scispace - formally typeset
Search or ask a question

Showing papers by "College of Engineering, Pune published in 2018"


Journal ArticleDOI
TL;DR: In this paper, an extensive literature review in the general area of post processing techniques which are used in additive manufacturing is presented. And the main objective of this work is to document an extensive review of the post-processing techniques used in Additive Manufacturing.
Abstract: The Additive Manufacturing (AM) processes open the possibility to go directly from Computer-Aided Design (CAD) to a physical prototype. These prototypes are used as test models before it is finalized as well as sometimes as a final product. Additive Manufacturing has many advantages over the traditional process used to develop a product such as allowing early customer involvement in product development, complex shape generation and also save time as well as money. Additive manufacturing also possess some special challenges that are usually worth overcoming such as Poor Surface quality, Physical Properties and use of specific raw material for manufacturing. To improve the surface quality several attempts had been made by controlling various process parameters of Additive manufacturing and also applying different post processing techniques on components manufactured by Additive manufacturing. The main objective of this work is to document an extensive literature review in the general area of post processing techniques which are used in Additive manufacturing.

217 citations


Journal ArticleDOI
TL;DR: An overview of current LDW system is provided, describing in particular pre-processing, lane models, lane de Ntection techniques and departure warning system.

196 citations


Proceedings ArticleDOI
11 May 2018
TL;DR: This paper proposed the development of the sensor node capable of measuring all the required parameter from the agriculture field and creating the actuation signal for all the actuator in the agriculture domain and also capable of sending this data to cloud.
Abstract: Internet is experiencing a very explosive growth nowadays with the amount of the devices connecting to it. Earlier we had only personal computers (pCs) and Mobile handset connected to internet but now with Internet of Things i.e. IoT concept of connecting things with internet, millions of device are connecting with it. This development of IoT leads to the idea of machine to machine communication which means that two machines can communicate to each other and also all the data which was previously with private server can now is available on internet so the user can access it remotely. Application of IoT is feasible in almost all industries particularly where speed of communication is not an issue. This paper proposes the application of cloud based IoT in the agriculture domain. Precision agriculture is basically a concept which insists to provide right amount of resources at and for exact duration of time. These resources can be any things such as water, light, pesticides etc. To implement precision agriculture the benefits of IOT has been utilized in the proposed paper. The fundamental idea is to sense all the required parameter from the agriculture field and take required decision to control the actuator. These agriculture parameters are Soil Moisture, Temperature & Relative Humidity around plant, Light intensity. Based on the reading sensed by the sensor suitable action is taken i.e. irrigation valve is actuated based on soil moisture readings, valve for fogger (for spraying water droplet) is actuated based on the Relative humidity(RH) readings etc. This paper proposed the development of the sensor node capable of measuring all these parameter and creating the actuation signal for all the actuator. On top of that sensor nodes are also capable of sending this data to cloud. An Android application is also developed in order to access all these agricultural parameter.

99 citations


Proceedings ArticleDOI
01 Nov 2018
TL;DR: This paper discusses the potential security threats to the Industries adapting to IIoT and study the various attacks that are possible on the components in the layeredIIoT architecture and some of the preventive measures and proposes IIoTs attack taxonomy which would help in mitigating the risks of the attacks.
Abstract: Industrial Internet of Things (IIoT) applications connect machines, sensors and actuators in high-stake manufacturing industries. Industrial systems are using the potential of IoT to reduce the unnecessary operational cost and increase the usability and reliability of the industrial assets to achieve more profits. However, such smart Industries need connectivity and interoperability to enhance performance which makes them susceptible to various attacks. Recent attacks on Cyber-physical systems raise a strong security concern as such attacks causes a huge property loss and may also lead to life threatening situations. In this paper we discuss the potential security threats to the Industries adapting to IIoT and study the various attacks that are possible on the components in the layered IIoT architecture and some of the preventive measures. Finally, we propose IIoT attack taxonomy which would help in mitigating the risks of the attacks.

62 citations


Proceedings ArticleDOI
01 Aug 2018
TL;DR: The aim of this paper is to detect DoS attack effectively using Machine learning (ML) and Neural Network (NN) algorithms and it is shown that RF provides better results than MLP.
Abstract: The current digital world is using the internet almost everywhere. The usage of internet has been increasing, however, threats are also increasing in numbers. One such threat is DoS attack which uses reasonable service requests to gain excessive computing and network resources and results in an inability to access them by legitimate users. The DoS attack can happen at different layers of OSI model such as network, transport and application layers. The aim of this paper is to detect DoS attack effectively using Machine learning (ML) and Neural Network (NN) algorithms. The detection is specifically focused on application layer DoS attack detection rather than at transport and network DoS attack detection. The latest DoS attack dataset CIC IDS 2017 dataset is used in the experiment. The experimentation has divided the dataset into different splits and the best split is found for each algorithm i.e. RF and MLP. Results of RF and MLP are compared and it is shown that RF provides better results than MLP.

54 citations


Proceedings ArticleDOI
10 Jul 2018
TL;DR: This paper proposes use of machine learning classification algorithms - XGBoost and AdaBoost with and without clustering to train a model for NIDS and the results are an improvement over the previous works related to intrusion detection on the same dataset.
Abstract: An unauthorized activity on the network is called network intrusion and device or software application which monitors the network parameters in order to detect such an intrusion is called network intrusion detection system (NIDS). With high rise in malicious activities on the internet, it is extremely important for NIDS to quickly and correctly identify any kind of malicious activity on the network. Moreover, the system must refrain from raising false alarms in case of normal usage detected as malicious. This paper proposes use of machine learning classification algorithms - XGBoost and AdaBoost with and without clustering to train a model for NIDS. The models are trained and tested using NSL KDD dataset and the results are an improvement over the previous works related to intrusion detection on the same dataset.

42 citations


Journal ArticleDOI
TL;DR: In this article, the authors show that the average increase in the initial cost of green buildings is 3.10% for those with three stars rating and 9.37 % for those that are five stars rated buildings.

41 citations


Proceedings ArticleDOI
01 Aug 2018
TL;DR: This work is working on heart disease prediction on the basis of the dataset with help of Naïve bayes and KNN algorithm, and proposes the disease risk prediction using structured data which answers the question related to disease which people face in their life.
Abstract: Data analysis plays a significant role in handling a large amount of data in the healthcare. The previous medical researches based on handling and assimilate a huge amount of hospital data instead of prediction. Due to an enormous amount of data growth in the biomedical and healthcare field the accurate analysis of medical data becomes propitious for earlier detection of disease and patient care. However, the accuracy decreases when the medical data is partially missing. To overcome the problem of missing medical data, we perform data cleaning and imputation to transform the incomplete data to complete data. We are working on heart disease prediction on the basis of the dataset with help of Naive bayes and KNN algorithm. To extend this work, we propose the disease risk prediction using structured data. We use convolutional neural network based unimodel disease risk prediction algorithm. The prediction accuracy of CNN-UDRP algorithm reaches more than 65%. Moreover, this system answers the question related to disease which people face in their life.

41 citations


Proceedings ArticleDOI
01 Jan 2018
TL;DR: In this paper, the authors have used different classifiers such as J48, LWL, LAD Tree and IBK for prediction and then the performance of each classifier is compared using WEKA tool.
Abstract: Agriculture is the most important sector that influences the economy of India. It contributes to 18% of India's Gross Domestic Product (GDP) and gives employment to 50% of the population of India. People of India are practicing Agriculture for years but the results are never satisfying due to various factors that affect the crop yield. To fulfill the needs of around 1.2 billion people, it is very important to have a good yield of crops. Due to factors like soil type, precipitation, seed quality, lack of technical facilities etc the crop yield is directly influenced. Hence, new technologies are necessary for satisfying the growing need and farmers must work smartly by opting new technologies rather than going for trivial methods. This paper focuses on implementing crop yield prediction system by using Data Mining techniques by doing analysis on agriculture dataset. Different classifiers are used namely J48, LWL, LAD Tree and IBK for prediction and then the performance of each is compared using WEKA tool. For evaluating performance Accuracy is used as one of the factors. The classifiers are further compared with the values of Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Relative Absolute Error (RAE). Lesser the value of error, more accurate the algorithm will work. The result is based on comparison among the classifiers.

39 citations


Journal ArticleDOI
TL;DR: The objective of regulating the output voltage in the presence of uncertainties in input voltage and load is met by proposing an integral sliding mode control (ISMC) combined with a disturbance observer.
Abstract: This brief proposes a control strategy to regulate nonminimum phase dc–dc converters affected by line and load uncertainties. The objective of regulating the output voltage in the presence of uncertainties in input voltage and load is met by proposing an integral sliding mode control (ISMC) combined with a disturbance observer. The ability of the controller in tracking the reference voltage and regulation of the output voltage is analyzed. The controller is validated experimentally and compared with another scheme based on ISMC.

35 citations


Proceedings ArticleDOI
01 Aug 2018
TL;DR: IoT devices like low power sensors will be used to collect data from patients and it will be displayed using LCD and stored on any personal computer and also on the cloud so that any actor in the system can refer to it.
Abstract: Health has become one of the global challenges for humanity. Cardiac diseases, Lung failures and heart related diseases are increasing at a rapid rate. Monitoring health of elderly people at home or patients at hospitals is necessary but it requires constant observation of Practitioners and Doctors. Information Technology (IT) and its growing applications are performing major role in making human life easier. Internet of Things (IoT) is transforming healthcare and the role of IT in healthcare. IoT consists of physical devices, such as sensors and monitoring devices for patients (glucose, blood pressure, heart rate & activity monitoring, etc) to connect to the internet and transforms information from the physical world into the digital world. The proposed system, with the help of IoT's such features, will help to keep the necessary details and reports of a patient organized and available to all actors in the system. IoT devices like low power sensors will be used to collect data from patients and it will be displayed using LCD and stored on any personal computer and also on the cloud so that any actor in the system can refer to it.

Proceedings ArticleDOI
01 Aug 2018
TL;DR: In this Experiment, this work successfully tried to classify handwritten Devanagari characters using transfer learning mechanism with the help of Alexnet, a convolutional neural network which shows impressive results.
Abstract: Since past few years, deep neural networks, because of their outstanding performance, are getting highly used in computer vision and machine learning tasks such as regression, segmentation, classification, detection, pattern recognition etc. Recognition of handwritten Devanagari characters is challenging task, but Deep learning can be effectively used as a solution for various such problems. Person to person variations in writing style makes handwritten character recognition one of the most difficult tasks. In this Experiment, we successfully tried to classify handwritten Devanagari characters using transfer learning mechanism with the help of Alexnet. Alexnet, a convolutional neural network, is trained over a dataset of around 16870 samples of 22 consonants of Devanagari script which shows impressive results. The transfer learning helps to learn faster and better even if the data samples are less as compared with the training a CNN from scratch.

Proceedings ArticleDOI
01 Aug 2018
TL;DR: First pre-processing of the skin image is done and proposed system results shows that support vector machine with linear kernel gives optimum accuracy.
Abstract: Now days, Skin cancer is life threatening disease which causes human death. Abnormal growth of melanocytic cells causes a skin cancer. Due to malignancy feature skin cancer is also known as melanoma. Melanoma appears on the skin due to exposure of ultraviolet radiation and genetic factors. So melanoma lesion appears as black or brown in colour. Early detection of melanoma can cure completely. Biopsy is a traditional method for detecting skin cancer. This method is painful and invasive. This method requires laboratory testing so it is time consuming. Therefore, in order to solve the above stated issues computer aided diagnosis for skin cancer is needed. Computer aided diagnosis uses Dermoscopy for capturing the skin image. In this paper first pre-processing of the skin image is done. After pre-processing lesion part is segmented by using image segmentation technique which is followed by feature extraction in which unique features are extracted from segmented lesion. After feature extraction, classification by using support vector machine is performed for classifying the skin image as normal skin and melanoma skin cancer. The proposed system results shows that support vector machine with linear kernel gives optimum accuracy.

Journal ArticleDOI
TL;DR: A novel automated tissue segmentation and classification method based on Independent Component Analysis with Band Expansion Process (BEP) and Support Vector Machine (SVM) classifier which with input as T1, T2 and Proton Density scans of patient, provides output indicating the possible atrophy in brain which can help in diagnosis of Alzheimer’s disease.

Journal ArticleDOI
TL;DR: In this paper, the authors assessed uncertainties in the projections of hydro-climatic variables over India by considering multiple downscaling techniques, multiple GCMs, and their combined effects (referred as the total uncertainty).
Abstract: India is a major agrarian country strongly impacted by spatio-temporal variations in the Indian monsoon. The impact assessment is usually accomplished by implementing projections from general circulation models (GCMs). Unfortunately, these projections cannot capture the dynamicity of the monsoon and require either statistical (SD) or dynamical (DD) downscaling of the GCM projections to a finer resolution. Both downscaling techniques can capture the spatio-temporal variation in climatic variables but are marred by uncertainty in the projections resulting from the choice of the GCM and downscaling method, which affects climate change adaptations. Here, we assessed uncertainties in the projections of hydro-climatic variables over India by considering multiple downscaling techniques, multiple GCMs, and their combined effects (referred as the total uncertainty). Multiple hydrological variables were simulated by implementing the variable infiltration capacity model that considered outputs from DD (derived by the coordinated regional climate downscaling experiment, CORDEX) and SD forced with multiple GCM simulations. Our results showed that the SD projections captured the observed spatio-temporal variability of hydro-climatic variables more efficiently than the DD projections. Importantly, contribution from the downscaled projections to the total uncertainty was significantly smaller compared to the inter-GCM uncertainty. We believe uncertainty analysis is an important component of good scientific practice; however, several researchers appear to be rather reluctant to embrace the concept of uncertainty in making projections, predictions, and forecasting. It remains a common practice to show climate change exercises to decision-makers/stakeholders, without uncertainty bounds. Here, a successful attempt was made to identify the key sources of uncertainty and adequately bracket the uncertainty, indicating a requirement of the code of practice to provide formal guidance, particularly for climate-change impact assessments. This consequently emphasized the importance of follow-up research to understand the inter-GCM uncertainty, which has a significant impact on sustainable agriculture and water resources management in India.

Journal ArticleDOI
TL;DR: In this article, the effects of GNP content on electrical properties and electromagnetic interference shielding effectiveness (EMI SE) of polycarbonate (PC)/graphite nanoplatelet (GNP) nanocomposites in X-band were studied.

Journal ArticleDOI
TL;DR: In this article, the effect of orientation angle of erosion wear on a test rig fabricated for the present work has been evaluated and the results showed typical ductile erosion behavior for the selected materials.

Proceedings ArticleDOI
01 Aug 2018
TL;DR: This project is going to analyse and mine this agricultural data to get useful results using technologies like data analytics and machine learning and this result will be given to farmers for better crop yield in terms of efficiency and productivity.
Abstract: Agricultural data is being produced constantly and enourmosly. As a result, agricultural data has come in the era of big data. Smart technologies contribute in data collection using electronic devices. In our project we are going to analyse and mine this agricultural data to get useful results using technologies like data analytics and machine learning and this result will be given to farmers for better crop yield in terms of efficiency and productivity.

Journal ArticleDOI
TL;DR: The cohort intelligence (CI) method is used for the first time to optimize the parameters of the fractional proportionalintegral- derivative (PID) controller and the standard deviations demonstrated the robustness of the proposed algorithm in solving control problems.
Abstract: The cohort intelligence (CI) method has recently evolved as an optimization method based on artificial intelligence. We use the CI method for the first time to optimize the parameters of the fractional proportionalintegral- derivative (PID) controller. The performance of the CI method in designing the fractional PID controller was validated and compared with those of some other popular algorithms such as particle swarm optimization, the genetic algorithm, and the improved electromagnetic algorithm. The CI method yielded improved solutions in terms of the cost function, computing time, and function evaluations in comparison with the other three algorithms. In addition, the standard deviations of the CI method demonstrated the robustness of the proposed algorithm in solving control problems.

Journal ArticleDOI
TL;DR: In this paper, the authors used the system identification black box approach to develop a number of simple but more realistic mathematical model structures for a PEM fuel cell, which can be used to predict the polarization behavior of the fuel cell under different loading conditions.
Abstract: A polymer electrolyte membrane (PEM) fuel cell is very useful for distributed generation and for portable users like electric vehicles because it is very efficient, emission free and operated at low temperature. However, it is not so easy to find direct experimental estimates of the actual performance of PEM fuel cell through various phenomena and operating conditions like chemical reactions, fuel pressure, working temperature and fuel humidity. Mathematical modeling, therefore, plays an important role in understanding operational performance of PEM fuel cell. The actual operating performance of PEM fuel cell depends on a number of parameters, therefore developing an accurate model that includes its dynamic behavior is most important. In this paper, first time, the system identification black box approach is used to develop a number of simple but more realistic mathematical model structures for a PEM fuel cell. The performance of each model structure is compared with the data from a 25 cm2 active area practical PEM fuel cell for result validation. The presented models can be used to predict polarization behavior of the PEM fuel cell under different loading conditions.

Proceedings ArticleDOI
01 Aug 2018
TL;DR: The main objective of the paper is a comprehensive analysis of five well-known supervised machine learning algorithms on IoT datasets that are compared on various performance metrics such as precision, recall, f1-score, kappa, and accuracy.
Abstract: Internet of Things(IoT) is one of the rapidly growing fields andn has a wide range of applications such as smart cities, smart homes, connected wearable, connected health-care, and connected automobiles, etc. These IoT applications generate tremendous amounts of data which needs to be analyzed to draw useful inferences required to optimize the performance of IoT applications. The artificial intelligence(AI) and machine learning (ML) play the significant role in building the smart IoT systems. The main objective of the paper is a comprehensive analysis of five well-known supervised machine learning algorithms on IoT datasets. The five classifiers are K-Nearest Neighbors (KNN), Naive Bayes (NB), Decision Tree (DT), Random Forest (RF) and Logistic Regression (LR). The feature reduction is performed using PCA algorithm. The performance of these five classifiers has been compared on the basis of six characteristics of IoT dataset such as size, number of features, number of classes, class imbalance, missing values and execution time. The classifiers have also been compared on various performance metrics such as precision, recall, f1-score, kappa, and accuracy. As per our results, the DT classifier gives the best accuracy of 99% among all the algorithms for all datasets. The results also show the performance of RF and KNN as almost similar and the NB and LR perform the worst among all the classifiers

Journal ArticleDOI
TL;DR: The study argues for the potential role of loud ‘OM’ chanting in offering relaxation, and provides a new perspective of meditation to the naive meditators, which may help to demystify meditation and encourage those considering this as beneficial practice.
Abstract: Mantra meditation is easy to practice. “OM” Mantra is the highest sacred symbol in Hinduism. The present study investigated the temporal dynamics of oscillatory changes after OM mantra meditation. Twenty-three naive meditators were asked to perform loud OM chanting for 30 min and the EEG were subsequently recorded with closed eyes before and after it. To obtain new insights into the nature of the EEG after OM chanting, EEG signals were analyzed using spectral domain analysis. Statistical analysis was performed using repeated measures of analysis of variance. It did not reveal any specific band involvement into OM mantra meditation. But significantly increase in theta power was found after meditation when averaged across all brain regions. This is the main effect of OM mantra meditation. However, the theta power showed higher theta amplitude after condition at all regions in comparison to the before condition of meditation. Finding was similar to other studies documenting reduction in cortical arousal during a state of relaxation. The study argues for the potential role of loud ‘OM’ chanting in offering relaxation. It provides a new perspective of meditation to the naive meditators. This information may help to demystify meditation and encourage those considering this as beneficial practice.

Journal ArticleDOI
TL;DR: In this paper, the authors presented the results of harmonic analysis of the aluminum shaft rotor bearing system with rigid coupling, under parallel misalignment, using FEA and compared with experimental results based on FFT analyzer for different sub critical speeds.

Journal ArticleDOI
TL;DR: In this article, the authors explored the formed bilayer on chitosan bead for the removal of Ni(II) from water by modifying the bead surface with sodium dodecyl sulfate (SDS).

Proceedings ArticleDOI
14 Jun 2018
TL;DR: A GUI based, trainable robotic arm which is being automated for multipurpose industrial applications, and to achieve the ability of commanding and controlling the arm through MATLAB Graphical User Interface (GUI) and to make the system more efficient.
Abstract: As the technology is growing day by day the world is adapting robotic for their comfort in daily life. So we have developed a GUI based, trainable robotic arm which is being automated for multipurpose industrial applications. The special feature which we are highlighting in our work is that, the arm is easily manipulated and has all in one solution for the certain range of pick and place application. The basic aim is to achieve the ability of commanding and controlling the arm through MATLAB Graphical User Interface (GUI) and to make the system more efficient. The designed system has been divided into 2 parts: (1) The AVR microcontroller has been programmed for the central controlling station which has GUI access and the arm control, and (2) to program the GUI for making the robot trainable and user-friendly. As it is a time-saving controlling method, we can use it for picking and placing the material over the conveyor assembly.

Proceedings ArticleDOI
01 Aug 2018
TL;DR: In this paper, an insight is provided into the different protocols for Inter-vehicles and In-vehicle communication network systems, overview and the emerging In-Vehicle networking standards and their security issues.
Abstract: As a new generation vehicle are in market now days, new networking architecture is defined for those vehicles. In-vehicle communication and different interfaces which are used to connect in-vehicle network to outside are vulnerable. Communication like Vehicle to Vehicle (V2V), Vehicle to Infrastructure (V2I) and Vehicle to Anything (V2X) is not secure as there are so many vulnerabilities present in designed communication protocol. The vehicles which are on road consist of several Electronic controller units (ECU). These ECUs takes input from different sensors or another ECU and take appropriate action. When vehicle is on road, these ECUs are communicating continuously. According to the current figure there are near about 70 to 100 ECUs present and communication of these ECU is taken place via different communication channel called bus. To reduce the complex wiring of buses, researchers developed different protocol for different type of communication bus protocol such as LIN, CAN, FlexRay, and MOST which is widely used by different automotive manufacturers. On the basis of speed used for communication the bus is chosen like, to play video there must be very high speed bus as streaming must be taken place with maximum speed without any delay. There are several safety critical ECUs also such as break system, Engine Control, Speed Control etc. Apart from these, as day by day the luxurious features are introduced by the automotive manufacturer by adding more ECU and security for that gaining more importance. So the risk of cyber-attack is quite high which can be life threat to driver and passenger. In addition to that, interfaces such as wireless communication, remote diagnostics, and firmware update over the air are new platforms where attacker have various option for intrusion. For example attacker can take control on vehicle steering using wireless communication interface and puts lives of passengers in danger. To reduce the complex wiring for communication and increase the efficiency of communication automotive manufacturers developed different protocols but the security for that. In this paper, we will provide an insight into the different protocols for Inter-vehicle and In-vehicle communication network systems, overview and the emerging In-Vehicle networking standards and their security issues.

Proceedings ArticleDOI
11 May 2018
TL;DR: The performance of the controller for closed loop state is compared with typical PID and fractional order PID controller(FOPID) and the improved performance of FOFPID controller over typical PID controller and FOPID controller is shown.
Abstract: This paper proposes a fractional order fuzzy PID controller(FOFPID) for a rotary servo system. The controller part consists of the summation of fractional integral of error and output of fuzzy logic controller which has two inputs, that are error and fractional derivative of error. The fractional order differentiation and error in the fuzzy logic controller (FLC) are kept as input scaling factors and are streamlined with fuzzy inference system (FIS) to limit integral error indices along with the control signal as the goal work. The performance of the controller for closed loop state is compared with typical PID and fractional order PID controller(FOPID). The performance of the designed controller is measured by evaluating different parameters like peak overshoot, settling time and rise time. Stability of the designed controller is evaluated by integral absolute error and integral time absolute error. Step response to each case shows the improved performance of FOFPID controller over typical PID controller and FOPID controller.

Journal ArticleDOI
TL;DR: In this paper, a two degree of freedom (DOF) system quarter car model with introducing non-linearity on stiffness and damping of a vehicle suspension have been developed to compare suspension performance parameters such as ride comfort (RC) and Settling Time.

Journal ArticleDOI
TL;DR: It is shown that the control in the cited paper cannot track the reference voltage and a modified control law is proposed that enables reference voltage tracking while preserving the other advantages of the commented paper.
Abstract: The purpose of this paper is to comment on the reference voltage tracking ability of a recently proposed state observer based adaptive sliding mode control for boost converters. It is shown that the control in the cited paper cannot track the reference voltage. A modified control law that enables reference voltage tracking while preserving the other advantages of the commented paper is proposed and validated by simulation and experimentation on laboratory hardware.

Book ChapterDOI
01 Jan 2018
TL;DR: This paper aims to highlight the state-of-the-art approaches based on the deep convolutional neural networks especially designed for object detection from images using powerful and robust GPUs.
Abstract: Detecting the objects from images and videos has always been the point of active research area for the applications of computer vision and artificial intelligence namely robotics, self-driving cars, automated video surveillance, crowd management, home automation and manufacturing industries, activity recognition systems, medical imaging, and biometrics. The recent years witnessed the boom of deep learning technology for its effective performance on image classification and detection challenges in visual recognition competitions like PASCAL VOC, Microsoft COCO, and ImageNet. Deep convolutional neural networks have provided promising results for object detection by alleviating the need for human expertise for manually handcrafting the features for extraction. It allows the model to learn automatically by letting the neural network to be trained on large-scale image data using powerful and robust GPUs in a parallel way, thus, reducing training time. This paper aims to highlight the state-of-the-art approaches based on the deep convolutional neural networks especially designed for object detection from images.