Deep learning is one of the most unexpected machine learning techniques which is being used in many applications like image classification, image analysis, clinical archives and object recognition.With an extensive utilization of digital images as information in the hospitals, the archives of medical images are growing exponentially. Digital images play a vigorous role in predicting the patient disease intensity and there are vast applications of medical images in diagnosis and investigation. Due to recent developments in imaging technology, classifying medical images in an automatic way is an open research problem for researchers of computer vision. For classifying the medical images according to their relevant classes a most suitable classifier is most important. Image classification is beneficial to predict the appropriate class or category of unknown images. The less discriminating ability and domain-specific categorization are the main drawbacks of low-level features. A semantic gap that exists between features of low-level as machine understanding and features of human understanding as high-level perception. In this research, a novel image representation method is proposed where the algorithm is trained for classifying medical images by deep learning technique. A pre-trained deep convolution neural network method with the fine-tuned approach is applied to the last three layers of deep neural network. The results of the experiment exhibit that our method is best suited to classify various medical images for various body organs. In this manner, data can sum up to other medical classification applications which supports radiologist’s efforts for improving diagnosis.

Wireless Sensor Networks (WSNs) offer a powerful technology for sensing and transmitting data across vast geographical regions. However, limitations inherent to WSNs, such as low-power sensor units, communication constraints, and limited processing capabilities, can significantly impact their lifespan. To address these limitations and enhance the energy efficiency of WSNs, it is often necessary to divide sensors into clusters and establish routing to conserve energy. Machine learning algorithms can potentially automate these processes, minimizing energy consumption and extending network lifetime. This research investigates the application of machine learning algorithms, specifically Q-learning and K-means clustering, to propose the Energy-Efficient Machine Learning-based Clustering and Routing (EEMLCR) method for WSNs. This method facilitates cluster formation and routing path selection. The proposed method is compared with the well-established LEACH algorithm and two multi-hop variants, DMHT LEACH and EDMHT LEACH to validate its effectiveness. Our experimental results demonstrate the effectiveness of EEMLCR compared to LEACH and its multi-hop variants (DMHT LEACH and EDMHT LEACH). After 600 rounds in networks comprising 400 nodes, EEMLCR showed significant improvements in key performance metrics. These include increased alive nodes, reduced average energy consumption, higher remaining energy levels, and improved packet reception. Additionally, we compared EEMLCR with recent state-of-the-art algorithms such as EECDA and CMML, where our method demonstrated comparable or superior performance in terms of network lifetime and energy efficiency. By optimizing clustering and routing strategies, WSNs can reduce energy consumption, leading to more efficient utilization of the limited energy resources available to sensor nodes. The primary objective of this research is to contribute to the development of energy-efficient WSNs by leveraging machine learning algorithms for data routing and the cluster-based organization of sensor nodes.

Skin wounds either minor or chronic may heal up with different time durations. But, this time duration of healing could not be easily predicted as healing is affected by different factors, e.g., age, nutrition, medication, and surroundings. Despite these factors, wound characteristic also plays a role in the healing process. Wound characteristics include wound size, wound type, internal and external wound environment, body temperature, body oxygenation, wound hydration, and infection. Therefore, monitoring of wound healing also required careful consideration of wound characteristics. Although the healthcare domain contains many applications for detection and monitoring of diseases, the wound care domain requires efficient techniques and sensing systems for the identification of wound biomarkers such as temperature, blood pressure, oxygen, and infection status of wound using biosensors. In the current research, we provide a wound care solution based on a biosensor-based sensing system to measure basic biomarkers, considered as major wound characteristics, i.e., body temperature and body oxygenation, and design a fuzzy inference system to predict their effect on wound hydration, which ultimately recommends necessary actions to boost healing.

Photovoltaic (PV) systems have been used extensively worldwide over the past few years due to the mitigation of fossils fuels; it is the best source because of its eco-friendly nature. In PV systems, the main research area concerns its performance under partial shading (PS) and complex partial shading (CPS) conditions. PV sources perform perfectly under ideal conditions, but under practical conditions, their performance depends upon many factors, including shading conditions, temperature, irradiance, and the angle of inclination, which can bring a photovoltaic or solar system into a PS or CPS condition. In these conditions, many power peaks appear, and it is hard to find the global peak among many local peaks. The ability to track the maximum power peak and maintain it to avoid fluctuations depends on the maximum power point tracking (MPPT) technique used in a photovoltaic system. This article is based on the implementation of a hybrid algorithm, combining Harris hawk’s optimization (HHO), a new technique which is based on natural inspiration, and a conventional perturb and observe (P&O) technique. The hybrid technique was tested under different weather conditions in MATLAB Simulink and showed less computational time, a fast convergence speed, and zero oscillations after reaching a power point’s maximum limit. A performance comparison of the hybrid technique was made with bio-inspired particle swarm optimization (PSO), adaptive cuckoo search optimization (ACS), the dragonfly algorithm (DFO), and the water cycle algorithm (WCA). The hybrid technique achieves 99.8% efficiency on average and performs very well among the rest of the competing techniques.