Search

The methodologies based on neural networks are substantial to accomplish sentiment analysis in the Social Internet of Things (SIoT). With social media sentiment analysis, significant insights can produce efficient and intelligent applications. Neural networks such as recurrent neural networks (RNNs) and convolution neural networks (CNNs) have been considered widely in many text classification tasks. However, RNNs are computationally expensive and require complex training to capture contextual information and long-term dependencies. Similarly, traditional CNNs must stack multiple convolutional layers, requiring massive computations and additional parameters. To address these problems, this work initialized the novel architecture, in which contextual representations (CRs) based on the textual framework are proposed at the initial step. In CRs, state-of-the-art word representation models, such as GloVe (global vectors) and FastText (subword information), collectively produce word representations upon the input sequence using a weight mechanism. Secondly, a unique way is introduced: a three-parallel layered dilated convolutional network with global mean pooling. The experimental results show that the proposed methods when compared with baseline methods, the dilation in CNNs following CRs significantly increases the accuracy from 72.45 to 98.98% and reduces computational resources. [ABSTRACT FROM AUTHOR]

Pomology, also known as fruticulture, is a significant contributor to the economies of many nations worldwide. While vertical farming methods are not well-suited for fruit cultivation, substrate-based cultivation is commonly practiced. Vertical farming methods use no soil for cultivation of the plants, and the cultivation is done in vertically stacked layers. Therefore, smaller herbs are best suited for such cultivation, whereas, the majority of the fruit trees are big and woody. Therefore, vertical farming methods are not well suited for fruit trees. However, to maximize fruit production, smarter substrate cultivation methods are needed. Utilizing remote sensing techniques, such as Internet of Things (IoT) devices, agriculture sensors, and cloud computing, allows for precision agriculture and smart farming in autonomous systems. Nevertheless, a lack of understanding of fruit nutrient requirements, growing conditions, and soil health conditions can result in reduced fruit production. To address these challenges, this paper proposes an intelligent model based on machine learning that recommends the best fruit to grow based on prevailing soil and climatic conditions. The system is trained on a dataset that includes details on eleven different fruits, such as Nitrogen (N), Phosphorous (P), Potassium (K), temperature, humidity, pH, and rainfall. The model takes into account the soil type and nutrient contents to recommend the most suitable fruit to grow in the prevailing climate. To enhance the model's efficiency, two novel techniques, Gradient-based Side Sampling (GOSS) and Exclusive Feature Bundling (EFB), have been incorporated. The results show that the proposed system has achieved 99% accuracy in recommending the right fruit based on the given environmental conditions. As a result, this system has the potential to significantly improve the profitability of the pomology industry and boost national economies.Article Highlights: This article aims at the creation of an efficient recommendation model for fruit cultivation in soil medium by analyzing the soil nutrient contents and the existing climatic conditions. The most suitable fruit plant corresponding to the existing conditions and soil type is recommended for an enhanced yield of the plant. Three climatic parameters, i.e., temperature, humidity, and rainfall; along with four soil-based parameters, i.e., pH, N content, P content, and K content are considered as the required growing condition for eleven varieties of fruits. To ensure enhanced accuracy, a hundred entries for each fruit type is entered in the dataset. The created dataset is then divided in the proportion of 7:3 as training data: testing data and Light Gradient Boosting Machine (Light GBM) model is applied to the created dataset. The correlation of all the parameters is checked for an efficient recommendation of fruits. Finally, the model is evaluated and its efficiency is checked. [ABSTRACT FROM AUTHOR]

IPv6 over Low Power Wireless Personal Area Network (6LoWPAN) provides IP connectivity to the highly constrained nodes in the Internet of Things (IoTs). 6LoWPAN allows nodes with limited battery power and storage capacity to carry IPv6 datagrams over the lossy and error-prone radio links offered by the IEEE 802.15.4 standard, thus acting as an adoption layer between the IPv6 protocol and IEEE 802.15.4 network. The data link layer of IEEE 802.15.4 in 6LoWPAN is based on AES (Advanced Encryption Standard), but the 6LoWPAN standard lacks and has omitted the security and privacy requirements at higher layers. The sensor nodes in 6LoWPAN can join the network without requiring the authentication procedure. Therefore, from security perspectives, 6LoWPAN is vulnerable to many attacks such as replay attack, Man-in-the-Middle attack, Impersonation attack, and Modification attack. This paper proposes a secure and efficient cluster-based authentication scheme (CBAS) for highly constrained sensor nodes in 6LoWPAN. In this approach, sensor nodes are organized into a cluster and communicate with the central network through a dedicated sensor node. The main objective of CBAS is to provide efficient and authentic communication among the 6LoWPAN nodes. To ensure the low signaling overhead during the registration, authentication, and handover procedures, we also introduce lightweight and efficient registration, de-registration, initial authentication, and handover procedures, when a sensor node or group of sensor nodes join or leave a cluster. Our security analysis shows that the proposed CBAS approach protects against various security attacks, including Identity Confidentiality attack, Modification attack, Replay attack, Man-in-the-middle attack, and Impersonation attack. Our simulation experiments show that CBAS has reduced the registration delay by 11%, handoff authentication delay by 32%, and signaling cost by 37% compared to the SGMS (Secure Group Mobility Scheme) and LAMS (Light-Wight Authentication & Mobility Scheme). [ABSTRACT FROM AUTHOR]

• The abnormal conduction or disturbance in the cardiac activity is called arrhythmia, except for sinus rhythm. • Over the last decades, contemporary health-related device usage has increased the demand for efficient computational models for real-time analysis of cardiac arrhythmia. • As a result, there is a need to investigate the exact features of PVC arrhythmia, which assist in avoiding biased diagnosis. • This study opens the door for a new direction of research using our unique, fully automatic model for PVC arrhythmia classification (FAPAC). • Our proposed FAPAC model successfully achieved 99.97% of accuracy, 99.99 % sensitivity,99.99% specificity, and 99.98% positive predictivity. Cardiac arrhythmias are one of the leading causes of increased mortality worldwide and place a heavy burden on the medical environment. Premature ventricular contraction is the disturbance in electrical activity which is the most dangerous arrhythmia. Frequent occurrence of this type of arrhythmia in a regular heartbeat can lead to sudden cardiac death. Over the last decades, contemporary health-related device usage has increased the demand for efficient computational models for real-time analysis of cardiac arrhythmia. Despite notable experiments that have been done in the past decades, due to the intricate nature of PVC arrhythmia, success stories are still unsatisfying. There are numerous morphological and temporal variations present in ECG signals due to the inter-patient variability issue; extracting important characteristics of ECG signals is the most challenging task. As a result, there is a need to investigate the exact features of PVC arrhythmia, which assist in avoiding biased diagnosis. Precisely predicting it is a difficult task due to the negative polarity of PVC arrhythmia, the irregular mechanic of the ECG cycle, and anomalies between the normal cardiac rhythm. Furthermore, most of the studies in the literature followed the public benchmark dataset for the PVC arrhythmia classification, which is already pre-processed dataset. This study opens the door for a new direction of research using our unique, fully automatic model for PVC arrhythmia classification (FAPAC). This study designed an ECG monitoring module using the IoMT devices to obtain the real-time dataset for experiments and extract the relevant features from ECG signals. To classify the ECG beats, the fastest extended version of the recurrent neural network (RNN) model cyclic echo state networks to predict PVC arrhythmia. Our proposed FAPAC model successfully achieved 99.97% of accuracy, 99.99 % sensitivity,99.99% specificity, and 99.98% positive predictivity using the MIT-BIH-arrhythmia dataset, which is relatively higher than compared studies. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is a revolutionary technique of sharing data for smart devices that generates huge amounts of data from smart healthcare systems. Therefore, healthcare systems utilize the convergence power and traffic analysis of sensors that cannot be satisfactorily handled by the IoT. In this article, a novel mutation operator is devised and incorporated with the differential evolution (DE) algorithm. Two tests have been conducted in the validation process. Firstly, the newly dual adaption-based operators incorporated with the differential evolution algorithm are being proposed. The proposed approach provides sufficient diversity and enhances the search speed of nature's local and global search environments in the problem. The proposed method incorporates the application of IoT-based smart healthcare. Second, an application-based test has been conducted, in which the proposed approach is applied to the application in the smart healthcare system. Therefore, IoT sensor deployment is an optimization problem to minimize service time, delay, and energy loss by considering the communication constraint between sensors(objects). The proposed algorithm is applied in this article to solve this optimization problem. Further, in the experimentation and comparative study, the proposed method is superior to the standard evolutionary algorithms in IoT applications concerning the minimum number of function evaluations and minimization of traffic services. The proposed approach also achieves efficiency in the minimum loss of energy in each service and reduces load and delay. [ABSTRACT FROM AUTHOR]