Abstract: Road traffic accident prediction models play a critical role to the improvement of traffic safety planning. The focus of this study is to extract key factors from the collected data sets which are responsible for majority of accidents. In this paper urban traffic accident analysis has been done using support vector machines (SVM) with Gaussian kernel. Multilayer perceptron (MLP) and SVM models were trained, tested, and compared using collected data. The results of the study reveal that proposed model has significantly higher predication accuracy as compared with traditional MLP approach. There is a good relationship between the simulated and the experimental values. Simulations were carried out using LIBSVM (library for support vector machines) integrated with octave.

Abstract: The harmony search (HS) is a music-inspired algorithm that appeared in the year 2001. Since its introduction HS has undergone a lot of changes and has been applied to diverse disciplines. The aim of this paper is to inform readers about the HS applications in data mining. The review is expected to provide an outlook on the use of HS in data mining, especially for those researchers who are keen to explore the algorithm’s capabilities in data mining.

Abstract: Fuzzy time series (FTS) forecasting models are widely applicable when the information is imprecise and vague. The concept of fuzzy set (FS) is generalized to intuitionistic fuzzy set (IFS) and proved that it is more suitable and powerful tool to deal with real life problems under uncertainty as compared to FSs theory. In this study, first we extended the definitions of FTS to the IFSs and proposed the notion of intuitionistic FTS. Further, the presented concept of intuitionistic FTS is applied to develop a forecasting model under uncertainty. Then, it is applied to the benchmark problem of the historical enrollments data of University of Alabama and the obtained results are compared with the results obtained by existing methods to show its effectiveness as compared to FTS.

Abstract: In the prevailing epoch, the application of mobile ad hoc networks (MANET) has risen quickly. All the nodes of the network communicate directly with each other to carve up information within the assortment. The network is vigorous and infrastructureless. So the topology of this network is able to amend very commonly. MANET nodes are power-driven through narrow capacity battery and due to this sometimes nodes cannot successfully broadcast data packets from source node to destination node. In this chapter, we propose a new energy efficient routing protocol for MANET using vague set. The main aim of this proposed protocol is to choose an energy efficient route that diminishes energy expenditure of MANET based on the scheme of vague set. The proposed scheme is primarily used for interval-based membership where each parameter of energy efficient routing (i.e. energy and distance) is characterized by true and false membership functions. Therefore, this approach helps to determine the energy efficient route. The simulation of proposed protocol by NS2 and relative study with available protocol AODV is scrutinized wherein proposed routing protocol improves the performance of MANET based on throughput, average end-to-end delay, packet delivery ratio and packet loss.

Abstract: The advent of social networking has given rise to the huge data processing in terms of image and video streams. This, in turn, increased the use of cloud computing services by the users. Secure data storage and access are the main challenges in front of the cloud scenario. This paper reports a novel method of multimedia data security in the cloud paradigm. The proposed method watermarks and compresses the data before its storage in the cloud. This approach not only safeguards the data storage but also reduces the storage requirement and allied monitory overheads. The simulation result shows a 7 and 36 % use of CPU and memory capacity, which overrules the additional hardware requirement for the proposed module in the cloud paradigm.

Abstract: Increased security concern has brought up an acute need for being thoughtful in the area of surveillance. The normal trend of surveillance followed is a grid of CCTV cameras with control centralized at a room, which is manually looked upon by a caretaker. Many a times there is no regular watch carried by caretaker, instead logs of video footage are maintained, which are used in the case of any mishaps occurring. This is the practice followed even at major sensitive places. This is a retroactive kind of situation handling. A solution to this could be a system that continuously has a watch using a camera and indentifies a human object and then tracks its movement to identify any uncommon behavior. The sudden responsive action (reaction) made by the caretaker is the expected design objective of the system. In this paper we have proposed a system that analyzes the real-time video stream from camera, identifying a human object anfd then tracking its movement if it tries to go out of the field of view (FoV) of the camera. That is, the camera changes its FoV with the movement of the object.

Abstract: Artificial bee colony (ABC) algorithm has been proven to be an effective swarm intelligence-based algorithm to solve various numerical optimization problems. To improve the exploration and exploitation capabilities of ABC algorithm a new phase, namely disruption phase is introduced in the basic ABC. In disruption phase, disrupted operator in which the solutions are attracted or disrupted from the best solution based on the their respective distance from the best solution, is applied to all the solutions except the best solution. Further, the proposed strategy has been evaluated on 15 different benchmark functions and compared with basic ABC and two of its variants, namely modified ABC (MABC) and best so for ABC (BSFABC).

Abstract: Classification is a widely used technique for image processing and is used to extract thematic data for preparing maps in remote sensing applications. A number of factors affect the classification process. But classification is only half part of image processing and incomplete without accuracy assessment. Accuracy assessment of classification tells how accurately the classification process has been carried out. This research paper presents a review study of image classification through soft classifiers and also presents accuracy assessment of soft classifiers using entropy. Soft classifiers help in the development of more robust methods for remote sensing applications as compared to the hard classifiers. In this paper, two supervised soft classifiers, FCM, and PCM have been used to demonstrate the improvement in the classification accuracy by membership vector, RMSE, and also it has tried to generate fraction output from FCM, PCM, and noise with entropy.

Abstract: This paper presents an adaptive evolution control based on the feasibility of solutions, which is used with the nearest-neighbor regression surrogate model, to approximate the objective function value and the sum of constraint violation when solving constrained numerical optimization problems. The search algorithm used is the “differential evolution with combined variants’’ (DECV) and the constraint-handling technique adopted is the set of feasibility rules. The approach is compared against one state-of-the-art algorithm that employs the same surrogate model with an adaptive evolution control, as well. Twenty-four well-known test problems are solved in the experiments. From the obtained results, it is found that the evolution control based on the feasibility of solutions reduces the number of evaluations in the expensive model, particularly in problems with inequality constraints.

Abstract: Kaveh and Mahdavi proposed a new metaheuristic method in 2014 known as colliding bodies optimization (CBO). The algorithm is based on the principle of collision between bodies (each has a specific mass and velocity). The collision makes the bodies move toward the optimum position in the search space. This paper deals with the multi-objective formulation of CBO termed as MOCBO. Simulation studies on benchmark functions Schaffer N1, Schaffer N2, and Kursawe have demonstrated the superior performance of the MOCBO over multi-objective particle swarm optimization (MOPSO) and non-dominated sorting genetic algorithm II (NSGA-II). The performance analysis are carried out for the proposed and benchmark algorithms in identical platforms using response matching between obtained and true Pareto front; the convergence matric, diversity matric, and computational efficiency achieved over fifty independent runs.

Abstract: This paper presents for the composition of software value a distributed data flow model as it is widely distributed over the internet. These services are ruled by user and they are connected to make a data processing system which is known as the megaservice. This distributed data flow model provides us the exchange of data directly among these services. This is completely different from central data flow model where the central hub for data traffic is the megaservice. This shows that this model that is distributed data flow model is better as compared to central data flow model in the sense of their performance and scalability. In distributed data flow model it fully use the network holding capacity for the free services and it also stops the blockage at the megaservices. The main aim of this paper is to develop web services and then apply the security over them.

Abstract: In order to reduce the energy consumption of the concentrating the black liquor in Kraft recovery process in paper mill, a mathematical models is developed and proposed for the analysis of multi stage evaporator (heptad’s effect evaporator system). These multistage evaporator is modeled based on the flow of black liquor and steam operation option. In the present study, live steam split, liquor feed split, pre-heaters and hybrid of these energy saving scheme are coupled with backward, forward and mixed feed multi stage evaporator system. The systematic material balance and heat balance equations are described as the form of matrix equation to realize the generality of the mathematical models. The advantage of these models are its simplicity, representation of equations in matrix form and linearity. The proposed mathematical models can be easily solved by numerical methods combining with the iteration method, which has one more advantages of less sensitive to its initial values, high convergence speed and stability. The developed models can also be easily simulate under different operating strategies once knowing the liquor, steam and effects parameters.

Abstract: This paper deals the problem of single deteriorating item, with stock-dependent and seasonal pattern demand rate. It is considered that a constant part of on-hand inventory deteriorates per unit of time. The model is solved for finite time horizon. The aim of this present paper is to give a new height to the inventory literature on stock-dependent and seasonal demand pattern. This paper can be applied in many realistic situations. Shortages are allowed and three different conditions of backlogging are discussed in this model. The purpose of this study is to optimize the overall cost of the system and to find out the optimal ordering quantity. To explain the model and its significant features a numerical illustration and sensitivity analysis with respect to different related parameters is also cited.

Abstract: The present study proposed a robust and secure watermarking scheme to authenticate the digital images for ownership claim. The proposed watermarking scheme is making use of 2-level of DWT (Discrete wavelet transform) to provide high capacity of watermark embedding. The SVD (singular value decomposition) is performed on the host and watermark images. Then, principal components are calculated for watermark image. The use of principal components for watermark embedding makes the scheme free from false positive error. PSO (particle swarm optimization) optimized multiple scaling factors along with principal components are utilized for watermark embedding in the singular values of host image. The PSO-optimized scaling factor provides a very good tradeoff between imperceptibility and robustness of watermarking scheme. The scheme is also extended to use for color images. The proposed scheme provides a secured and high data embedding with good robustness toward different signal processing attacks.

Abstract: With the advancement in technology, gait analysis plays a vital role in sports, science, rehabilitation, geriatric care, and medical diagnostics. Identification of accurate gait phase is of paramount importance. The objective of this paper is to put forward a novel approach via passive marker-based optical approach that automatically recognizes gait subphases using fuzzy logic approach from hip and knee angle parameters extracted at RAMAN lab at MNIT, Jaipur. In addition to stance phase and swing phase, the approach is capable of detecting all the subphases such as initial swing, mid swing, and terminal swing, loading response, mid stance, terminal stance and preswing. The prototype of the system provides an effective and accurate gait phase that could be used for understanding patients’ gait pathology and in control strategies for active lower extremity prosthetics and orthotics. It is an automated, easy to use, and very cost-efficient yet reliable model.

Abstract: Differential evolution (DE) is one of the most influential optimization algorithms up-to-date. DE works through analogous computational steps as used by a standard evolutionary algorithm. Nevertheless, not like traditional Evolutionary Algorithms, the DE-variants agitate the current generation populace members with the scaled differences of indiscriminately preferred and dissimilar population members. Consequently, no discrete probability dissemination has to be utilized for producing the offspring. Ever since its commencement in 1995, DE has dragged the interest of numerous researchers around the globe ensuing in a lot of alternative of the fundamental algorithm with enhanced working. This paper introduces a comprehensive review of the basic conception of a DE and an inspection of its key alternatives and the academic studies carried out on DE up to now.

Abstract: Image Segmentation exists as a challenge that aims to extract the information from the image, making it simpler to analyze. There are some major issues associated with the conventional segmentation approaches. To come up with an improvised solution, image segmentation can be modeled as a nonlinear optimization problem which is also very difficult to be solved as global optimization. So to deal with this problem, we present metaheuristic algorithm namely Genetic Algorithm and its combination with OTSU giving the better results. These results have been analyzed with the help of parameters namely Threshold values, CPU Time and Region Non Uniformity.

Abstract: The scientific and industrial community increased their attention on wireless sensor networks (WSNs) during the past few years. WSNs are used in various critical applications like disaster relief management, combat field reconnaissance, border protection, and security observation. In such applications a huge number of sensors are remotely deployed and have cooperatively worked in unaccompanied environments. The disjoint groups are formed from these sensor nodes and such nonoverlapping groups are known as clusters. Clustering schemes have proven to be effective to support scalability. In this paper, authors have reported a detailed analysis on clustering algorithms and have outlined the clustering schemes in WSNs. We also make a comparative analysis of clustering algorithms on the basis of different parameters like cluster stability, cluster overlapping, convergence time, failure recovery, and support for node mobility. Moreover, we highlight the various issues in clustering of WSNs.

Abstract: This paper presents a novel scheme for the compression of encrypted images through which we can efficiently compress the encrypted images without compromising either the compression efficiency or the security of the encrypted images. In the encryption phase, content owner encrypts the original image using pseudorandom numbers which are derived from a secret key. Then, the channel provider without the knowledge of secret key can compress the encrypted image. For compression, encrypted image is decomposed into subimages and each of these subimages is compressed independently using quantization and wavelet difference reduction coding technique. Then the compressed data obtained from all the subimages is regarded as the compressed bit stream. At receiver side, a reliable decompression and decryption technique is used to reconstruct the image from compressed bit stream. To evaluate the performance, the proposed technique has passed through a number of test cases such as compression ratio (CR) and peak signal-to-noise ratio (PSNR). All the analysis and experimental results clearly show that the proposed encryption-then-compression technique is reckon secure and shows good compression performance. To show the efficiency of proposed work it is compared with a well-known scheme on compression of encrypted images and experimental results show better compression performance with improved image quality.

Abstract: The process of medical diagnosis, like many other fields, has to pass through various stages of uncertainty, especially in cases where the data is mostly available in linguistic format. Under such circumstances of vague data, application of fuzzy logic concepts can play an important role in extracting approximate information which in turn may help in reaching to a particular diagnosis. This study is devoted to the application of fuzzy logic in the psychological domain. The paper provides a detailed literature review on the use of fuzzy logic rules in analyzing the different aspects of psychological behavior of human beings. Further, it also provides some suggestions to make the system more effective.

Abstract: This article offers an enriched biogeography-based optimization (EBBO) technique to crack the economic power dispatch (EPD) problem of coal-fired generating units. The considered EPD involves the complex limitations including valve point loading effects, transmission line losses, and ramp rate limits. The geographical smattering of biological species is the vital scope of this algorithm. The proposed EBBO describes the arousal, enhanced migration of species from one environment to another. The algorithm has two main steps specifically, migration and mutation. These steps are involved in searching the global optimum solution. The EBBO’s efficiency has been verified on 13 and 40 generating test systems. The proposed technique produces superior results when compared with the conventional biogeography-based optimization (BBO) and other prevailing techniques. Also, it gives the quality and promising results for solving the EPD problems. Further, it can be applied for practical power system.

Abstract: This paper compares the results of the optimization techniques for feature selection of face recognition system in which face as a biometric template gives a large domain of features for optimizing feature selection. We attempt to minimize the number of features necessary for recognition while increasing the recognition accuracy. It presents the application of differential evolution and genetic algorithm for feature subset selection. We are using local directional pattern (LDP), an extended approach of local binary patterns (LBP), to extract features. Then, the results of DE and GA are compared with the help of an extension of support vector machine (SVM) which works for multiple classes. It is used for classification. The work is performed on 10 images of ORL database resulting in better performance of differential evolution.

Abstract: Composite sketching belongs to the forensic science where the sketches are drawn using freely available composite sketch generator tools. Compared to pencil sketches, composite sketches are more effective because it consumes less time. It can be easily adopted by people across different regions; moreover, it does not require any skilled artist for drawing the suspects faces. Software tool used to generate the faces provides more features which can be used by the eyewitness to provide better description, which increases the clarity of the sketches. Even the minute details of the eyewitness description can be captured with great accuracy, which is mostly impossible in pencil sketches. Now that a composite sketch is provided, it has to be identified effectively. In this paper we have analyzed two state-of-the-art techniques for composite sketch image recognition: Self-similarity descriptor (SSD)-based composite sketch recognition and local descriptors (LD)-based composite sketch recognition. SSD is mainly used for developing a SSD dictionary-based feature extraction and Gentle Boost KO classifier-based composite sketch to digital face image matching algorithm. LD is mainly used for multiscale patch-based feature extraction and boosting approach for matching composites with digital images. These two techniques are validated on FACES and IdentiKit databases. From our analysis we have found that SSD descriptor works better than LD. Using SSD method we obtained the results for FACES (ca) as 51.9 which is greater when compared to LD which gives a result of 45.8. Similarly, using SSD, values of 42.6 and 45.3 for FACES (As) and IdentiKit (As), respectively, are obtained which are much better than the values of 20.2 and 33.7 for FACES (As) and IdentiKit (As), respectively, using LD method.

Abstract: Asynchronous differential evolution (ADE) is recently introduced variant of differential evolution (DE). In ADE the mutation, crossover, and selection operations are performed asynchronously whereas in DE these operations are performed synchronously. This asynchronous process helps in good exploration and well suited for parallel optimization. In this study the strength of ADE is enhanced by incorporating convex mutation. Convex mutation efficiently utilizes the information of the parents which assists in faster convergence. The proposal is named ADE–CM. The potential of the proposal is evaluated and compared with state-of-the-art algorithms over a selected noisy benchmark functions consulted from the literature.

Abstract: This paper is to improvising and optimizing the scenario of Big data processing in cloud computing. A homogeneous cluster setup supports static nature of processing which is a huge disadvantage for optimizing the response time towards clients. In order to avail utmost client satisfaction, the host server needs to be upgraded with the latest technology to fulfil all requirements. Big data processing is a common frequent event in today’s Internet and the proposed framework improvises the response time. This will also make sure that the user gets its entire requirement fulfilled in optimal time. In order to avail utmost client satisfaction, the server needs to eliminate homogeneous cluster setup that is encountered usually in parallel data processing. The homogeneous cluster setup is static in nature and dynamic allocation of resources is not possible in this kind of environment. This will improve the overall resource utilization and, consequently, reduce the processing cost.

Abstract: The Hulk Gripper has been constructed by replacing the fingers of a robotic hand with a mass filled with granular material, e.g., grounded coffee. This mass applies pressure on the article due to which the gripper adapts to the surface and engrosses it. Using the vacuum pump attached at the other end, air is pumped out making the granules contracted and hardened. It has been discovered that the volume change of approximately 0.5 is quite adequate to grab the object infallibly and lift them with a very large force. The ability of the granules to jam against each other in vacuum and unjam with air around is called as the principle of operation. The grip of the hand is based on three different mechanisms: friction, suction, and interlocking, which contributes to the engrossing force. With the help of all the mechanisms involved, it becomes possible in lifting heavy objects, exposing new prospects of design, with the ability to stand out quick engrossing of complicated objects. Our gripper is controlled mechanically with the help of radio frequencies. We are controlling the gripper with an android application. The mobile application will give commands to the microcontroller via Wi-Fi or Bluetooth, which in turn controls the movement of the gripper. The microcontroller being used turns the vacuum pump on and off. The existing gripper requires number of small and large joints which are to be controlled individually, in order to lift objects of different sizes, shapes, and delicacies whereas, our gripper uses a single point of contact to form the grip and do its task.

Abstract: Side-channel attack is a new area of research which exploits the leakages such as power consumption, execution time, EM radiation, etc., of crypto algorithms running on electronic circuitry to extract the secret key. This paper describes the VHDL implementations of Advanced Encryption Standard (AES) algorithm on Field Programmable Gate Array board (Spartan 3E) employing Xilinx tool and discusses briefly about Correlation Power/EM Analysis attacks. These attacks have been mounted on part of power and EM traces corresponding to tenth round of AES algorithm. Power and EM traces are being acquired using current probe and EM probe station respectively with the help of oscilloscope and PC. Effects of different ways of implementations on these attacks have been explored. Studies have been carried out to find the effect of operating frequencies and number of samples per clock on the computational complexities in terms of number of traces required to extract the key.

Abstract: Automobile industries worldwide are unified in opinion, that successful management of sustainable supply chains is the most important driver to improve both their economic and ecological performances. The significance of sustainable supply chain management (SSCM) is a critical corporate matter in the automobile industries that offers incredible potential for achieving better environmental performance, consumer fulfillment, pull down operating expenditures, reducing inventory investments in addition to achieving better fixed asset usage. The environment concerns, climatic changes, and additional ecological concerns in automobile industries are not only articulated by campaigners or researchers, but also by the common man as well, which has motivated the industries to focus on sustainability. The present research focuses on a DEA-based mathematical model and employs differential evolution to select the competent suppliers providing the utmost fulfillment for the sustainable criteria determined. This study aims to examine the sustainable supplier evaluation and selection practices likely to be adopted by the Indian automobile industry for their products.

Abstract: In today’s growing world of digital technology, access to the multimedia content is very easy and for some sensitive applications such as medical imaging, military system, legal problems, it is very essential to not only reinstate the original media without any loss of information but also to increase content’s security. Reversible data hiding is an approach to extract the information embedded covertly as well as the host image. In this paper, we have proposed a novel hybrid reversible watermarking scheme based on DWT and SVD. In this scheme, we have provided double layer of security by utilizing the multiresolution property of wavelet and strong features of SVD. In the proposed scheme, watermark is embedded into the singular values of all high-frequency subbands obtained by wavelet decomposition of the original image and at the time of extraction, watermark bits are used along with singular vectors to obtain the original image. Our scheme provides high security even after the extraction of watermark, without knowing the extraction algorithm, original image cannot be recovered in its entirety. The proposed scheme is tested on various test images and the obtained results after applying different performance metrics such as PSNR and UIQI show the effectiveness of the proposed scheme.