Abdul Ahad Abro

Facial recognition and emotion detection have become indispensable in modern civilization, affecting a wide range of businesses like banking, social media, education, and commerce. This chapter provides a thorough investigation of emotion recognition from facial expressions, focussing on three important aspects of the process: pre-processing, feature extraction, and classification. With an emphasis on deep learning algorithms that leverage visual facial data, the chapter looks at a variety of cutting-edge and conventional approaches to better understand human emotions. With an emphasis on recent advancements in emotion recognition, comparative results from existing methodologies are shown. The findings show how crucial automated emotion recognition is to some industries and offer useful data regarding the efficacy of various approaches.

Accurate prognosis of degradation trend is considered very important for the maintenance of critical industrial equipment and asset. This leads to increase in service availability and life expectancy. Accurate and timely degradation prognosis enables maintenance managers to efficiently plan maintenance regime and reduce failure occurrences. Recently, Artificial Intelligence (AI) based prognosis and prediction techniques have been in limelight and attracted the interest of the research community. One such popular AI based technique is the Long Short-Term Memory (LSTM), which is very efficient in making predictions using time series and sequential data. This paper proposes a novel prognostic technique based on LSTM to predict the degradation trend. The proposed LSTM technique uses a dynamic training window approach with a fixed look-back window for forecasting future steps. The size of the training window is iteratively increased for each prediction as more data is available. This enables the model to utilize the complete sequence trends while making future degradation state predictions. To mitigate over-fitting during model training, dropout technique and L2 regularization are also incorporated to the proposed generic LSTM model. The performance of the proposed LSTM based technique is evaluated using experimental results on a real-world application and data. As a case study, degradation trend of Aerial Bundled Cables (ABCs) using actual thermal degradation data acquired from in-service cables (ABC) is predicted. Moreover, the proposed LSTM based technique is further compared with a particle filter based statistical prognosis technique. Promising results validate the efficacy of the proposed LSTM based approach for degradation prognosis.

The distribution companies that deal with ventilators in Pakistan face challenges related to inventory control because of inadequate product shelf life, shortages, excess inventory, and unnecessary stock. This study, which focuses on Pakistani ventilator distribution companies, aims to offer a novel approach to sales estimation, avoid unnecessary stock expenditures, and stop clientele loss brought on by ventilator shortages. The results of this study will help determine key elements and standards that Pakistani distributors of ventilators might employ to boost sales. Most ventilator distribution businesses in Pakistan are independent wholesalers that purchase stock from their stores and distribute it to customers. To maximize ventilator distribution firms' sales for various products, this study examined distribution and sales data from 2019 to 2024 for many locations and dates. To create an accurate sales forecasting model for a ventilator distribution company, this research also aims to apply artificial neural networks (ANN) for effective sales prediction. An Artificial Neural Network (ANN) model was trained using a dataset from ventilator distribution businesses and the proposed model produced an accuracy of 90%, which is good for early prediction.

Present dynamic performance reputation and technical innovations in Internet of Things (IoT) technologies have endowed ultra-inexpensive, energy efficient, smart, and tiny IoT gadgets. IoT gadgets can be easily implanted inside, attached to, or placed around the chronic patient body, to be employed in several healthcare monitoring systems such as mobile, wearable, and implantable healthcare monitoring for chronic diseases. Healthcare monitoring for chronic diseases is one of the major applications of IoT, and also a typical challenging area. The rapidly rising proportion of patients with chronic diseases brought great pressure on governments, and healthcare providers, and required up-to-date long-term healthcare service and continuous monitoring. In this survey paper, we provide an extensive review of numerous industrial and non-commercial contemporary healthcare monitoring systems (HMS) and applications. We present a design layout of IoT-based HMS for chronic diseases. We presented societal and technological challenges associated with the design of IoT-based HMS and their solutions. To accomplish this, more than 80 different healthcare monitoring systems have been characterized and classified. Moreover, we describe contemporary healthcare monitoring networks and communication technologies. This review also presents the dynamic capabilities of key IoT technologies for chronic diseases healthcare monitoring, to show dedicated research pathways to IoT researchers. Last, we deeply analyze different healthcare monitoring systems and also, describe open issues that will help researchers and healthcare system designers in designing future systems.

Natural Language Processing (NLP) is the computerized approach to analyzing text using both structured and unstructured data. NLP is a simple, empirically powerful, and reliable approach. It achieves state-of-the-art performance in language processing tasks like Semantic Search (SS), Machine Translation (MT), Text Summarization (TS), Sentiment Analyzer (SA), Named Entity Recognition (NER) and Emotion Detection (ED). NLP is expected to be the technology of the future, based on current technology deployment and adoption. The primary question is: What does NLP have to offer in terms of reality, and what are the prospects? There are several problems to be addressed with this developing method, as it must be compatible with future technology. In this paper, the benefits, challenges and limitations of this innovative paradigm along with the areas open to do research are shown.

The ensemble learning method is considered a meaningful yet challenging task. To enhance the performance of binary classification and predictive analysis, this paper proposes an effective ensemble learning approach by applying multiple models to produce efficient and effective outcomes. In these experimental studies, three base learners, J48, Multilayer Perceptron (MP), and Support Vector Machine (SVM) are being utilized. Moreover, two meta-learners, Bagging and Rotation Forest are being used in this analysis. Firstly, to produce effective results and capture productive data, the base learner, the J48 decision tree is aggregated with the rotation forest. Secondly, machine learning and ensemble learning classification algorithms along with the five UCI Datasets are being applied to progress the robustness of the system. Whereas, the recommended mechanism is evaluated by implementing five performance standards concerning the accuracy, AUC (Area Under Curve), precision, recall and F-measure values. In this regard, extensive strategies and various approaches were being studied and applied to obtain improved results from the current literature; however, they were insufficient to provide successful results. We present experimental results which demonstrate the efficiency of our approach to well-known competitive approaches. This method can be applied to image identification and machine learning problems, such as binary classification.

Machine learning (ML) is a prominent and extensively researched field in the artificial intelligence area which assists to strengthen the accomplishment of classification. In this study, the main idea is to provide the classification and analysis of ML and Ensemble Learning (EL) algorithms. To support this idea, six supervised ML algorithms, C4.5 (J48), K-Nearest Neighbor (KNN), Logistic Regression (LR), Support Vector Machine (SVM), Naive Bayes (NB) and One Rule (OneR) in addition the five UCI Datasets of ML Repository, are being applied that demonstrates the robustness and effectiveness of numerous approaches. In this paper, a voting-based ensemble classifier has been proposed along with two base learners (namely, Random Forest and Rotation Forest) to progress the performance. Whereas, for analytical procedures, significant parameters have been considered: Accuracy, Area under Curve (AUC), recall, precision, and F-measure values. Hence, the prime objective of this research is to obtain binary classification and efficiency by conducting the progress of ML and EL approaches. We present experimental outcomes that validate the effectiveness of our method to well-known competitive approaches. Image recognition and ML challenges, such as binary classification, can be solved using this method.

Distributed forecasting of agriculture commodity prices has an attractive research perspective that delivers active breakthrough analysis of the rapid fluctuations in pricing forecasts for participating stakeholders without being manually dispatched lists. The increased use of an efficient forecasting mechanism for the agriculture information management of generated records and processing creates emerging challenges and limitations. These include new government mandates and regulations, the price of land for expansion, forecasting the growing demand for commodities, fluctuations in the global financial market, food security, and bio-based fuels. Building and deploying distributed dynamic scheduling, management, and monitoring systems of agricultural activities for commodity price forecasting and supply chains require a significant secure and efficient approach. Thus, this paper discusses a collaborative approach where two different folds are demonstrated to cover distinct aspects with different objectives. A metaheuristic-enabled genetic algorithm is designed to receive day-to-day agricultural production details and process and analyze forecast pricing from the records by scheduling, managing, and monitoring them in real-time. The blockchain hyperledger sawtooth distributed modular technology provides a secure communication channel between stakeholders, a private network, protects the forecasting ledger, adds and updates commodity prices, and preserves agricultural information and node transactions in the immutable ledger (IPFS). To accomplish this, we design, develop, and deploy two distinct smart contracts to register the system’s actual stakeholders and allow for the addition of node transactions and exchanges. The second smart contract updates the forecasting commodity pricing ledger and distributes it to participating stakeholders while preserving detailed addresses in storage. The simulation results of the proposed collaborative approach deliver an efficient E-agriculture commodity price forecast with an accuracy of 95.3%. It also maintains ledger transparency, integrity, provenance, availability, and secure operational control and access of agricultural activities.

Outlier detection is considered as one of the crucial research areas for data mining. Many methods have been studied widely and utilized for achieving better results in outlier detection from existing literature; however, the effects of these few ways are inadequate. In this paper, a stacking-based ensemble classifier has been proposed along with four base learners (namely, Rotation Forest, Random Forest, Bagging and Boosting) and a Meta-learner (namely, Logistic Regression) to progress the outlier detection performance. The proposedmechanism is evaluated on five datasets from the ODDS library by adopting five performance criteria. The experimental outcomes demonstrate that the proposed method outperforms than the conventional ensemble approaches concerning the accuracy, AUC (Area Under Curve), precision, recall and Fmeasure values.This method can be used for image recognition and machine learning problems, such as binary classification.

Vote-based is one of the ensembles learning methods in which the individual classifier is situated on numerous weighted categories of the training datasets. In designing a method, training, validation and test sets are applied in terms of an ensemble approach to developing an efficient and robust binary classification model. Similarly, ensemble learning is the most prominent and broad research area of Machine Learning (ML) and image recognition, which assists in enhancing the capability of performance. In most cases, the ensemble learning algorithm yields better performance than ML algorithms. Unlike existing methods, the proposed technique aggregates an ensemble classifier, known as vote-based, to employ and integrate the advantage of ML classifiers, which are Artificial Neural Network (ANN), Naive Bayes (NB) and Logistic Model Tree (LMT). This paper proposes an ensemble framework that aims to evaluate datasets from the UCI ML repository by adopting performance analysis. Furthermore, the experimental outcomes indicate that the proposed method provides more accurate results according to the base learner approaches in terms of accuracy rates, an area under the curve (AUC), precision, recall, and F-measure values.