The Internet of Things is an emerging domain in the field of establishing the effective communications. Routing protocols are crucial for ensuring dependable data transmission in networks with limited resources. RPL is a standardized protocol used in low power lossy networks. However, it encounters difficulties in effectively managing energy usage while maintaining a satisfactory level of quality of service. The Trickle algorithm is an integral part of RPL that minimizes the frequency of control message transmission, further enhancing its efficiency and scalability. The redundancy level of transmissions is determined by the impact on the redundancy constant K in the trickle, default higher K value leads to more frequent transmissions, ensuring messages are received even in unreliable networks in the standard trickle. The research investigates the variants of K with different values and optimizes the value as K-Trickle. We evaluate K-Trickle using simulation in Contiki 3.0 of Cooja under various network configurations along with mobility. Our results demonstrate that K-Trickle significantly improves network performance compared to standard trickle and reduces energy consumption by up to 3

Human life and existence are intertwined with a few domestic animals. One of the most important animals of this kind is the cow. Cows play a vital role in daily activities. Most of the people in India consume cow’s milk as one of their major nutrients. Monitoring the health of a cow’s everyday life is quite challenging. After infertility and mastitis, lameness is typically ranked as the third most economically significant health issue in dairy herds.Lameness are caused due to genetics, lack in nutrition i.e. a diet deficient in essential nutrients such as biotin, which can lead to hoof problems. Due to geographical environments like cows kept in wet, muddy conditions are more likely to develop hoof problems. This investigation analyses the typical characteristics of cow behavior, and a Smart Cow Health Monitoring System (ScHeMoS) using IoT is proposed to identify the cow’s health through the data obtained from Internet of Things (IoT) sensors, including position, body temperature, stability, acceleration, and animal feed. IoT is combined with Deep learning (DL) technique to monitor and diagnose animal health. We used the Long Short Term Memory (LSTM) network to predict cow lameness by capturing the body temperature and other parameters, which will aid in predicting their illness. The accelerometer values are stored so that it will further help to determine which cow is lame and which is pregnant or regular and could be intimated to the care takers in the farms. We utilised a self collected dataset to perform the investigation. By implementing this system, we achieved 92.45\% accuracy and 0.92 as F1 score.

Internet of Things (IoT) plays a vital role in the world of Internet and integrates computing devices. The digital machines provide unique identifiers. The capacity to send data through the network using a better path is one of the capabilities of digital machines. IoT generates huge data based on fast aggregation data and processes these data efficiently. In this paper, a multi-objective hybrid woodpecker and flamingo search optimization algorithm is proposed for finding optimum Cluster Head (CH)-based energy-aware routing protocol in IoTs environment (Hyb-WFSOA-CHS-IoT). Here, the proposed Hyb-WFSOA-CHS-IoT model executes routing method through CH. The woodpecker and flamingo search optimization algorithm is used as the intelligent CH selection that consumes same energy as sensors. Hybrid woodpecker and flamingo search optimization algorithm (Hyb-WFSOA) is examined by using fitness functions, like distance, delay, energy consumption, throughput. The proposed Hyb-WFSOA-CHS-IoT method is activated in MATLAB software. Then, the performance of the proposed system is examined with different metrics, like delay, packet delivery ratio, throughput, network lifetime, energy consumption. Therefore, the proposed method attains lower delay 28.38%, 32.34% and 47.45%, higher delivery ratio 19.34%, 23.12% and 18.96% and lower energy consumption 11.25%, 7.90% and 12.88% compared with existing methods, like multi-objective fractional gravitational search algorithm for energy-efficient routing on IoT (FGSA-CHS-IoT), multi-objective sunflower-based gray wolf optimization algorithm for multiple path routing on IoT network (SFG-CHS-IoT) and energy-aware routing in the IoT with improved grasshopper metaheuristic algorithm with chaos theory and fuzzy Logic (FLGOA-CHS-IoT).

Internet of Things (IoT) based real-time applications are highly prone to sensor faults because of their deployment in a risky environment.One of the important applications of IoT that is in great demand in this modern era is the air quality monitoring system because of the increase in air pollution over the years around the globe.Hence handling the reliability issue of air quality sensors is of great concern.In this article, a data based diverse fault detection and classification technique is implemented to overcome the sensor fault issue involved in air quality monitoring systems.The proposed work is a two-phase process; first, a Gaussian Hidden Markov Model (GHMM) is used to perform sensor fault detection on real-time air quality sensor data to detect the presence of fault in sensors followed by performing sensor fault classification using a Support Vector Machine (SVM) on the faulty sensor data obtained from fault detection to identify the most difficult to find sensor fault types like 'Out of bounds' and 'Spike fault'.The proposed technique efficiently carries out sensor fault detection and classification with an overall accuracy of 99.48%.Compared to Machine Learning (ML) algorithms like Logistic Regression (LR), Naive Bayes (NB), and Multi-Layer Perceptron (MLP) the diverse proposed technique works well with a precision of 99.50%, recall of 99.08%, and an F1-score of 99.53%.

Attention-based neural machine translation (attentional NMT), which jointly aligns and translates, has got much popularity in recent years. Besides, a language model needs an accurate and larger bilingual dataset_ from the source to the target, to boost translation performance. There are many such datasets publicly available for well-developed languages for model training. However, currently, there is no such dataset available for the English-Afaan Oromo pair to build NMT language models. To alleviate this problem, we manually prepared a 25K English-Afaan Oromo new dataset for our model. Language experts evaluate the prepared corpus for translation accuracy. We also used the publicly available English-French, and English-German datasets to see the translation performances among the three pairs. Further, we propose a deep attentional NMT model to train our models. Experimental results over the three language pairs demonstrate that the proposed system and our new dataset yield a significant gain. The result from the English-Afaan Oromo model achieved 1.19 BLEU points over the previous English-Afaan Oromo Machine Translation (MT) models. The result also indicated that the model could perform as closely as the other developed language pairs if supplied with a larger dataset. Our 25K new dataset also set a baseline for future researchers who have curiosity about English-Afaan Oromo machine translation.

We present a review of Neural Machine Translation (NMT), which has got much popularity in recent decades. Machine translation eased the way we do massive language translation in the new digital era. Otherwise, language translation would have been manually done by human experts. However, manual translation is very costly, time-consuming, and prominently inefficient. So far, three main Machine Translation (MT) techniques have been developed over the past few decades. Viz rule-based, statistical, and neural machine translations. We have presented the merits and demerits of each of these methods and discussed a more detailed review of articles under each category. In the present survey, we conducted an in-depth review of existing approaches, basic architecture, and models for MT systems. Our effort is to shed light on the existing MT systems and assist potential researchers, in revealing related works in the literature. In the process, critical research gaps have been identified. This review intrinsically helps researchers who are interested in the study of MT.

Semantic segmentation is crucial for autonomous driving as the pixel-wise classification of the surrounding scene images is the main input in the scene understanding stage. With the development of deep learning technology and the impressive hardware capabilities, semantic segmentation has seen an important improvement towards higher segmentation accuracy. However, an efficient sematic segmentation model is needed for real-time applications such as autonomous driving. In this paper, we discover the potential of employing the design principles of two deep learning models, namely PSPNet and EfficientNet to produce a high accurate and efficient convolutional autoencoder model for semantic segmentation. Also, we benefit from data augmentation for better model training. Our experiment on CamVid dataset produces optimistic results and the comparison with other mainstream semantic segmentation models justifies the used approach.

The past technique of manual dataset preparation was time-consuming and needed much effort. Another attempt to the data acquisition method was using web scraping. Such web scraping tools also produce a bunch of data errors. For this reason, we developed "Oromo-grammar" a novel Python package that accepts a raw text file from the user, extracts every possible root verb from the text, and stores the verbs into a Python list. Our algorithm then iterates over list of root verbs to form their corresponding list of stems. Finally, our algorithm synthesizes grammatical phrases using the appropriate affixations and personal pronouns. The generated phrase dataset can indicate grammatical elements like numbers, gender, and cases. The output is a grammar-rich dataset, which is applicable to modern NLP applications like machine translation, sentence completion, and grammar and spell checker. The dataset also helps linguists and academia in teaching language grammar structures. The method can easily be reproducible to any other language with a systematic analysis and slight modifications to its affix structures in the algorithm.

An important sector of India's fishing industry is prawn farming. Gross prawn exports came to 5,90,275 MT (metric tonnes) and were worth $4,426.19 million. White-leg prawn exports decreased from 5,12,204 MT to 4,92,271 MT in 2020–21. To show the problem with the traditional approach of monitoring brackish water prawn aquaculture, a study was conducted. After further investigation, it became clear that the farmers were up all night trying to maintain the perfect water quality needed to produce healthy shrimp. This is because shrimp ponds have a tolerance level for a variety of environmental factors, including temperature, pH (potential of hydrogen), and humidity. As a result, the farmers must continuously check on the pond's status throughout the night. An Intelligence forecasting approach would address the complexity of farmer's crop monitoring issues. A hybrid intelligence mechanism for forecasting efficiently and handling a large amount of streaming data is achieved through Auto regressive long short-term memory integrated moving averages (ARLSTMIMA ). The intelligent algorithm is embedded into Tiny ML an IoT device developed for getting real-time data. As a result of this procedure, the pond's water quality and environmental conditions are checked to guarantee a healthy prawn crop. To get real-time environmental data and weather behavior of brackish water shrimp aquaculture as well as Real-time data collection over some time from various shrimp farming locations, the goal of this work is to construct a small ML-based resilient and wireless sensor network. For additional ML training, the appropriate sensor data are gathered and input into Google Sheets. Tiny ML thereby forecasts the sensor data before it is displayed. With this method, aquaculture producers can save time and money by receiving information at the right times from pre-established designs and achieving an efficiency of 95.16 in the prediction in comparison with the existing forecasting mechanisms such as Random Forest regressor, ARIMA, and LSTM by outperforming with the highest accuracy in forecasting values. In achieving higher accuracy, an optimal architectural design is achieved by inducting the ARLSTMIMA which has a decreased time complexity in comparison with other architectures in forecasting with time complexity of the order O(n 2 ) with the least time for forecasting is achieved.

Design and development of simple, affordable and 'turn-ON' fluorescent probes for fluoride ion sensing is an incessant research target over the decades. In this context, we have developed the new benzothiophene derivatives for the selective detection of trace-level fluoride ions. The synthesized derivatives were meticulously characterized using pivotal techniques and contented results were accomplished. Intriguingly, the developed probe is selectively responded to a trace amount of fluoride ions. The fluorescence quantum yield of the probe is also enhanced upon introducing the fluoride ion, thus this probe could be act as a 'turn-ON' fluorescent probe. The mechanism of fluoride ion detection was elucidated using H-1 NMR and FT-IR investigations. The recovery and reversibility studies of the probe were conducted and the probe was stable upto 10 cycles. On the other hand, a portable Arduino-based platform is developed for the first time to validate the experimental results. The arduino microcomputer device is interfaced with the RGB sensors which identify the colour changes and quantifies fluoride concentration with respect to the RGB values. The RGB results were also shared to the developed android application through wired/wireless tethering. The application is also designed to share the data with remote users through cloud platform. (C) 2021 Elsevier B.V. All rights reserved.

Manufacturing ecosystems that are real-time, smart, transparent, and self-reliant are the goal of the 4th industrialized renaissance (Industry 4.0). Industry 4.0 relies heavily on a well-functioning network and computing infrastructure to function at its optimum potential. An influential Industry 4.0 platform relies heavily on solitary chip computing and machine learning (ML) techniques. With Industry 4.0, the ability to identify malfunctions is critical because of the self-optimized functioning of equipment and the abundance of significant information gathered. This paper proposes an efficient and powerful ML model, namely CNN-BLSTM (Convolution Neural Network Bi-Directional Long Short-Term Memory) based fault prognosis assessment of machinery in Industry 4.0 ecosystem. Machine characteristics such as temperature, vibration, and pressure can be controlled using smart objects like actuators and sensors embedded in industrial machinery's practicality processes. This method allows for more thorough and effective diagnosis of machinery. All three variants of faults, namely transient, intermittent, and permanent, are considered. The identified evidence in this investigation reveals that our technique has a significant capability to handle unfavorable consequences due to manufacturing faults in contrast to existing strategies.

The multihop underwater acoustic sensor network (M-UASN) collects oceanographic data at different depths. Due to the harsh underwater environment, the route is a major research problem. In this article, the routing path from source to sink is adapted by the vector-based forwarding (VBF) protocol. In VBF, based on the vector size, the packets are transmitted within the pipe from hop to hop. The limitation is that every node inside the pipe vector receives the same packets. That results in a waste of battery energy and, in turn, reduces the lifetime of the acoustic node. To enhance, in this article, it is divided into two parts. The first part is that the first hop nodes from the source are optimally divided into subsets such that all the second hop nodes will receive packets from each subset. This optimal route cover subset is identified with an evolutionary memetic algorithm. The election of subset is done through a voltage reference model, and the battery voltage is modeled mathematically and the role of the nodes is given based on the voltage profile and Markov probability approach. This method enhances the lifetime of the underwater acoustic network when compared with the VBF algorithm. The proposed model also provides improved throughput and equal load sharing. The results are compared with VBF, quality-of-service aware evolutionary routing protocol (QERP), and multiobjective optimized opportunistic routing (BMOOR).

Internet of Things (IoT) based healthcare monitoring system is becoming the present and the future of the medical field around the world. Here the monitoring system acquires the regular health details of hospital discharged patients like elderly patients, patients out of critical operations, and patients from remote areas, etc., and transmits it to the doctors. But the system is highly susceptible to sensor faults. Hence a data-driven hybrid approach of Hidden Markov Model (HMM) based on baum-welch algorithm with Support Vector Machine (SVM) is proposed to predict the abnormality caused by the medical sensors. The proposed work first perform the abnormality detection on the sensor data using the HMM based on baum-welch algorithm in which the normal data is separated from abnormal data followed by classifying the abnormal data as critical patient data or sensor fault data using the SVM. Here the proposed work efficiently performs fault diagnosis with an overall accuracy of 99.94% which is 0.59% better than the existing SVM model. And also a comparison is made between the hybrid approach and the existing ML algorithms in terms of recall and F1-score where the proposed approach outperforms the other algorithms with a recall value of 100% and F1-score of 99.7%.

Autonomous driving research has progressed significantly in recent years. In order to travel safely, comfortably, and effectively, an autonomous car must completely comprehend the driving scenario at all times. The key criteria for a comprehensive understanding of the driving situations are proper perception and localization. The research on perception and localization of autonomous cars has increased substantially as a result of recent breakthroughs in AI, such as the wide range of deep learning approaches. However, owing to environmental uncertainties, sensor noise, and the complex interaction between the parts of the driving environment, additional study is required to achieve totally trustworthy perception and localization systems. In this survey, we demonstrate the advanced perception and localization processes in the field of autonomous driving. We show how cutting-edge approaches and practices have brought today’s autonomous cars closer than ever to completely comprehending the driving environment.

The Industry 4.0 technology relies on Single-board computers and the Internet of Things (IOT) and Machine Learning (ML). In addition, sensory detectors, controllers, and a communication interface are employed to address the demands of distant supervision and operational management. In today's industrial environment, understanding machines and giving effective interpretation and prognostics is a challenging issue. This paper presents an effective on-process identification tool for monitoring and advising the operator based on sensor parameters. The data is analysed with the Fast Fourier Transform (FFT) inference and machine learning strategies to detect the production calibre of an industrial Computer Numerical Control (CNC) machine, including vibration, temperature, humidity, and operating temperatures. The vibration parameter is provided to the FFT algorithm to produce frequency, and the diameter dataset is also provided manually from the hole diameter in the job piece to correctly monitor and inspect the product quality to prognostics to the fault in machines. Improper machine settings cause varied vibrations and changes in parameters, whereas our Industry 4.0 module detects and warns about faulty parameters. The device is put through its trials using three distinct machine learning approaches, and the results are collected. ML combines the outcomes of many baseline estimators to provide better results. This research work utilizes the Linear regression model since it has a high-power detection ability and minimizes variance as well as bias. The Single board computer using FFT and linear regression monitoring gives greater data accuracy of 97.6 percent on comparing the outcomes of 5.4%improved efficiency than K-Nearest Neighbourhood (KNN), 95.5% Random Forest Network (RN), and 95% Support Vector Machine (SVM) algorithms. The proposed system was validated via the deployment of suitable test scenarios, illustrating the technique's effectiveness in manufacturing environments.

In this work, we have employed an intramolecular charge transfer-based DMN colorimetric probe for the rapid naked-eye detection of cyanide ions in solution as well as real water samples. The intermolecular interaction between the DMN probe and cyanide ions in solution was investigated using a combination of spectroscopic and computational methods in this study. The DMN probe exhibited a selective colorimetric response for cyanide ions over the other anions exposed. The cyanide sensing mechanism of the probe has been investigated by 1H NMR titration and density functional theory calculations. The results reveal that the colorimetric response of the DMN probe is due to the Michael adduct formation in the β-conjugated position of the dicyanovinyl group with cyanide, which blocks intramolecular charge transfer transition. Under optimized experimental conditions, the DMN probe showed a linear plot in the concentration range of 0.01-0.25 μM, with a detection limit of 23 nM. Further, a 3D printed portable accessory for the smartphone and an open-source android application is developed to suit the DMN probe for on-site work. In addition, we have developed the microfluidic paper-based analytical device that could selectively detect cyanide ions at very low concentration using a colorimetric DMN probe. In addition, the DMN probe was effectively used to determine the cyanide ion in a variety of water samples.

Diabetic retinopathy disease is one of the notorious metabolic disorders happens due to increase of blood sugar level in human body. In computer vision, images are recognized as the indispensable tool for precise prediction and diagnosis of diabetic retinopathy. Therefore, the proposed research study considers the fundus images of various patients containing the diabetic disease. Basic idea behind this research is to introduce a stochastic neighbor embedding (SNE) feature extraction approach for the sake of dimensional reduction and unnecessary noise removal from the fundus images. After feature extraction, the proposed optimized deep belief network (O-DBN) classifier model is capable of measuring the image features into various classes that gives the severity levels of diabetic retinopathy disease. Moreover, the proposed cloud-enabled diabetic retinopathy prediction system using the SNE feature extraction and O-DBN classification model could outperform the existing online prediction systems in terms of sensitivity, specificity, F1-score, prediction time and accuracy.

Wireless adhoc and sensor networks play a critical role in giving data to the Internet of Things ecosystem. Ambulance services and vehicular adhoc networks connect to local routers to provide reliable data connectivity between the source and the sink. This study paper focuses on the availability of routers that can handle data. The system will randomly break down when it is idle or providing a packet. If a server fails while providing a service to a node, the service is terminated immediately, and the repair procedure begins. The pre-empted packet service is started after the repair is completed. The breakdown and repair constraints’ transient probability are estimated. With transient state probabilities, the article presents a more comprehensive view of data flow.

Autonomous mission capabilities with optimal path are stringent requirements for Unmanned Aerial Vehicle (UAV) navigation in diverse applications. The proposed research framework is to identify an energy-efficient optimal path to achieve the designated missions for the navigation of UAVs in various constrained and denser obstacle prone regions. Hence, the present work is aimed to develop an optimal energy-efficient path planning algorithm through combining well known modified ant colony optimization algorithm (MACO) and a variant of A*, namely the memory-efficient A* algorithm (MEA*) for avoiding the obstacles in three dimensional (3D) environment and arrive at an optimal path with minimal energy consumption. The novelty of the proposed method relies on integrating the above two efficient algorithms to optimize the UAV path planning task. The basic design of this study is, that by utilizing an improved version of the pheromone strategy in MACO, the local trap and premature convergence are minimized, and also an optimal path is found by means of reward and penalty mechanism. The sole notion of integrating the MEA* algorithm arises from the fact that it is essential to overcome the stringent memory requirement of conventional A* algorithm and to resolve the issue of tracking only the edges of the grids. Combining the competencies of MACO and MEA*, a hybrid algorithm is proposed to avoid obstacles and find an efficient path. Simulation studies are performed by varying the number of obstacles in a 3D domain. The real-time flight trials are conducted experimentally using a UAV by implementing the attained optimal path. A comparison of the total energy consumption of UAV with theoretical analysis is accomplished. The significant finding of this study is that, the MACO-MEA* algorithm achieved 21% less energy consumption and 55% shorter execution time than the MACO-A*. moreover, the path traversed in both simulation and experimental methods is 99% coherent with each other. it confirms that the developed hybrid MACO-MEA* energy-efficient algorithm is a viable solution for UAV navigation in 3D obstacles prone regions.