In the recent era, various diseases have severely affected the lifestyle of individuals, especially adults. Among these, bone diseases, including Knee Osteoarthritis (KOA), have a great impact on quality of life. KOA is a knee joint problem mainly produced due to decreased Articular Cartilage between femur and tibia bones, producing severe joint pain, effusion, joint movement constraints and gait anomalies. To address these issues, this study presents a novel KOA detection at early stages using deep learning-based feature extraction and classification. Firstly, the input X-ray images are preprocessed, and then the Region of Interest (ROI) is extracted through segmentation. Secondly, features are extracted from preprocessed X-ray images containing knee joint space width using hybrid feature descriptors such as Convolutional Neural Network (CNN) through Local Binary Patterns (LBP) and CNN using Histogram of oriented gradient (HOG). Low-level features are computed by HOG, while texture features are computed employing the LBP descriptor. Lastly, multi-class classifiers, that is, Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN), are used for the classification of KOA according to the Kellgren–Lawrence (KL) system. The Kellgren–Lawrence system consists of Grade I, Grade II, Grade III, and Grade IV. Experimental evaluation is performed on various combinations of the proposed framework. The experimental results show that the HOG features descriptor provides approximately 97% accuracy for the early detection and classification of KOA for all four grades of KL.

A bstract : Plant-based synthesis of eco-friendly nanoparticles has widespread applications in many fields, including medicine. Biofilm—a shield for pathogenic microorganisms—once formed, is difficult to destroy with antibiotics, making the pathogen resistant. Here, we synthesized gold nanoparticles (AuNPs) using the stem of an Ayurvedic medicinal plant, Tinospora cordifolia, and studied the action of AuNPs against Pseudomonas aeruginosa PAO1 biofilm. The synthesized AuNPs were characterized by techniques such as ultraviolet-visible spectroscopy, Fourier-transform infrared (FTIR) spectroscopy, energy-dispersive X-ray diffraction, X-ray diffraction, scanning electron microscopy (SEM), and transmission electron microscopy. The AuNPs were spherically shaped with an average size of 16.1 nm. Further, the subminimum inhibitory concentrations (MICs) of AuNPs (50, 100, and 150 µg/mL) greatly affected the biofilm-forming ability of P. aeruginosa, as observed by crystal violet assay and SEM, which showed a decrease in the number of biofilm-forming cells with increasing AuNP concentration. This was further justified by confocal laser scanning microscopy (CLSM), which showed irregularities in the structure of the biofilm at the sub-MIC of AuNPs. Further, the interaction of AuNPs with PAO1 at the highest sub-MIC (150 µg/mL) showed the internalization of the nanoparticles, probably affecting the tendency of PAO1 to colonize on the surface of the nanoparticles. This study suggests that green-synthesized AuNPs can be used as effective nano-antibiotics against biofilm-related infections caused by P. aeruginosa.

With opportunities brought by the Internet of Things (IoT), it is quite a challenge to maintain concurrency and privacy when a huge number of resource-constrained distributed devices are involved. Blockchain have become popular for its benefits, including decentralization, persistence, immutability, auditability, and consensus. Great attention has been received by the IoT based on the construction of distributed file systems worldwide. A new generation of IoT-based distributed file systems has been proposed with the integration of Blockchain technology, such as the Swarm and Interplanetary File System. By using IoT, new technical challenges, such as Credibility, Harmonization, large-volume data, heterogeneity, and constrained resources are arising. To ensure data security in IoT, centralized access control technologies do not provide credibility. In this work, we propose an attribute-based access control model for the IoT. The access control lists are not required for each device by the system. It enhances access management in terms of effectiveness. Moreover, we use blockchain technology for recording the attribute, avoiding data tempering, and eliminating a single point of failure at edge computing devices. IoT devices control the user’s environment as well as his or her private data collection; therefore, the exposure of the user’s personal data to non-trusted private and public servers may result in privacy leakage. To automate the system, smart contracts are used for data accessing, whereas Proof of Authority is used for enhancing the system’s performance and optimizing gas consumption. Through smart contracts, ciphertext can be stored on a blockchain by the data owner. Data can only be decrypted in a valid access period, whereas in blockchains, the trace function is achieved by the storage of invocation and the creation of smart contracts. Scalability issues can also be resolved by using the multichain blockchain. Eventually, it is concluded from the simulation results that the proposed system is efficient for IoT.

This paper proposes a novel high voltage gain structure of DC-DC converter with soft-switching ability for photovoltaic (PV) applications. A small size coupled inductor with one magnet core is utilized to improve the voltage conversion ratio in the proposed converter. The converter has one active MOSFET with low conducting resistance ( $R_{DS}-_{ON}$ ), which in turn reduces the conduction losses and complexity of the control section. Due to the low input current ripple, the lifetime of the input PV panel is increased, and the maximum power point (MPP) of the PV panel can be easily tracked. The MOSFET’s zero-voltage and zero-current switching and diodes are the other countenance of the proposed converter, which improve its efficiency. Additionally, an improved Perturb and Observe MPP tracking (IP&O MPPT) algorithm is introduced to boost the extracted power of the input PV sources. To validate the performance of this converter, the operation modes principle, steady-state and efficiency survey, and comparison results with other same family converters are carried out. Finally, an experiential prototype is built with 20 V input, 200 V output, power rate of 200 W, and 50 kHz operating frequency to validate the mathematical analysis and effectiveness of the proposed structure. The efficiency of the proposed converter was estimated by over 95% at various power levels.

Portfolio theory underpins portfolio management, a much-researched yet uncharted field. This research suggests a collective framework combined with the essence of deep learning for stock selection through prediction and optimal portfolio formation through the mean-variance (MV) model. The CNN-LSTM model, proposed in Stage I blends the benefits of the convolutional neural network (CNN) and the long-short-term memory network (LSTM). The model combines feature extraction and sequential learning about temporal data fluctuations. The experiment considers thirteen input features, combining fundamental market data and technical indicators to capture the nuances of the wildly fluctuating stock market data. The input data sample of 21 stocks was collected from the National Stock Exchange (NSE) of India from January 2005 to December 2021, spanning two significant market crashes. Thus, the sample makes it possible to catch subtle market shifts for model execution. The shortlisted stocks with high potential returns are advanced to Stage II for optimal stock allocation using the MV model. The proposed hybrid CNN-LSTM outperformed the single models, i.e., CNN and LSTM, per the six-performance metrics and advocated by the 10-fold cross-validation technique. Furthermore, the statistical significance of the model is established using non-parametric tests followed by post hoc analysis. In addition, this method is validated by comparing the proposed model to four baseline strategies and relevant pieces of research, which it considerably outperforms in terms of cumulative return per year, Sharpe ratio, and average return to risk with and without transaction cost. These findings highlight the effectiveness of the hybrid CNN-LSTM approach in stock selection and portfolio optimization.