Smart farming for a sustainable future: implementing IoT-based systems in precision agriculture

Modern industry improves anthropogenic activities and greatly simplifies human effort and the industrial world. Cloud computing and mobile applications are more than just buzzwords; they are crucial elements of how business is conducted and how it will be conducted in the future. A rising number of SMEs are currently utilizing mobile and cloud computing technology. The purpose of this paper is to analyze the linkages between user reviews and ratings and the adoption of mobile accounting apps among SMEs in Kenya. The study collected data on 35 commonly used mobile accounting applications and performed a regression analysis on 27 apps that had received user reviews. Data on mobile apps' usage rate, volume of user reviews, and user ratings were gathered for this study. The authors also took note of the deficiencies identified by the selected mobile app reviewers. This study's findings revealed a significant relationship between the number of user evaluations and the adoption of mobile accounting apps. However, a significant effect of user reviews on the adoption of mobile accounting apps was not observed. This paper also identifies shortcomings that app users have pointed out in their reviews. It was concluded that Kenya's degree of mobile app adoption has greatly increased due to the volume of app reviews. This study advises entrepreneurs, particularly those who engage with SMEs, to embrace technology and adopt freely downloadable mobile apps for their accounting and bookkeeping requirements.

This study aims to investigate the key features necessary for the development of a mobile application for human resource management (HRM). It addresses the shortage of empirical studies on digital HRM in the Middle East and emphasizes the increasing importance of HRM mobile applications in the region. The research utilizes qualitative research methods, including the Delphi method, in-depth interviews, literature review, historical analysis, and critical discussion.A qualitative research strategy is employed, analyzing data from 43 HR experts and mobile app development team members from international and local businesses in the UAE and the Kingdom of Bahrain. NVivo software is used for data analysis, encompassing over 120 transcriptions, notes, and academic papers. The study identifies and explores the logical and practical features required for an HRM mobile app. It uncovers challenges related to the Delphi survey experiences, such as managing heterogeneous information and ensuring compatibility with iOS and Android platforms. This research fills a gap in the literature by investigating the digital HRM landscape and HRM mobile applications in the Middle East. It provides valuable insights from HR and technology experts, contributing to the advancement of digital HRM, mobile applications, and the application of the Delphi method methodology. The study highlights implications for industries to enhance HR operations and productivity through the adoption of mobile HR applications. Theoretical contributions include new insights into the digital HRM literature, specifically regarding the identification and discussion of essential features in HRM mobile applications. Practical implications involve the benefits of transitioning from traditional HRM to digitalized HRM in the professional era, as identified through the analyzed features of the HR app. The study offers practical insights for the development and implementation of mobile HR apps. Organizations can leverage these insights to create effective mobile HR apps that enhance HR operations and employee productivity.

This research uses an IoT chip to integrate with sensors, temperature control systems, and so forth to construct a hot water remote monitoring system. The system can monitor the water temperature of the heating system using a mobile phone application (app), and upload and record the water temperature to a cloud server. The system contains: (1) a heating system: heater, temperature display, relay, and so forth; (2) a remote monitoring system: including server, mobile phone monitoring app, network monitoring system, Bluetooth or Wi-Fi module; (3) a hot water system: including inner and outer tank and a heat preservation device; (4) IoT chips: containing Arduino chip control cards and other communication protocols. The system can be used for heating systems for large companies or hot water systems for home use, and for remote control and data access through the mobile app. Monitoring through the mobile app can have the following advantages: (1) remote access to the system for heating, recording and querying usage status. The data stored in the cloud can be used for an analysis of energy efficiency and guide policy decisions for the company’s energy consumption. (2) Remote monitoring through the mobile phone app can be used to determine whether any repairs are required to the heating system. (3) Through the use of the statistical data, the heating temperature can be adjusted, and the system can be optimized according to time and temperature changes, which can save energy. The network monitoring management, temperature sensing and control, and data access control of the app are used in this research. The average control temperature error is 3% after experimental analysis. The data access time error value is three seconds. The data access stability is over 99%.

One of the main economic sectors in the world is agriculture. The need to increase productivity, ensure food security and reduce waste has led to the application of modern technologies in agriculture. Increasing productivity, lessening the impact on the environment, and improving livelihoods are the objectives of revolutionizing agriculture through the use of innovative technologies, environmentally friendly methods, and efficient systems. Machine learning (ML) and Deep learning (DL) have demonstrated significant promise in recent years for precision agriculture. This paper discusses Advancements in Precision Agriculture: A Literature Review of Machine Learning Applications for Crop Monitoring and Yield Prediction. In precision agriculture system, to predict crop health monitoring and yield prediction includes soil parameters such as organic carbon and moisture content, crop yield prediction, disease and weed detection, species identification, and nitrogen status estimation are reviewed. Furthermore, the review explores the integration of ML/DL models with IoT-enabled farm machinery to enhance livestock production by predicting fertility patterns, diagnosing eating disorders, and monitoring cattle behavior using collar sensors. Additionally, the review discusses the implementation of intelligent irrigation and harvesting techniques, which reduce human labor while optimizing resource utilization. By analyzing the literature, this review demonstrates the potential of knowledge-based agriculture to improve sustainable productivity and product quality. Moreover, it identifies challenges and opportunities for future research, highlighting the need for interdisciplinary collaborations and ethical considerations in deploying ML- based solutions in agricultural settings. Overall, this review contributes to the understanding of how ML and DL technologies are revolutionizing precision agriculture, paving the way for informed decision-making, resource optimization, and enhanced sustainability in food production systems. This paper provides a comprehensive survey of existing papers and applications of ML in agriculture. In order to demonstrate the numerous uses of ML, the author reviewed 100 publications that were published between 2020 and 2024, among them 53 ML/DL-based algorithms were used in revolutionizing precision agriculture, paving the way for informed decision-making, resource optimization, and enhanced sustainability in food production systems.

Purpose/Hypothesis: Advances in technology have recently resulted in the development of mobile learning applications (apps) for college students. Despite a recent influx of mobile apps, there is a lack of empirical data about the effectiveness of these apps on learning in the area of cardiovascular and pulmonary physical therapy (PT). The purpose of this study was to evaluate the effect of a researcher-generated cardiopulmonary mobile application on student skills in assessing blood pressure (BP), heart rate (HR), and pedal pulses. Number of Subjects: Twenty first-year PT graduate students were recruited for the study. Participants’ names were randomly chosen out of an envelope to assign them into 1 of 3 groups: demonstration (N = 7), mobile app (N = 7), or demonstration/mobile app (N = 6). Materials/Methods: After providing informed consent, each group participated in their randomized intervention. The demonstration group received demonstrations of each skill from a scripted therapist, followed by laboratory practice; the mobile app group received a 5-minute tutorial of how to use the app, followed by laboratory practice; the demonstration/mobile app group received both demonstration and the mobile app tutorial, followed by laboratory practice. Independent of group type, all participants were allotted 45 minutes in the laboratory to practice performing and interpreting BP, HR, and pedal pulses, after demonstration, demonstration/mobile app, or mobile app instruction. After the laboratory practice, participants were individually tested on the skills learned during the laboratory by a short competency examination administered by 3 licensed physical therapists. These physical therapists were blinded to each group's identity. Results: Total competency was highest among the demonstration/mobile app group as compared with the other 2 groups. The total competency examination score was statistically significant for different teaching methods with the use of demonstration and the mobile application being more effective than only using the mobile application P = .032. No significant difference was noted between the mobile app group and the group using demonstration only, P = .24. No other group differences were noted. Conclusion: Findings of this study suggest PT students demonstrate improved total competency examination scores (total score of BP, HR, and pedal pulses) when provided a mobile application combined with traditional demonstration. Clinical Relevance: There is currently a paucity of literature in PT education pertaining to mobile learning. The results of the current study support the use of a mobile app in addition to traditional learning methods. Future research should include a multisite design and validation of a clinical competency instrument.

Optimization of agricultural practices for enhanced crop yield is considered to be essential phenomena for the countries like India. In order to strengthen the economy and also to meet the food demand for the exponentially growing population, optimizing the agricultural practices has become necessity. In India, weather and geographical conditions are highly variable and were thought to be the major bottleneck of agricultural practices to achieve improved crop yield. Agricultural practices in India are facing many challenges such as change in climatic conditions, different geographical environment, conventional agricultural practices; economic and political scenario. Economic loss due to the lack of information on crop yield productivity is another major concern in the country. These hurdles can be overcome by the implementation of advanced technology in agriculture. Some of the trends observed are smart farming, digital agriculture and Big Data Analytics which provide useful information regarding various crop yields influencing factors and predicting the accurate amounts of crop yield. The exact prediction of crop yield helps formers to develop a suitable cultivation plan, crop health monitoring system, management of crop yield efficiently and also to establish the business strategy in order to decrease economic losses. This also makes the agricultural practices as one of the highly profitable venture. This paper presents insights on the various applications of technology advancements in agriculture such as Digital Agriculture, Smart Farming or Internet of Agriculture Technology (IoAT), Precision Agriculture, Crop Management, Weed and Pest control, Crop protection and Big data analytics.

Nowadays, rapid development in information technologies has been experienced in the aviation industry as in other industries. This development has affected both passengers and airlines in different aspects. The use of information technologies enables passengers to carry out flight-related transactions more easily and quickly, without place and time constraints. Information technologies have necessitated the use of different applications in the marketing activities of airlines. So in terms of airlines, it is extremely important to adapt these information technologies to all processes in order to achieve sustainable competitive advantage. Today airlines have also started to use mobile applications (mobile apps) in their marketing activities. They encourage their passengers to use these apps, which require great investment. However, some passengers may avoid using mobile apps due to a variety of reasons such as technology anxiety, privacy concerns, complexity, etc. In this case, high investments made for the development of these apps may not be compensated and the competitiveness of airlines may be weakened. Therefore, the purpose of this study is to determine the factors affecting passengers’ avoidance of using airlines’ mobile apps. A survey was conducted using a face-to-face interview technique with convenience sampling method to collect data. Questionnaire items were measured by a five-point Likert scale ranging from 1 (strongly disagree) to 5 (strongly agree). The survey was conducted in the two busiest airports in Turkey (Atatürk and Sabiha Gökçen Airports in Istanbul). A total of 450 respondents have been reached but 400 valid questionnaires were analyzed by using Partial Least Squares method. A pilot study was conducted on 20 volunteer participants before the field research was initiated. In this context, the questionnaire was finalized by taking into consideration the suggestions expressed in order to maintain the coherence. The survey questionnaire consisted of two sections. The first section comprised of perceived irritation, perceived lack of utility, perceived lack of incentive, technology anxiety, privacy concern, and mobile app usage avoidance. In the second section, there were questions about passenger’s demographic characteristics such as; age, gender, education level, average income level, and flight frequency. Respondents were also asked about their general usage related to smartphones and mobile apps. According to the results; perceived irritation, perceived lack of utility, perceived lack of incentive, technology anxiety, and privacy concerns have a positive and significant effect on mobile app usage avoidance. Among these variables, technology anxiety is the most affected variable on passengers’ avoidance of using mobile apps. Both in national and international literature, there are numerous studies on mobile internet, apps adoption, and actual usage of mobile apps in different industries. Previous studies are especially related to the factors accepting the mobile apps. In addition to this, there are limited studies including avoidance of using airline mobile apps. In aviation industry also, there are a few studies both national and international literature on passengers’ avoidance of using airline mobile apps. Therefore, this study will be one of the few studies both shedding light on literature and airlines to increase the use of mobile apps.KeywordsPassengersMobile applicationsAvoidanceAirlines

Bridging the data gap: engaging developing country farmers in greenhouse gas accounting

Development of a mobile health application for those who have experienced pregnancy loss

The rapid and accurate prediction of crop yield and the construction of optimal yield prediction models are important for guiding field-scale agronomic management practices in precision agriculture. This study selected the leaf area index (LAI) of winter wheat (Triticum aestivum L.) at four different stages, and collected canopy spectral information and extracted vegetation indexes through unmanned aerial vehicle (UAV) multi-spectral sensors to establish the yield prediction model under the condition of slow-release nitrogen fertilizer and proposed optimal fertilization strategies for sustainable yield increase in wheat. The prediction results were evaluated using random forest (RF), support vector machine (SVM) and back propagation neural network (BPNN) methods to select the optimal spectral index and establish yield prediction models. The results showed that LAI has a significantly positive correlation with yield across four growth stages of winter wheat, and the correlation coefficient at the anthesis stage reached 0.96 in 2018–2019 and 0.83 in 2019–2020. Therefore, yield prediction for winter wheat could be achieved through a remote sensing estimation of LAI at the anthesis stage. Six vegetation indexes calculated from UAV-derived reflectance data were modeled against LAI, demonstrating that the red-edge vegetation index (CIred edge) achieved superior accuracy in estimating LAI for winter wheat yield prediction. RF, SVM and BPNN models were used to evaluate the accuracy and precision of CIred edge in predicting yield, respectively. It was found that RF outperformed both SVM and BPNN in predicting yield accuracy. The CIred edge of the anthesis stage was the best vegetation index and stage for estimating yield of winter wheat based on UAV remote sensing. Under different N application rates, both predicted and measured yields exhibited a consistent trend that followed the order of SRF (slow-release N fertilizer) > SRFU1 (mixed TU and SRF at a ratio of 2:8) > SRFU2 (mixed TU and SRF at a ratio of 3:7) > TU (traditional urea). The optimum N fertilizer rate and N fertilizer type for winter wheat in this study were 220 kg ha−1 and SRF, respectively. The results of this study will provide significant technical support for regional crop growth monitoring and yield prediction.

Mobile phone applications (apps) provide a new platform for delivering tailored services especially applied to Human Immunodeficiency Virus (HIV) infection prevention and care. To review mobile phone apps currently available related to the prevention and care of HIV infections as well as other diseases. The articles were systematically identified and the research was indexed with the following keywords: Africa, Telephone, Mobile App, SMS, associated with the word Health, HIV, or PMTCT. Research papers published between 2006 and 2016. In Africa, many mobile health applications have been developed, in different domains such as: disease knowledge, risk reduction/safer disease, health promotion, HIV/AIDS testing information, resources for HIV-positive persons and focus on key populations. Use of SMS and call of mobile phone have the potential of improving adherence to medication in outpatient setting by reminding patients of dosing schedules and attendance to scheduled appointments through SMS and voice calls. Mobile phone apps should be extended to all health facilities, community to increase the impact of new development in the field of HIV testing, Prevention and Treatments.

Precision agriculture is an innovative technique that encourages the use of Information Technology devices to produce high-quality yield with the best utilization of available resources. Presently, the practice of precision agriculture has become more common due to the inclusion of varied technologies and communication mediums. This technique can be acquired by farmers to optimize their crop returns with proper preservation of resources. This study proposes a Platform to measure soil and environmental parameters such as humidity, temperature, and moisture of the soil. In contrast, the population is increasing in an inclined order, to keep an eye on the growth level of the population level and requirement of the food resources, the researchers are still struggling for the dataset availability of their region. Thus, a need to measure crop parameters for analysis was felt. This study uses Raspberry Pi, Sensors and other information technology-based types of equipment to fetch the data and readings of the soil and environment. Further, a methodology has been devised which uses a cloud platform, for real-time analysis of the data gathered from the proposed platform. This analysis includes several plots that are based on the readings of the sensors from the station. The upshot of this study is the possibility that the researchers could implement the model using the observed reading from the soil and environment and it could also be aggregate, visualize and analyze the live stream of data for their local region. The study could further be used as a foundation for implementing precision agriculture models such as unmanned aerial vehicle-based precision farming.

Mobile phones are considered extremely crucial for their daily usage due to their unique features such as mobility, availability, and compatibility. Moreover, the need for mobile apps periodically increases in terms of the variety of end-users as well as mobile platforms. Iraq is an emerging country concerning the development and requirements of mobile apps. There are numerous challenges faced by this trend on mobile phone app requirements, development, and usage. Consequently, the major consideration is how to build a suitable mobile app that can be adopted, adapted, and customized according to Iraqi market requirements. An essential fact worth mentioning is the increase in unemployed computer departments alumni in Iraq. Those who can develop mobile apps and software need to recruit suitable candidates. The purpose of this article is to develop a customized flight booking mobile application to partially reduce and solve the problem of unemployed computer alumni. The target of this application is to reduce time and effort for passengers and offer unique features. The developed application is the adoption of previous applications and the improvement of their inadequacies. By following a six-phase methodology to set a procedural technique for optimizing the use of the mobile application as a source of revenue for unemployed alumni as well as being beneficial for the customer. The validation and verification of the proposed application of this current research are done by evaluating and executing the mobile application. The results of this paper meet the main objective, where, the special features have been implemented and tested. In addition, the application has been installed on mobile phones and tested. Furthermore, the income from this application is obtained through purchasing it or subscribing to it for a specific duration. We encourage researchers as well as alumni who are targeted in this field to be attentive to cutting-edge technology and advancement and the concept of this paper.

PurposeCompulsive usage of mobile applications may have a negative effect on people’s health and social interaction. Past studies have indicated that personality traits were related to compulsive usage of technologies, but most of them have explored the factors from the system and interface design perspectives, specifically. The purpose of this paper is to explore how the Big Five personality traits, materialism, and external locus of control affect compulsive mobile application usage, and examines how compulsive usage impacts technostress.Design/methodology/approachThe present study proposes a framework based on Big Five personality traits and related literature. The author collected a total of 546 valid responses to the online survey, and the author examined the 18 proposed hypotheses using SmartPLS software.FindingsThe results show that neuroticism, extraversion, materialism, and external locus of control have significant effects on compulsive usage of mobile social applications. In addition, agreeableness, materialism, and external locus of control significantly influence compulsive usage of mobile game applications. Compulsive usage (of both mobile social apps and mobile games), materialism, and external locus of control all have a positive, direct impact on technostress.Practical implicationsThis study offers mobile app design companies and educational institutions a understanding of the social problems caused by the misuse of mobile devices, helping them to prevent the increase of the negative influences of such misuse.Originality/valueThe primary value of this paper lies in providing a better understanding of the influence of personality traits on the compulsive use of mobile apps and technostress.

Rice is one of the six priority crops chosen by the government of Rwanda to increase agricultural productivity. This crop faces significant challenges from climate variability and soil conditions, affecting yields and food security. The past studies concentrated on building machine learning regression models for predicting the rice productivity with the help of weather parameters as predictors. Few researchers incorporated some soil nutrients to improve the precision of the prediction model. However, most of the farmers in Rwanda rely on agricultural input like inorganic fertilizer to boost the agriculture productivity. This means that the weather parameters are not sufficient to build a robust crop yield prediction model without incorporating the soil parameters. In this paper, rice yield status (favorable, unfavorable) prediction model was optimized using machine learning techniques, including logistic regression, random forest, gradient boosting, extreme gradient boosting, support vector machine, and artificial neural networks. The models were trained on historical weather parameters and soil nutrient data collected from the National Institute of Statistics of Rwanda, Rwanda Agriculture and Animal Resources Development Board and Rwanda Meteorology Agency. Findings indicated that the eXtreme Gradient Boosting (XGBOOST) model outperformed other models under consideration with 91%, 94.1%, and 82.7% of prediction accuracy, sensitivity, and precision, respectively. The above results demonstrate that the XGBOOST is the most robust model in predicting rice yield. The feature importance technique applied in this study also revealed that weather parameters (rainfall, and temperature), phosphorus, sulfur, manganese and carbon were crucial factors to prioritize for rice yield prediction compared to other model predictors under study. The results may provide valuable insights into whether the rice yield will be classified as low or high. This information is essential for helping farmers and decision-makers obtain actionable insights into expected crop yields, enabling them to make informed decisions on agricultural inputs resource allocation to maximize Rwanda's agricultural productivity. Key words: artificial intelligence, machine learning, precision farming, Smart agriculture, yield prediction