Recognizing the urgency of addressing the issue of deceptive fraudulent messages in the contemporary digital landscape that lead to financial losses or distressing incidents, detecting and identifying such fraudulent or spam messages is imperative before they reach users' inboxes. This article proposes the eXplainable Artificial Intelligence (XAI) - SHAP-based feature selection framework (FSSHAP) for the classification of spam messages using the random forest algorithm. The model relies on the selection of significant handcrafted features based on SHapley Additive exPlanations (SHAP) values. The features are selected based on the threshold value determined using SHAP values. The research uses three datasets, including the short message services in Dravidian languages like Tamil, Kannada, Telugu, and Malayalam. The traditional feature selection techniques are compared with the proposed FSv values approach in various performance metrics. This comprehensive approach aims to mitigate the impact of fraudulent messages, safeguarding users from potential harm in the digital realm.

Smartphone-based Human Activity Recognition (HAR) uses spatiotemporal time series data collected from a smartphone’s in-built accelerometer, gyroscope, and magnetometer sensor. Real-time HAR datasets such as UCI-HAR and UCI-HAPT extract time and frequency domain statistical features for activity recognition from the collected time series signals. Various Machine Learning techniques have been proposed in the perspective of feature selection through ensemble, traditional, hybrid, and meta-heuristic-based techniques to improve the recognition performance. Though the feature selection techniques have shown promising results, the computational time and selection of valid significant features for better classification performance still need to be included. Moreover, these techniques are highly parameter-dependent and critical to threshold values used for experimentation. This research proposes a novel method of parameter-free ensemble feature selection by combining traditional feature selection algorithms with the concept of association rule mining to obtain the Maximal Feature Subset (MFS), which is used for training and testing the classification model for HAR. Mathematical association rule mining is framed rather than the traditional one to select the associated frequent feature(s) from the feature set evolved by traditional techniques. Experimentation has been carried out on UCI-HAR and UCI-HAPT, and the proposed method has increased the classification efficiency by selecting significant features and reduces computation time significantly.

With the exponential growth of mobile communication, the prevalence of SMS spam has become a significant concern, necessitating robust filtering mechanisms. This research focuses on optimizing SMS spam filtering in mobile applications by selecting the refined set of features for the two multilingual SMS Spam datasets. This paper uses eXplainable AI (XAI) approach for selecting the significant feature set based on the SHapley Additive exPlanations (SHAP) values. The average of SHAP values is used for setting the threshold value for the dataset. The feature whose feature importance score is greater than the threshold value is included in the significant feature set. Our experimentation demonstrates that employing fewer but highly significant features enhances the efficiency and accuracy of real-time SMS spam detection 90-92%. By leveraging this approach, mobile applications can deploy more resource-efficient and responsive spam filtering processes, thereby improving the overall user experience and security. This research contributes to the ongoing efforts in mitigating the impact of SMS spam, providing a valuable framework for enhancing spam filtering mechanisms in the dynamic world.

The escalating threat of cybercrime, particularly in the form of spam, fraudulent messages, and phishing attacks, poses a substantial risk to individuals who may unknowingly divulge sensitive information to malicious user. This paper addresses the urgent need for a robust spam filtering model capable of detecting and preventing these deceptive messages before reaching users’ inboxes or SMS folders. Focusing on the English spam SMS dataset from the UCI repository, we propose a sequential learning-based spam message filtering framework using the meta-data feature of SMS message. The performance of the meta-data features are compared with the various other methods such as vectorization, sequential model with embedding layers. Performance shown that the Meta-data feature vectors doesn’t depend on any parameters for the process of vectorization and it leverages the performance of the sequential models.

The share of the aged population over and above 65 years increased from 6% in 1990 to 9% in 2019. The percentage of the aged population might increase further to 16% by 2050. Due to socio-demographic changes and nuclear family setups, elder people live alone and encounter many issues at home, especially falls, while doing their daily activities. The probability of a fall inside the bathroom is higher than a fall inside the living place due to specific hazards. Various research works have been proposed to monitor people from falls (fall detection systems -FADE) inside the home environment. However, those systems do not concentrate much on fall detection inside the bathrooms (FADEB). Alternatively, we witness certain smart gadgets for the safety of the elders inside the bathroom, which prevents them from a fall by assisting. However, these gadgets are not designed in a way to report the fall. To overview the FADEB systems, electronic databases such as PubMed, Web of Science (WoS), Scopus, Google Scholar, and DBLP were used to fetch the research works published from 2007 to 2023. The FADEB papers are filtered out and critically reviewed in terms of implementation details concerning data collection, feature extraction, and classification. The specific challenges related to FADEB are quoted that need to be addressed in the near future to monitor the falls inside the bathroom.

Human Activity Recognition (HAR) is the art of identifying and naming activities using Artificial Intelligence (AI) from the gathered raw activity data by utilizing various devices such as Smartphones, Vision systems, Wearable sensors, Ambient sensors, etc., The AI models that includes Machine Learning and Deep Learning techniques implemented towards the HAR is entirely black box model, and many users do not know the mathematics behind the process. Thus, the eXplainable Artificial Intelligence (XAI) model named Shapley Additive exPlanations (SHAP) is implemented in this paper to deal with the local and global interpretations of the Smartphone-based HAR dataset on how it achieves the predictions using an XGBoost classifier and a SHAP Tree explainer. The SHAP visualization plot makes the end-user to understand how each and individual feature/ complete feature set impacts the prediction of activities, either positively or negatively in real-time.

In recent times, numerous human activity recognition (HAR) schemes have been proposed with embedding sensors, wearable devices, smart phones, and vision and ambient sensors. Though the systems have shown better performance they are mostly standalone and still lack the ability to share, host, and perform real-time analysis and visualization of activity data. The Internet of Things (IoT) paradigm has a solution to render the limitations and this will pave the way for HAR in the smart home environment. Thus in this article, an IoT-centric multiactivity recognition system is proposed and deployed on the cloud platform for activity data tracking in the smart home environment. The proposed system collects the real-time data collected using IMU sensors and transmitted to the IoT-Edge Server via Wi-Fi where the data has been fused and classified using light-weight deep learning models. This system has a provision of a Web-based dashboard which is helpful for the home dwellers to monitor the activities in the remote. The performance evaluation justified that the developed system can measure IoT-based activity recognition with greater efficiency in terms of accuracy and F1-score in a shorter response time as of deployment in the cloud platform to detect the activity.

With social networks' increased popularity and smartphone technology advancements, Facebook, Twitter, and short text messaging services (SMS) have gained popularity. The availability of these low cost text-based communication services has implicitly increased the intrusion of spam messages. These spam messages have started emerging as an important issue, especially to short-duration mobile users such as aged persons, children, and other less skilled users of mobile phones. Unknowingly or mistakenly clicking the hyperlinks in spam messages or subscribing to advertisements puts them under threat of debiting their money from either the bank account or the balance of the network subscriber. Different approaches have been attempted to detect spam messages in the last decade. Many mobile applications have also evolved for spam detection in English, but still, there is a lack of performance. As English has been completely covered under natural language processing, other regional languages, such as Urdu and Hindi variants, have specific issues detecting spam messages. Mobile users suffer greatly from these issues, especially in multilingual countries like India. Thus, this paper critically reviews the artificial intelligence-based spam detection system. The review lists out the existing systems that use machine and deep learning techniques with their limitations, merits, and demerits. In addition, this paper covers the scope for future enhancements in natural language processing to efficiently prevent spam messages rather than detect spam messages.

Lumpy skin disease (LSD) is an infectious disease caused by a Poxviridae family of viruses to the cattle, and it is a transboundary disease affecting the cattle industry worldwide. Asia has the highest number of LSD reports from the year 2019 till today, as per the LSD outbreak report data generated by the World Organization of Animal Health. In India, it started in 2022 and resulted in the death of over 97,000 cattle in three months between July and September 2022. LSD transmission is mainly due to blood-feeding insects. The other water feed troughs and contaminated environments are minor cases. According to Cattle India Foundation (CIF) analysis, more than 16.42 lakh cattle have been infected by LSD, and 75,000 have died since July 2022. Thus, the reduction of the livestock mortality rate of cattle is significant today either by analyzing skin diseases or through early detection mechanisms. The LSD research is evolving and attracts various Artificial Intelligence (AI) experts to analyze the problem through image processing, machine learning, and deep learning. This chapter compares the performance of deep and hybrid deep learning models for detecting LSD. The challenges and limitations of this study have been extended into future scope for enhancements in LSD detection.

Daytime-based fall detection systems (FADEs) are designed to prevent falls and help individuals carry out their activities independently. However, FADE for nighttime use is still a challenge for researchers. This article reviews various FADE systems and categorizes the open challenges for the design of nighttime-based FADE.

In this digital era, people are cheated in multiple ways by sending fake messages. Without realizing its impact, they respond to the links the cyber frauds share. This immediate reaction to the fraud messages makes people lose their balance in bank accounts or fall into some other horrible events. These types of fake or spam messages have to be identified earlier before they come to users' Inbox. This paper proposes a Spam message filtering model that extracts significant hand-crafted features and is classified using machine learning algorithms. This research collects 7700 short messages in Dravidian languages like Tamil, Kannada, Telugu, and Malayalam and creates an optimal Spam-Ham filtering framework. Experimentation has also been carried out with a benchmark dataset for performance comparison regarding accuracy, precision, recall, and F1-score.

Data has increased significantly in recent years due to technical and technological advancements, especially in the medical field. Machine learning is an astounding field with precise outcomes in medical domains such as detection, diagnosis, imaging, personalized medicine, etc. The machine learning algorithms analyze the feature-engineered data and produce precise outcomes using different learning methods, such as supervised and unsupervised. In the case of medical applications, these algorithms play a vital role in disease diagnosis and recognition of patterns, even in the absence of medical experts. For instance, during the coronavirus (Covid-19) pandemic, machine learning algorithms have accurately identified the infected persons using chest X-ray recordings, real-time polymerase chain reaction (RT-PCR) tests, and blood samples in the early stages. However, the learning algorithms have certain limitations in recognizing an imbalanced dataset collected for the deadliest diseases such as coronary heart disease, strokes, respiratory illness, COPD, cancers, diabetes, Alzheimer's disease, TB, cirrhosis, etc. To investigate the 2performance of such a class-imbalanced dataset and to improve its performance in terms of false positive rates, this chapter utilizes various methods such as random oversampling, random undersampling, and SMOTE to handle the class-imbalance problem in two different medical datasets. Then, the balanced dataset is evaluated using algorithms like naïve Bayes, decision tree, and k-nearest neighbor in different evaluation models. The learning algorithms are evaluated with familiar metrics – precision, accuracy, recall, F-measure, and ROC area. Experiments on two utilized class-imbalanced datasets show that SMOTE performs better in handling class-imbalance problems.

Human Activity Recognition (HAR) integrates ambient assisted living (AAL), leading to smart home automation for monitoring activities, healthcare, fall detection, etc. Various researchers have proposed a single-resident HAR system for ambient-sensor based smart home data, which is simple, and single-resident is not always the case. Multi-resident recognition is slightly complex and time-consuming. The researchers have made several efforts to generate benchmark datasets, such as CASAS, ARAS, vanKasteren, etc., for baseline comparison and performance analysis. However, these datasets have certain limitations, such as data association, annotation scarcity, computational cost, and even with data collection itself. This paper profoundly analyzed these limitations and manually clustered the activity labels to record the improvement in the performance of the system in terms of both recognition rate and computational time on the ARAS dataset.

Technology is improving day by day and every new face of it is engrossing, making applied science astonishment. Robotics and Artificial Intelligence have taken the world beyond automation. Automation was once considered as a challenge, but now the same technology has stunned the whole world, with the transformation of vision to the reality of live cell robots. In this modern era, evolutionary algorithms with Artificial Intelligence have made an impact on the automation and the creation of rare live-cell species by integrating biological aspects of frog cells. It would be thus useful in various domains to build technologies using self-renewing, and biocompatible materials of which the ideal candidates are living themselves. Thus, this paper presents a live cell robot named Xenobots, its design method, formation, applications, and transformation of live cell robots to humanoid robots that mimic the human brain.

Smart home automation is protective and preventive measures that are taken to monitor elderly people in a non-intrusive manner using simple and pervasive sensors termed Ambient Assistive Living. The smart home produces a large volume of sensor activations to predict an elder’s health status to improve the quality of life and independent living. Machine learning techniques are very familiar and popular in recognizing single resident activities using such a sensor reading. However, multi-resident activities are more complex, and no correlation exists between sensor readings and activities. Recently deep learning and graphical models have been proposed to solve this problem, but it consumes more time to train the model. Moreover, models are primarily executed in parallel, or multi-resident activity recognition has been converted to single for classifying events. This paper proposes a Multi-label Multi-output Hybrid Sequential Model (MLMO-HSM), a feature engineering approach with a hybrid sequential model to recognize the multi-resident activities concurrently in the shortest time. Experimentation has been performed with various machine learning, graphical and deep learning models at the different sizes of the ARAS dataset to validate the efficiency of the proposed model in terms of activity recognition and computation time.

Analyzing big stream data is a significant task for real-time high-voluminous data. Various research works have evolved to analyze those big stream data. However, state-of-the-art systems have certain limitations, such as scheduling time (ST), resource-aware predictive scheduling efficiency (RAPSE), memory consumption (MC), false positive rate (FPR), etc. This paper proposes a hybrid algorithm for predictive resource-aware scheduling to address the issues. The algorithm integrates Elastic-net regularization with Kernelized Fisher Discriminant (KFD) and Map Reduce classification process for a case study on a high volume of human activity recognition (HAR) dataset. The Elastic-net regularization process selects significant features from the dataset and adds certain performance measures for efficient scheduling by the KFD process. The Map Reduce classifier classifies the data streams assigned to a respective processor by the KFD to achieve a low false positive rate. Experimentation has been validated with state-of-the-art systems using standard challenges such as RAPSE, MC, FPR, and ST. Results have also proven that the proposed system has certain merits in implementation over the other state-of-the-art systems in realtime human activity recognition.

Indoor Air Quality (IAQ) monitoring has been a significant research domain in energy conservation. Many energy resources are required to maintain the IAQ using airconditioning or other ventilation systems. Currently, the research works highly optimize an on-demand driven energy usage depending on the occupant present inside the building. In the last decade, numerous research works have evolved for such an optimization by installing sensors and predicting occupants using machine learning techniques. This research fails to deploy non-intrusive sensors and appropriate machine learning algorithms to predict the occupancy count. Advancement in neural network techniques termed deep learning has made significant performance in recognition and cognitive tasks. Thus, this paper proposes a hybrid deep learning model that stacks the convolutional neural network (CNN) and long short term memory (LSTM) to improve the prediction rate of the occupancy count. Experimentation has been carried out in real-time multivariate sensor data for the occupancy estimation and evaluated the performance in terms of accuracy, RMSE, MAPE, and coefficients of determinants.

Human activity recognition (HAR) plays a vital role in the field of ambient assisted living (AAL) for the welfare of the elders who live alone in the home. AAL provides service through ambient sensors, vision systems, smartphone devices, and wearable sensors. Smartphone devices are familiar, portable, cost-effective, and make the process of monitoring easier. Various research works have proposed smartphone-based HAR systems to recognize basic and complex activities. However, the results are not satisfactory for the case of postural transitions such as stand-to-sit, sit-to-sleep, etc. To improve the recognition rate, this paper couples principal component analysis with stacking ensemble learning for dimensionality reduction and classification respectively. Extensive experimentation of UCI repository datasets such as UCI-HAR has been performed and the performances are measured using familiar metrics such as accuracy, precision, and recall.

Online education has gained immense popularity among the working people and students pursuing higher education. Various renowned universities all over the world are offering online degrees and diplomas to all people through digital technologies. This enhances the concept of online classes due to the complete shutdown of educational institutions for an indefinite COVID-19 pandemic situation. Though the online classes are an immediate and emergency paradigm shifting in teaching and learning, it has certain drawbacks that concern the student to a larger extent. To examine the effects of online classes in terms of quality, comfort, and compatibility, this study analyzes the students' perception of various arts, science, and engineering colleges. Drawing on data from various students and its statistical test has inferred various challenges faced by the students with respect to their discipline and living locality. The result of statistical analysis recommends more improvisations and special considerations to the educational institutions to make this mode a viable solution.

Mobile and Internet banking have introduced a new way of monetary transactions without the need for physical presence. This research proposes to analyze the sentiments of people regarding digital transactions, Mobile and Internet banking. The explosion of Internet usage and the huge funding initiatives in electronic banking has drawn the attention of researchers towards Internet and mobile banking. This study focuses on customer value perceptions of the Internet and mobile banking in India. The recent and forecasted Digital India scheme shows high growth in e-banking in India. The demographic, attitudinal, and behavioral characteristics of mobile bank users were examined. In this study, datasets obtained from Twitter were used. After extensive and repeated analysis, it is found that both Mobile and Internet banking are well received, the number of positive Tweets, especially regarding mobile banking, is much higher than that of Internet banking. This leads to the interpretation that people find mobile banking easier and safer, especially during the ongoing COVID-19 pandemic.