Journal of Information Technology Management
Volume:15 Issue: 2, Spring 2023

Digital twin-enabled neural networks will develop innovative processes in feature selection and simulation. In addition, this methodology will have development in autonomous driving, natural language processing, healthcare, and many other fields. Recently sensors have been widely used for environment monitoring, and massive data has to be processed efficiently and effectively, which requires managed neural architectures for sustainable computing. The sustainable digital twin-empowered architectures create new biological evolution simulation algorithms and intelligent system architectures for supervised and unsupervised learning. Some of today's fundamental artificial intelligence issues, including adaptive machine learning and neuromorphic cognitive models, can be overcome by this methodology. The goals of this special issue on digital twin-enabled neural network architecture management for sustainable computing aim to pay attention to the researchers and industries towards recent advances in decision-making algorithms, neural network models and architectures for faster processing.

Wireless Sensor Networks (WSNs) have been employed in various real-time applications and addressed fundamental issues, such as limited power resources and network life. Several sensor nodes in a WSN monitor the actual world and relay discovered data to base stations. The biggest issue with WSN is that the sensors have a limited lifetime and use much electricity to relay data to the base station. This paper proposes an improved PSO-based Enhanced Distributed Energy Efficient Clustering (EDEEC) algorithm to extend the network's life and reduce power consumption. Clustering is the process of forming groups of sensor nodes. The cluster aims to improve the network's scalability, energy efficiency, and other characteristics. The particle swarm optimization algorithm is modified to obtain energy-efficient WSNs. The assessment is based on the essential WSN characteristics, including network lifetime and energy efficiency (power consumption). Compared to LEACH, HEED, and DEEC, our proposed IPSO-EDEEC uses less energy.

Cloud Computing, employed in various applications and services, refers to using computational resources as a service depending on customer needs via the Internet. The computing paradigm is built on data outsourcing to third-party-controlled data centers. Despite the significant developments in Cloud Services and Applications, various security vulnerabilities remain. This research proposes the EBBKG Model for Efficient Data Sharing in Cloud. For secure data sharing in the cloud, the approach combines BBKG with ABS. The method offers good data management that efficiently specifies the subsequent processing processes. The paradigm imposes encrypted access control, along with specific enhanced access capabilities. Secondly, the user's privacy may be adequately protected with a secure authentication paradigm that employs ABS to safeguard the user's private data. The key is optimized using BOA to enhance security and cloud providers and limit dangerous user threats using these implementations. Criteria like security, time complexity, and accountability govern the suggested method's effectiveness.

A greater community of researchers widely studies fog computing as it reduces the massive data flow to the existing cloud-connected network and performs better for real-time systems that expect a quick response. As the fog layer plays a significant role in a fog-cloud system, all of the devices participating in fog computing must be balanced with appropriate load to upstretched the system performance. The proposed method is founded on a tree-based dynamic resources arrangement mechanism that refreshes the fog clusters created using Fuzzy C Mean (FCM) to increase the speed of resource allocation. With the help of Fuzzy rule-based load calculation and intra-cluster job allocation, the load inside the group is maintained. The system also has the facility of inter-cluster job forwarding, which works on demand. A novel load balancing strategy, Real-Time Flexi Forwarded Cluster Refreshing System (RTFRS) is proposed by which all the tasks can be handled efficiently within the fog cloud system. The proposed system is designed so that overall complexity is not upraised and becomes suitable for fog computing architecture with low processing capacity by maintaining the quality of service. Experimental results show that the proposed model outperforms standard methods and algorithms used in fog computing concerning average turnaround time, average waiting time, resource utilization, average failure rate, and the load on the gateway.

In intrusion detection applications, wireless sensor networks are commonly used. Many research literature papers are aimed at generating and evaluating the information on intruder detection in terms of probability of detection and false alarm rates. In two modalities, the model for acoustic signal and the sensor probability model, and in this research paper, the problems of passive motive intrusion detections have been solved. The aim is to establish a three-stage hierarchy to determine if mobile intruders are present. The sensor nodes at the fundamental level have a k-mean clustering grouping. For binary hypothesis testing, the strengths or probabilities in the cluster head are employed. Cluster leaders send their judgments to the Fusion Centre (FC) after completing a Likelihood Ratio Test (LRT) to ensure invaders are correctly inferred. A numerical analysis of the signals received determines the optimal value for probability computation. The resulting fusion rule maximizes detection likelihood regarding the allowed falsifying rates. The number of absolute sensor nodes determines the exact fusion rule. Compared to earlier fusion rules, simulation results show that the new fusion rule has a better ability to follow mobile invaders and enhanced accuracy and detection speed.

Social media is a popular data source in the research community. It provides different opportunities to design practical applications to favor humanity and society. A significant amount of people consumes social media content. Thus, sometimes content promoters and influencers publish misleading and toxic content. Therefore, this paper proposes an unhealthy content filtering system using the information retrieval model SOIR to identify and remove poisonous content from social media. The Semantic query Optimization-based Information Retrieval (SOIR) uses Fuzzy C Means (FCM) clustering to produce a particular data structure. To incorporate a query generation technique for the generation of multiple queries to increase the probability of correct outcomes. The SOIR model is modified in this work to utilize the model with the social media toxic content filtering model. The model uses linguistic and semantically information to craft new feature sets. The Part of Speech (POS) tagging is used to construct the linguistic feature. Finally, the pattern-matching algorithm is designed to classify the tweets as toxic or nontoxic. Based on lexical and semantic analysis of similar semantic queries (Tweets), it is identified with the class labels of the tweets. Twitter text posts are used to create training and test samples in this context. Here, a total of 2002 tweets are used for the experiment. The experimental study has been carried out with the different I.R. models (K-NN, Cosine) based on precision, recall, and F1-Score demonstrating the superiority of the proposed classification model

The global demand for food can be eliminated by precision farming. This research work proposes a low-cost IoT-enabled handy device to measure soil water content. Three different sensor probes are designed in COMSOL Multiphysics 5.4 and fabricated using PCB Technology. The designed sensor probes are calibrated to effectively measure moisture content for three different soil types (silt/sandy/clay). An electronic system has been programmed according to Optimized-Moisture-Value (OMV) algorithm to read and collect the soil moisture information. Three sensor probes, capacitance, and voltage responses are analyzed using linear fitting. It has been observed from the response data that model B's performance is better than the other two presented models in terms of soil moisture. The obtained goodness of fitness value for model B is around 0.999 for all the categories of soils. The electronic system is built around W78E054D and ESP8266 controllers. The W78E054D controller is used to excite the sensor probe with a signal having a frequency of 500 kHz. The IoT-enabled controller ESP8266 reads and collects the soil moisture data according to the OMV algorithm.

The Industrial Internet of Things (IIoT) is a potential platform for developing industry 4.0 and its related applications, especially in cyber-physical systems. Such a new trend in manufacturing sectors offers further potential to optimize operations, realize business models, and reduce costs. Such accomplish may also lead to complex and complicated tasks; hence, to deal with such issues, Reference Architecture Model Industry 4.0 (RAMI 4.0) is developed to structure Industry 4.0. In this paper, the standardized framework is considered RAMI 4.0 and its integration with an IIoT software named Software Platform Embedded Systems (SPES). Integrating Model-Based Engineering (MBE) with a framework requires using a deep learning model called Recurrent Neural Network (RNN). The RNN-MBE, which optimizes the entire process, is responsible for optimizing the process and reducing industry costs. The optimization problem has been fixed, and the MBE simulation has shown that using the proposed MBE is efficient.

The scope of the Internet of Things (IoT) becomes inevitable in the communication and information-sharing routines of human life, similar to any technological architecture. The IoT is also not exempted from vulnerability to security issues and is even more vulnerable as the networks of IoT are built of non-smart devices. Though the few contributions endeavored to defend against the botnet's attacks on IoT, they partially or poorly performed to defend against the flash crowd or attacks by botnets on IoT networks. In this context, the method “Flash Attack Prognosis by Ensemble Supervised Learning for IoT Networks” derived in this manuscript is centric on defending the flash attacks by botnets. Unlike contemporary models, the proposed method uses the fusion of traditional network features and temporal features as input to train the classifiers. Also, the curse of dimensionality in the training corpus, which is often, appears in the corpus of flash attack transactions by a botnet, has addressed by the ensemble classification strategy. The comparative analysis of the statistics obtained from the experimental study has displayed the significance and robustness of the proposed model compared to contemporary models

Extracting sentiments from the English-Telugu code-mixed data can be challenging and is still a relatively new research area. Data obtained from the Twitter API has to be in English-Telugu code-mixed language. That data is free-form text, noisy, lexicon borrowings, code-mixed, phonetic typing and misspelling data. The initial step is language identification and sentiment class labels assigned to each tweet in the dataset. The second step is the data normalization task, and the final step is classification, which can be achieved using three different methods lexicon, machine learning, and deep learning. In the lexicon-based approach, tokenize each tweet with its language tag. If the language tag is in Telugu, transliterate the roman script into native Telugu words. Words are verified with TeluguSentiWordNet, and the Telugu sentiments are extracted, and English SentiWordNets are used to extract sentiments from the English tokens. In this paper, the aspect-based sentiment analysis approach is suggested and used with normalized data. In addition, deep learning and machine learning techniques are applied to extract sentiment ratings, and the results are compared to prior work.

Measurement of soil moisture and control of irrigation according to the measured data is crucial in agriculture fields where water scarcity is always a serious issue. For this purpose, a cost-effective distributive network system has been proposed and developed using technology like IoT to control complex irrigation processes. An internet-enabled embedded moisture sensing unit was designed that consists of a capacitive sensor probe and electronic system to process the soil moisture value. The sensor probe was calibrated for six different varieties of soil using the Thermo gravimetric method. The output response is inspiring, with a goodness of fit value of 0.99. Algorithms are developed for irrigation control that operates by a developed web-based application from the control station. The system was implemented at a total cost of 122.37 US dollars and tested in cassava agriculture field for loam soil in Nagaland, India, for 91 days and showed magnificent water saving of up to 95% compared with traditional approaches.