Convolution Technique Research Articles

Convolution- and Deconvolution-Based Approaches for Prediction of Pharmacokinetic Parameters of Diltiazem Extended-Release Products in Flow-Through Cell Dissolution Tester

The present study evaluated the effect of different configuration setups of the Flow-Through Cell (USP IV) dissolution tester in developing in vitro–in vivo correlation (IVIVC). A Biopharmaceutics Classification System (BCS) Class I Diltiazem (DTZ), formulated in extended-release (ER) gel-matrix system, was employed for this purpose. The study also assessed the validity and predictability of IVIVC employing both deconvolution- and convolution-based approaches. In vitro release was conducted in USP IV as open- or closed-loop setups, while the pharmacokinetic (PK) data were obtained from a previous fasted-state cross-over study conducted on 8 healthy male volunteers, after oral administration of ER matrix tablets against market product (Tildiem Retard® 90 mg). PK parameters (Cmax, AUC0-t and AUC0-∞) were predicted, and compared with actual data to establish the strength of correlation models. Results showed that DTZ release from ER products was influenced by operating the FTC in different configuration-setups, where ≥ 75% of labeled DTZ was released after 6 h and 12 h using the open- and closed-loop settings, respectively. Correlation between fraction-dissolved versus fraction-absorbed for both ER products displayed linear relation upon employing FTC open-loop setup. Convolution-based approach was more discriminative in predicting DTZ in vivo PK parameters with a minimal prediction error, compared to deconvolution-based approach. A successful trial to predict DTZ PKs from individual in vitro data performed in USP IV dissolution model was established, employing convolution technique. Basic principle of the convolution approach provides a simple and practical method for developing IVIVC, hence could be utilized for other BCS Class I extended-release drug products.Graphical abstract

Feature Extraction and Recognition of Human Physiological Signals Based on the Convolutional Neural Network

Human physiological signal processing is one of the research fields widely used in recent years. Research on human physiological signals plays a vital role in predicting human health and detecting and classifying certain disease outbreaks. The network of human physiological signals is difficult to determine because it contains a lot of information about human activities. To this end, a variety of feature extraction, feature selection, and classification algorithms have been implemented in the anomaly prediction process. However, it has the main disadvantage of classification results, using a large number of features and increasing complexity. In order to solve these problems, this paper proposes a convolutional neural network-based extraction technique for human physiological signal features and uses an MPL classifier to detect whether the ECG signal is normal or not, taking the ECG signal as an example. In this paper, the signal preprocessing method based on wavelet transform and morphological filtering is adopted, and the high-frequency signal is removed by wavelet transform, and the low-frequency signal is removed by morphological filtering. A wide range of tests on ECG signals obtained from the MIT-BIH-AR databank and INCART database showed that the method has good detection performance with sensitivity Sen = 99.54%, positive prediction rate PPR = 99.65%, detecting mistake ratio DER = 0.35% and precision Acc = 99.55%, which is an improved performance compared to other techniques, proving the superiority of the present technique.

Real-Time Identification of Nonstandard Thermal Inkjet Codes on the Surface of Hot-Rolled Steel Sheets in Complex Environments

Many steel mills currently rely on thermal spray codes to carry and convey information about the steel plate at different stages of production. Thermal inkjet codes are patterns of numbers, letters, and symbols formed by continuous spraying of high-temperature resistant coatings on the surface of billets, so it is especially important to identify thermal inkjet code information accurately and timely during the processing stage of steel plates. Most of the existing mainstream identification methods rely on manual visual observation and traditional image recognition to obtain them, with low recognition efficiency and poor recognition effect. In this paper, a lightweight YOLO with ResNet18 as the backbone network is used as the detection and recognition framework, and deformable convolution and text feature extraction techniques are purposefully added to detect the location of thermal inkjet codes images to achieve accurate and fast positioning and segmentation of thermal spray codes. Meanwhile, an attention mechanism-based character recognition module is added to quickly infer the content within the ROI location of thermal inkjet codes. The experimental results show that the thermal inkjet code character recognition method proposed in this paper has a high recognition rate and fast recognition speed, which meets the practical application requirements of relevant enterprises.

An Image-Based Data-Driven Model for Texture Inspection of Ground Workpieces.

Nowadays, the grinding process is mostly automatic, yet post-grinding quality inspection is mostly carried out manually. Although the conventional inspection technique may have cumbersome setup and tuning processes, the data-driven model, with its vision-based dataset, provides an opportunity to automate the inspection process. In this study, a convolutional neural network technique with transfer learning is proposed for three kinds of inspections based on 750–1000 surface raw images of the ground workpieces in each task: classifying the grit number of the abrasive belt that grinds the workpiece, estimating the surface roughness of the ground workpiece, and classifying the degree of wear of the abrasive belts. The results show that a deep convolutional neural network can recognize the texture on the abrasive surface images and that the classification model can achieve an accuracy of 0.9 or higher. In addition, the external coaxial white light was the most suitable light source among the three tested light sources: the external coaxial white light, the high-angle ring light, and the external coaxial red light. Finally, the model that classifies the degree of wear of the abrasive belts can also be utilized as the abrasive belt life estimator.

Convolution Properties of q-Janowski-Type Functions Associated with (x,y)-Symmetrical Functions

The purpose of this paper is to define new classes of analytic functions by amalgamating the concepts of q-calculus, Janowski type functions and (x,y)-symmetrical functions. We use the technique of convolution and quantum calculus to investigate the convolution conditions which will be used as a supporting result for further investigation in our work, we deduce the sufficient conditions, Po´lya-Schoenberg theorem and the application. Finally motivated by definition of the neighborhood, we give analogous definition of neighborhood for the classes S˜qx,y(α,β) and K˜qx,y(α,β), and then investigate the related neighborhood results, which are also pointed out.

The Usage of High Voltage Amplifiers to Set up Reference Calibrators for Combined and Impulse Voltages up to 1 kV

An approach to set up reference calibrators to generate combined voltages, using voltage amplifiers, has been demonstrated. Four high voltage amplifiers were tested and studied. Measurements and experiments have shown that this approach could be used to set up calibrators for combined voltages, at least up to 1 kV. The advantage is the flexibility to generate separate or combined wave shapes (combination of AC, DC, distorted shapes, double exponential impulses such as lightening and switching impulses). This method could be beneficial to the fields where impulses, combined or not with DC or AC voltages, need a reference calibrator to calibrate digitizers. This method, relatively cheaper and simple to develop, reaches high metrological performance. For example, for lightning impulses up to 900 V, the uncertainties are lower than 0.2 % for the peak voltage, 1 % for the front time and 0.5 % for the time to half value . The traceability to the international system of units can be ensured by characterizing the gain using a step response, followed by the convolution technique.

Application of Line Integral Convolution Techniques in the Generation of Fine Art Painting Effects

Since the 1980s, nonrealistic drawing techniques have become one of the main focuses of research in computer graphics. In recent years, with the rapid development of computer graphics, nonrealistic drawing techniques have become capable of rendering any digital image into an image with an alternative artistic style. As a result, many scholars have focused on the pencil sketch style. Against this backdrop, research into how to create more realistic art drawings has become a hot topic. Although the rapid development of computer technology has led to advances in art drawing techniques, traditional fine art painting methods are not yet able to simulate realistic pencil sketches in a quite realistic way. In other words, the following issues have been noted. For example, they fail to simulate the gradation of shades and densities of real sketches, the direction of the shadows does not conform to the general rules of sketching, and the results produced are not artistic and realistic. After all, unlike realistic graphics, which seeks a photo-like realism, nonrealistic graphics wants to highlight the message of the image with the help of computer simulations. As a result, nonrealistic graphics often ignores unimportant details in the image. On the other hand, nonrealistic graphics can also simulate an artist’s painting to a certain extent, thus producing an artistically effective image. Many nonrealistic drawing methods have been devised to simulate the styles of oil, watercolour, and ink, but not many algorithms have been developed to generate colour sketches. In order to address this topic, this study improves a fine art drawing generation approach based on the line integral convolution techniques. To be specific, this investigation begins by segmenting the colour images through cluster analysis. Two basic colours are then assigned to each region by calculating the colour variability, and the density of each colour is calculated using a two-tone mapping technique. After that, the line integral convolution technique is applied to generate sketch textures for each of the two basic colour layers, and the two layers are fused to produce the coloured textures. At the same time, a neon transform is used to generate the sketch contour lines. Eventually, the contours are blended with the coloured textures to obtain the coloured sketch effect. The experimental results show that the art painting generation method designed in this paper is able to automatically transform from colour images to coloured pencil drawings, thus improving the efficiency of the process as well as meeting the real-time requirements.

COMPUTATIONAL MODEL FOR MENTAL FACTOR CLASSIFICATION

Artificial Wisdom is advancement of Artificial Intelligence where wisdom should be recognized with the intelligence. Wisdom can be realized by adding values in the positive decisions. This is resulted in to the overall behavior of human being. Behavior can be demonstrated with the help of simulating thought process. Thoughts are generated in the mind along with the mental state. Mental state also known as mental factor is responsible for arousal of different types of thoughts. Ancient Indian cannon Abhidhamm claimed 52 mental factors. These are categorized in three classes such as Ethically Variable Factor, Unwholesome Factor and Beautiful Factor. Proposed computational model of consciousness demonstrates the classification of the mental states. Dataset consists of 445 samples collected from various respondents by asking three questions. Preprocessing is performed by using the techniques of Natural language processing and nonaxiomatic logic. Convolutional Neural Network Machine learning technique applied to classify the mental factors. Performance of the proposed system is measured by applying statistical measures such as Accuracy, Precision, Specificity, Recall and F1-Score. Accuracy for small and large database is obtained as 86.92% and 93.02% respectively.

Image De-Noising Using Convolutional Variational Autoencoders

Abstract: Typically, image noise is random colour information in picture pixels that serves as an unfavourable by-product of the image, obscuring the intended information. In most cases, noise is injected into photographs during the transfer or reception of the image, or during the capture of an image when an object is moving quickly. To improve the noisy picture predictions, autoencoders that denoise the input images are employed. Autoencoders are a sort of unsupervised machine learning that compresses the input and reconstructs an output that is very similar to the original input. The autoencoder tries to figure out non-linear correlations between data points. An encoder, a latent space, and a decoder all exist in autoencoders. The encoder reduces the dimensionality of an original picture to its latent space representation, which is then used by the decoder to reconstruct the reduced dimensional image back to its original image. Basic Autoencoder, Variational Autoencoder, and Convolutional Autoencoder are the three approaches that were employed to denoise the picture. In the basic and convolutional autoencoders, there is only one loss parameter, however in the variational autoencoder, there are two losses: generative loss and latent loss. TensorFlow as the frontend and Keras as the backend are used to implement autoencoders in this project. The noisy pictures are trained on every convolutional variational autoencoder techniques to produce a decent prediction of noisy test data.

LAGConv: Local-Context Adaptive Convolution Kernels with Global Harmonic Bias for Pansharpening

Pansharpening is a critical yet challenging low-level vision task that aims to obtain a higher-resolution image by fusing a multispectral (MS) image and a panchromatic (PAN) image. While most pansharpening methods are based on convolutional neural network (CNN) architectures with standard convolution operations, few attempts have been made with context-adaptive/dynamic convolution, which delivers impressive results on high-level vision tasks. In this paper, we propose a novel strategy to generate local-context adaptive (LCA) convolution kernels and introduce a new global harmonic (GH) bias mechanism, exploiting image local specificity as well as integrating global information, dubbed LAGConv. The proposed LAGConv can replace the standard convolution that is context-agnostic to fully perceive the particularity of each pixel for the task of remote sensing pansharpening. Furthermore, by applying the LAGConv, we provide an image fusion network architecture, which is more effective than conventional CNN-based pansharpening approaches. The superiority of the proposed method is demonstrated by extensive experiments implemented on a wide range of datasets compared with state-of-the-art pansharpening methods. Besides, more discussions testify that the proposed LAGConv outperforms recent adaptive convolution techniques for pansharpening.

CNN-Based Brain Tumor Detection Model Using Local Binary Pattern and Multilayered SVM Classifier.

In this paper, an autonomous brain tumor segmentation and detection model is developed utilizing a convolutional neural network technique that included a local binary pattern and a multilayered support vector machine. The detection and classification of brain tumors are a key feature in order to aid physicians; an intelligent system must be designed with less manual work and more automated operations in mind. The collected images are then processed using image filtering techniques, followed by image intensity normalization, before proceeding to the patch extraction stage, which results in patch extracted images. During feature extraction, the RGB image is converted to a binary image by grayscale conversion via the colormap process, and this process is then completed by the local binary pattern (LBP). To extract feature information, a convolutional network can be utilized, while to detect objects, a multilayered support vector machine (ML-SVM) can be employed. CNN is a popular deep learning algorithm that is utilized in a wide variety of engineering applications. Finally, the classification approach used in this work aids in determining the presence or absence of a brain tumor. To conduct the comparison, the entire work is tested against existing procedures and the proposed approach using critical metrics such as dice similarity coefficient (DSC), Jaccard similarity index (JSI), sensitivity (SE), accuracy (ACC), specificity (SP), and precision (PR).

FOREST FIRE DETECTION USING CONVOLUTIONAL NEURAL NETWORK

Fire outbreaks are a typical occurrence all throughout the world, and the harm they bring to both nature and humans is enormous. In comparison to classic sensor-based fire detection systems, vision-based fire detection systems have recently gained favour. The detection process using image processing techniques, on the other hand, is extremely time consuming. We designed a Convolutional Neural Network-based fire detection technique. Through training with datasets, obtain high-accuracy fire image detection that is consistent with fire detection. In this paper, we propose a system for detecting fire using Convolutional Neural Networks (CNN). This paper critically analyzes the scope of Artificial intelligence for detection with video from CCTV footages. This project uses dataset containing video frames with fire. The data is then preprocessed and use the CNN to build a model to detect fire. The dataset is given as input for validating the algorithm and experiments are noted. This project focus on building high accuracy and cost efficient machine that can be used for fire detection.There are 755 and 244 images in the datasets for fire and non-fire, respectively. There are 999 photos in all. These images were created using fire-related video and some images found on the internet. There are 999 images that have been scaled and reshaped to convert to a training dataset and 999 images that have been resized and reshaped to convert to a testing dataset. Convolution, activation functions, and the max pooling technique are used to train the model. The model is trained by varying batch sizes and epoch values. As a result, we obtain a high accuracy and detection rate. Key words: CNN,fire detection,machine learning.

Accurate Prediction of Voltage of Battery Electrode Materials Using Attention-Based Graph Neural Networks.

Performing first-principles calculations to discover electrodes' properties in the large chemical space is a challenging task. While machine learning (ML) has been applied to effectively accelerate those discoveries, most of the applied methods ignore the materials' spatial information and only use predefined features: based only on chemical compositions. We propose two attention-based graph convolutional neural network techniques to learn the average voltage of electrodes. Our proposed methods, which combine both atomic composition and atomic coordinates in 3D-space, improve the accuracy in voltage prediction significantly when compared to composition-based ML models. The first model directly learns the chemical reaction of electrodes and metal ions to predict their average voltage, whereas the second model combines electrodes' ML predicted formation energy (Eform) to compute their average voltage. Our Eform-based model demonstrates improved accuracy in transferability from our subset of learned Li ions to Na ions. Moreover, we predicted the theoretical voltage of 10 NaxMPO4F (M = Ti, Cr, Fe, Cu, Mn, Co, and Ni) fluorophosphate battery frameworks, which are unavailable in the Material Project database. It could be shown that we can expect average voltages higher than 3.1 V from those Na battery frameworks except from the NaTiPO4F and TiPO4F pair of electrodes, which offer an average voltage of 1.32 V.

A convolution neural network with multi-level convolutional and attention learning for classification of cancer grades and tissue structures in colon histopathological images

A clinically comparable Convolutional Neural Network framework-based technique for performing automated classification of cancer grades and tissue structures in hematoxylin and eosin-stained colon histopathological images is proposed in this paper. It comprised of Enhanced Convolutional Learning Modules (ECLMs), multi-level Attention Learning Module (ALM), and Transitional Modules (TMs). The ECLMs perform a dual mechanism to extract multi-level discriminative spatial features and model cross-channel correlations with fewer computations and effectual avoidance of vanishing gradient issues. The ALM performs focus-refinement through the channel-wise elemental attention learning to accentuate the discriminative channels of the features maps specifically belonging to the important pathological regions and the scale-wise attention learning to facilitate recalibration of features maps at diverse scales. The TMs concatenate the output of these two modules, infuse deep multi-scalar features and eliminate resolution degradation issues. Varied pre-processing techniques are further employed to improvise the generalizability of the proposed network. For performance evaluation, four diverse publicly available datasets (Gland Segmentation challenge(GlaS), Lung Colon(LC)-25000, Kather_Colorectal_Cancer_Texture_Images (Kather-5k), and NCT_HE_CRC_100K(NCT-100k)) and a private dataset Hospital Colon(HosC) are used that further aids in building network invariance against digital variability that exists in real-clinical data. Also, multiple pathologists are involved at every stage of the proposed research and their verification and approval are taken for each step outcome. For the cancer grade classification, the proposed model achieves competitive results for GlaS (Accuracy(97.5%), Precision(97.67%), F1-Score(97.67%), and Recall(97.67%)), LC-25000 (Accuracy(100%), Precision(100%), F1-Score(100%), and Recall(100%)), and HosC(Accuracy(99.45%), Precision(100%), F1-Score(99.65%), and Recall(99.31%)), and while for the tissue structure classification, it achieves results for Kather-5k(Accuracy(98.83%), Precision(98.86%), F1-Score(98.85%), and Recall(98.85%)) and NCT-100k(Accuracy(97.7%), Precision(97.69%), F1-Score(97.71%), and Recall(97.73%)). Furthermore, the reported activation mappings of Gradient-Weighted Class Activation Mappings(Grad-CAM), Occlusion Sensitivity, and Local Interpretable Model-Agnostic Explanations (LIME) evidence that the proposed model can itself learn the similar patterns considered pertinent by the pathologists exclusive of any prerequisite for annotations. In addition, these visualization results are inspected by multiple expert pathologists and provided with a validation score as (GlaS(9.251), LC-25000(9.045), Kather-5k(9.248), NCT-100k(9.262), and HosC(9.853)). This model will provide a secondary referential diagnosis for the pathologists to ease their load and aid them in devising an accurate diagnosis and treatment plan.

CogEmoNet: A Cognitive-Feature-Augmented Driver Emotion Recognition Model for Smart Cockpit

Driver’s emotion recognition is vital to improving driving safety, comfort, and acceptance of intelligent vehicles. This article presents a cognitive-feature-augmented driver emotion detection method that is based on emotional cognitive process theory and deep networks. Different from the traditional methods, both the driver’s facial expression and cognitive process characteristics (age, gender, and driving age) were used as the inputs of the proposed model. Convolutional techniques were adopted to construct the model for driver’s emotion detection simultaneously considering the driver’s facial expression and cognitive process characteristics. A driver’s emotion data collection was carried out to validate the performance of the proposed method. The collected dataset consists of 40 drivers’ frontal facial videos, their cognitive process characteristics, and self-reported assessments of driver emotions. Another two deep networks were also used to compare recognition performance. The results prove that the proposed method can achieve well detection results for different databases on the discrete emotion model and dimensional emotion model, respectively.

Modelling of basic Indonesian Sign Language translator based on Raspberry Pi technology

Deaf people have hearing loss from mild to very severe. Such people have difficulty processing language information both with and without hearing aids. Deaf people who do not use hearing aids use sign language in their everyday conversations. At the same time, it is difficult for general people to communicate with the deaf, so in order to communicate with the deaf they must know sign language. There are two sign languages in Indonesia, namely SIBI (Indonesian Sign Language System) and BISINDO (Indonesian Sign Language). To help with communication between deaf and normal people, we developed a model using the one-handed SIBI method as an example, and then further developed it using the one-handed and two-handed BISINDO. The main function of the method is the recognition of basic letters, words, sentences and numbers using a Raspberry Pi single-board computer and a camera which are designed to detect the movements of language gestures. With the help of a special program, images are translated into text on the monitor screen. The method used is image processing and machine learning using the Python programming language and Convolutional Neural Network techniques. The device prototype issues a warning to repeat the sign language if the translation fails, and delete the translation if it doesn’t match the database. The prototype of the device requires further development providing its flexibility: to provide reading of dynamic movements, facial expressions, to provide translation of words not included in the existing database. You need to add a database other than SIBI, such as BISINDO, or sign languages from other regions or countries.

Computational Fluid Dynamic Evaluation of Deep Inferior Epigastric Artery Perforator (DIEP) Flap End-to-Side Anastomosis.

BackgroundEnd-to-side (ETS) microvascular anastomoses are utilized within deep inferior epigastric artery perforator (DIEP) flap breast reconstruction procedures. Optimization of these anastomoses via a computational fluid dynamic (CFD) model can minimize ischemia and contribute to flap success.Methods A CFD model of a deep inferior epigastric artery to internal mammary artery anastomosis was constructed with OpenFOAM software (OpenCFD Ltd., Bracknell, UK). Blood was modelled as an incompressible Newtonian fluid. Viscosity and density were assumed to be constant throughout the simulation. Mean arterial pressure was held constant at 100 mmHg. Individual virtual meshes were created for 30-, 45-, 60-, 75-, and 90-degree anastomotic angle simulations. Fluid flow was visualized with line integral convolution (LIC) and pure fluid velocity (PFV) techniques. Vessel wall shear stress (WSS) was also visualized.Results The LIC revealed blood recirculation was associated with large anastomotic angles with minimal to no recirculation seen in the 45- and 30-degree simulations. Any recirculation visualized was confined to the toe of the bifurcation. This recirculation was associated with stagnation in the toe of the graft vessel as well, as visualized by the PFV model. A linear relationship was identified between anastomotic angle and percentage of stagnant fluid, with stagnation increasing as the anastomotic angle increased. Wall shear stress increased with the anastomotic angle and was concentrated in the heel and toe of the model.Conclusions The CFD modelling shows that increased acuity of anastomotic angles in ETS DIEP flaps is essential to minimize stagnation, recirculation, and WSS. Successful implementation of this recommendation may directly decrease the risk of flap failure from ischemia.

Efficient Weed Segmentation with Reduced Residual U-Net using Depth-wise Separable Convolution Network

Selective weed treatment is a cost-effective method that reduces manpower and usage of the agrochemical, at the same time it requires an effective computer vision system to identify weeds and should be smaller in size to run in resource-constrained devices. To accomplish this, a convolution neural network named Reduced Residual U-Net using Depth-wise separable Convolution (RRUDC) network is proposed in this paper. Residual Depth-wise separable Convolution Block (RDCB) is introduced as a functional unit in both contractive and expanding paths. Residual connection is incorporated inside every RDCB unit. This network employs semantic segmentation to analyze the crop field images pixel-wise. To reduce the parameter size, a depth-wise separable convolution technique is used which curtail the number of parameters generated by the model at a ~1/9 ratio with a very negligible drop in accuracy. The model is trained using Crop Weed Field Image Dataset (CWFID) and then the trained model is pruned to reduce the model size further. It compresses the final model size by around ~70% without affecting the performance. It has achieved segmentation accuracy of ~96%, a lesser error rate with a model size less than 3 MB. It can be compatible with converting the proposed deep learning model into a real-time computer vision application that seems more convenient for farmers in their resource-constrained devices on their agricultural land.

A Novel Approach of Text to Audio Conversion for Blindly Disable Using Raspberry Pi

One of the most difficult tasks for visually impaired people is reading. Blind persons may now recognise boundaries, read labels or certain currencies, and even read written, typed, or printed information, thanks to a technology developed by a group of academics. In this work, an assistance system is designed for blind persons who are visually challenged by using Raspberry Pi as a 32-bit micro controller that utilizes the character recognition technology for image to audio conversion; this work proposes a more effective solution. A camera is the heart of the system, serving as the primary vision for identifying product reports, bills, bank account information, menu boards, school handouts, product packaging, and medication bottle directions. The proposed technique consists of four major steps: i) object identification, ii) text localization, iii) text extraction, iv) text to speech conversion. An optical character recognition (OCR) after recognizing printed text with a technique, the image is digitally processed to extract the label with the use of an open CV library. After the Region of Interest is extracted from the congested backdrop, the text localization technique is utilized to find and extract the text. The ROI's text is retrieved and converted into speech. For training the words independently, a convolutional recurrent neural network technique is proposed.

Novel Framework for the Improvement of Object Detection Accuracy of Smart Surveillance Camera Visuals Using Modified Convolutional Neural Network Technique Compared with Global Color Histogram

The objective of the proposed work is to evaluate the accuracy of Global Color Histogram (GCH) and Modified Convolutional Neural Networks Techniques (MCNNT) by changing the hierarchical data processing for Smart Surveillance System. Methods and materials: Our novel framework with MCNNT uses the data in hierarchical models of data processing, which is constructed with fully connected layers and the neurons were connected to every other node to handle complex object detection tasks and evaluated using the sample size of 20 per group with model image dataset. Result: The recorded mean accuracy of MCNNT (95.28%) is better than GCH (80.48%). There is a statistical significant difference in accuracy for two algorithms performed by independent sample t-test (P<0.05) for the Confidence Interval (CI) 95%. Conclusion: MCNNT appears to have better accuracy than GCH for object detection of Smart Surveillance System.