The use of deep learning, specifically time series neural networks, in predicting stock market trends has emerged as a significant use case in financial analysis. However, the complex interrelationships and instability of the stock market have made the timely and accurate prediction of its behaviour as a confronting endeavour. To address this difficulty, in this research work a stock market index prediction model called SenT-In, which combines the with a sentiment awareness model. A sentiment awareness model using Convolutional Neural Networks (CNN) and Gated Recurrent Unit (GRU) is proposed to calculate the sentiment index of a large volume of news articles collected from reputable financial websites. In addition, a sentiment attention method is developed to combine stock data and news sentiment index as the input for training and predicting using the SenT-In network, which is both simple and efficient. The proposed model is evaluated in four different stock market datasets which include FSTE, SSE, Nifty 50 and S&P 500. On comparing the results with conventional deep learning algorithms such as GRU, LSTM, CNN and SVM, proposed SenT-In outperforms existing methods in accuracy with 9%, F1-Score with 7%, AUC-ROC curve with 13% and PR-AUC curve with 9% efficiency (on average).

The standard approach for Partially Observable Markov Decision Processes (POMDPs) is to convert them to a fully observed belief-state MDP. However, the belief state depends on the system model and is therefore not viable in reinforcement learning (RL) settings. A widely used alternative is to use an agent state, which is a model-free, recursively updateable function of the observation history. Examples include frame stacking and recurrent neural networks. Since the agent state is model-free, it is used to adapt standard RL algorithms to POMDPs. However, standard RL algorithms like Q-learning learn a stationary policy. Our main thesis that we illustrate via examples is that because the agent state does not satisfy the Markov property, non-stationary agent-state based policies can outperform stationary ones. To leverage this feature, we propose PASQL (periodic agent-state based Q-learning), which is a variant of agent-state-based Q-learning that learns periodic policies. By combining ideas from periodic Markov chains and stochastic approximation, we rigorously establish that PASQL converges to a cyclic limit and characterize the approximation error of the converged periodic policy. Finally, we present a numerical experiment to highlight the salient features of PASQL and demonstrate the benefit of learning periodic policies over stationary policies.

Abstract In the western world,the prostate cancer is major cause of death in males. Magnetic Resonance Imaging (MRI) is widely used for the detection of prostate cancer due to which it is an open area of research. The proposed method uses deep learning framework for the detection of prostate cancer using the concept of Gleason grading of the historical images. A3D convolutional neural network has been used to observe the affected region and predicting the affected region with the help of Epithelial and the Gleason grading network. The proposed model has performed the state-of-art while detecting epithelial and the Gleason score simultaneously. The performance has been measured by considering all the slices of MRI, volumes of MRI with the test fold, and segmenting prostate cancer with help of Endorectal Coil for collecting the images of MRI of the prostate 3D CNN network. Experimentally, it was observed that the proposed deep learning approach has achieved overall specificity of 85% with an accuracy of 87% and sensitivity 89% over the patient-level for the different targeted MRI images of the challenge of the SPIE-AAPM-NCI Prostate dataset.

Recently the field of sentiment analysis has gained a lot of attraction in literature. The idea that a machine can dynamically spot the text’s sentiments is fascinating. In this paper, we propose a method to classify the textual sentiments in Twitter feeds. In particular, we focus on analyzing the tweets of products as either positive or negative. The proposed technique utilizes a deep learning schema to learn and predict the sentiment by extracting features directly from the text. Specifically, we use Convolutional Neural Networks with different convolutional layers. Further, we experiment with LSTMs and try an ensemble of multiple models to get the best results. We employ an n-gram-based word embeddings approach to get the machine-level word representations. Testing of the method is conducted on real-world datasets. We have discovered that the ensemble technique yields the best results after conducting experiments on a huge corpus of more than one million tweets. To be specific, we get an accuracy of 84.95%. The proposed method is also compared with several existing methods. An extensive numerical investigation has revealed the superiority of the proposed work in actual deployment scenarios.

We propose a theoretical framework for approximate planning and learning in partially observed systems. Our framework is based on the fundamental notion of information state. We provide two definitions of information state---i) a function of history which is sufficient to compute the expected reward and predict its next value; ii) a function of the history which can be recursively updated and is sufficient to compute the expected reward and predict the next observation. An information state always leads to a dynamic programming decomposition. Our key result is to show that if a function of the history (called AIS) approximately satisfies the properties of the information state, then there is a corresponding approximate dynamic program. We show that the policy computed using this is approximately optimal with bounded loss of optimality. We show that several approximations in state, observation and action spaces in literature can be viewed as instances of AIS. In some of these cases, we obtain tighter bounds. A salient feature of AIS is that it can be learnt from data. We present AIS based multi-time scale policy gradient algorithms and detailed numerical experiments with low, moderate and high dimensional environments.

Abstract — In current network routing domains, routing information exchange usually lacks protection based on confidentiality. This makes network routing vulnerable to a variety of security attacks. In this paper, we present a framework to provide confidentiality for a link state routing protocol. This framework involves creation of a trust structure among routers as well as key management. Routing information is encrypted so that it can be accessed only by authorized routers. We present an implementation framework for our approach by extending Open Shortest Path First (OSPF), a commonly deployed link-state routing protocol. Based on our performance assessment, we have found that the additional cost in implementing our scheme has fairly moderate impact on the overall performance. I.

This paper describes the security threats associated with 802.11 based wireless local area networks (WLANs) and outlines a comprehensive architecture for a wireless intrusion protection system (WIPS). The AirDefense WIPS based on this architecture is currently used to monitor and protect tens of thousands of networks and over one million devices around the globe in almost 500 enterprises, healthcare organizations and government agencies. The paper also describes the essential attributes that define the figure of merit (FOM) of a WIPS. The FOM can be used to quantify and compare the performance and functionality of a WIPS and distinguish enterprise class solutions from simple checkbox systems.

The double authentication (DA) scheme presented in D. Huang et al., (2003) is designed to provide security against impersonation attack to link state routing protocol at a lower computational cost as compared to the existing schemes, such as, digital signature scheme S. Murphy et al. (1997). In this paper, we present a key distribution scheme that can be used for generating and distributing keys to provide DA. This scheme leads to a storage complexity for each router that varies linearly with the number of routers in the network in the worst case (fully connected network with n nodes). Moreover, for router with four or less average number of links, the storage complexity falls below log/sub 2/n. This scheme also increases the security robustness of DA as the subverted routers can collude only if they are neighbors.

In this paper, we present an authentication scheme to prevent impersonation attack in link state routing protocol. The existing authentication schemes are either simple to compute but vulnerable to attacks of too robust against attacks but has exponential computation cost. We introduce a double authentication (DA) scheme which provides authentication to the routing information data carried by link state routing packets. In this scheme every router needs to sign the routing data twice with two different keys using a group keying scheme, which is based on one-way hash function. Based on our performance assessment, we found that this scheme is simpler to implement, computationally efficient and provides the degree of robustness desired with less communication overhead but has higher memory requirement.

Energy conscious software design can significantly improve the energy efficiency of a portable system. A software energy estimation technique using instruction class profiling is presented. The technique is shown to have an estimation error of less than 3% with trivial runtime overhead, based on a set of application programs evaluated on the StrongARM SA-1100 and Hitachi SH-4 microprocessors. A technique to isolate the switching and leakage energy components of software is outlined. The energy overhead of a real-time operating system is also profiled. The overall impact of system-level software energy management is quantified using the MIT /spl mu/AMPS system as an application example.

We introduce the notion of energy-scalable system-design. The principal idea is to maximize computational quality for a given energy constraint at all levels of the system hierarchy. The desirable energy-quality (E-Q) characteristics of systems are discussed. E-Q behavior of algorithms is considered and transforms that significantly improve scalability are analyzed using three distinct categories of commonly used signal-processing algorithms on the StrongARM SA-1100 processor as examples (viz., filtering, frequency domain transforms and classification). Scalability hooks in hardware are analyzed using similar examples on the Pentium III processor and a scalable programming methodology is proposed. Design techniques for true energy scalable hardware are also demonstrated using filtering as an example.

A software energy estimation methodology is presented that avoids explicit characterization of instruction energy consumption and pre-dicts energy consumption to within 3% accuracy for a set of bench-mark programs evaluated on the StrongARM SA-1100 and Hitachi SH-4 microprocessors. The tool, JouleTrack, is available as an online resource and has various estimation levels. It also isolates the switch-ing and leakage components of the energy consumption.

Real-time scheduling on processors that support dynamic voltage and frequency scaling is analyzed. The Slacked Earliest Deadline First (SEDF) algorithm is proposed and it is shown that the algorithm is optimal in minimizing processor energy consumption and maximum lateness. An upper bound on the processor energy savings is also derived. Real-time scheduling of periodic tasks is also analyzed and optimal voltage and frequency allocation for a given task set is determined that guarantees schedulability and minimizes energy consumption.

The potential for collaborative, robust networks of microsensors has attracted a great deal of research attention. For the most part, this is due to the compelling applications that will be enabled once wireless microsensor networks are in place; location-sensing, environmental sensing, medical monitoring and similar applications are all gaining interest. However, wireless microsensor networks pose numerous design challenges. For applications requiring longterm, robust sensing, such as military reconnaissance, one important challenge is to design sensor networks that have long system lifetimes. This challenge is especially difficult due to the energyconstrained nature of the devices. In order to design networks that have extremely long lifetimes, we propose a physical layer driven approach to designing protocols and algorithms. We first present a hardware model for our wireless sensor node and then introduce the design of physical layer aware protocols, algorithms, and applications that minimize energy consumption of the system. Our approach prescribes methods that can be used at all levels of the hierarchy to take advantage of the underlying hardware. We also show how to reduce energy consumption of non-ideal hardware through physical layer aware algorithms and protocols. 1

Wireless microsensor networks lend themselves to trade-offs in energy and quality. In these networks, the individual sensor data per se are not necessarily important to the end user. Rather, it is the combined knowledge of all the sensors that describes what is occurring in the environment. By allowing the algorithms and protocols to adapt the quality of this description, with a corresponding change in energy dissipation, sensor networks can be flexible to the end-user's requirements. In this paper, we provide models for predicting quality and energy and show the advantages of trading off these two parameters. By ensuring that the system operates at a minimum energy for each quality point, the system can achieve both flexibility and energy efficiency, allowing the end-user to maximize system lifetime.

We introduce the notion of energy scalable computation on general purpose processors. The principle idea is to maximize computational qualityfor a given energy constraint. Teh desirable energy-quality behavior of algorithms is discussed. subsequently the energy-quality scalability of three distinct categories of commonly used signal processing algorithms (viz. filtering, frequency domain transforms and classification) are analyzed on the StrongARM SA-1100 processor and transformations are described which obtain significant improvements in the energy-quality scalability of the algorithm.

We present a technique for low power realization of Finite Impulse Response (FIR) filters implemented using Distributed Arithmetic. In most applications, the distribution profile of input data values is known. The proposed technique uses a data encoding which can be tuned to the specific distribution profile so as to reduce toggles in the shift register chain. We present a generic Nega-Binary coding approach and show how a specific Nega-Binary scheme can be derived to achieve maximum power reduction. We also show how the binary to Nega-binary conversion can be performed bit-serially with minimal area (and hence power dissipation) overhead. The paper finally presents a shift-free implementation which uses memory array to store data values. We present a technique based on Gray coded addressing to reduce the power dissipation in such implementations.