Search

Unlike edaphic factors, it is difficult to control climatic conditions and their changes that affect plant growth and development. To deal with such posture, farmers have to cultivate their crops at the right time. From this point, over two–year of 2014 and 2015, a field experiment was performed at El-Nubaria region, El-Behaira Governorate, Egypt, to assess the response of sunflower to different combinations between sowing dates (early, mid and delayed) and ascorbic acid treatments (with ascorbic acid and without ascorbic acid). Ascorbic acid was sprayed at 30, 40 and 50 days after sowing. The results showed that sowing sunflower in mid sowing (May 21) achieved the highest values of cumulative heat units utilization efficiency as well as all growth and yield traits, while the lowest values were recorded under the delayed sowing date (June 21). Application of ascorbic acid was effective for promoting growth and yield traits under all studied sowing dates. Ascorbic acid achieved 11.6, 10.1, 10.7 and 12.9% increases under early sowing, and 9.5, 6.6, 8.6 and 10.3% increases under delayed sowing in head diameter, seed weight plant−1, seed yield and oil yield, respectively. Comparing to mid sowing × without ascorbic acid, application of ascorbic acid alleviated seed yield losses associated early sowing from 15.7–6.6% and from 23.0–16.4% with delayed one. In conclusion, for remediating the thermal stressful impacts of early or late sowing of sunflower, farmers are advised to treat crop plants with ascorbic acid to avoid yield losses.

Maximizing the utilization of water unit is of paramount importance in arid zones and worldwide. This is even more significant when plants are subjected to both thermal and water stress. Hence, a two-year (2014 and 2015 seasons) field trial was carried out to study the effect of three sowing dates (April 21, May 21, and June 21); two irrigation levels (I100 and I85) and two ascorbic acid rates, ASA (0 and 450 mg L−1), on physiological and biochemical traits, productivity and water use efficiency (WUE) of sunflower. Results showed that subjecting sunflower plants to water deficit under any sowing date caused decreases in chlorophyll, carotenoids, oil% and seed yield and an increase in proline content. As averages of the two seasons, ASA treated plants caused increases in seed yield amounted to 11.7%, 10.6% and 8.4% with I100 and 5.1%, 14.4% and 7.7% with I85 compared to non-treated plants sown in April, May and June, respectively. In ASA treated plots, WUE values of sowing in April x I100 or sowing in June x I85 in 2014 and sowing in May x I85 in 2015 were as similar as that of conventional practice (sowing in May x I100 × 0 mg L−1 ASA). Accordingly, results clarify that ASA can be used successfully in sunflower management programs, particularly under abiotic stresses e.g. unfavorable heat and drought.

Given the limited accessibility to Speech and Language Pathologists (SLPs) children in need often have, pediatric Computer-Aided Speech Therapy (CAST) tools can play an important role in the early diagnosis and treatment of speech disorders. However, various challenges impede the implementation of accurate automated analysis of speech disorders in children. In this article, we first discuss three key challenges in processing child disordered speech: 1) the unreliability of low-level annotation and scarcity of speech corpora, 2) speaker diarization of therapy sessions and 3) inaccurate children's acoustic models. We next explore opportunities to overcome some of these challenges. First, we investigate the effectiveness of high-level paralinguistic features in disordered speech detection to reduce the dependency on annotated data. A binary classifier trained using paralinguistic features extracted from both typically developing children and those suffering from Speech Sound Disorders (SSD) achieved 87% subject-level classification accuracy. Second, we tackle the speech disorder detection problem as an anomaly detection problem where models are trained merely on typically developing speech, reducing the need for disordered training data. A phoneme-level F 1 score of 0.77 was obtained from an anomaly detection-based system trained on speech attribute features to classify between typical and atypical phoneme pronunciations of children with speech disorder. Finally, we test the efficiency of an x-vector based speaker diarization technique in pediatric therapy sessions. The method successfully distinguished between therapist and child speech with a Diarization Error Rate (DER) of 10%.

Childhood apraxia of speech (CAS) commonly affects the production of lexical stress contrast in polysyllabic words. Automated classification tools have the potential to increase reliability and efficiency in measuring lexical stress. Here, factors affecting the accuracy of a custom-built deep neural network (DNN)-based classification tool are evaluated. Sixteen children with typical development (TD) and 26 with CAS produced 50 polysyllabic words. Words with strong–weak (SW, e.g., dinosaur) or WS (e.g., banana) stress were fed to the classification tool, and the accuracy measured (a) against expert judgment, (b) for speaker group, and (c) with/without prior knowledge of phonemic errors in the sample. The influence of segmental features and participant factors on tool accuracy was analysed. Linear mixed modelling showed significant interaction between group and stress type, surviving adjustment for age and CAS severity. For TD, agreement for SW and WS words was &gt, 80%, but CAS speech was higher for SW (&gt, 80%) than WS (~60%). Prior knowledge of segmental errors conferred no clear advantage. Automatic lexical stress classification shows promise for identifying errors in children’s speech at diagnosis or with treatment-related change, but accuracy for WS words in apraxic speech needs improvement. Further training of algorithms using larger sets of labelled data containing impaired speech and WS words may increase accuracy.

Here we present AusKidTalk [1], an audio-visual (AV) corpus of Australian children’s speech collected to facilitate the development of speech based technological solutions for children. It builds upon the technology and expertise developed through the collection of an earlier corpus of Australian adult speech, AusTalk [2,3]. This multi-site initiative was established to remedy the dire shortage of children’s speech corpora in Australia and around the world that are sufficiently sized to train accurate automated speech processing tools for children. We are collecting ~600 hours of speech from children aged 3–12 years that includes single word and sentence productions as well as narrative and emotional speech. In this paper, we discuss the key requirements for AusKidTalk and how we designed the recording setup and protocol to meet them. We also discuss key findings from our feasibility study of the recording protocol, recording tools, and user interface.

Vincristine (VCR), a naturally occurring vinca alkaloid, has received significant attention in recent years due to its vast therapeutic applications in the management of several types of cancer such as acute myeloid leukemia, acute lymphocytic leukemia, neuroblastoma, and small cell lung cancer. It is used as a unique component in several polychemotherapy combinations due to its unique clinical properties including lack of bone marrow suppression at the recommended dose. However, the narrow therapeutic index due to the dose-limiting irreversible neurotoxicity is hindering its immense potential. A conventional dosage form as an injectable solution has been successful to some extends, overcoming the challenges faced in developing an effective formulation. Recently, nanotechnology-based formulations are being looked on as a novel method for improving the pharmacokinetic properties, as well as enhancing the targetability of VCR. This review summarizes the therapeutic potential of VCR, explores its mechanisms of action, and discusses the success and challenges of VCR liposomes as well as nanoparticles in the past decade. This review also covers the potential techniques to improve the performance of VCR nanoformulations, thereby enhancing its clinical potential.

Computer aided pronunciation training tools require accurate automatic pronunciation error detection algorithms to identify errors made by their users. However, the performance of these algorithms is highly dependent on the amount of mispronounced speech data used to train them and the reliability of its manual annotation. To overcome this problem, we turned the mispronunciation detection into an anomaly detection problem, which utilize algorithms trained with only correctly pronounced speech data. In this work we adopted the One-Class SVM as our anomaly detection model, with a specific model built for each phoneme. Each model was fed with a set of speech attribute features, namely the manners and places of articulation, extracted from a bank of binary DNN speech attribute detectors. We also applied multi-task learning and dropout approaches to alleviate the overfitting problem in the DNN speech attribute detectors. We trained the system using the WSJ0 and TIMIT standard data sets which contain only native English speech data and then evaluated it using three different data sets, a native English speaker corpus with artificial errors, a foreign-accented speech corpus and a children's disordered speech corpus. Finally, we compared our system with the conventional Goodness-of-Pronunciation (GOP) algorithm to demonstrate the effectiveness of our method. The results show that our method reduced the false-acceptance and false-rejection rates by 26% and 39% respectively compared to the GOP method.

In clinical practice, heart arrhythmias are manually diagnosed by a doctor, which is a time-consuming process. Furthermore, this process is error-prone due to noise from the recording equipment and biological non-idealities of patients. Thus, an automated arrhythmia classifier would be time and cost-effective as well as offer better generalization across patients. In this paper, we propose an adversarial multitask learning method to improve the generalization of heartbeat arrythmia classification. We built an end-to-end deep neural network (DNN) system consisting of three sub-networks; a generator, a heartbeat-type discriminator, and a subject (or patient) discriminator. Each of these two discriminators had its own loss function to control its impact. The generator was "friendly" to the heartbeat-type discrimination task by minimizing its loss function and "hostile" to the subject discrimination task by maximizing its loss function. The network was trained using raw ECG signals to discriminate between five types of heartbeats - normal heartbeats, right bundle branch blocks (RBBB), premature ventricular contractions (PVC), paced beats (PB) and fusion of ventricular and normal beats (FVN). The method was tested with the MIT-BIH arrhythmia dataset and achieved a 17% reduction in classification error compared to a baseline using a fully-connected DNN classifier.Clinical Relevance—This work validates that it is possible to develop a subject-independent automated heart arrhythmia detection system to assist clinicians in the diagnosis process.

Background Obstructive sleep apnea (OSA) syndrome is strongly associated with obesity and inflammation. Adipose tissue is not simply an inactive storage depot for lipids but is also an active endocrine organ that plays a crucial role regarding endocrine, metabolic, and inflammatory signals of which leptin, ghrelin, adiponectin, and resistin play an important role in body homeostasis. So, we aimed to study leptin and ghrelin serum levels in OSA patients. Patients and methods The study included 15 healthy control participants and 30 patients diagnosed with OSA. All patients were subjected to history taking, clinical examination, routine laboratory investigations, and polysomnography. Manual analysis and scoring were performed using the criteria established by the American Academy of Sleep Medicine. Results Patient’s serum leptin ranged between 11.4 and 66.4 ng/ml with a mean±SD of 33.303±15.728 while in control participants it ranged between 0.5 and 34.7 ng/ml with a mean±SD of 10.467±10.339. Patient’s serum ghrelin ranged between 103.5 and 6673 pg/ml with a mean±SD of2034.527±1815.687 while in control participants it ranged between 976 and 2184 pg/ml with a mean±SD of 1682.467±334.064. Leptin levels were statistically significantly higher in obstructive sleep apnea syndrome (OSAH) patients versus control participants. Leptin levels statistically significantly correlated with some indices of obesity hypoventilation syndrome severity, that is, apnea–hypopnea index and desaturation index. Leptin levels statistically significantly correlated with a variety of anthropometric measurements, including BMI and neck circumference. Leptin levels statistically significantly correlated with serum triglyceride levels. Regression analysis showed that the best predicting variables for leptin levels were the lowest oxygen saturation, average SaO2, sleep time with oxygen saturation of less than 90% (t90%) and BMI. There was no statistically significant difference between the two studied groups regarding serum ghrelin levels and no statistically significant correlation was found between serum ghrelin and any parameter.

Ascorbic acid (AsA) is considered as one of the most important and profusely known occurring water soluble antioxidants in plants, however, it is not well known to what extent this antioxidant might contribute in alleviating the adverse effects of water deficit on plant growth, yield and irrigation water use efficiency (IWUE). In attempt to clarify whether exogenous application of AsA could alleviate the adverse effects of water deficit on sunflower plants, two seasons (2014 and 2015) of field experimentation were conducted using six combinations of two AsA levels (AsA(–) and AsA(+), i.e. zero and 450 ppm AsA, respectively) and three irrigation water amounts (I100, I85, and I70, i.e. 100, 85 and 70% of crop evapotranspiration, respectively). Under water shortage, leaf chlorophyll content increased but proline content lowered in AsA–treated plants compared to the untreated ones. Lower values of LAI, head weight, seed yield ha–1, and oil yield ha–1 were recorded with decreasing water supply, while the highest values were gained when supplying plants with sufficient water (I100) plus application of AsA (i.e. AsA(+)), i.e., I100AsA(+). Plants under the latter treatment grew well and possessed higher yields compared to that of suffering from deficit water without AsA application, i.e. I85AsA(–) or I70AsA(–). Head weight and seed as well as oil yields ha–1 produced in 2014 season under sufficient water supply without AsA application (I100AsA(–)) could be achieved under moderately water–stressed condition in conjunction with applying AsA (I85AsA(+)). Implication of AsA tends to minimize the reduction in seed yield due to insufficient water supply, where I85AsA(+) and I85AsA(–), each saved same percentage of water (15.0%) but the reduction in seed yield associated the former treatment was less than that under the latter one. On the other hand, IWUE reached the maximal values in both seasons under I100AsA(+) treatment but, however, without marked differences in comparing to those recorded I85AsA(+) in 2014 season. Moreover, the differences in IWUE values exhibited by I100AsA(–) and I85AsA(+) did not reach the P

Abiotic stresses represent a major impediment to crop productivity, especially in arid regions. Thus, over two years of 2014 and 2015, a field experiment was undertaken at El Nubaria region, Egypt to assess the productivity and water use efficiency (WUE) of sunflower as affected by planting dates (April 21, May 21, and June 21) and irrigation levels (ET100%, ET85% and ET70%,). Results clarified that leaf chlorophyll a content was higher by sowing in May than in either April or June sowings, while leaf carotenoides of plant sown in May or June surpassed those sown in April. The minimal value of proline was obtained with sowing in May. Sowing in May increased plant height by 52.2 and 22.3 as well as LAI by 19.3 and 73.1% than sowing in April and June, respectively. The reductions in seed yield, oil yield and WUE amounted to 10.5 and 12.8, 13.7 and 18.3 as well as 11.8 and 9.8 % with April and June sowings, respectively, compared to May sowing. ET100% showed superiority over than ET85% and ET70% in improving sunflower yields and its attributes, but WUE did not affect. Sunflower sown in May and irrigated with ET100% gave the maximum values of seed yield and its attributes and WUE surpassing other interaction treatments. In June, WUE value increased under severe water deficit i.e. ET70% comparing to moderately water–stressed (ET85%) or well–watered conditions (ET100%).

In submersed rice fields, weeds are considered the main source of nutrients removal. Hence, reduction in yield and grain quality is realized. Thus, a two–year field experiment was performed to find out the best cooperative effect between herbicides and micronutrients for controlling rice weeds with yield in mind. Two herbicides (halosulfuron–methyl and bentazone) and three micronutrients (Fe, Mn and Zn) were arranged in a strip plot design with three replicates. Results exhibited that in plots treated by halosulfuron–methyl, the control treatment (without fertilizing) showed the maximum reductions in weed N, P and K uptake, however, it statistically equaled Fe and Mn treatments in weed N uptake and Mn, Fe and Zn treatments in weed K uptake. With controlling weeds by halosulfuron–methyl herbicide, Zn treatment was as similar as Fe and Mn treatments for increasing plant height, straw yield and grain yield of rice. The interactions of halosulfuron–methyl x Zn treatment (for N and P in rice grain) and halosulfuron–methyl x Zn or Fe treatments (for P in rice grain) had synergistic effects. Moreover, the highest increases in Fe, Mn and Zn contents in rice grains were recorded with halosulfuron–methyl plus Fe, Mn and Zn treatments, respectively. In conclusion, rice producers should be aware of the synergism and co–operative effects between herbicides and micronutrients. The synergistic effect could be exploited for reducing the hazardous impacts of weeds, and hence, it raises yield potentiality and quality.

Effective sleep analysis is hampered by the lack of automated tools catering to disordered sleep patterns and cumbersome monitoring hardware. In this paper, we apply deep learning on a set of 57 EEG features extracted from a maximum of two EEG channels to accurately differentiate between patients with insomnia or controls with no sleep complaints. We investigated two different approaches to achieve this. The first approach used EEG data from the whole sleep recording irrespective of the sleep stage (stage-independent classification), while the second used only EEG data from insomnia-impacted specific sleep stages (stage-dependent classification). We trained and tested our system using both healthy and disordered sleep collected from 41 controls and 42 primary insomnia patients. When compared with manual assessments, an NREM + REM based classifier had an overall discrimination accuracy of 92% and 86% between two groups using both two and one EEG channels, respectively. These results demonstrate that deep learning can be used to assist in the diagnosis of sleep disorders such as insomnia.

Subjective screening of children with speech disorders is costly, time consuming and infeasible due to the limited availability of Speech and Language Pathologists (SLPs). Therefore, there is an increasing interest in automatic speech analysis of children with speech disorders as it can offer a practical alternative to human assessment. Paralinguistic features are a set of low-level descriptors commonly used in speech emotion recognition. However, they have not yet been examined with childhood speech sound disorders such as, apraxia-of-speech and phonological and articulation disorders. In this paper, we investigated the effectiveness of paralinguistic features in discriminating between typically developing children and those who suffer from different types of speech sound disorders. Two types of standard paralinguistic features were explored, the Geneva Minimalistic Acoustic Parameter Set (GeMAPS) and its extended version, (eGeMAPS) feature sets. We applied feature selection to find the most discriminant set of features and employed binary classification using a support vector machine (SVM) to discriminate between the two groups. The method was tested on a recently-released public speech corpus collected from typically developing children and children with various types of speech sound disorders. The system achieved segment-level and subject-level unweighted average recall (UAR) of around 78% and 87% respectively.

Advanced metering infrastructure (AMI) is the primary step to establish a modern smart grid. AMI enables a flexible two-way communication between smart meters and utility company for monitoring and billing purposes. However, AMI suffers from the deceptive behavior of malicious consumers who report false electricity usage in order to reduce their bills, which is known as electricity theft cyber-attacks. In this chapter, we present deep learning-based detectors that can efficiently thwart electricity theft cyber-attacks in smart grid AMI networks. First, we present a customer-specific detector based on a deep feed-forward and recurrent neural networks (RNN). Then, we develop generalized electricity theft detectors that are more robust against contamination attacks compared with customer-specific detectors. In all detectors, optimization of hyperparameters is investigated to improve the performance of the developed detectors. In particular, the hyperparameters of the detectors are optimized via sequential, random, and genetic optimization-based grid search approaches. Extensive test studies are carried out against real energy consumption data to investigate all detectors performance. Also, the performance of the developed deep learning-based detectors is compared with a shallow machine learning approach and a superior performance is observed for the deep learning-based detectors.

Chronic insomnia can significantly impair an individual's quality of life leading to a high societal cost. Unfortunately, limited automated tools exist that can assist clinicians in the timely detection of insomnia. In this paper, we propose a two stage approach to automatically detect insomnia from an overnight EEG recording. In the first stage we trained a sleep stage scoring model and an epoch-level insomnia detection model. Both models are deep neural network (DNN)- based which are fed by a set of temporal and spectral features derived from 2 EEG channels. In the second stage we computed two subject-level feature sets. One is computed using the output of the sleep stage scoring model and consists of the sleep stage ratios, the stage pair ratios and the stage transition ratios. The second feature set is derived from the output of the epoch-level insomnia detection model and represents the ratio of detected insomniac epochs in each stage and their average posterior probability. These features are then used to train a final binary classifier to classify each subject as control, i.e., with no sleep complaints, or insomniac. We compared 5 different binary classifiers, namely the linear discriminant analysis (LDA), the classification and regression trees (CART) and the support vector machine (SVM) with linear, Gaussian and sigmoid kernels. The system was evaluated against data collected from 115 participants, 61 control and 54 with insomnia, and achieved $F1$ score, sensitivity and specificity of 0.88, 84% and 91% respectively.

Modern smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing purposes. However, such an approach suffers from electricity theft cyberattacks. Different from the existing research that utilizes shallow, static, and customer-specific-based electricity theft detectors, this paper proposes a generalized deep recurrent neural network (RNN)-based electricity theft detector that can effectively thwart these cyberattacks. The proposed model exploits the time series nature of the customers' electricity consumption to implement a gated recurrent unit (GRU)-RNN, hence, improving the detection performance. In addition, the proposed RNN-based detector adopts a random search analysis in its learning stage to appropriately fine-tune its hyper-parameters. Extensive test studies are carried out to investigate the detector's performance using publicly available real data of 107,200 energy consumption days from 200 customers. Simulation results demonstrate the superior performance of the proposed detector compared with state-of-the-art electricity theft detectors.

The automatic assessment of speech plays an important role in Computer Aided Pronunciation Learning systems. However, modeling both the correct and incorrect pronunciation of each phoneme to achieve accurate pronunciation verification is unfeasible due to the lack of sufficient mispronounced samples in training datasets. In this paper, we propose a novel approach that handles this unbalanced data distribution by building multiple one-class SVMs to evaluate each phoneme as correct or incorrect. We model the correct pronunciation of each individual phoneme with a one-class SVM trained using a set of speech attributes features, namely the manner and place of articulation. These features are extracted from a bank of pre-trained DNN speech attributes classifiers. The one-class SVM model measures the similarity between the new data and the training set and then classifies it as normal (correct) or an anomaly (incorrect). We evaluated the system using native speech corpus and disordered speech corpus and compared it with the conventional Goodness of Pronunciation (GOP) algorithm. The results show that our approach reduces the false-acceptance and false-rejection rates by around 26% and 39% respectively.

Advanced metering infrastructure (AMI) networks are vulnerable against electricity theft cyber attacks. Different from the existing research that exploits shallow machine learning architectures for electricity theft detection, this paper proposes a deep neural network (DNN)-based customer-specific detector that can efficiently thwart such cyber attacks. The proposed DNN-based detector implements a sequential grid search analysis in its learning stage to appropriately fine tune its hyper-parameters, hence, improving the detection performance. Extensive test studies are carried out based on publicly available real energy consumption data of 5000 customers and the detector's performance is investigated against a mixture of different types of electricity theft cyber attacks. Simulation results demonstrate a significant performance improvement compared with state-of-the-art shallow detectors.

We present a multitier system for the remote administration of speech therapy to children with apraxia of speech. The system uses a client-server architecture model and facilitates task-oriented remote therapeutic training in both in-home and clinical settings. The system allows a speech language pathologist (SLP) to remotely assign speech production exercises to each child through a web interface and the child to practice these exercises in the form of a game on a mobile device. The mobile app records the child's utterances and streams them to a back-end server for automated scoring by a speech-analysis engine. The SLP can then review the individual recordings and the automated scores through a web interface, provide feedback to the child, and adapt the training program as needed. We have validated the system through a pilot study with children diagnosed with apraxia of speech, their parents, and SLPs. Here, we describe the overall client-server architecture, middleware tools used to build the system, speech-analysis tools for automatic scoring of utterances, and present results from a clinical study. Our results support the feasibility of the system as a complement to traditional face-to-face therapy through the use of mobile tools and automated speech analysis algorithms.

Automated tool to assess productions from children with apraxia of speech.Consists of clinician interface, mobile application and speech processing engine.Automatically detects groping errors, articulation errors and prosodic errors.Lattice-based Pronunciation Verification module detects articulation errors.Lexical Stress Pattern Verification module detects prosodic errors. Children with developmental disabilities such as childhood apraxia of speech (CAS) require repeated intervention sessions with a speech therapist, sometimes extending over several years. Technology-based therapy tools offer the potential to reduce the demanding workload of speech therapists as well as time and cost for families. In response to this need, we have developed "Tabby Talks," a multi-tier system for remote administration of speech therapy. This paper describes the speech processing pipeline to automatically detect common errors associated with CAS. The pipeline contains modules for voice activity detection, pronunciation verification, and lexical stress verification. The voice activity detector evaluates the intensity contour of an utterance and compares it against an adaptive threshold to detect silence segments and measure voicing delays and total production time. The pronunciation verification module uses a generic search lattice structure with multiple internal paths that covers all possible pronunciation errors (substitutions, insertions and deletions) in the child's production. Finally, the lexical stress verification module classifies the lexical stress across consecutive syllables into strong-weak or weak-strong patterns using a combination of prosodic and spectral measures. These error measures can be provided to the therapist through a web interface, to enable them to adapt the child's therapy program remotely. When evaluated on a dataset of typically developing and disordered speech from children ages 4-16years, the system achieves a pronunciation verification accuracy of 88.2% at the phoneme level and 80.7% at the utterance level, and lexical stress classification rate of 83.3%.

Future smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing purposes. However, several research works have revealed that such AMI networks are vulnerable to different kinds of cyber attacks. In this research work, we consider one type of such cyber attacks that targets electricity theft and we propose a novel detection mechanism based on a deep machine learning approach. While existing research papers focus on shallow machine learning architectures to detect these cyber attacks, we propose a deep feedforward neural network (D-FF-NN) detector that can thwart such cyber attacks efficiently. To optimize the D-FF-NN hyper-parameters, we apply a sequential grid search technique that significantly improves the detector»s performance while reducing the associated complexity in the learning process. We carry out extensive studies to test the proposed detector based on a publicly available real load profile data of 5000 customers. The detector»s performance is investigated against a mixture of different attacks including partial reduction attacks, selective by-pass attacks, and price-based load control attacks. Our study reveals that the proposed D-FF-NN detector presents a superior performance compared with state-of-the-art detector»s that are based on shallow machine learning architectures

Nowadays, many electrical utilities are moving towards self-healing distribution grid. This is realized by adding to distribution system various sensors, intelligent electronic devices (IEDs), phasor measurement units (PMU), sequence of event recorders (SERs), reclosers, detectors, measurement units, automated controllers, and other automation equipment. Those elements provide a continuous stream of data to support grid performance and improve its reliability. Huge amount of data obtained from different smart grid sources satisfy all the Big Data (BD) characteristics. The success of future electric grid depends mainly on the effective utilization of the huge amount of the data flow. This mass of information is essential to make next generation electric grid more efficient, reliable, secure, independent, and supportive during normal conditions and contingencies. The self-healing grid requires a robust real-time computation system that monitors, processes, provides predictive analytics, performs data mining and statistics, and makes faster decisions of the diverse and complex data collected within the traditional and nextgeneration electric grid. This helps to detect, locate, and isolate various faults, reconfigure and reroute power of the distribution network to minimize service disruptions and outages.Implementation of self-healing control system is associated with big data utilization which is a persisting challenge. Computational complexity challenges is associated with processing huge amounts of data during operation of the electric power system. Therefore, this paper presents acomprehensive studies of the impact of implementing a smart real-time dynamic self-healing control strategy using BD process platform with deep learning technique on the distribution system for current grid and future smart grid. The deep learning technique is a subfield of machine learning. The deep learning is shown to be highly efficient solution for the analysis of massive amounts of data which is performed by discovering and utilizing available regularities in the inputs to help self-healing control system to network reconfiguration, and coordination of various distributed energy resourcesin the smart grid. The deep learning system complexity does notdepend on the number of grid buses, this is because the power flow solving time is approximately linear with respect to the number of system buses. However, the complexity of the system depends on the number of the system inputs. The Long Short Term Memory (LSTM) recurrent neural network will be used in modeling sequential data such as time series data. Such network has the ability to learn contextual information over the history of the input sequence. The BD analyticswill be used as a key to deal with the uncertainties and different sizes of structured and unstructured data. The advanced analytics techniques such as predictive analytics, in addition to data mining, statistics, and faster decisions making will be utilized for data coming from sensors within the traditional and next-generation electric grid. The studies performed are based on real-time monitoring and control of the network topology and operating conditions taking into account different power sources and hybrid renewable energy sources which usually have different characteristics on the electric power grid. Finally, the real-time implementations of the proposed system will achieve dynamic resources optimization, network reconfiguration, and optimum operation of power grid using LSTM with big data platform.

Absorbable collagen sponge (ACS) loaded with bone morphogenetic protein-2 (BMP-2) is approved for selected clinical applications; however, burst release limits its widespread use. Therefore, nanofiber (NF)-based scaffold with ACS backbone was developed to sustain release of loaded BMP-2 to improve the outcomes of bone grafting in a rodent model of cleft palate.BMP-2 was loaded on ACS scaffold and then NF hydrogel with different densities (1-2%) was added to sustain the BMP-2 release. The release profiles of BMP-2 from constructs with different NF densities were evaluated in vitro to explore the optimum NF density that could recapitulate physiological bone healing process. Subsequently, scaffold with the appropriate NF density was implanted into a rodent model of cleft palate. Wistar rats, with surgically induced maxillary cleft defects, were then assigned to one of the following groups (n=6/group): no scaffold (control), ACS, ACS+BMP-2, NF+ACS, and NF+ACS+BMP-2. Micro-computed tomography (μCT) was utilized to evaluate percent bone filling (%BF) at defect site as well as changes in anteroposterior and transverse dimensions of the maxilla at weeks 0, 4, and 8. Histological assessment of bone healing was performed at week 8.In vitro release experiments showed that scaffolds containing 2% NF exhibited a release profile conducive to the natural stages of bone healing and, hence, it was utilized for subsequent in vivo studies. Bone healing occurred at the defect margins leaving a central bone void in the control, ACS, and NF+ACS groups over the 8-week study period. BMP-2-treated groups demonstrated higher %BF as compared with other groups at week 8 (p0.05). Whereas the NF+ACS+BMP-2 group showed bone bridging of the defect as early as 4 weeks, which was not evident in ACS+BMP-2 group. In all groups, bone grafts did not disrupt anteroposterior and transverse growth of maxilla. Based on histological evaluations together with μCT data, NF+ACS+BMP-2 treatment resulted in clinically significant and consistent bone healing throughout the implanted scaffold when compared with the ACS+BMP-2 group.NF+ACS+BMP-2 constructs exhibited osteoinductive properties together with preparation simplicity, which makes it a novel approach for BMP-2 delivery for cleft palate reconstruction.

Sleep disorders are becoming increasingly prevalent in society. However most of the burgeoning research on automated sleep analysis has been in the realm of sleep stage classification with limited focus on accurately diagnosing these disorders. In this paper, we explore two different models to discriminate between control and insomnia patients using support vector machine (SVM) classifiers. We validated the models using data collected from 124 participants, 70 control and 54 with insomnia. The first model uses 57 features derived from two channels of EEG data and achieved an accuracy of 81%. The second model uses 15 features from each participant's hypnogram and achieved an accuracy of 74%. The impetus behind using these two models is to follow the clinician's diagnostic decision-making process where both the EEG signals and the hypnograms are used. These results demonstrate that there is potential for further experimentation and improvement of the predictive capability of the models to help in diagnosing sleep disorders like insomnia.

Two field experiments were conducted in the experimental station farm, faculty of agriculture, Ain Shams University at Shalakan, Kalubia Governorate, during the two growing seasons, i.e. 2009 and 2010, to investigate the response of growth and forage yield production of pearl millet cv. Shandaweel 1 to nitrogen fertilization rates and cutting height above the soil surface. Four nitrogen rates as ammonium nitrate (33.5%N), 0, 30, 45, and 60 kg N/fed, were arranged in the main plots and two levels of cutting heights (10 and 20 cm above the soil surface) in the subplot with four replicates in split-plot design. In the second season, nitrogen application increased up to 75 kg N/fed. The main results were as follows: Significant increases were appeared in plant height (cm), number of tillers/m 2 , number of leaves/m 2 , and leaf area index during the two growing seasons as nitrogen fertilization rates increased except at the third cut in the first season for plant height (cm) and number of tillers/m 2 , the first and second cuts of the first season for number of leaves/m 2 and at the third cut during the first season of study for leaf area index, while leaf/stem ratio was not affected significantly during the two growing seasons. Green forage yield/fed was significantly increased as nitrogen application rates increased during the two growing seasons except at the third cut of the first season of study. Increasing nitrogen fertilization rates up to 75 kg N/fed caused significant increases in dry forage yield during the three collected cuts in the second season of study and the second cut during the first season of study as well as in the combined results. Plant height (cm) was significantly affected as cutting height above the soil surface increased in the second cut (2009) and the first cut (2010) where plant height increased at 10 cm as cutting height than at 20 cm above the soil surface. Significant differences were appeared in number of tillers/m 2 as cutting height varied from 10 to 20 cm in the two studied seasons. The highest cut of number of tillers/m 2 was scored at 20 cm cutting height than those at 10 cm in the second and third cuts during the two growing seasons. A number of leaves/m 2 as well as leaf area index were influenced significantly as cutting height increased during the two growing seasons except in the second and third cuts during 2009 or the third cut during 2010 for number of leaves/m 2 and in the second cut of the first season (2009) and the third cut during 2010 for leaf area index. Significant effects were noticed in leaf/stem ratio as cutting height differed in the second or third cut in 2009 and in the three collected cuts in combined analysis. Green forage yield, dry forage yield/feddan increase significantly as cutting height differed during the two growing seasons as well as the combined results except in the first cut during the first season of study for dry forage yield. Green forage yield as well as dry forage yield was significantly affected by the interaction between nitrogen fertilization rates and cutting height, where the highest yield was detected with adding 60–75 kg N/fed and 20 cm as cutting height (30.7 ton/fed).

The specific targeting ability of novel breast cancer targeting peptides as ligands coupled to polymeric micelles was evaluated in the present study. In this context, engineered breast cancer cell targeting peptides, denoted as peptide 11 (RGDPAYQGRFL) and peptide 18 (WXEAAYQRFL), were compared with the lead 12-mer p160 peptide and cyclic RGDfK peptide. All four peptides were conjugated individually to poly(ethylene oxide)-b-poly(caprolactone) (PEO-b-PCL) diblock polymeric micelles to obtain targeted carrier systems PM11, PM18, PM 160, and PM c-RGD. Physical blending of the peptides 11 and 18 with PEO-b-PCL was also done to yield combination micelles, comPM11 and comPM18. The structural confirmation of polymer was carried out using (1)H NMR and MALDI-TOF, and the size distribution and zeta potential of the micelles were determined using dynamic light scattering. Lipophilic cyanine fluorescent probe DiI was physically incorporated in the polymeric micelles to imitate the hydrophobic drug loaded in the micellar core. The cellular uptake of DiI-loaded peptide-containing polymeric micelles by MDA-MB-435, MDA-MB-231, and MCF7 breast cancer cell lines, as well as HUVEC and MCF10A noncancerous cells, were analyzed using flow cytometry and confocal microscopy techniques. Modification of polymeric micelles with peptide 11 or 18 led to an increase in micellar uptake specifically in breast cancer cells compared to p160, c-RGD modified, or naked micelles. The peptide-micelle combinations (comPM11 and comPM18) displayed better uptake by the cells compared to the covalently conjugated PM11 and PM18 micelles; however, the combinations were less selective toward cancer cells. The results point to a potential for peptides 11- and 18-micelle conjugates as attractive platforms for improved performance of a wide range of chemotherapeutic drugs and/or imaging agents in cancer therapy and diagnosis.

Emulgel topical formulation is a vehicle of potential for topical delivery of antifungal drugs.The imidazole derivative antifungal drug, clotrimazole (CZ), was formulated into emulgels using two grades of hydrophobically modified co-polymers of acrylic acid, namely Pemulen TR1 and TR2. The prepared emulgels were evaluated for their rheological properties, short- and long-term stability, in vitro release at 37°C. Microbiological evaluation of the formula showed that optimum stability and release was carried out to measure its antifungal activity.All formulae showed non-Newtonian shear thinning behavior with little thixotropy or antithixotropy. Five of the prepared formulae showed good physical stability under different treatment conditions. Isopropyl myristate (IPM) emulgels exhibited higher rate of CZ release than either jojoba oil (JB) or liquid paraffin-based emulgels. A selected formula containing JB together with a combination of Pemulen TR1 and TR2 showed excellent stability as well as high rate of CZ release. Microbiological evaluation of the selected formula containing similar amount of CZ revealed 1.2-folds increase in the antifungal activity compared to commercially available formulation.Emulgel dosage form based on Pemulen polymeric emulsifier and JB is a promising vehicle for topical delivery of CZ and further in vivo animal studies are recommended.

Background and Objectives: As English is a stress-timed language, lexical stress plays an important role in the perception and processing of speech by native speakers. Incorrect stress placement can reduce the intelligibility of the speaker and their ability to communicate more effectively. The accurate identification of lexical stress patterns is thus a key assessment tool of the speaker's pronunciation in applications such as second language (L2) learning, language proficiency testing and speech therapy. With the increasing use of Computer-Aided Language Learning (CALL) and Computer-Aided Speech and Language Therapy (CASLT) tools, the automatic assessment of lexical stress has become an important component of measuring the quality of the speaker's pronunciation. In this work we proposed a Deep Neural Network (DNN) classifier to discriminate between the unequal lexical stress patterns in English words, strong-weak (SW) and weak-strong (WS). The features used in training the deep neural network are derived from the duration, pitch and intensity of each of the two consecutive syllables along with a set of energies of different frequency bands. The robustness of our proposed lexical stress detector has been validated by testing it on the standard TIMIT dataset collected from adult male and female speakers distributed over 8 different dialect regions. Method: Our lexical stress classifier is applied on the speech signal along with the prompted word. Figure 1 shows a block diagram of the overall system. The speech signal is first force aligned with the predetermined phoneme sequence of the word to obtain the time boundaries of each phoneme. The alignment is performed using a Hidden Markov Model (HMM) Viterbi decoder along with set of HMM acoustic models trained from the same corpus to reduce the error caused by inaccurate phone level segmentation. A set of features is then extracted from each syllable and the features of each pair of consecutive syllables combined using the extracted features directly and concatenating them into one wide feature vector.Lexical stress is identified by the variation in the pitch, energy and duration produced between different syllables in a multi-syllabic word. The stressed syllable is characterized by increased energy and pitch as well as a longer duration compared to the other syllables within the same word. Therefore we extracted seven features f1–f7 related to these characteristics as listed in Table 1. The energy based features (f1, f2, f3) were extracted after applying the non-linear Teager energy operator (TEO) on the speech signal to obtain a better estimation of the speech signal energy and reduce the noise effect. These seven features are commonly used in the detection of the stressed syllable in a word. As the speech signal energy is distributed over different frequency bands, we also computed the energy in the Mel-scale frequency bands in each frame of the syllable nucleus. The speech signal was divided into 10 msec non-overlapped frames and the energy, pitch and the frequency bands energies calculated for each frame.As seen in Figure 1, to input the raw extracted features directly to the DNN, we concatenate the extracted features into one wide feature vector. Each syllable has 7 scalar values f1–f7 and 27*n Mel-coefficients where n is the number of frames in each syllable's vowel.To handle variable vowel lengths, we limit the number of input frames provided to the DNN to a maximum N frames for each syllable. This provides the DNN with a fixed length Mel-energy input vector and allows the DNN to use information about the distribution of the Mel-energy bands over the vowel. If the vowel length (n) is greater than N frames, only the middle N frames are used. If the length of the vowel (n) is smaller than N frames, inputs frames are padded to N frames. The final size of the input vector to the DNN is 2*(7+27*N) for a pair of consecutive syllables, with N tuned empirically.The DNN is trained using the mini-batch stochastic gradient decent method (MSGD) with adaptive learning rate. The learning rate starts with an initial value (typically 0.1) and after each epoch the loss in the error of the validation data set is computed. If the loss is greater than zero (i.e. the error increases) the training continues with the same learning rate.If the error continues increasing for 10 consecutive epochs, the learning rate is halved and the parameter of the classifier returned to the one that achieved minimum error. Training is terminated when the learning rate reaches its minimum value (typically 0.0001) or after 200 epochs, whichever is earlier. The performance of the DNN is then computed using a separate testing set. Experiments and Results: We extracted raw features from consecutive syllables belonging to the same word from the TIMIT speech corpus. With the TIMIT corpus, we achieved a minimum error rate of 12.6% using a DNN classifier with 6 hidden layers and 100 hidden units per layer. Due to the unavailability of sufficient male and female data, we were unable to build a separate model for each gender. In Fig. 2, we present the error rate for each gender using a model trained on both male and female data. The results show that the classification of the SW is better in male speakers compared to female speakers while the WS error rate is lower for female speakers. However, the overall misclassification rate for both male and female speakers is almost the same.To study the influence of the dialect on the algorithm, we compared the error rate when testing each dialect using a model trained with the training data of all dialects and when the model was trained with training data from all dialects except the tested one as shown in Fig. 3. As seen, the error rate of most of the dialects remains unchanged except for DR1 where the error rate increased significantly from 4.8 % to 8%. This can be explained by the small amount of test samples for this dialect (only 5% of the test samples). DR4 also shows a considerable increase in the error rate. Although the smallest amount of training samples was from the DR1 (New England) dialect, it produced the lowest error rate among the other dialects. Further work is needed to explain this behavior. Conclusion: In this work we present a DNN classifier to detect bisyllabic lexical stress patterns in multi-syllabic English words. The DNN classifier is trained using a set of features extracted from pairs of consecutive syllables related to pitch, intensity and duration along with energies in different frequency bands. The feature set of each pair of consecutive syllables is combined by concatenating the raw features into one wide vector. When applied on the standard TIMIT adult speech, the algorithm achieved a classification accuracy of 87.4%. The system performance show high stability over different dialects and gender.

Lexical stress is a key diagnostic marker of disordered speech as it strongly affects speech perception. In this paper we introduce an automated method to classify between the different lexical stress patterns in children's speech. A deep neural network is used to classify between strong-weak (SW), weak-strong (WS) and equal-stress (SS/WW) patterns in English by measuring the articulation change between the two successive syllables. The deep neural network architecture is trained using a set of acoustic features derived from pitch, duration and intensity measurements along with the energies in different frequency bands. We compared the performance of the deep neural classifier to a traditional single hidden layer MLP. Results show that the deep neural classifier outperforms the traditional MLP. The accuracy of the deep neural system is approximately 85% when classifying between the unequal stress patterns (SW/WS) and greater than 70% when classifying both equal and unequal stress patterns.

This paper introduces a pronunciation verification method to be used in an automatic assessment therapy tool of child disordered speech. The proposed method creates a phonebased search lattice that is flexible enough to cover all probable mispronunciations. This allows us to verify the correctness of the pronunciation and detect the incorrect phonemes produced by the child. We compare between two different acoustic models, the conventional GMM-HMM and the hybrid DNN-HMM. Results show that the hybrid DNNHMM outperforms the conventional GMM-HMM for all experiments on both normal and disordered speech. The total correctness accuracy of the system at the phoneme level is above 85% when used with disordered speech.

Background and Objectives Childhood Apraxia of Speech (CAS) is a speech disorder characterized by articulation errors, i.e. the replacement of certain phonemes with alternatives. In previous work we proposed a simple method to evaluate the child's speech as correct or incorrect with an overall accuracy of 88.2%. In this work we present an enhanced method that increases the accuracy of the correct/incorrect evaluation to 92.7%, in addition to identifying the incorrect phonemes with an accuracy of 60%. Method The goal of the mispronunciation detection system is to compare each phoneme in the child's production to their given prompt and identify mispronunciations. Figure 1 shows the block diagram of the system, which uses a search lattice for each prompt in the child's speech therapy treatment protocol to identify errors made. Each prompt is transcribed as per the corresponding phoneme sequence using the CMU pronunciation dictionary and then passed to the lattice generator along with the expected mispronunciation rules to generate the search lattice. Mel Frequency Cepstral Coefficients (MFCC) are extracted from the speech signal with delta and acceleration to produce a 39- dimensional feature vector per frame. The extracted features are then fed to the speech recognizer along with the created lattice and the Hidden Markov Model (HMM) acoustic models to generate a sequence of phones from the child's utterance. An evaluation report is then generated by matching the recognized phoneme sequence with the correct phoneme sequence and specifying the errors made by the child. We use a search lattice with a specific number of alternative pronunciations for each phoneme; this limits the decoder search, making it faster and more accurate. Each phoneme in the correct phoneme sequence is compared with expected mispronunciation rules developed by a therapist after an assessment of 20 children with CAS; if a rule is matched, the pronunciation variants are added as alternative arcs to the current phoneme sequence. The mispronunciation rules depend on the type of the phoneme (consonant/vowel), the phoneme position in the word (Initial/Medial/Final) and the context of the phoneme. The lattice is then created using the matched rules as shown in Figure 2, where the garbage model absorbs any mispronounced phoneme not in the lattice. PA and PG are insertion penalties added to the alternative and the garbage arcs respectively so the decoder does not align the speech to the alternative error phonemes or the garbage node unless it is confident enough. Results The system overall system accuracy is 92.7% where the Correct Acceptance (CA) is 97.6% and the Correct Rejection (CR) is 83.1%. The system also detects phoneme errors made by the child with 60% accuracy. Conclusion In this paper we proposed a mispronunciation detection tool that can detect phonemes mispronounced by children with CAS and specify the errors made.

We present a multi-tier system for the remote administration of speech therapy to children with apraxia of speech. The system uses a client-server architecture model and facilitates task-oriented remote therapeutic training in both in-home and clinical settings. Namely, the system allows a speech therapist to remotely assign speech production exercises to each child through a web interface, and the child to practice these exercises on a mobile device. The mobile app records the child's utterances and streams them to a back-end server for automated scoring by a speech-analysis engine. The therapist can then review the individual recordings and the automated scores through a web interface, provide feedback to the child, and adapt the training program as needed. We validated the system through a pilot study with children diagnosed with apraxia of speech, and their parents and speech therapists. Here we describe the overall client-server architecture, middleware tools used to build the system, the speech-analysis tools for automatic scoring of recorded utterances, and results from the pilot study. Our results support the feasibility of the system as a complement to traditional face-to-face therapy through the use of mobile tools and automated speech analysis algorithms.

Background and Objectives Language production and speech articulation can be delayed in children due to developmental disabilities and neuromotor disorders such as childhood apraxia of speech (CAS). One of the behaviors that are commonly associated with the CAS is the articulation errors where the child mispronounced some of the produced phonemes. The presented Pronunciation Verification (PV) method automatically evaluates the child speech and detects any insertion, deletion or substitution errors made by the child on the phoneme level. Method The proposed PV method based on a search lattice with different competing paths to allow the system to detect insertions, deletions and substitutions of phonemes. Fig. 1 shows a block diagram of the lattice based PV component. The prompted word is first phonetically transcribed to obtain the expected phoneme sequence. The lattice generator then uses the phoneme sequence to generate a search lattice fed to the speech recognizer. The generated lattice is flexible enough to cover all the possible pronunciation errors (insertion, deletion and substitution) by adding alternative paths to the correct path for each of the expected errors. The deletion path can be represented as a null arc to allow the recognizer to skip the phoneme node during decoding while the garbage node is used as an alternative to collect phoneme other than the expected one (substitution error). A garbage loop is also added between two consecutive phonemes to collect inserted phonemes frames. Fig. 2 (a) shows an example of the lattice for the word "chair" where PG and PD are the penalties attached to the garbage and deletion arcs respectively, these penalties are added to avoid the recognizer skipping phonemes or aligning speech to the garbage node unless the fit is better than the correct path. The garbage node is composed of all the phonemes connected in parallel as shown in Fig. 2 (b). The Mel Frequency Cepstral Coefficients (MFCC) are extracted from the speech signal with delta and acceleration to produce a 39 dimension feature vector per frame. The extracted features are then fed to the speech recognizer along with the created lattice and the Hidden Markov Model (HMM) acoustic models to generate a sequence of phonemes from the child's utterance. The Context Dependent (CD) HMM model consists of multi-mixture tied-state tri-phones while the garbage model consists of single mixture mono-phones to reduce the complexity and speed up the recognition process. The output phoneme sequence is then compared to the expected phoneme sequence, if matched the utterance is marked as correct otherwise incorrect. Results The system overall accuracy is 88.2% where the Correct Acceptance (CA) is 91.5% and the Correct Rejection (CR) is 83.4%. Conclusion A PV method that uses a search lattice with different alternative paths and a garbage model was used to detect the articulation errors made by the child with overall accuracy around 88%.

Technology based speech therapy systems are severely handicapped due to the absence of accurate prosodic event identification algorithms. This paper introduces an automatic method for the classification of strong-weak (SW) and weak-strong (WS) stress patterns in children speech with American English accent, for use in the assessment of the speech dysprosody. We investigate the ability of two sets of features used to train classifiers to identify the variation in lexical stress between two consecutive syllables. The first set consists of traditional features derived from measurements of pitch, intensity and duration, whereas the second set consists of energies of different filter banks. Three different classifiers were used in the experiments: an Artificial Neural Network (ANN) classifier with a single hidden layer, Support Vector Machine (SVM) classifier with both linear and Gaussian kernels and the Maximum Entropy modeling (MaxEnt). these features. Best results were obtained using an ANN classifier and a combination of the two sets of features. The system correctly classified 94% of the SW stress patterns and 76% of the WS stress patterns.

Chemotherapy is still the treatment of choice for many types of cancer; but its effectiveness is hampered by dose limiting toxicity. Properly designed delivery systems can overcome this shortcoming by reducing the non-specific distribution and toxicity of chemotherapeutics in healthy organs and at the same time increasing drug concentrations at tumor tissue. In this study, we developed stealth liposomal formulations of doxorubicin (DOX) having a novel stable engineered peptide ligand, namely p18-4, that binds specifically to breast cancer cell line MDA-MB-435 on its surface. The coupling of p18-4 to liposomes was carried out through conventional, post insertion and post conjugation techniques and prepared liposomes were characterized for their size and level of peptide modification. The p18-4 decorated liposomal DOX formulations were then evaluated for their cellular uptake as well as cytotoxicity against the human breast cancer MDA-MB-435 cells. In this context, the effect of coupling technique on the uptake and cytotoxicity of p18-4 liposomal DOX in MDA-MB-435 cells was evaluated. The conventional and post conjugation methods of peptide incorporation were found to be more reliable for the preparation of p18-4 decorated liposomes for active DOX targeting to MDA-MB-435 cells. p18-4 decoration of liposomes by these methods did not have a notable effect on the size of prepared liposomes and DOX release, but increased the uptake and cytotoxicity of encapsulated DOX in MDA-MB-435 cells. The results show a potential for p18-4 decorated liposomes prepared by conventional and post conjugation method for tumor targeted delivery of DOX in breast tumor models.