EMO-MoviNet: Enhancing Action Recognition in Videos with EvoNorm, Mish Activation, and Optimal Frame Selection for Efficient Mobile Deployment.

The primary goal of this study is to develop a deep neural network for action recognition that enhances accuracy and minimizes computational costs. In this regard, we propose a modified EMO-MoviNet-A2* architecture that integrates Evolving Normalization (EvoNorm), Mish activation, and optimal frame selection to improve the accuracy and efficiency of action recognition tasks in videos. The asterisk notation indicates that this model also incorporates the stream buffer concept. The Mobile Video Network (MoviNet) is a member of the memory-efficient architectures discovered through Neural Architecture Search (NAS), which balances accuracy and efficiency by integrating spatial, temporal, and spatio-temporal operations. Our research implements the MoviNet model on the UCF101 and HMDB51 datasets, pre-trained on the kinetics dataset. Upon implementation on the UCF101 dataset, a generalization gap was observed, with the model performing better on the training set than on the testing set. To address this issue, we replaced batch normalization with EvoNorm, which unifies normalization and activation functions. Another area that required improvement was key-frame selection. We also developed a novel technique called Optimal Frame Selection (OFS) to identify key-frames within videos more effectively than random or densely frame selection methods. Combining OFS with Mish nonlinearity resulted in a 0.8-1% improvement in accuracy in our UCF101 20-classes experiment. The EMO-MoviNet-A2* model consumes 86% fewer FLOPs and approximately 90% fewer parameters on the UCF101 dataset, with a trade-off of 1-2% accuracy. Additionally, it achieves 5-7% higher accuracy on the HMDB51 dataset while requiring seven times fewer FLOPs and ten times fewer parameters compared to the reference model, Motion-Augmented RGB Stream (MARS).

Management of the bone loss by metaphyseal sleeves in primary and revision knee arthroplasty: clinical experience and outcome after forty three cases.

AIM OF THE STUDY: Management of metaphyseal bone loss in complex primary and revision TKA is a challenge for surgeons. Out of various types of bony defects, large metaphyseal bone loss (AORI types IIB and III) requires special augments in the form of cones or sleeves. The aim of this study is to assess the reliability of metaphyseal sleeves, in dealing with massive bone defects to provide stability for immediate weight bearing and also to check short to mid-term survivorship of metaphyseal sleeves in Asian population by assessing various parameters and complications. METHODS: This is a retrospective study that includes 36 patients (43 knees), operated from 2011 to 2019. Patients with AORI type IIB (large metaphyseal bone defect) and AORI type III (metaphyseal defect with compromised collateral ligaments) were included. We included both the primary and revision knee arthroplasties in our study. Our interest in this study was to look for incidence of intra-operative iatrogenic fracture on the one hand, and post-operative complications in the form of peri-prosthetic joint infection and aseptic loosening on the other hand. Knee Society Score (KSS) was used to assess improvement in patient's clinical outcome. SPSS version 23 was used to process data. RESULTS: The average age of patients in our study was 59.4 (SD 9.78) years. Male to female ratio was 21:15. The average follow-up was 5.42 (SD 2.24) years with the longest follow up of nine years. Metaphyseal sleeves were used in 12 primary TKA and 31 revision TKA. During surgery, iatrogenic fracture of tibial condyle was encountered in three patients (6.9%), all were managed without any intervention and union was achieved in all cases. There was not a single case with aseptic loosening as per radiological criteria in our study. Peri-prosthetic joint infection (PJI) was encountered in a single case (2.3%). Pre-op Knee Society Score (KSS) was 36.21 (SD 7.43) where as it improved to 92.00 (SD 5.66), six months after surgery. Also the range of flexion was increased from 76.83o (SD 14.07o) to 122.91o (SD 4.84o). CONCLUSION: In our study, metaphyseal sleeves showed excellent short to mid-term survivorship in AORI types IIB and III boneloss in Asian population. These results are comparable to various studies conducted on North American and European population. Metaphyseal sleeve is a reliable tool in the armamentarium of the arthroplasty surgeon. It is user friendly implant and provides immediate stability to allow full weight-bearing mobilization.

Multiobjective reconfiguration of unbalanced distribution networks using improved transient search optimization algorithm considering power quality and reliability metrics.

This paper proposes a new intelligent algorithm named improved transient search optimization algorithm (ITSOA) integrated with multiobjective optimization for determining the optimal configuration of an unbalanced distribution network. The conventional transient search optimization algorithm (TSOA) is improved with opposition learning and nonlinearly decreasing strategies for enhancing the convergence to find the global solution and obtain a desirable balance between local and global search. The multiobjective function includes different objectives such as power loss reduction, enhancement of voltage sag and unbalance, and network energy not supplied minimization. The decision variables of the reconfiguration problem including opened switches or identification of optimal network configuration are determined using ITSOA and satisfying operational and radiality constraints. The proposed methodology is implemented on unbalanced 13-bus and 118-bus networks. The results showed that the proposed ITSOA is capable to find the optimal network configuration for enhancing the different objectives in loading conditions. The results cleared the proposed methodology's good effectiveness, especially in power quality and reliability enhancement, without compromising the different objectives. Comparing ITSOA to conventional TSOA, particle swarm optimization (PSO), gray wolf optimization (GWO), bat algorithm (BA), manta ray foraging optimization (MRFO), and ant lion Optimizer (ALO), and previous approaches, it is concluded that ITSOA in improving the different objectives.