According to an FAO report by 2050, the population may rise to 9 billion, and 9 billion people approx. 60%more plant-based food is required which is obtained by agriculture. In the current scenario 70%of the fresh water is being used in agricultural irrigation. To obtain more food and to increase the productivity of agriculture, irrigation needs to be managed properly using technologies. The study is about the integration of the IoT and cloud computing to make irrigation smart. The smart irrigation system reduces the wastage of water due to overflow while irrigating the field increases the returns on the farmer's inputs. The study collects data such as soil moisture, soil type, soil pH, crop type, and crop stage, this data will be taken using open-source sensors and open-source modules and uploaded to the cloud storage. It provides farmers the freedom of monitoring and real-time access to the field data. After analysis, the study identifies some suggestions for working in future in the technology-based irrigation. In the future crop health, health monitoring, disease detection, fertilization suggestion, and Artificial intelligence and machine learning-based decision-making based on the data.

The United Nation highlighted a remarkable agenda to reduce the danger of natural disasters. It is to make the environment safe for everyone. The United Nations also acknowledged this need through the Sustainability Development Goals (SDG 11, SDG 15 & SDG 9) to reduce the impact and effect of natural disasters & sustainable disaster management & infrastructure development. Previous studies gave the solution of Data Transmission, analysis and Long-Range Network Protocol usage and the usage of IoT 3Layer Architecture but they didn't emphasize how to overcome with some serious problems as; latency and data transmission to far areas which can't be covered by various networking protocols. The current study indicates the use of IOT 5-layer architecture and its benefits in Data analysis and prediction making and reduces the latency. This paper also addressed the use of the cloud hub to transmit the warning message to the far places. On the foundation of analysis, the paper indicates the lacks and some suggestions for future works. In early Warning System in Flash Flood Monitoring, 5-layer architecture, Cloud Hub LoRa range increasing are some vital suggestions in the study. (Abstract)

Precision Livestock Farming (PLF) technologies may boost the well-being of livestock by providing real-time welfare evaluations and encouraging timely therapies, their ultimate objective remains undefined. The livestock digital revolution delivers constant surveillance of the welfare of livestock at both the group and individual levels. To evaluate changes in behavioral patterns or physiological indicators, multiple sensors and data analytics are employed. PLF systems empower farmers with excellent real-time monitoring and management capacities, facilitating immediate intervention in scenarios associated with production concerns. Creating effective real-time algorithms for such platforms requires adherence to fundamental principles. Precision Nutrition (PN), a subsection of the PLF technique, encompasses the timely distribution of nourishment to livestock, necessitating automated data collection, processing, and supervision measures. Deploying such mechanisms appears to be complicated. This study suggests a hybrid offline–online training approach for long-term behavioral monitoring systems in precision livestock farming. The method addresses the concern of concept drift by guaranteeing consistent training data, which improves both animal welfare and production. This article examines recent advancements in PLF to assess the welfare of dairy cattle, encompassing physical condition, mastitis, and lameness. It also examines at how PLF data may be integrated into an expanded welfare assessment framework. Real-time sensing technologies are employed for determining nutritional requirements, therefore supporting the sustainability pillars of financial, ecological, and ethical conduct.

Spinning, weaving, knitting, braiding, stitching, and dyeing are fundamental textile production processes that have been in use since ancient times. However, contemporary technology have posed new environmental dangers. This chapter investigates current breakthroughs in sustainable textile technology and their implications for the developing world's textile industry. It also looks at the sustainability issues that these modern systems confront in addressing the growing population requirements. Neurobiological research is looking at the brain underpinnings of insect behaviors, which will help us understand biology and have possible applications in robotics and artificial intelligence (AI). Micro-biomics studies insect-microbial connections and proposes novel pest management tactics. Environmental entomology studies the effects of habitat change and climatic variability on insect populations, which are critical for biodiversity conservation. The field is at the forefront of technological advancements and multidisciplinary techniques, which improve our understanding of insects' roles in ecosystems, adaptation, and ecological balance. This future path has intriguing scientific research implications for sustainable ecosystem management and conservation policy. Due to their porous nature, 3D-printed silk fibroin scaffolds provide several benefits in wound healing, including cell infiltration, nutrition exchange, waste disposal, and tissue regeneration. By modifying the printing settings, they guarantee stability and support throughout recovery. AI-driven printing processes increase wound dressing accuracy, customization, and personalization, while also increasing time and cost efficiency and accelerating research and development. AI algorithms improve design and manufacture using patient-specific data, leading in better-fitting dressings, faster production, and better wound healing results. The study examined traditional classifiers such as support vector machines (SVM) and K nearest neighbors (KNN) for detecting the sex of silkworm pupae from different years and species. A CNN model was trained to determine the gender using hyperspectral spectra. According to principal component analysis (PCA), CNN outperformed SVM and KNN in terms of accuracy. The study also found that HSI technology coupled with CNN was effective in detecting the gender of silkworm pupae.

The healthcare industry is plagued by data inconsistencies, with patients and organizations dissatisfied by redundant contact information and impediments to acquiring real-time patient information. Blockchain technology, which has proven effective in boosting transaction security in the banking industry, is being examined as a solution. This study provides an approach for leveraging blockchain to share data among healthcare organizations. The study intends to improve the security and privacy of electronic healthcare records (EHRs) by employing blockchain technology, as existing centralized systems frequently reveal critical health data, lowering vulnerabilities and avoiding cyberattacks. Internet of Things (IoT) and blockchain have emerged into feasible digital technologies in the healthcare sector. Real-time data may be captured and saved utilizing IoT devices and blockchain, assuring transparency and security. This technique tackles billing and insurance claim challenges by assuring quick reporting, protected data storage, and a transparent system, therefore improving the overall efficiency and transparency of the healthcare industry. This study examines the benefits of Blockchain technology in healthcare, focusing on its capabilities, enablers, and unified workflow procedure. It highlights important Blockchain applications including detecting clinical trial deception, increasing data efficiency, minimizing data tampering, and offering security through unique storage patterns. Blockchain also provides flexibility, interconnectedness, accountability, and authentication for data access, assuring the security and confidentiality of health records.

Network systems function based on rules that are intrinsically dynamic, subject to temporal circumstances set by outside events like host utilisation, bandwidth measurements, intrusion detection, or time-specific events. Software-defined networking (SDN) presents an opportunity to streamline network configuration through the provision of more sophisticated configuration tools. In an attempt to lower network monitoring costs and traffic overheads, we offer a software-defined cloud resource management solution that customises network resource distribution using a Flexible Analytical Hierarchy Procedure (Fuzzy-AHP). Through an Application Programme Interface, this framework may be easily integrated into cloud infrastructures that support SDN (API). We demonstrate how our system improves network resource management and efficiently responds to growing traffic requests using real-time data. Moreover, we confirm the performance of our framework using simulations.

A considerable number of individuals struggle with pneumonia, a condition caused by viruses which is most prevalent in emerging and impoverished nations where there is an inadequate number of medical services, contaminated and jam-packed environments, and other issues. Pericardial effusion, a disorder where fluid fills the lungs and makes breathing difficult, is brought on by pneumonia. Early diagnosing pneumonia is an important action that must be taken in order to enhance the chance of survival and develop services for therapy. The efficient development of predictive algorithms can be made easier by the artificial intelligence discipline of deep learning. There are several methods for identifying pneumonia, including pulse oximetry, CT scanning, and many more, but X-ray tomography is the most often used method. In this study, pneumonia can be identified and categorized via a deep learning (DL) system which employs DenseNet169. Neural Networks (NN) on the DenseNet169 yields accuracy values of 86%, 84.11% and 89% for SVM, Naive Bayes and RF respectively.

This paper uses a thorough case study experiment to examine the real-world applications of IoT-driven innovations within the context of Industry 5.0. The factory floor has a temperature of 32.5°C, a warehouse humidity of 58%, and a safe pressure level of 102.3 kPa on the manufacturing line, according to an analysis of IoT sensor data. A 5.7% decrease in energy use was made possible by the data-driven strategy, as shown by the office's CO2 levels falling to 450 parts per million. The case study participants, who had a varied range of skills, were instrumental in the implementation of IoT, and the well-organized schedule guaranteed a smooth deployment. Key Industry 5.0 indicators, such as +2% in production efficiency, -5.7% in energy usage, -29% in quality control flaws, and +33.3% in inventory turnover, show significant gains. Key metrics evaluation, data-driven methodology, case study, Industry 5.0, IoT-driven innovations, and revolutionary potential are highlighted by these results.

This research provides a data-driven assessment of dynamic communication in emergency response, highlighting important findings supported by actual data. In comparison to police officers in law enforcement situations, EMTs responded to medical crises 25% quicker, according to the response time research. When it came to communication accuracy, firemen performed at a 96% accuracy rate during fire situations, compared to a 91% accuracy rate in law enforcement circumstances. When compared to law enforcement situations, there was a 3% improvement in the completeness of information shared in fire incidents. Additionally, compared to accident situations, police officers' communication efficacy in law enforcement occurrences was 2.3% greater. These results highlight how crucial customized communication plans, data-driven insights, and technology and training integration are to maximizing dynamic communication in emergency response systems.

The Internet of Vehicles (IoV) has a strong requirement for the security of user data in recent years with the rapid development of autonomous driving technology. The paper discusses the privacy security issues in the current IoV system and the security issues in the current IoV system. Many attacks can be applied to IoV systems, including authentication, identification, availability, confidentiality, routing, and data authenticity, resulting in several security and privacy requirements. Recently, many security scientists have worked on ensuring the security and privacy of the Internet of Vehicles. A review of the current security and privacy issues regarding the IoV is presented in this paper, including IOV security requirements, attack types, and security threats, as well as the relevant solutions.

Biosensors provide an efficient and cost-effective alternative for researchers and medical practitioners to carry out examination, safeguard public safety, and present tailored health care options. They play an increasingly essential role in biological research, infectious disease screening, chronic illness treatment, health management, and well-being monitoring. Improved biosensor technology facilitates for early illness identification and observation of the body's reaction to medication, making it a vital component of contemporary medical equipment. Wearable biosensors provide real-time physiological information through the dynamic measurements of biochemical markers in biofluids including sweat, tears, saliva, and interstitial fluid. Additional biomarkers will demand more on-body bioaffinity testing and sensing techniques. Large-scale verification experiments have to be performed for clinical acceptability. Accurate, dependable biosensor technology could potentially have significant effects on everyday life. Wearable health sensors determine the wearer's health and environment in real time by transmitting data to a control unit via biological responses. This article explores the creation, technology, business, ethics, and future of wearable biosensors in healthcare, with an emphasis on their application in a multitude of scenarios along with potential implementations. The study investigates the utilization of biosensors in medicine, particularly in cardiovascular disorders, emphasizing their potential for breakthrough medicines, real-time insights, tailored solutions, and informed advice, paving the way for a bright future in healthcare.

In this study, we introduce and assess a novel feature extraction technique that analyzes the extent of character image boundaries to enhance recognition accuracy. This method is evaluated in conjunction with Nearest Neighbors (NN) and Support Vector Machine (SVM) classifiers, and compared against various feature selection methods including Consistency Based Analysis (CBA), Correlation Feature Set (CFS), Chi-Squared Attribute (CSA), Independent Component Analysis (ICA), Latent Semantic Analysis (LSA), Principal Component Analysis (PCA), and Random Projection (RP). Our extensive experiments demonstrate that CSA consistently outperforms the other techniques, achieving high recognition rates of 90.4

This paper discusses the deployment of Seasonal Autoregressive, including shifting common (SARIMA) fashions to expect the reliability of networks. SARIMA is an extension of autoregressive incorporated shifting average models, which seize seasonality inside the information and comprise consequences of earlier lags. The SARIMA model can be implemented to install reliability facts to expect future traits in network reliability. This paper offers an in-depth description of the additives of the SARIMA version and a step-by-step process to deploy the model for network reliability prediction efficiently. The effectiveness of this model in expecting networks’ reliability is proven by using it to present an archive of reliability records from benchmark networks. Effects display that the SARIMA version can appropriately expect the fast-time period reliability of the networks.Additionally, the paper discusses ways to leverage version estimates to design or improve destiny networks. Every day, the SARIMA version can play a vital role in consulting and decision-making associated with destiny networks’ reliability. The deployment of Seasonal Autoregressive has been studied significantly in recent years. SARIMA models are proper for predicting brief-time period adjustments in network reliability as they provide a powerful way to version seasonality traits. They’re capable of capturing the predictable periodic cycles of community occasions that occur during a specific time Of the year and the overall traits that recur each year.Furthermore, SARIMA fashions allow for the integration of autocorrelation structure of the information, that’s vital for predicting reliability trends over long durations of time. In realistic packages, SARIMA models had been used to predict traffic parameters, including the number of packets in step with 2d, packet put off, and jitter, in addition to the success or failure of packet transmissions. For instance, via predicting the modifications in packet transmission achievement/failure quotes for the duration of holidays, visitor scheduling algorithms can be stepped forward to deal with seasonal adjustments. Additionally, by monitoring the impact of upkeep and protection sports on the community’s overall performance, SARIMA models can estimate device availability for the duration of predictable operational changes..

Machine learning is commonly used to automate disease classification by extracting features from segmented objects, but automated segmentation can be difficult. Model proposed uses average values to compute features based on the whole image, eliminating the need to perform additional steps. Results obtained by the algorithm were encouraging, but implementing it requires considerable computational expertise. Lung cancer detection is a very important field of medical processing. We have included two processes named feature extraction and feature selection processes and evaluated and compared the performance of feature extraction and feature extracting and selection processes. In addition, some benchmark sets can be used to compare the performance of the proposed work model. PCA, ICA, and SURF were used to develop the friendly disease prediction model. The feature selection process is applied after the feature extraction process to select the relative features and will compare with the feature extraction criteria. The feature selection is done using the HPSO-CSO Algorithm. The proposed method in which the work has been done using canny edge operator and feature selection has shown good result values in comparison to feature extraction. The proposed techniques aim to minimise classification errors and maximise accuracy. From the results, it has been concluded that accuracy was achieved at 97.94%.

Multimodal medical image fusion is a perennially prominent research topic that can obtain informative medical images and aid radiologists in diagnosing and treating disease more effectively. However, the recent state-of-the-art methods extract and fuse features by subjectively defining constraints, which easily distort the exclusive information of source images. To overcome these problems and get a better fusion method, this study proposes a 2D data fusion method that uses salient structure extraction (SSE) and a swift algorithm via normalized convolution to fuse different types of medical images. First, salient structure extraction (SSE) is used to attenuate the effect of noise and irrelevant data in the source images by preserving the significant structures. The salient structure extraction is performed to ensure that the pixels with a higher gradient magnitude impact the choices of their neighbors and further provide a way to restore the sharply altered pixels to their neighbors. In addition, a Swift algorithm is used to overcome the excessive pixel values and modify the contrast of the source images. Furthermore, the method proposes an efficient method for performing edge-preserving filtering using normalized convolution. In the end,the fused image are obtained through linear combination of the processed image and the input images based on the properties of the filters. A quantitative function composed of structural loss and region mutual data loss is designed to produce restrictions for preserving data at feature level and the structural level. Extensive experiments on CT-MRI images demonstrate that the proposed algorithm exhibits superior performance when compared to some of the state-of-the-art methods in terms of providing detailed information, edge contour, and overall contrasts.

This article presents a novel hybrid learning approach that combines hand-crafted features, including Scale-Invariant Feature Transform (SIFT) and Haralick texture, with deep-activated VGG19 features for image classification. The extracted features are used to classify objects into multiple categories through various machine learning algorithms, such as Decision Tree, Naive Bayes, Random Forest, and XGB classifier. Experiments on the Caltech-101 dataset, which contains noisy, rotated, and rescaled images, show the proposed method achieving an outstanding 99.13

This study explores mathematical models to enhance our understanding of information generated by neural machines. We tested various models, including Statistical Machine Translation (SMT), Neural Machine Translation (NMT), Mathematical Transformation Recurrent Neural Networks (M.T RNN), and Simple Recurrent Units (SRU). Our research indicates that these models significantly improve the coherence and understanding of computer-generated writing, revolutionizing natural language processing and machine learning. Proper categorization facilitates the organization and utilization of interpreted data, opening avenues for diverse applications across academic fields. For more information, click on this link. These findings empower researchers and professionals to choose effective interpretation strategies for specific language combinations, enhancing machine translation intelligibility and accuracy.