Sign language is essential for deaf and mute people to communicate with normal people and themselves. As ordinary people tend to ignore the importance of sign language, which is the mere source of communication for the deaf and the mute communities. These people are facing significant downfalls in their lives because of these disabilities or impairments leading to unemployment, severe depression, and several other symptoms. One of the services they are using for communication is the sign language interpreters. But hiring these interpreters is very costly, and therefore, a cheap solution is required for resolving this issue. Therefore, a system has been developed that will use the visual hand dataset based on an Arabic Sign Language and interpret this visual data in textual information. The dataset used consists of 54049 images of Arabic sign language alphabets consisting of 1500\ images per class, and each class represents a different meaning by its hand gesture or sign. Various preprocessing and data augmentation techniques have been applied to the images. The experiments have been performed using various pretrained models on the given dataset. Most of them performed pretty normally and in the final stage, the EfficientNetB4 model has been considered the best fit for the case. Considering the complexity of the dataset, models other than EfficientNetB4 do not perform well due to their lightweight architecture. EfficientNetB4 is a heavy-weight architecture that possesses more complexities comparatively. The best model is exposed with a training accuracy of 98 percent and a testing accuracy of 95 percent.

Diseases of internal organs other than the vocal folds can also affect a person’s voice. As a result, voice problems are on the rise, even though they are frequently overlooked. According to a recent study, voice pathology detection systems can successfully help the assessment of voice abnormalities and enable the early diagnosis of voice pathology. For instance, in the early identification and diagnosis of voice problems, the automatic system for distinguishing healthy and diseased voices has gotten much attention. As a result, artificial intelligence-assisted voice analysis brings up new possibilities in healthcare. The work was aimed at assessing the utility of several automatic speech signal analysis methods for diagnosing voice disorders and suggesting a strategy for classifying healthy and diseased voices. The proposed framework integrates the efficacy of three voice characteristics: chroma, mel spectrogram, and mel frequency cepstral coefficient (MFCC). We also designed a deep neural network (DNN) capable of learning from the retrieved data and producing a highly accurate voice-based disease prediction model. The study describes a series of studies using the Saarbruecken Voice Database (SVD) to detect abnormal voices. The model was developed and tested using the vowels /a/, /i/, and /u/ pronounced in high, low, and average pitches. We also maintained the “continuous sentence” audio files collected from SVD to select how well the developed model generalizes to completely new data. The highest accuracy achieved was 77.49%, superior to prior attempts in the same domain. Additionally, the model attains an accuracy of 88.01% by integrating speaker gender information. The designed model trained on selected diseases can also obtain a maximum accuracy of 96.77% ( ). As a result, the suggested framework is the best fit for the healthcare industry.

Skin cancer is one of the most serious forms of the disease, and it can spread to other parts of the body if not detected early. Therefore, it is crucial to diagnose and treat skin cancer patients at an early stage. Due to the fact that a manual diagnosis of skin cancer is both time-consuming and expensive, an incorrect diagnosis is made due to the high degree of similarity between the various skin lesions. Improved categorization of multi-class skin lesions requires the development of automated diagnostic systems. We offer a fully automated method for classifying several skin lesions by fine-tuning the deep learning models, namely VGG16, ResNet50, and ResNet101. Prior to model creation, the training dataset should undergo data augmentation using traditional image transformation techniques and generative adversarial networks (GANs) to prevent class imbalance issues that may lead to model overfitting. In this study, we investigate the feasibility of creating dermoscopic images that have a realistic appearance using conditional generative adversarial network (CGAN) techniques. Afterward, the traditional augmentation methods are used to augment our existing training set to improve the performance of pretrained deep models on the skin lesion classification task. This improved performance is then compared to the models developed using the unbalanced dataset. In addition, we formed an ensemble of finely tuned transfer learning models, which we trained on balanced and unbalanced datasets. These models were used to make predictions about the data. With appropriate data augmentation, the proposed models attained an accuracy of 92% for VGG16, 92% for ResNet50, and 92.25% for ResNet101. The ensemble of these models increased the accuracy to 93.5%. There was a comprehensive discussion on the performance of the models. It is possible to conclude that using such a method leads to enhanced performance in skin lesion categorization compared to the efforts made in the past.

Water, one of the most valuable resources, is underutilized in irrigated rice production. The yield of rice, a staple food across the world, is highly dependent on having proper irrigation systems. Alternate wetting and drying (AWD) is an effective irrigation method mainly used for irrigated rice production. However, unattended, manual, small-scale, and discrete implementations cannot achieve the maximum benefit of AWD. Automation of large-scale (over 1000 acres) implementation of AWD can be carried out using wide-area wireless sensor network (WSN). An automated AWD system requires three different WSNs: one for water level and environmental monitoring, one for monitoring of the irrigation system, and another for controlling the irrigation system. Integration of these three different WSNs requires proper dimensioning of the AWD edge elements (sensor and actuator nodes) to reduce the deployment cost and make it scalable. Besides field-level monitoring, the integration of external control parameters, such as real-time weather forecasts, plant physiological data, and input from farmers, can further enhance the performance of the automated AWD system. Internet of Things (IoT) can be used to interface the WSNs with external data sources. This research focuses on the dimensioning of the AWD system for the multilayer WSN integration and the required algorithms for the closed loop control of the irrigation system using IoT. Implementation of the AWD for 25,000 acres is shown as a possible use case. Plastic pipes are proposed as the means to transport and control proper distribution of water in the field, which significantly helps to reduce conveyance loss. This system utilizes 250 pumps, grouped into 10 clusters, to ensure equal water distribution amongst the users (field owners) in the wide area. The proposed automation algorithm handles the complexity of maintaining proper water pressure throughout the pipe network, scheduling the pump, and controlling the water outlets. Mathematical models are presented for proper dimensioning of the AWD. A low-power and long-range sensor node is developed due to the lack of cellular data coverage in rural areas, and its functionality is tested using an IoT platform for small-scale field trials.

Because underlying cognitive and neuromuscular activities regulate speech signals, biomarkers in the human voice can provide insight into neurological illnesses. Multiple motor and nonmotor aspects of neurologic voice disorders arise from an underlying neurologic condition such as Parkinson’s disease, multiple sclerosis, myasthenia gravis, or ALS. Voice problems can be caused by disorders that affect the corticospinal system, cerebellum, basal ganglia, and upper or lower motoneurons. According to a new study, voice pathology detection technologies can successfully aid in the assessment of voice irregularities and enable the early diagnosis of voice pathology. In this paper, we offer two deep-learning-based computational models, 1-dimensional convolutional neural network (1D CNN) and 2-dimensional convolutional neural network (2D CNN), that simultaneously detect voice pathologies caused by neurological illnesses or other causes. From the German corpus Saarbruecken Voice Database (SVD), we used voice recordings of sustained vowel /a/ generated at normal pitch. The collected voice signals are padded and segmented to maintain homogeneity and increase the number of samples. Convolutional layers are applied to raw data, and MFCC features are extracted in this project. Although the 1D CNN had the maximum accuracy of 93.11% on test data, model training produced overfitting and 2D CNN, which generalized the data better and had lower train and validation loss despite having an accuracy of 84.17% on test data. Also, 2D CNN outperforms state-of-the-art studies in the field, implying that a model trained on handcrafted features is better for speech processing than a model that extracts features directly.