The rapid growth in the number of vehicles has led to traffic congestion, pollution, and delays in logistic transportation in metropolitan areas. IoT has been an emerging innovation, moving the universe towards automated processes and intelligent management systems. This is a critical contribution to automation and smart civilizations. Effective and reliable congestion management and traffic control help save many precious resources. An IoT-based ITM system set of sensors is embedded in automatic vehicles and intelligent devices to recognize, obtain, and transmit data. Machine learning (ML) is another technique to improve the transport system. The existing transport-management solutions encounter several challenges resulting in traffic congestion, delay, and a high fatality rate. This research work presents the design and implementation of an Adaptive Traffic-management system (ATM) based on ML and IoT. The design of the proposed system is based on three essential entities: vehicle, infrastructure, and events. The design utilizes various scenarios to cover all the possible issues of the transport system. The proposed ATM system also utilizes the machine-learning-based DBSCAN clustering method to detect any accidental anomaly. The proposed ATM model constantly updates traffic signal schedules depending on traffic volume and estimated movements from nearby crossings. It significantly lowers traveling time by gradually moving automobiles across green signals and decreases traffic congestion by generating a better transition. The experiment outcomes reveal that the proposed ATM system significantly outperformed the conventional traffic-management strategy and will be a frontrunner for transportation planning in smart-city-based transport systems. The proposed ATM solution minimizes vehicle waiting times and congestion, reduces road accidents, and improves the overall journey experience.

Cassava is a crucial food and nutrition security crop cultivated by small-scale farmers because it can survive in a brutal environment. It is a significant source of carbohydrates in African countries. Sometimes, Cassava crops can be infected by leaf diseases, affecting the overall production and reducing farmers’ income. The existing Cassava disease research encounters several challenges, such as poor detection rate, higher processing time, and poor accuracy. This research provides a comprehensive learning strategy for real-time Cassava leaf disease identification based on enhanced CNN models (ECNN). The existing Standard CNN model utilizes extensive data processing features, increasing the computational overhead. A depth-wise separable convolution layer is utilized to resolve CNN issues in the proposed ECNN model. This feature minimizes the feature count and computational overhead. The proposed ECNN model utilizes a distinct block processing feature to process the imbalanced images. To resolve the color segregation issue, the proposed ECNN model uses a Gamma correction feature. To decrease the variable selection process and increase the computational efficiency, the proposed ECNN model uses global average election polling with batch normalization. An experimental analysis is performed over an online Cassava image dataset containing 6256 images of Cassava leaves with five disease classes. The dataset classes are as follows: class 0: “Cassava Bacterial Blight (CBB)”; class 1: “Cassava Brown Streak Disease (CBSD)”; class 2: “Cassava Green Mottle (CGM)”; class 3: “Cassava Mosaic Disease (CMD)”; and class 4: “Healthy”. Various performance measuring parameters, i.e., precision, recall, measure, and accuracy, are calculated for existing Standard CNN and the proposed ECNN model. The proposed ECNN classifier significantly outperforms and achieves 99.3% accuracy for the balanced dataset. The test findings prove that applying a balanced database of images improves classification performance.

Healthcare, one of the most important industries, is data-oriented, but most of the research in this industry focuses on incorporating the internet of things (IoT) or connecting medical equipment. Very few researchers are looking at the data generated in the healthcare industry. Data are very important tools in this competitive world, as they can be integrated with artificial intelligence (AI) to promote sustainability. Healthcare data include the health records of patients, drug-related data, clinical trials data, data from various medical equipment, etc. Most of the data management processes are manual, time-consuming, and error-prone. Even then, different healthcare industries do not trust each other to share and collaborate on data. Distributed ledger technology is being used for innovations in different sectors including healthcare. This technology can be incorporated to maintain and exchange data between different healthcare organizations, such as hospitals, insurance companies, laboratories, pharmacies, etc. Various attributes of this technology, such as its immutability, transparency, provenance etc., can bring trust and security to the domain of the healthcare sector. In this paper, a decentralized access control model is proposed to enable the secure interoperability of different healthcare organizations. This model uses the Ethereum blockchain for its implementation. This model interfaces patients, doctors, chemists, and insurance companies, empowering the consistent and secure exchange of data. The major concerns are maintaining a history of the transactions and avoiding unauthorized updates in health records. Any transaction that changes the state of the data is reflected in the distributed ledger and can be easily traced with this model. Only authorized entities can access their respective data. Even the administrator will not be able to modify any medical records.

Neural Networks and SVM are recently being used in various kind of pattern recognition. As humans, it is easy to recognize numbers, letters, voices, and objects, to name a few. However, making a machine solve these types of problems is a very difficult task .Character Recognition has been an active area of research in the field of image processing and pattern recognition and due to its diverse applicable environment, it continues to be a challenging research topic. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. In this paper an attempt is made to recognized handwritten character using the multi layer feed forward back propagation neural network without feature extraction and SVM classifier. Character data is used for training the neural network and SVM. The trained network is used for classification and recognition. For the neural network, each character is resized into 70x50 pixels, which is directly subjected to training. That is, each resized character has 3500 pixels and these pixels are taken as features for training the neural network. For the SVM classifier recognition model is divided in two phases namely, training and testing phase. In the training phase 25 features are extracted from each character and these features are used to train the SVM. In the testing phase SVM classifier is used to recognize the characters. The results show that by applying the proposed system, we reached a high accuracy for the problem of handwritten character recognition.

No abstract