Smart Cognitive IoT Devices Using Multi-Layer Perception Neural Network on Limited Microcontroller.

The Internet of Things (IoT) era is mainly dependent on the word "Smart", such as smart cities, smart homes, and smart cars. This aspect can be achieved through the merging of machine learning algorithms with IoT computing models. By adding the Artificial Intelligence (AI) algorithms to IoT, the result is the Cognitive IoT (CIoT). In the automotive industry, many researchers worked on self-diagnosis systems using deep learning, but most of them performed this process on the cloud due to the hardware limitations of the end-devices, and the devices obtain the decision via the cloud servers. Others worked with simple traditional algorithms of machine learning to solve these limitations of the processing capabilities of the end-devices. In this paper, a self-diagnosis smart device is introduced with fast responses and little overhead using the Multi-Layer Perceptron Neural Network (MLP-NN) as a deep learning technique. The MLP-NN learning stage is performed using a Tensorflow framework to generate an MLP model's parameters. Then, the MLP-NN model is implemented using these model's parameters on a low cost end-device such as ARM Cortex-M Series architecture. After implementing the MLP-NN model, the IoT implementation is built to publish the decision results. With the proposed implemented method for the smart device, the output decision based on sensors values can be taken by the IoT node itself without returning to the cloud. For comparison, another solution is proposed for the cloud-based architecture, where the MLP-NN model is implemented on Cloud. The results clarify a successful implemented MLP-NN model for little capabilities end-devices, where the smart device solution has a lower traffic and latency than the cloud-based solution.

Early Outcome of Enhanced Recovery Programs Versus Conventional Perioperative Care in Elective Open Left Side Colonic Carcinoma Surgery: Analysis of 80 Cases.

According to recent clinical practice guidelines, enhanced recovery programs (ERP) have been practiced to improve surgical outcomes and decrease cost. However, these are still opposed by the traditional measures in the treatment of colorectal carcinoma that is still practiced with the concept of protection of anastomosis and decrease postoperative complications. The aim of this study was to report our experience in ERP in elective open left side colonic carcinoma surgery in comparison with the conventional perioperative care. The current prospective multicenter randomized controlled study included a total of 80 adult patients with left side colonic cancer who were eligible for elective colonic resection. Included patients were randomly divided into two equal groups: group (A) where conventional perioperative care was performed and group (B) where ERP were applied. Follow-up was designed for at least 1 month to evaluate and compare hospital stay and postoperative complications. There was no statistically significant difference between the two groups as regards demographic data and preoperative comorbidities. There were statistically significant less pain (P = 0.24), less postoperative nausea and vomiting (P = 0.045), and less hospital stay (P < 0.001) in group B than group A. Otherwise, there was no statistically significant difference in comparing the rest of postoperative surgical or non-surgical complications or rates of readmissions between the two groups. ERP are safe, reliable, simple, and applicable in open left side cancer colon surgery with no negative impact over the postoperative complications in comparison with the conventional care.