Advanced Modelling of Soil Organic Carbon Content in Coal Mining Areas Using Integrated Spectral Analysis: A Dengcao Coal Mine Case Study

International Journal of Innovative Science and Research Technology (IJISRT), Journal Year: 2024, Volume and Issue: unknown, P. 2844 - 2853

Published: June 14, 2024

Effective modelling and integrated spectral analysis approaches can advance precision. To develop an forecast of soil organic carbon (SOC), this research investigated a mining coal in Dengcao Coal Mine Area, Zhengzhou. The study utilizes the Lasso Ranger algorithms were utilized band analysis. Four primary models employed during process include Artificial Neural Network (ANN), Support Vector Machine, Random Forest (RF), Partial Least Squares Regression (PLSR). ideal model was chosen. results showed that, contrast to when collection based on algorithm modelling, precision higher it algorithm. ANN had goodness acceptance, developed by RF steadiest consequences. Based results, distinct method is proposed for assortment at earlier stage SOC. be used check particles, or chosen prediction different statistics sets, which appropriate create SOC content Area. This avails position Analysis Advanced Modelling Soil Organic Carbon Content Sources alongside theoretical foundation innovating portable device assessment habitats. might significant changing monitoring environmental areas.

Language: Английский

---

COVID-19 and hospitality 5.0: Redefining hospitality operations

International Journal of Hospitality Management, Journal Year: 2021, Volume and Issue: 94, P. 102869 - 102869

Published: Jan. 23, 2021

Language: Английский

---

The fourth industrial revolution in the food industry—Part I: Industry 4.0 technologies

Critical Reviews in Food Science and Nutrition, Journal Year: 2022, Volume and Issue: 63(23), P. 6547 - 6563

Published: Feb. 3, 2022

Climate change, the growth in world population, high levels of food waste and loss, risk new disease or pandemic outbreaks are examples many challenges that threaten future sustainability security planet urgently need to be addressed. The fourth industrial revolution, Industry 4.0, has been gaining momentum since 2015, being a significant driver for sustainable development successful catalyst tackle critical global challenges. This review paper summarizes most relevant 4.0 technologies including, among others, digital (e.g., artificial intelligence, big data analytics, Internet Things, blockchain) other technological advances smart sensors, robotics, twins, cyber-physical systems). Moreover, insights into trends (such as 3D printed foods) have emerged result revolution will also discussed Part II this work. significantly modified industry led substantial consequences environment, economics, human health. Despite importance each mentioned above, ground-breaking solutions could only emerge by combining simultaneously. Food era characterized challenges, opportunities, reshaped current strategies prospects production consumption patterns, paving way move toward 5.0.

Language: Английский

---

Opportunities of Artificial Intelligence and Machine Learning in the Food Industry

Journal of Food Quality, Journal Year: 2021, Volume and Issue: 2021, P. 1 - 10

Published: July 12, 2021

The food processing and handling industry is the most significant business among various manufacturing industries in entire world that subsidize highest employability. human workforce plays an essential role smooth execution of production packaging products. Due to involvement humans, are failing maintain demand-supply chain also lacking safety. To overcome these issues industries, industrial automation best possible solution. Automation completely based on artificial intelligence (AI) or machine learning (ML) deep (DL) algorithms. By using AI-based system, delivery processes can be efficiently handled enhance operational competence. This article going explain AI applications which recommends a huge amount capital saving with maximizing resource utilization by reducing error. Artificial data science improve quality restaurants, cafes, online chains, hotels, outlets increasing utilizing different fitting algorithms for sales prediction. could significantly packaging, shelf life, combination menu algorithms, safety making more transparent supply management system. With help ML, future smart farming, robotic drones.

Language: Английский

---

Covid-19 vaccine hesitancy: Text mining, sentiment analysis and machine learning on COVID-19 vaccination Twitter dataset

Expert Systems with Applications, Journal Year: 2022, Volume and Issue: 212, P. 118715 - 118715

Published: Sept. 5, 2022

In 2019 there was an outbreak of coronavirus pandemic also known as COVID-19. Many scientists believe that the originated from Wuhan, China, before spreading to other parts globe. To reduce spread disease, decision makers encouraged measures such hand washing, face masking, and social distancing. early 2021, some countries including United States began administering COVID-19 vaccines. Vaccination brought a relief public; it generated lot debates anti-vaccine pro-vaccine groups. The controversy debate surrounding vaccine influenced several people in either accept or reject vaccination. Because data limitations, media data, collected through live streaming public tweets using Application Programming Interface (API) search, is considered viable reliable resource study opinion on Covid-19 hesitancy. Thus, this examines 3 sentiment computation methods (Azure Machine Learning, VADER, TextBlob) analyze Five learning algorithms (Random Forest, Logistics Regression, Decision Tree, LinearSVC, Naïve Bayes) with different combination three vectorization (Doc2Vec, CountVectorizer, TF-IDF) were deployed. Vocabulary normalization threefold; potter stemming, lemmatization, stemming lemmatization. For each vocabulary strategy, we designed, developed, evaluated 42 models. shows hesitancy slowly decreases over time; suggesting gradually feels warm optimistic about Moreover, combining lemmatization increased model performances. Finally, result our experiment TextBlob + TF-IDF LinearSVC has best performance classifying into positive, neutral, negative accuracy, precision, recall F1 score 0.96752, 0.96921, 0.92807 0.94702 respectively. It means achieved when score, classification model. We found out two vectorizations (CountVectorizer accuracy.

Language: Английский

---

Big Data in food safety- A review

Current Opinion in Food Science, Journal Year: 2020, Volume and Issue: 36, P. 24 - 32

Published: Nov. 21, 2020

The massive rise of Big Data generated from smartphones, social media, Internet Things (IoT), and multimedia, has produced an overwhelming flow data in either structured or unstructured format. technologies are being developed implemented the food supply chain that gather analyse these data. Such demand new approaches collection, storage, processing knowledge extraction. In this article, overview recent developments applications safety presented. This review shows use remains its infancy but it is influencing entire chain. analysis used to provide predictive insights several steps chain, support actors taking real time decisions, design monitoring sampling strategies. Lastly, main research challenges require efforts introduced.

Language: Английский

---

Application of machine learning to the monitoring and prediction of food safety: A review

Comprehensive Reviews in Food Science and Food Safety, Journal Year: 2021, Volume and Issue: 21(1), P. 416 - 434

Published: Dec. 14, 2021

Abstract Machine learning (ML) has proven to be a useful technology for data analysis and modeling in wide variety of domains, including food science engineering. The use ML models the monitoring prediction safety is growing recent years. Currently, several studies have reviewed applications on foodborne disease deep food. This article presents literature review predicting safety. paper summarizes categorizes this domain, discusses types used modeling, provides suggestions sources input variables future applications. based three scientific databases: Scopus, CAB Abstracts, IEEE. It includes that were published English period from January 1, 2011 April 2021. Results show most applied Bayesian networks, Neural or Support vector machines. Of various reviewed, all relevant showed high accuracy by validation process. Based applications, identifies avenues applying safety, addition providing variables.

Language: Английский

---

Emerging Applications of Machine Learning in Food Safety

Annual Review of Food Science and Technology, Journal Year: 2021, Volume and Issue: 12(1), P. 513 - 538

Published: Jan. 21, 2021

Food safety continues to threaten public health. Machine learning holds potential in leveraging large, emerging data sets improve the of food supply and mitigate impact incidents. Foodborne pathogen genomes novel streams, including text, transactional, trade data, have seen applications enabled by a machine approach, such as prediction antibiotic resistance, source attribution pathogens, foodborne outbreak detection risk assessment. In this article, we provide gentle introduction context an overview recent developments applications. With many these still their nascence, general domain-specific pitfalls challenges associated with begun be recognized addressed, which are critical prospective use future deployment large models for

Language: Английский

---

Artificial Intelligence and Sensor Innovations: Enhancing Livestock Welfare with a Human-Centric Approach

Human-Centric Intelligent Systems, Journal Year: 2023, Volume and Issue: 4(1), P. 77 - 92

Published: Nov. 22, 2023

Abstract In the wake of rapid advancements in artificial intelligence (AI) and sensor technologies, a new horizon possibilities has emerged across diverse sectors. Livestock farming, domain often sidelined conventional AI discussions, stands at cusp this transformative wave. This paper delves into profound potential innovations reshaping animal welfare livestock with pronounced emphasis on human-centric paradigm. Central to our discourse is symbiotic interplay between cutting-edge technology human expertise. While mechanisms offer real-time, comprehensive, objective insights welfare, it’s farmer’s intrinsic knowledge their environment that should steer these technological strides. We champion notion as an enhancer farmers’ innate capabilities, not substitute. Our manuscript sheds light on: Objective Animal Welfare Indicators: An exhaustive exploration health, behavioral, physiological metrics, underscoring AI’s prowess delivering precise, timely, evaluations. Farmer-Centric Approach: A focus pivotal role farmers adept adoption judicious utilization coupled discussions crafting intuitive, pragmatic, cost-effective solutions tailored farmers' distinct needs. Ethical Social Implications: discerning scrutiny digital metamorphosis encompassing facets like privacy, data safeguarding, responsible deployment, access disparities. Future Pathways: Advocacy for principled design, unambiguous use guidelines, fair access, all echoing fundamental principles computing analytics. essence, furnishes pioneering crossroads technology, ethics. It presents rejuvenated perspective, bridging chasm beneficiaries, resonating seamlessly ethos Human-Centric Intelligent Systems journal. comprehensive analysis thus marks significant stride burgeoning intelligent systems, especially within farming landscape, fostering harmonious coexistence animals, humans.

Language: Английский

---

Making food systems more resilient to food safety risks by including artificial intelligence, big data, and internet of things into food safety early warning and emerging risk identification tools

Comprehensive Reviews in Food Science and Food Safety, Journal Year: 2024, Volume and Issue: 23(1)

Published: Jan. 1, 2024

Abstract To enhance the resilience of food systems to safety risks, it is vitally important for national authorities and international organizations be able identify emerging risks provide early warning signals in a timely manner. This review provides an overview existing experimental applications artificial intelligence (AI), big data, internet things as part risk identification tools methods domain. There ongoing rapid development fed by numerous, real‐time, diverse data with aim risks. The suitability AI support such illustrated two cases which climate change drives emergence namely, harmful algal blooms affecting seafood fungal growth mycotoxin formation crops. Automation machine learning are crucial future real‐time systems. Although these developments increase feasibility effectiveness prospective tools, their implementation may prove challenging, particularly low‐ middle‐income countries due low connectivity availability. It advocated overcome challenges improving capability capacity authorities, well enhancing collaboration private sector organizations.

Language: Английский

---