28725 research outputs found
Sort by
Reinforcement Learning Algorithm for Optimising Durian Irrigation Systems: Maximising Growth and Water Efficiency
Get PDFThis study presents a Reinforcement Learning-based algorithm designed to optimise irrigation for Durio Zibethinus (i.e., durian) trees, aiming to maximise tree growth and reduce water usage. Traditional irrigation methods, as well as current machine learning models, often focus only on soil moisture and weather data, neglecting critical factors like actual tree growth. This study proposed a reinforcement learning irrigation (RL-Irr) algorithm incorporating tree growth stages, soil moisture, and weather conditions to determine precise irrigation needs. The algorithm was developed by calibrating the AQUACROP model using data from actual durian plantations where rain-fed irrigation (rain-fed) was practised. Daily irrigation volumes were calculated based on real-time soil moisture, weather forecasts, and weekly tree growth measurements. The reinforcement learning method was used to optimise irrigation schedules, with rewards based on soil moisture, tree growth, rainfall, and weather conditions. The algorithm was tested using AQUACROP simulations and compared against soil moisture balance irrigation (SMB-Irr) and rain-fed. The results showed that the RL-Irr reduced water use by up to 75 percent while maintaining tree growth. These findings suggest the algorithm could significantly improve water efficiency in durian farming, though real-world applications should consider potential model limitation
Automatic Negation Detection for Semantic Analysis in Arabic Hotel Reviews Through Lexical and Structural Features: A Supervised Classification
Get PDFOne significant challenge in sentiment analysis is the presence of negation, which reverses the meanings of sentences, transforming positive statements into negative ones and impacting the sentiment conveyed in the text. This issue is particularly pronounced in Arabic, a language known for its complex morphology. Detecting negation is crucial for enhancing sentiment analysis performance and various natural language processing applications. This paper presents an approach for automatically detecting negation in user-generated Arabic hotel reviews through lexical and structural features. It comprises several stages: data collection, text pre-processing, feature extraction, supervised learning classification, and evaluation. The study employed multiple supervised classification techniques, including naïve Bayes, random forest, logistic regression, support vector machines, and deep learning, to analyse lexical and structural features extracted from the dataset. The results of the experiments yielded promising outcomes, demonstrating the feasibility of the approach for practical applications. The classifiers exhibited highly comparable performance in identifying negation, with only marginal deviations in their performance metrics. Notably, the deep learning classifier consistently emerged as the top performer, achieving an exceptionally high overall accuracy rate of 99.24 percent, surpassing established benchmarks in Arabic text processing and underscoring its potential for practical applications. These findings hold significant implications for advancing Arabic text processing, particularly in sentiment analysis and related NLP tasks. The high accuracy of 99.24 percent achieved by the deep learning classifier highlights its robustness in accurately detecting negation, a critical challenge in sentiment analysis. This classifier performance demonstrates the potential to be integrated into real-world applications, such as automated review systems and opinion mining tools, where accurate sentiment interpretation is essentia
Unveiling the Determinant Factors Effecting the Willingness to Share Waqf Information among Malaysians
No full textThis study aimed to evaluate the determinant factors of willingness to share the waqf information among Malaysian. The study investigates the impact of trust, reciprocity, power, life satisfaction and commitment as independent factors on the willingness of waqf stakeholders in Malaysia to share information. Design/methodology/approach: This study adopts a quantitative research approach, utilising the information sharing theory. The analysis employs the SPSS software to analyse the demographic factor for descriptive analysis and partial least square structural equation modelling (PLS-SEM) using SMART PLS4 for hypotheses testing. The study was conducted between April until August 2023, involving 370 purposively sampled respondents who were Waqif, Mawquf Alaih, or possessed knowledge about endowing waqf. The study intends to demonstrate the validity of factors influencing waqf stakeholders' willingness to share information, thereby enhancing Malaysia's waqf co-creation ecosystem. Findings: The result show that power, life satisfaction and commitment positively significant with the willingness to share the waqf information. Meanwhile, trust and reciprocity do not appear significantly influence the willingness to share the waqf information. Research limitations/implications: Given that the current study relied solely on questionnaires for data collection, a qualitative approach (interviews) should be incorporated to provide in-depth data. As the respondents were limited to the public, data from waqf institutions should also be collected to gain a more comprehensive perspective and generate new ideas to increase a person’s willingness to share waqf information among Malaysian. Practical implications: This study contributes significantly to the current literature concerning the willingness to share the waqf information. Policy makers encourage to develop of stakeholder-oriented strategy to promote power, life satisfaction and commitment to increase the willingness of waqf to share information. Aside from that, waqf institutions need to improve the waqf trust and reciprocity. The study offers empirical insights, bridging the gap between theory and practice in building trust and improving waqf contribution among stakeholders. These findings can influence the economic impact through policy implications. Society's willingness to share waqf information significantly impact fund sustainability. Increased waqf contributions can drive substantial projects, benefiting society and improving overall quality of life. Originality/value: to the best of authors’ knowledge, this is among the first comprehensive empirical studies that examine the willingness to share information focusing on the waqf area. Thus, the findings offer a valuable contribution to the waqf institutions to strategise and improvement the waqf sustainabilit
Penentu yang Mempengaruhi Tingkah Laku Kewangan Peribadi dalam Kalangan Asnaf
No full textSetiap manusia perlu mempunyai pengetahuan dan kemahiran dalam pengurusan kewangan dengan berlatih merancang, mengatur, mengawal dan menilai. Oleh itu, tujuan kajian ini bagi mengkaji tahap pengurusan kewangan, sikap kewangan, pengaruh normatif, dan tingkah laku kewangan. Selain itu, kajian ini juga menilai hubungan antara pengurusan kewangan, sikap kewangan, dan pengaruh normatif terhadap tingkah laku kewangan peribadi golongan asnaf. Seramai 120 orang asnaf telah terlibat dalam kajian ini. Kajian ini menggunakan pendekatan kuantitatif dan pengumpulan data menggunakan teknik persampelan mudah (convenience sampling). Instrumen kajian ialah soal selidik yang mengandungi tiga elemen tingkah laku kewangan iaitu pengurusan, sikap, pengaruh normatif, dan tingkah laku. Elemen pengurusan kewangan diukur berdasarkan skala likert. Statistik deskriptif dan korelasi digunakan untuk menjelaskan hasil kajian. Hasil kajian menunjukkan tahap pengurusan kewangan, sikap kewangan, dan pengaruh normatif dalam kalangan asnaf adalah sederhana manakala tahap tingkah laku kewangan adalah tinggi. Tambahan pula, terdapat hubungan yang signifikan antara pengurusan kewangan dan sikap kewangan terhadap tingkah laku kewangan peribadi. Secara keseluruhannya, tahap tingkah laku kewangan peribadi golongan asnaf adalah sederhana. Implikasi kajian mencadangkan bahawa elemen perancangan, penyusunan, pengawalan, dan penilaian kewangan perlu dipandang serius dalam kalangan asna
Protection of Sustainable Agricultural Land and Food (PLP2B) as an Indonesian Strategy for Sustainable Development Goals (SDGs): Banyuwangi Agrarian Conflict Study, Indonesia
Get PDFAgrarian conflict is inevitable, considering that Indonesia is known as an agricultural country. One of the agrarian conflicts that takes place continuously is the conflict that occurred in Banyuwangi, namely between PT. Bumi Sari with the Farmers Pillar of Pakel Village. This conflict involves the Company and civil society. The purpose of this study is to analyze the authority of the Banyuwangi local government in realizing the Protection of Agricultural Land and Food (PLP2B) in reducing agrarian conflicts as an effort to create Sustainable Development Goals (SDGs) in Banyuwangi, Indonesia. This study actualizes the juridical normative model with the types of statute approach and conceptual approach. The study consisted of primary data and secondary data. Primary data comprises PLP2B, SPPN, PPA, and Regional Government Law, while secondary data contains various journals and books. Data analysis includes data collection, data reduction, and conclusions drawn. The data analysis of this study uses the theory of autonomy. Concluding uses an inductive pattern (generalization). The study results stated that after enacting the Job Creation Law, which imposed PSN (National Strategic Program), it could precede PLP2B in running a program. The Banyuwangi local government has the authority to ratify the PLP2B Law through the function of regional autonomy as an implication of the concept of decentralization in Indonesia’s government system. The Banyuwangi Regency government should optimize this function to create regulations or programs that have a relationship or correlation with the resolution of agrarian conflict
Assessment of Data Quality Dimensions Influencing Big Data Analytics Role in Sustainable Development Growth Performance
Get PDFMany nations are increasingly interested in the value of massive amounts of data, driven by the growing importance of Big Data Analytics (BDA) in today's competitive landscape. The adoption of Big Data Analytics enables organizations to strategically enhance their operations efficiencies, gain a competitive edge, and sustain long-term growth. In the context of Sustainable Development Growth (SDG), ensuring high data quality becomes even more critical, as decisions based on inaccurate or incomplete data can lead to suboptimal outcomes and potentially adverse environmental or social impacts. Prior research on Big Data Analytics has ignored data quality in favor of adding more big data attributes – referred to as Vs (volume, variety, velocity, etc.) Poor quality, outdated, and incomplete data can result in inadequate decision-making. Therefore, the primary aim of this study is to explore the importance of Data Quality Dimensions (DQD) and Big Data Analytics adoption can influence the effective impact measurement and data collection for the success of SDGs. Key variables from research literature reviews were incorporated into the research framework for this study. This study used quantitative method of cross-sectional survey to data professional practitioners and management board (senior and middle managers) that involved in Big Data Strategies within Malaysia. By introducing novel insights in the realm of Big Data Analytics, this study contributes to the body of literature and serves as a valuable resource for future scholars and industry practitioners who wish to investigate BDA solutions associated to performance of SDG
Credit Accessibility and Small and Medium Sized Enterprises (SMEs) in Osun State, Nigeria
Get PDFThis research study examined the accessibility of credit for small and medium-sized enterprises (SMEs) in Osun State, Nigeria. More specifically, the study examined the factors that impact SMEs' credit accessibility and determined the degree to which government institutional funds and credit schemes have influenced SMEs' credit accessibility in Osun State. The study utilized a descriptive survey research design, randomly selecting 238 SMEs and collecting data through a structured questionnaire. The data was analyzed using both descriptive statistics and a logit regression model. The results demonstrate that small and medium-sized businesses in the research area can more easily obtain financing attributable to government institutional funds. The survey also showed that excessive levels of documentation and bank interest rates had a major detrimental impact on small and medium-sized businesses' ability to obtain funding. Therefore, the study suggests that policy measures be implemented by the government to control the interest rate that banks charge on loans to small and medium-sized enterprises. Second, proactive steps must be taken by the government, financial institutions, and other stakeholders to make credit more accessible to SME
Factors Influencing Fast Food Consumption among Public University Students: A Case Study at Universiti Utara Malaysia
Get PDFThe prevalence of fast food consumption among students is on the rise. Although there is a growing study investigating consumption of fast food among adolescents and adults in Malaysia, little attention has been paid to university students. This is perhaps the first study to examine factors influencing fast food consumption within a sample of students in Universiti Utara Malaysia (UUM). Primary data from a survey were used. An ordered logistic regression analysis was utilised to estimate the odds of consuming fast food. The explanatory variables consisted of demographic factors, peer influence, knowledge about fast food, lifestyle and mental health. Findings of the present study showed that most of the students in UUM consumed 1 to 2 times of fast food per week. Males tended to consume more fast food than females. Fast food consumption was lower among Chinese students than Malays, Indians and those of other ethnicities. Students who have excellent academic performance were less likely to consume fast food than those with poor academic performance. High personal income was associated with increased odds of consuming fast food. Students who were influenced by their peers were more likely to consume fast food compared to those who were not. Living a healthy lifestyle was associated with reduced odds of fast food consumption. These findings are important in the sense that they can assist UUM and government in developing more effective measures aimed at lowering students’ fast food intake. Intervention measures directed toward reducing fast food consumption among UUM students who are males, are Malays, have poor academic performance, have high income and adopt unhealthy lifestyles may yield promising outcome
The Role of Extended Value Chain Activities in Enhancing Economic Value Added Plantation Companies in Malaysia
Get PDFThe palm oil industry in Malaysia has faced issues of lower palm oil price and limited land area, and these issues have created a challenging environment for plantation companies to operate in. Plantation companies are constrained in maximizing their profits. Thus, this paper aims to examine the Economic Value Added (EVA) and the factors that influence the EVA of different value chain activities. The dynamic generalized method of moments (DGMM) estimators were adopted for the analysis and the focus was on the -40 Malaysian plantation companies that were listed in the Bursa Malaysia from 2010 to 2018. The results revealed that both downstream integrated activities, namely oleo-chemicals/biodiesel and refineries activities had a significant influence on the plantation companies’ EVA, with the coefficient value 1.12 and 0.09 respectively. Other factors such as the gross margin, crude palm oil price, and exchange rate also significantly influenced the plantation companies’ EVA. The empirical results which were based on the plantation companies’ EVA were influenced by different value chain activities as expected. The findings show that the downstream integrated activities like refineries, and oleo-chemicals/biodiesel activities have played a significant role in increasing the EVA of plantation companie
Revolutionising Diabetic Retinopathy Diagnosis with Modified Regularisation Long Short-Term Memory Framework
Get PDFThe diagnosis of Diabetic Retinopathy (DR) demands a paradigm shift towards more accurate and efficient solutions to overcome vision impairment. Therefore, the current study introduces a new Modified Regularisation Long Short-term Memory (MR-LSTM) framework approach for DR diagnosis. The proposed framework leverages the power of deep learning and provides a dynamic and robust solution for the early detection of DR, which in turn preserves a patient’s vision. The proposed framework uses a DR Debrecen Dataset from the UCI database with 21 distinct features relevant to retinal health, and employs a series of data preprocessing steps, including data cleaning, normalisation, and transformation, to ensure data quality and compatibility. The MR-LSTM framework excels at capturing temporal dependencies in sequential retinal images, offering a unique advantage in understanding the progression of DR. The MR-LSTM framework is implemented using Python libraries, and the results are compared with those of other popular models. It is observed that the MR-LSTM framework outperforms other models and achieves an accuracy of 97.12 percent and an F1 Score of 98.49. Furthermore, the Receiver Operating Characteristic (ROC) curve reveals an area under the curve of 0.97, highlighting the exceptional ability to discriminate between positive and negative cases of the proposed framework. By revolutionising DR diagnosis with the proposed MR-LSTM framework, it can achieve accurate, timely, and accessible solutions in the fight against vision-threatening condition