shaped by large rocks such as boulders. However, it is difficult to comprehend these mountain streams because significant information is unavailable regarding these channels as compared to plane bed streams. To address this issue, a critical review of the numerical, computational fluid dynamics, and machine learning mechanisms underlying sediment transport across different flow conditions in steep channels is presented while considering the current and foreseeable conditions for various sediment transport phenomena. The present study emphasized to carry out further analysis on these steep channels using advanced available techniques to get an insight into the morphology of these channels. Furthermore, the hazards associated with steep mountain channels are reviewed as they have a significant impact on infrastructure and habitation in mountainous regions.

Hybrid deep model for predicting anti-cancer drug efficacy in colorectal cancer patients

Cancers are genetically diversified, so anticancer treatments have different levels of efficacy on people due to genetic differences. The main objective of this work is to predict the anticancer drug efficiency for colorectal cancer patients to reduce the mortality rates and provides immune energy for the patients. This paper proposes a novel anti-cancer drug efficacy system in colorectal cancer patients. The input data gene is normalized with the Min–Max normalization technique that normalizes the data in distinct scales. Subsequently, proposes an improved entropy-based feature to evaluate the uncertainty distribution of data, in which it induces weight to overcome the issue of computational complexity. Along with this feature, a correlation-based feature and statistical features are also retrieved. Subsequently, proposes a Recursive Feature Elimination with Hybrid Machine Learning (RFEHML) mechanism for selecting the appropriate feature set by eliminating the recursive features with the aid of hybrid Machine Learning strategies that combine decision tree and logistic regression. Also, the Gini impurity is employed for ranking the feature and selecting the maximum importance score by eliminating the least acquired importance score. Further, proposes a hybrid model for predicting the drug efficiency with the trained feature set. The hybrid model comprises of Long Short-Term Memory (LSTM) and Updated Rectified Linear Unit-Deep Convolutional Neural Network (UReLU-DCNN) model, in which DCNN is modified by updating the activation function at the fully connected layer. Consequently, the learned feature predicts the drug efficacy of anti-cancer in colorectal cancer patients by determining whether the patient is a responder or non-responder of the drug. Finally, the performance of the proposed RFEHML model is compared with other traditional approaches. It is found that the developed method has higher accuracy for each learning percentage, with values of 60LP = 92.48%, 70LP = 94.28%, 80LP = 95.24%, and 90LP = 96.86%, respectively.

Performance and security Evaluation of Ad Hoc Networking Technologies for IoT Environments

A new age of unparalleled connectedness has been ushered in by the fast growth of Internet of Things (IoT) devices, allowing everything from smart homes and industrial automation to healthcare and agriculture. Ad hoc networking technologies play a pivotal role in facilitating communication among IoT devices, providing the flexibility and scalability required to support the diverse and dynamic IoT ecosystem. However, this connectivity comes with significant challenges related to both performance and security. This paper presents a comprehensive study focused on the performance and security evaluation of ad hoc networking technologies in the context of IoT environments. The need for enhancing security in ad hoc networking has seen a significant growth over the last decade. There are several security systems that prioritise the detection of assaults. Various machine learning mechanisms are taken into consideration for the purpose of identifying attacks. However, a significant concern associated with current research endeavours is to the constrained aspects of security and performance. There is still a need to improve the security of ad hoc networking. To accomplish this purpose, hybrid mechanisms have been devised. Advanced machine learning techniques are used to classify attacks such as man-in-the-middle attacks, denial of service attacks, and brute force attacks. In order to improve the precision of decisions and the categorization of assaults in ad hoc networks, the suggested research makes use of the Long Short-Term Memory (LSTM) model.

ACStalk: Design and Implementation of An Access/Entry Control System using an Internet of Things (IoT) Platform

&lt;p&gt;An access/entry control system usually consists of many subsystems. These subsystems have different Application Programming Interfaces (APIs), but they need to be integrated and interacted well. Without a good integrated platform, the communications between subsystems will be very complicated. In addition, except user name and password, Radio Frequency Identification (RFID), and the human&amp;rsquo;s biometrics (e.g., fingerprint and face) are used to identify users. Wireless Local Area Network (WLAN), mobile communications (e.g. 4G/5G) and Bluetooth are adopted as the remote access technologies. In addition, with the COVID-19 pandemic, public health and personal safety are getting more concerns. People are required to wear personal protective equipment (PPE) in some special areas (e.g., barns and factories) to ensure the personal healthy and food&amp;rsquo;s safety. To identify the user and detect whether the PPE is correctly worn, this paper proposes an access/entry control system by using an Internet of Things (IoT) platform. Through the proposed IoT system architecture, different identification mechanisms and communication technologies can be adopted, and the messages can be exchanged between two mechanisms. This paper elaborates the architecture design of the IoT platform and discusses the implementation/deployment issues of the PPE detection by using machine learning mechanisms.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

An ARIMA-LSTM model for predicting volatile agricultural price series with random forest technique

Machine learning mechanism is establishing itself as a promising area for modelling and forecasting complex time series over conventional statistical models. In this article, focus has been made on presenting a machine learning algorithm with special attention to deep learning model in form of a potential alternative to statistical models such as Autoregressive Integrated Moving Average (ARIMA) and ARIMA-Generalised Autoregressive Conditional Heteroscedasticity (GARCH) models. Further, an improved hybrid ARIMA-Long Short-Term Memory (LSTM) model based on the random forest lag selection criterion has been introduced. ARIMA model has been used to estimate the mean effect and the GARCH model is employed with the residuals obtained from the ARIMA model to estimate the volatile behaviour of the series. ARIMA-GARCH models act as superior statistical models over ARIMA models based on the lowest AIC and BIC values. LSTM model is employed on all normalised training data series. After which we built a comparison scenario independently between ARIMA, ARIMA-GARCH, LSTM and ARIMA-LSTM models on forecasting accuracy in terms of the lowest RMSE, MAPE and MASE values. The proposed random forest-based ARIMA-LSTM model proved its superiority over the conventional statistical models with an improvement to the tune of 8–25% for RMSE, 2–28% for MAPE and 2–29% for MASE. The proposed hybrid model has been successfully applied to volatile monthly price indices of pulses namely gram, moong and urad. This piece of work will enrich the literature on machine learning and further intrigue researchers to apply it to various other volatile data sets.

Grey Wolf Optimization for Facial Emotion Recognition: Survey

Human face expression Recognition is one of the most effective forms of social communication. Generally, facial expressions are a simple and obvious way for people to express their feelings and intentions. Typically, the goal of facial expression recognition is to categorize facial expressions into specific classes of expression labels. This paper presents a survey of facial emotion expression classification based on different machine learning and deep learning mechanisms and optimization algorithms. In order to evaluate the basic emotion of a person's face, a technology called facial expression recognition employs a computer as a helper with specific algorithms. Seven basic emotions were represented by facial expressions, including a smile, sadness, anger, disgust, surprise, fear, and a natural expression. In this paper, the focus is on using the Grey Wolf algorithm for selection of the optimal features from feature extraction from input image faces to recognize human facial emotions. In most studies, the FER system was applied to popular datasets such as the JAFEE database and the Cohn-Kanade database.